Intelligent Communication Technologies and Virtual Mobile Networks

The intrusion detection system (IDS) is an important aspect of network security. This research article presents an analysis of machine and deep learning algorithms for intrusion detection systems. The study utilizes the CICIDS2017 dataset that consists of 79 features. Multilayer perceptrons (MLPs) and random forests (RFs) algorithms are implemented. Four features extraction techniques (information gain, extra tree, random forest, and correlation) are considered for experimentation. Two models have been presented, the first one using the machine learning random forest (RF) algorithm and the second using deep learning multilayer perceptron (MLP) algorithm. The increased accuracy has been observed when using the random forest algorithm. The RF algorithm gives the best results for the four feature selection techniques, thus proving that RF is better than MLP. The RF algorithm gives 99.90% accuracy, and 0.068% false positive rate (FPR) with 36 features. Furthermore, the dimensionality of the features has been reduced from 79 to 18 features with an accuracy of 99.70% and FRP of 0.19%.

This article describes a modified genetic algorithm (MGA) for solving a multicriteria optimization problem for the selection and optimization of the information security means (ISM) quantity for sets located on the nodes of the informatization objects’ (OBI) distributed computing system (DCS). Corresponding computational experiments were carried out, during which it was shown that MGA is distinguished by a sufficiently high efficiency. The time spent on solving the problem of the options evaluation for selecting and optimizing the placement of DSS sets along the DCS nodes for OBI, when using MGA, is approximately 16–25.5 times less in comparison with the indicators of the branch-and-bound method. The proposed approach of the MGA usage for solving the above written problem is characteristically exhibited by its integrated approach. In contrast to similar studies devoted to this problem, which, as a rule, consider only some aspects of information security (e.g., assessing the risks for OBI, comparing different information security systems, building maps of cyberthreats, etc.), the approach we are extending makes it possible to combine all areas of ISM selection in the process of the OBI information security (IS) contours optimization. The DSS module for solving the problem of selecting and optimizing the number of information security systems for the sets located on the nodes of the informatization objects’ DCS was described.

Deep learning comes under machine learning. It includes statistics and predictive modeling, which plays vital role in data science. It helps in acquiring and analyzing vast amount of data quick and easier. This technique is employed in image recognition tools and natural language processing. Carcinoma is one other frequently occurring cancer in women. Carcinoma can be identified in two variants: One is benign, and another one is malignant. Automatic detection in medical imaging has become the vital field in many medical diagnostic applications. Automated detection of breast cancer in magnetic resonance imaging (MRI), and mammography is very crucial as it provides information about breast lesions. Human inspection is the conventional method for defect detection in magnetic resonance images. This method is impractical for large amount of data. So, cancer detection methods are developed as it would save radiologist time and also the risk faced by woman. Various machine learning algorithms are used to identify breast cancer. Deep learning models have been widely used in the classification of medical images. To improvise the accuracy in the model various, deep learning approaches are to be used to detect the breast cancer. The proposed approach classifies the breast cancer not just as benign or malignant, but it will classify the subclasses of breast cancer. They are Benign, Lobular Carcinoma, Mucinous Carcinoma, Ductal Carcinoma, and Papillary Carcinoma. To classify the subclasses of tumor, we use DenseNet Architecture. Image preprocessing is done using histogram equalization method.

Every organization has implemented cybersecurity for network security. Both web applications and organizations’ network security should be free from complex vulnerabilities. It refers to the security flaws in the network or weakness in the web applications. By using the exploits available, the hacker could attack our target system to steal confidential data. So, to secure the security of networks the most common and major technique used is ethical hacking. It comprises complex levels of vulnerability assessment and performing penetration testing by using the identified exploits. In this research paper, I have demonstrated and analyzed the methodologies through which the pen tester accesses the target system, identifying exploits, attacking the target system using the identified exploit privilege escalation, and capturing the root flag to access the data. Finally, before exiting he should clear the system as before. Finally, the pen tester generates a report containing the guidelines to eliminate the security flaws and improve network security.

Vehicle-to-vehicle or V2V communication, a progressively developing technology that uses IEEE 802.11 p-based systems to enable vehicular communication over a few hundreds of meters, is being introduced in numerous vehicle designs to equip them with enhanced sensing capabilities. However, it can be subjected to a lot of interference due to sensitivity that can cause potential channel congestion issues. V2V can be complemented using visible light communication (VLC), an alternative technology that uses light emitting diodes (LEDs), headlights or tail lights to function as transmitters, whereas the photodiodes or cameras function as receivers. Although, in real-time applications, a V2V-VLC cannot be demonstrated due to unreliability. In this paper, the overall performance of the vehicle-to-vehicle communication is being implemented using orthogonal frequency division multiplexing (OFDM) in combination with amplitude shift keying (ASK), also termed as on–off keying (OOK) modulation, binary phase shift keying (BPSK) and quadrature phase shift keying (QPSK) digital modulation techniques. All the above-mentioned modulation techniques, i.e., OFDM-OOK, OFDM-BPSK and OFDM-QPSK, are being compared using the following design parameters, i.e., signal to noise ratio (SNR) versus bit error rate (BER) as well as spectral efficiency, in order to choose the best technique for V2V communication. By extensive analysis, in terms of rate and error performances, we have observed that QPSK modulation technique with OFDM performs better when compared to OFDM with OOK and BPSK modulation techniques for V2V communication.

In democratic countries such as India, voting is a fundamental right given to citizens of their countries. Citizens need to physically present and cast their vote in ballot paper-based voting systems. Most of the citizens fail to fulfill this constraint and have stayed away from their fundamental duty. Electronic voting systems are often considered as one of the efficient alternatives in such situations. Blockchain technology is an emerging technology that can provide a real solution as it is characterized by immutable, transparent, anonymous, and decentralized properties. This paper presents a security requirement analysis for e-voting systems and evaluates blockchain technology against these requirements.

The idea of this project is to improve the security performance in houses and safe places by using Arduino and GSM. In this project, we are going to make an OTP-based door opening system using Arduino and GSM. The method we have developed will generate a one-time password that helps you unlock the door. This method will enhance the security level further, which is much safer than the traditional key-based system. In the traditional key-based system, we used to face the problem of what to do if I miss the key somewhere or what to do if the key gets stolen. We do not have to worry about it since the password is automatically generated on your mobile phone and you can enter it and unlock the door.

Tourism plays significant role for enhancing economic potential worldwide. The natural beauty and historical interests of Bangladesh remarked as a major tourist destination for the international tourists. In this study, we target to propose a deep learning-based application to recognize historical interests and tourist spots from an images. Making use of on-device neural engine comes with modern devices makes the application robust and Internet-free user experience. One of the difficult tasks is to collect real images from tourist sites. Our collected images were in different sizes because of using different smartphones. We used following deep learning algorithms—convolution neural network (CNN), support vector machine (SVM), long short-term memory (LSTM), K-nearest neighbor (KNN) and recurrent neural network (RNN). In this proposed framework, tourists can effortlessly detect their targeted places that can boost the tourism sector of Bangladesh. For this regard, convolutional neural network (CNN) achieved best accuracy of 97%.

Heart disease prediction is a challenging task that is under research from many decades. There are several factors that cause heart attacks in patients. These factors can be used to analyse and predict if a patient is having a risk of getting heart attack. This paper presents a risk factor analysis of factors that result in heart attack and put forth the association between different factors. The analysis of the association can help doctors personalize the treatment based on the patient condition. The rules of association, namely support, confidence and lift, have been used to find out how different factors, single and combined, can play a role in causing heart attack to the patients. The risk factor parameters under study are: thal, age, exang, restecg, chol, sex, cp, fbs, trestbps, and thalach. Finding the association between parameters can help us analyse what factors, when combined, can have the highest risk in causing heart attack.

The applications like security framework, agriculture, and traffic maintenance have been utilized from wireless sensor networks (WSNs). The data redundancy is the common cause of problem while the similar data has been gathered from several sensors which require an accurate data aggregation function for providing real-time processing. Originally, the network is framed with the active nodes with groups and the cluster head is elected according to the rank parameter through the geographical location with base station. The data aggregator is used inside the clusters to maintain the energy utilization and whenever the value has produced low, identify another data aggregator. The performance results demonstrate that the proposed technique minimizes the end-to-end delay.

It is necessary to ensure historic artefacts that are damaged or deteriorating are accurately documented, and that steps are done to restore them. To improve user experiences in the areas of virtual visitation, science, and education, this paper explains a method of repurposing and restoring historic structures. Nowadays, virtual reality, immersive reality, and augmented reality applications play a major role in allowing people to view and learn about historic monuments, sites, scenes, and buildings. The procedure for working employs digital models that are then integrated into a virtual reality environment that is interactive and immersive. The work method was applied at a Poompuhar is likewise called Kaveripattinam, and one of the maximum exceptional historical Chola ports played a essential position in maritime records of Tamil Nadu. To recreate, to feel, to inculcate interest closer to the research of the cultural heritage, to enhance tourism, this project brings up a new technology closer to mastering and enables masses to push tourism. This work demonstrates how the details of a severely degraded historic structure were retrieved digitally. We created 3D models using Blender which helped to restore deteriorated and nearly non-existent historical buildings, and the resulted images were inserted into game engine Unity, then by using the cross-platform VR environment, they were introduced into an immersive and interactive VR experience. The end consequence, however, is a virtual reality environment that is both immersive and interactive that contains architectural and artistic content developed utilising the Unity video game engine, allowing the user to explore, watch, and interact real-time interaction with a cultural heritage site.

Fog computing is one of the most promising and current technology that allows the innovation of 5G by giving cloud computing services nearer to the end devices or IoT devices. It helps to perform computation locally in a fog server instead of doing it in a distant centralized cloud platform. Due to heavy load at cloud servers which is the result of too much centralization leads to adverse effects on several real-time issues like load balancing, automated service provisioning, fault tolerance, traffic overload, resource utilization, power/energy consumption and response time, etc. It is difficult to manage and processing load for the edge computing nodes in fog environment. Dynamic energy efficient-based Load balancing is still a major issue for the full-scale realization of fog computing in many application domains. The suggested system must assign appropriate workload amongst all the fog or edge nodes in order to effectively increase network performance, minimize delay, and reduce energy consumption owing to network traffic occurring at cloud servers. In this present approach, primarily the user will transmit an incoming task to the Tasks Manager for execution. The available resources can be arranged by the Scheduler according to their usage. The Resource Compute Engine gets task and resource information from the Scheduler and resources are allotted to the task based on organized list and also transmit the result to the user. When compared to the existing dynamic load balancing method, the suggested methodology is more effective for fog computing settings in terms of minimizing overall energy usage and computational cost by 8.78% and 16.78%, respectively.

Sentimental analysis is a study of emotions or analysis of text as an approach to machine learning. It is the most well-known message characterization device that investigates an approaching message and tells whether the fundamental feeling is positive or negative. Sentimental analysis is best when utilized as an instrument to resolve the predominant difficulties while solving a problem. Our main objective is to identify the emotional tone and classify the tweets on COVID-19 data. This paper represents an approach that is evaluated using an algorithm namely—CatBoost and measures the effectiveness of the model. We have performed a comparative study on various machine learning algorithms and illustrated the performance metrics using a Bar-graph.

With every passing day, the amount in which social media content is being produced is enormous. This contains a large amount of data that is abusive. Which in turn is responsible for disturbing the peace, affecting the mental health of users going through that kind of data and in some cases is responsible for causing riots and chaos leading to loss of life and property. Knowing the sensitivity of such situations, it becomes necessary to tackle the abusive textual content. This paper presents the analysis of abusive textual content detection techniques. And for these, researchers have been developing methods to automatically detect such content present on social media platforms. This study also discusses the domains of automatic detection that have been investigated utilizing various methodologies. Several machine learning techniques that have recently been implemented to detect abusive textual material have been added. This paper presents a detailed summary of the existing literature on textual abusive content detection techniques. This paper also discusses the categorization of abusive content presented in the research, as well as potential abusive communication methods on social media. Deep learning algorithms outperform previous techniques; however, there are still significant drawbacks in terms of generic datasets, feature selection methods, and class imbalance issues in conjunction with contextual word representations.

The increasing advanced devices in the recent communication systems, such as 5G, mm wave, and ultrawideband communication systems, led to the antenna design. This antenna design accomplishes better radiation efficiency, stable radiation pattern and higher data rates. In the recent years, a lot of Antipodal Vivaldi Antenna (AVA) structures have been designed to support the proliferation of advanced devices. Different methods are developed and analysed in the more compact AVA structure by using the chosen substrate, introducing flare shapes, and fern-shaped fractals, introducing the multiple slots and different feeding connectors. In this paper, various enhancement and optimization of the performance enhancement techniques of AVA structures have been discussed. The recently proposed antenna structures are explained in detail by incorporating the merits and demerits. Moreover, the illustrations from the literature demonstrate the future directions and improvements by applying the performance enhancement techniques.

5G technology plays a very important role in the technical revolution in communication domain that aims to meet the demand and needs of the users in high-speed communication systems. This technology is widely used to support different types of users not only the smartphones, but in smart city, smart building and many more applications worldwide. In this paper, a comprehensive survey on different antennas and its designs proposed by the various researchers in recent literatures has been detailed. This paper elaborates on the state-of-the-art of research in various 5G wideband multi-input multi-output (MIMO) antennas with their suitable performance enhancement techniques. Moreover, it gives a detailed review about the 5G wideband antenna designs, structural differences, substrate chosen, comparison and future breakthroughs in a detailed manner.

Background subtraction is a classical approach for real-time segmentation of moving objects in a video sequence. Background subtraction involves thresholding the error between an estimate of the reference frame without moving objects and the current frame with moving objects. There are numerous approaches to this problem, and each differs in the type of estimation technique used for generating the reference background frame. This paper implements a transprecision Gaussian average background subtraction methodology to count as well as track the moving vehicles present in complex road scenes. The background information at pixel level is collected periodically for frames in order to track the moving vehicles in foreground, hence the name ‘transprecision’ Gaussian average background subtraction. It is observed that this technique improves the accuracy of vehicle tracking and vehicle counting when compared to the conventional techniques. We have illustrated the robust performance of the proposed method in various operating conditions including repetitive motion from clutter, different view angles and long-term scene changes, words.

The constant traffic of messages keeps increasing whether be it email or SMS. This leads to a direct increase of attacks from spammers. Mobile spams are particularly threatening as spam messages are often disguised as messages from banks, which cause immense harm. Due to this, having a method to identify if the messages are spam or not becomes pivotal. Several techniques exist where deep learning tasks show higher accuracy compared to classic machine learning tasks. Hence, this paper compares the BERT with traditional machine learning techniques which are used in this paper are logistic regression, multinomial Naive Bayes, SVM, and random forest. This paper uses an open-source dataset from Kaggle of labelled spam and not spam messages. It has a total of 5585 messages of which 4825 are labelled as spam and 760 as spam. This paper uses various machine learning algorithms and an algorithm with BERT. In comparison with the other machine learning techniques, it was discovered that the BERT algorithm delivered the highest testing accuracy of 98%. BERT has an encoding layer which generates encodings such that they are not biased and are then fine-tuned for spam detection. With this attribute, the algorithm obtains a higher accuracy.

This paper describes an application framework which uses Li-Fi (Light Fidelity) technology to reduce the time delay and congestion caused at the toll system. The Li-Fi is a disruptive technology driven by the visible light spectrum that makes the data transmission process much faster and enhances the system efficiency. In Li-Fi, there is no interference as in radio waves and it provides higher bandwidth. It is a bidirectional wireless data carrier medium that uses only visible light and photodiodes. Everything happens very fast in this world, including transportation. In the present scenario, spending a long time in traffic is irritating. Even after the introduction of FASTag, there is not much change in toll booth queues. It is at this point where we start to think about a different plan to avoid unwanted blocks at toll booths. Hence, we introduce the concept of Li-Fi where vehicles can move through the toll booths without any pause. All that we are using here is DRL (Daytime Running Lights). This will have a corresponding receiver section which will accept the signals from the DRL. This method also has certain extra perks which will provide an interdisciplinary help to many major fields.

Today, a big number of people suffer from various cardiac problems all over the world. As a result, knowing how the ECG signal works is critical for recognising a number of heart diseases. The electrocardiogram (ECG) is a test that determines the electrical strength of the heart. In an ECG signal, PQRST waves are a group of waves that make up a cardiac cycle. The amplitude and time intervals of PQRST waves are determined for the learning of ECG signals in the attribute removal of ECG signals. The amplitudes and time intervals of the PQRST segment can be used to determine the appropriate operation of the human heart. The majority of approaches and studies for analysing the ECG signal have been created in recent years. Wavelet transform, support vector machines, genetic algorithm, artificial neural networks, fuzzy logic methods and other principal component analysis are used in the majority of the systems. In this paper, the methodologies of support vector regression, kernel principal component analysis, general sparse neural network and generative adversarial network are compared. The GAN method outperforms both of the other methods. However, each of the tactics and strategies listed above has its own set of benefits and drawbacks. MATLAB software was used to create the proposed system. The proposed technique is demonstrated in this study with the use of the MIT-BIH arrhythmia record, which was used to manually annotate and establish validation.

Pulmonary embolism, often referred to as PE, is a condition in which a blood clot becomes trapped in a pulmonary artery and prevents flow of blood to the lungs. If left ignored, this might be life-threatening and in most circumstances, fatal. Since the identification of whether a scan contains an embolus or not is a cumbersome process, we propose an approach using VGG16 and XGBoost to classify whether an image contains an embolus or not. The dataset used has been downloaded from Kaggle and segregated into two classes, namely “PE” (the images that contain embolus) and “no PE” (the images without any embolus in the lungs). Each directory contains over 1000 images. The methodology employed in this paper using VGG16 to extract features and XGBoost to further classify images rendered an accuracy of 97.59% and a sensitivity of 97.00% with 5 misclassifications.

The 5G wireless networks are expected to provide fastest mobile Internet connectivity, efficient network access, capable of handling large amount of data traffic, connecting large number of mobile devices with high-throughput and very-low latency. The new technologies such as cloud computing, network function virtualization (NFV), and software-defined networking (SDN) are being used in 5G wireless networks. The number of small cells in 5G networks creating a heterogeneous network environment (HetNet), where users will join and leave the network frequently causing repeated authenticated vertical handoff across the different cells leading to delay in the network. There are new security requirements and challenges in 5G mobile wireless network due to its advanced features. Therefore, in this paper to deal with secured vertical handoff, a trusted authenticating mechanism is proposed to secularly authenticate the user based on the credibility in 5G wireless networks. It is generating a trust relationship between user, base station, and home networks based on the user credibility and performs quick and secured handoff. The user credibility is comprises the direct credibility and indirect credibility calculation. Based on the user credibility, the trustworthiness of user equipment (UE) is identified and vertical handoff performed without re-authentication across different heterogeneous small cells in 5G wireless networks.

Internet attacks have become more sophisticated over time, and they can now circumvent basic security measures like antivirus scanners and firewalls. Identifying, detecting, and avoiding breaches is essential for network security in today's computing world. Adding an extra layer of defence to the network infrastructure through an Intrusion Detection System is one approach to improve network security. Anomaly-based or signature-based detection algorithms are used by existing Intrusion Detection Systems (IDS). Signature-based IDS, for example, detects attacks based on a set of signatures but is unable to detect zero day attacks. In contrast, anomaly-based IDS analyses deviations in behaviour and can detect unexpected attacks. This study suggests designing and developing an Advanced signature-based Intrusion Detection System for Improved Performance by Combining Signature and Anomaly-Based Approaches. It includes three essential stages, first Signature-based IDS used for checking the attacks from the Signature Ruleset using Decision Tree received accuracy 96.96%, and the second stage Anomaly-based IDS system used Deep learning technique ResNet50. The model relies on ResNet50, a Convolutional Neural Network with 50 layers that received an accuracy of 97.25%. By classifying all network packets into regular and attack categories, the combination of both detect known and unknown attacks is the third stage and generates signature from anomaly-based IDS. It gives the accuracy of 98.98% for detection of intrusion. Here findings show that the suggested intrusion detection system may efficiently detect real-world intrusions.

Nowadays, in this technologically sound world, the use of social media is very popular. Along with the advantages of social media, there are many terrible influences as well. Cyberbullying is a crucial difficulty that needs to be addressed here. Cyberbullying influences both men and women victims. Harassment by way of cyberbullies is a big issue on social media. Cyberbullying affects both in terms of the mental and expressive manner of someone. So there's a need to plan a technique to locate and inhibit cyberbullying in social networks. To conquer this condition of cyberbullying, numerous methods have been developed using Machine Learning techniques. This paper presents a brief survey on such methods and finds that Support Vector Machine (SVM) is a very efficient method of cyberbullying detection that provides the highest accuracy.

To assist users in identifying the right book, recommendation systems are crucial to e-commerce websites. Methodologies that recommend data can lead to the collection of irrelevant data, thus losing the ability to attract users and complete their work in a swift and consistent manner. Using the proposed method, information can be used to offer useful information to the user to help enable him or her to make informed decisions. Training, feedback, management, reporting, and configuration are all included. Our research evaluated user-based collaborative filtering (UBCF) and estimated the performance of similarity measures (distance) in recommending books, music, and goods. Several years have passed since recommendation systems were first developed. Many people struggle with figuring out what book to read next. When students do not have a solid understanding of a topic, it can be difficult determining which textbook or reference they should read.

Personal health records (PHR) are a new type of health information exchange that allows PHR possessor to share their personal health details with a wide range of people, inclusive of healthcare professionals, close relative and best friends. PHR details are typically externalization and kept in third-party cloud platforms, reducing PHR possessor of the load of managing their PHR details while improving health data accessibility. To ensure the secrecy of personal health records maintained in public clouds, encrypting the health details prior to uploading on the cloud is a typical practice. The secrecy of the information from the cloud is guaranteed since the cloud does not know the keys used to encrypt the information. Elliptic curve cryptography encryption is used to attain secure and systematic way to interact PHRs with re-encryption server.

Organizations in the contemporary period face a number of problems as a result of the changing nature of the environment. One of a company's numerous problems is to please its workers in order to manage with an ever-altering and dynamic environment, attain success and stay competitive. The firm must meet the demands of its employees by offering appropriate working circumstances for enhancing efficacy, proficiency, job dedication, and throughput. Twitter is an online social networking site where users may share their thoughts on a wide range of topics, debate current events, criticize and express a wide range of feelings. As a result, Twitter is one of the greatest sources of information for emotion analysis, sentiment analysis, and opinion mining. Owing to a huge volume of opinionated material now created by internet users, Sentiment Analysis (SA) has emerged highly popular in both industry and research. Thus, this paper examines the problem by examining sentiment text as well as emotion symbols such as emoji. Therefore, utilizing the Flair Pytorch (FP) technique, an embedding type Natural Language Programming (NLP) system, and unique strategy for Twitter SA with a focus on emoji is presented. It overtakes state-of-the-art algorithms when it comes to pulling out sentiment aware implanting of emoji and text. Furthermore, 3520 tweets from an organization are accumulated as a dataset, with each tweet containing an emoji. As a result, the recommended FP technique has utilized the “en-sentiment” model for text classification and tokenization to determine the divergence of a sentence established on sentiment words, such as negative or positive, in the sentimental status of tweet, which could be assessed using the respective method’s confidence score.

Musical genres are used as a way to categorize and describe different types of music. The common qualities of musical genre members are connected with the song's melody, rhythmic structure, and harmonic composition. The enormous amounts of music available on the Internet are structured using genre hierarchies. Currently, the manual annotation of musical genres is ongoing. Development of a framework is essential for automatic classification and analysis of music genre which can replace human in the process making it more valuable for musical retrieval systems. In this paper, a model is developed which categorizes audio data in to musical genre automatically. Three models such as neural network, CNN, and RNN-LSTM model were implemented and CNN model outperformed others, with training data accuracy of 72.6% and test data accuracy of 66.7%. To evaluate the performance and relative importance of the proposed features and statistical pattern recognition, classifiers are trained considering features such as timbral texture, rhythmic content, pitch content, and real-world collections. The techniques for classification are provided for both whole files and real-time frames. For ten musical genres, the recommended feature sets result in a classification rate with an accuracy of 61%.

Hafiz, A. M.Reinforcement learning (RL) is being intensely researched. The rewards lie with the goal of transitioning from human-supervised to machine-based automated decision making for real-world tasks. Many RL-based schemes are available. One such promising RL technique is deep reinforcement learning. This technique combines deep learning with RL. The deep networks having RL-based optimization goals are known as Deep Q-Networks after the well-known Q-learning algorithm. Many such variants of Deep Q-Networks are available, and more are being researched. In this paper, an attempt is made to give a gentle introduction to Deep Q-networks used for solving RL tasks as found in existing literature. The recent trends, major issues and future scope of DQNs are touched upon for benefit of the readers.

Blind mobility is one of the most significant obstacles that visually impaired people face in their daily lives. The loss of their eyesight severely limits their lives and activities. In their long-term investigation, they usually navigate using a blind navigation system or their gathered memories. The creation of the work to develop a user-friendly, low-cost, low-power, dependable, portable, and built navigation solution. This paper (Smart Glasses for Blind People) is intended for people who are visually challenged. They encounter various threats in their everyday life, as current dependable gadgets fail to fulfil their expectations in terms of price. The major goal is to aid in a variety of daily tasks by utilizing the wearable design format. This project includes an ultrasonic sensor, a microcontroller, and a buzzer as far as hardware goes. Here, an ultrasonic sensor is used to identify obstacles ahead. When the obstacles are detected, the sensor sends the information to the microcontroller. The data is then processed by the microcontroller, which determines whether the barrier is within the range. The microcontroller delivers a signal to the buzzer if the obstacle is within the range. When an impediment is recognized within a certain range, a buzzer or beeper emits a buzzing sound. These data are saved in the cloud, and a mobile app is developed to keep track of the location and receive alarm notifications.

Dyslexia is the hidden learning disability where students feel difficulty in attaining skills of reading, spelling, and writing. Among different Specific Learning disabilities, Dyslexia is the most challenging and crucial one. To make dyslexia detection easier different approaches have been followed by researchers. In this research paper, we have proposed an effective feature selection and classification technique based on the Voting ensemble approach. Our proposed model attained an accuracy of about 90%. Further Comparative analysis between results of various classifiers shows that random forest classifier is more accurate in its prediction. Also using bagging and the Stacking approach of ensemble learning accuracy of classification was further improved.

The world population is increasing rapidly, and the consumption pattern of mankind has made a drastic drift over the recent years. Sustainable food production is important for our existence. The main focus of the study is to build a model that can predict the crop yield for spices such as black pepper, dry ginger, and turmeric based on given factors such as the district of cultivation, year of cultivation, area of production, production per year, temperature, and rainfall. The dataset was obtained from the Spice Board of India and Meteorological Database of India. The region primarily focused on is the districts of Kerala. Neural networks were used for the prediction, and a comparative study was done on different models such as deep neural network (DNN), recurrent neural network (RNN), gradient recurrent unit (GRU), long short-term memory (LSTM), bi directional long short-term memory (BiLSTM), backpropagation neural network (BPNN). The validation techniques taken into consideration include normalized mean absolute error (MAE), normalized root mean square error (RMSE), and mean absolute percentage error (MAPE). For dry ginger, GRU performed better compared to other algorithms followed by SRN. For black pepper, DNN performed better compared to other algorithms followed by simple recurrent network (SRN). For turmeric, GRU performed better compared to other algorithms followed by BPNN.

With the evolution of healthcare technologies, increased involvement and awareness are seen by mankind regarding health. This has widened the demand for remote healthcare than ever before. Henceforth, IoT explication in healthcare has sanctioned hospitals to lift patient care. Due to sudden heart attacks, the patients are going through a troublesome phase because of the non-availability of quality maintenance to the patients. This has expanded the sudden demise rates. Consequently, in this paper, the patient health monitoring system is proposed to dodge the unforeseen passing of humans. This remote healthcare system has made use of sensor technology which provides alerts to the patient in case of emergency. This system employs various sensors to fetch the data from the patient’s body and delivers the data to the microcontroller Arduino Uno. Therefore, the patient’s health can be tracked anytime according to your comfort and convenience.

The connection between the growth in the compensation of CEOs as compared to its employees and organisational performance has been an area of academic research with conflicting results over the past few decades. Surprisingly, with the continuous increase in the disparity of CEO compensation and average employees, there is scant literature on how this affects employee motivation and performance and its impact on other stakeholders of the organisation. This viewpoint brings to the forefront the need for further academic research on whether the compensation divide results in lower organisational performance and negatively affects shareholder wealth.

This study aims to identify the patterns and relationships of smartphone use on adolescent well-being. This study uses qualitative research methods through document analysis. The document analysis method in this study uses the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) technique. A systematic review of 32 studies was conducted to investigate the patterns and relationships of smartphone use on adolescent well-being. The results of the study found that there are four patterns that have been identified that can affect the well-being of adolescents. The four patterns are health, social, behavioral, and educational aspects. Based on the findings of this study, it is clearly proven that there is a relationship between smartphone use and adolescent well-being. However, negative effects were found to be higher than positive ones. Therefore, the use of smartphones among adolescents should be controlled and given attention by various parties such as parents, teachers, and the government.

Trust is very important in the non-profit organizations to give their cash to the association. Very few of the non-profit organizations use technology to make it simple for donors to give assets through them. Through this proposal, we aim to build a trustworthy crowd funding platform using blockchain technology. Due to the utilization of Blockchain and the removal of intermediaries, with smart contracts, it additionally reduces the time and effort required in primary cycle of raising money by having the option to gather subsidizes more productively. The major outcomes of the work are to develop the frontend of the application which is easy to use with modern, robust and intuitive features. The different pages of the web application are designed keeping performance in mind. The application includes a chat feature which allows investors and campaign creators to get in touch with each other. Provided with the security that blockchain offers, the exchange of messages is very secure, thereby making the process of crowdfunding fast and hassle-free.

The EEG recording resembles a wave with peaks and dips. Every peak and valley has distinct frequencies and is well defined. Abnormalities in this wave structure reflect a variety of brain-related disorders, including epileptic seizures, sleepiness, memory loss, tumour, drowsiness and so on. The EEG signal can detect a variety of brain-related disorders. In the head, there can be both minor and severe disorders. EEG datasets are gathered and analysed for peak conditions which are analysed in this paper. The input is an EEG data file, which consists of different noises which are removed using high-pass filter as a part of preprocessing. After the noise has been removed, independent component analysis (ICA) is used as a feature extraction methodology for extracting the features from the signal. Artificial neural network (ANN) is a deep learning concept used for classifying the signal from the extracted features. When compared to existing combinations on the market today, the proposed system, which is a combination of ICA and ANN, allowed the performance characteristics to reach a high value.

Agriculture is the most important element of any country in several ways. The growth in agriculture helps to improve the country’s economy. Today, AgriTech is a growing field in the world that helps to improve the crop quality and quantity. Using different advanced techniques, farmers can be benefited. So many challenges are faced by the farmers during crop production. Crop disease is one of the most difficult obstacle of agriculture field. Many advanced techniques such as deep learning methods have been introduced to detect the crop diseases. Some convolutional neural network (CNN) architectures used for tomato crop disease detection are discussed in this paper. Comparative study of different CNN models like AlexNet, GoogleNet, ResNet, UNet, and SqueezNet has been performed.

Organizations can use big data analytics to evaluate large data volumes and collect new information. It aids in answering basic inquiries concerning business operations and performance. It also aids in the discovery of unknown patterns in massive datasets or combinations of datasets. Overall, companies use big data in their systems to enhance operations, provide better customer service, generate targeted marketing campaigns, and take other activities that can raise revenue and profitability in the long run. Therefore, it’s becoming increasingly important to apply and analyze big data approaches for business growth in today’s data-driven world. More precisely, given the abundance of data available on the Internet, whether via social media, websites, online portals, or platforms, to mention a few, businesses must understand how to mine that data for meaningful insights. In this context, Web scraping is an essential strategy. As a result, this work aims to explain the application of the developed tool to the specific case of retrieving big data information about the particular companies in our sample. The paper starts with a short literature review about Web scraping then discusses the tools and methods utilized, describing how the developed technology was applied to the specific scenario of retrieving information about big data usage in the enterprises present in our sample.

The fast growth of wireless technology in today’s scenario has paved huge demand for licenced and unlicenced frequencies of the spectrum. Cognitive radio will be useful for this issue as it provides better spectrum utilisation. This paper deals with the study of machine learning algorithm for cognitive radio. Two supervised machine learning techniques namely SVM and KNN are chosen. The probability of detection is plotted using SVM and KNN algorithms with constant probability of false alarm. Comparison of the two machine learning methods is made based on performance with respect to false alarm rate, from which KNN algorithm gives better spectrum sensing than SVM. ROC curve is also plotted for inspecting the spectrum when secondary users are used.

In this project, we propose an automated system for Speech emotion recognition using convolution neural network (CNN). The system uses a 5 layer CNN model, which is trained and tested on over 7000 speech samples. The data used is .wav files of speech samples. Data required for the anlysis is gathered from RAVDESS dataset which consists of samples of speech and songs from both male and female actors. The different models of CNN were trained and tested on RAVDESS dataset until we got the required accuracy. The algorithm then classifies the given input audio file of .wav format into a range of emotions. The performance is evaluated by the accuracy of the code and also the validation accuracy. The algorithm must have minimum loss as well. The data consists of 24 actors singing and speaking in different emotions and with different intensity. The experimental results gives an accuracy of about 99.8% and a validation accuracy of 93.33% on applying the five layer model to the dataset. We get an model accuracy of 92.65%.

Present work describes a full bridge series resonant converter (FBSRC) for a 150 KW induction furnace. Resonant converter topologies are pretty common from few years in transmission of high-power applications: “pulse power supplies” and “particle accelerators”. The proposed converter topology is popular mainly in “applications of solid-state transformers” where fault tolerance is very much desired feature which is achieved from its redundancy without compromising efficiency of the system. This work explores full bridge SRC (FBSRC) used for transfer of “high voltage and power applications” with PI controller. It is also proposed to improve the fault tolerance of current converter by reconfiguration of the network during fault, which may negotiate the performance of the same but will prevent from halting. The FBSRC under open circuit fault is reconfigured in to half bridge SRC (HBSRC). The proposed work is implemented in MATLAB/SIMULINK environment. Various configurations are proposed with PI controllers for 150 KW induction furnace when FBSRC is experiencing open-circuit fault. Also, the switching losses with and without resonant converter are addressed.

An approach is proposed for the formalization procedure of the indicative functional representation of illegal actions of a computer intruder in the course of implementing the functions of unauthorized access (UA) to the resources of information systems (IS) of companies and enterprises. The completed formalization of the hierarchical scheme for the formation of the UA attribute space to the company's IS resources is the basis for the subsequent synthesis of an intelligent system for detecting UA attempts in conditions of hard-to-explain signs or a small number of them. It, in turn, makes it possible to effectively implement the primary formalization of illegal actions of computer intruders for the subsequent mathematical description of the UA probability parameter, for example, based on Markov chains. The proposed approach has been developed in relation to the task of substantiating the functional requirements for information security systems. The concretization of the multifactorial nature of the implementation of the UA functions to the IS information resources is based on the Markov chain. In the course of the study, a variant was considered in which the presentation of signs of UA is based on the construction of a combinational functional model of illegal actions of an information security violator (IS).

Mountain climbing, skiing, and hiking are some of the dangerous sports where many fatalities occur. Indian army is the one that is mostly affected by avalanches in India. Most of the casualties can be avoided if they can be addressed sooner. In the case of an avalanche, it is hard to find the people who got buried in it or even hard to find whether there are people buried under it. It is an important issue that is to be addressed. To tackle this problem, we have come up with a solution using long range (Lo-Ra) sensor-based technology. Using this methodology, the rescue team can pinpoint the location of the incident and the rescue time reduces drastically. When rescue can be done quickly, it drastically reduces the fatality rate. Hence, with the reported solution, we can revolutionize avalanche rescue process and thus create a positive impact in lives of people affected by this natural calamity. With this communication technology, we have achieved a wide coverage of 6 km.

In recent times, blockchain technologies have emerged to the maximum to provide a successful and promising era. Blockchain technology has proven promising application potentialities. It has modified people’s issues in a few areas due to its fantastic influence on many businesses and industries. Blockchain is the generation that the cryptocurrency is built on, and bitcoin is the first digital crypto-forex. It is a ledger that is publicly dispensed and facts every bitcoin transaction. Though there are research done on the security and privacy issues of blockchain, yet they lack a scientific examination on the safety of the blockchain system. This paper provides a scientific look at the security threats and discusses how two-factor authentication has been developed to cope with the lack of ability of single authentication structures. The foremost point of blockchain generation is that, it improves privacy, but then features additional two-component authentication to the block for a further layer of safety. Two-element authentication is also referred to as two-FA. Moreover, this paper includes, evaluation on the safety enhancement answers for blockchain, which may be used in the development of diverse blockchain structures and recommends few destiny directions to stir the research efforts in this field.

The lifestyle of the people has changed completely after the COVID-19 pandemic. The virus has also undergone various mutation and causing scare to human existence. Hence, it is important to monitor the health conditions of the faculty members and students before letting them into the college premises. So, we have introduced a system which implements 3 stage screening process. First, it checks whether the visitor is fully vaccinated or not. Then during the second phase, the health condition of the people is monitored. Finally, people without mask are also prevented from entering into college campus. In addition to it, the system also dispenses the hand sanitizing liquid to the visitors.

Smart environment is the need of today’s world. Smart environment means smart in every field like smart gadgets, smart cities, smart vehicles, smart healthcare systems and many more. The main aim of smart environment is to provide quality life and easiness to people and this can be achieved with the help of Internet of Things (IoT). Internet of Things is the web of devices that are connected with the help of Internet and smart in nature. As IoT is totally dependent on Internet, security and privacy is the primary concern in it. Traditional approaches to combat security and privacy threats are not applicable to IoT as these devices have smaller storage capacity, less computation capability and they are battery operated. So there is a key requirement to develop a smart intrusion detection system (IDS) that can work efficiently in IoT environment. IDS can be signature-based (SBID), anomaly-based (ABID) or hybrid in nature. There is also a major concern about latency in IoT which is not desirable in real-time applications. To overcome this latency issue edge computing came into existence. Machine learning is one of the promising approaches to implement IDS. The aim of the present research study is to provide a deep insight into different models based on machine learning to detect intrusion in edge-based IoT networks.

A furnace is an enclosed structure for controlled heating of solid or liquid raw materials to a high temperature. The existing furnaces used in most developing nations are expensive due to the importation cost from foreign countries. This study focuses on the development of smart refractory furnace (SRF) using locally sourced refractory materials that can withstand operational temperature above 12,000 °C. Some smart components were integrated into the furnace for easy monitoring and effective control from an android phone at a distance up to 100 m from the furnace. The developed furnace uses a heating coil of 750 watts and refractory lining made from kaolinite material which was sourced locally. It has a heating chamber volume of 3 × 106 mm3, and fiber grass was used as the insulating material to prevent heat loss. A user-friendly Android application named ‘iFurance’ was developed with Java Development Kit (JDK) and Android Software Development Kit (ASDK) in Android Studio 3.0 to control and monitor the smart furnace heating/cooling rate via wireless (Wi-Fi) module, which is integrated into the furnace through an embedded system provided by NodeMCU development board. To establish remote communication between the iFurnace and the hardware components, a programming language was used for coding and for the configuration of the hardware system. The developed SRF is safe to operate, and there is a great reduction in the cost and the time taken to operate it. This study can serve as a baseline for local manufacturers of smart electric furnaces.

The application of machine learning (ML) and natural language processing (NLP) is being extensively used for research in the area of healthcare and biomedicine. This pattern goes especially in accordance with the course, and the healthcare system is headed in the highly networked world which includes the World Wide Web where the regular users and health experts conduct discourses on health issues. To glean knowledge from medical texts and discourses which are mostly in text in natural language, many text analysis frameworks and techniques have been designed. Those techniques do not produce a comprehensive summary about the content related to a disease from content available online. So in our work, we propose text summarization based on natural language processing algorithms combined with machine learning algorithms for extracting all information pertaining to a disease from online healthcare forums.

In terms of house security, the door is crucial. To keep the residence safe, the inhabitants will keep the door shut at all times. However, house residents may forget to lock the door because they are in a rush to leave the house, or they may be unsure whether they have closed the door or not. This paper presents a door status monitor prototype utilizing ESP8266 NodeMCU microcontroller board interfaced with a magnetic reed switch. Any change in the door status either being opened or being closed a notification message is received in the telegram account. The need is to have access to the Internet on your smartphone, and you will be notified no matter where you are. This prototype aids in security and monitoring of various valuable items in real time.

The Internet of things (IoT) has made healthcare applications more accessible to the rest of the globe. On a wide scale, IoT has been employed to interconnect therapeutic aids in order to provide world-class healthcare services. The novel sensing devices can be worn to continuously measure and monitor the participants’ vital parameters. Remotely monitored parameters can be transferred to medical servers via the Internet of things, which can then be analyzed by clinicians. Furthermore, machine learning algorithms can make real-time decisions on the abnormal character of health data in order to predict disease early. This study presents a machine learning and Internet of things (IoT)-based health monitoring system to let people measure health metrics quickly. Physicians would also benefit from being able to monitor their patients remotely for more personalized care. In the event of an emergency, physicians can respond quickly. In this study, the Espressif modules 8266 are used to link health parameter sensors, which are implanted to measure data and broadcast it to a server. With the real-time data from the sensors, three statistical models were trained to detect anomalous health conditions in the patients: K-nearest neighbors (KNNs), logistic regression, and support vector machine (SVM). Due to abnormal health markers, these models uncover patterns during training and forecast disease in the subject.

Balaji, Lavanya Anita, H. B. Ashok Kumar, BalajiVolatility has become increasingly important in derivative pricing and hedging, risk management, and portfolio optimisation. Understanding and forecasting volatility is an important and difficult field of finance research. According to empirical findings, stock market returns demonstrate time variable volatility with a clustering effect. Hence, there is a need to determine the volatility in Indian stock market. The authors use Nifty Energy data to analyse volatility since the Nifty Energy data can to be used to estimate the behaviour and performance of companies that represents petroleum, gas, and power sector. The results reflect that Indian stock market has high volatility clustering.

In the twenty-first century, it’s important to communicate with each other to stay connected with everyday events. IoT has become most prominent technology in many applications over the past years. Especially in medical applications, IoT is used to exchange the collected information from IoT smart devices to the server. In healthcare monitoring system, it’s important to maintain the patient health record in server for monitoring and tracking patient health information without any privacy issues. Maintaining a secured of electronic health record (EHR) is one of the major concerns in this vast society. To improve the security in healthcare monitoring system, many algorithms have been implemented. In this paper, the security of IoT healthcare data with some data analytics techniques such as RFID, deep learning, machine learning and blockchain is analyzed. Apart from many issues in healthcare monitoring system, this analysis aims to discuss and exhibits how these analytics techniques impact the prediction and decision making based on the performance, security, data transportation efficiency and accuracy.

Electrocution is a major fatal issue faced by electricians worldwide. This proposed system incorporates a password-protected Arduino-controlled circuit to protect lineman against electrocution. It has an Arduino unit linked to a relay, a keypad and a liquid crystal display attached to the Arduino to show whether the power supply in the line is switched ON or OFF. When the lineman inputs the correct password, the Arduino uses a relay to turn OFF the power supply. This mechanism cuts the circuit when an electrical wire becomes defective, and the lineman may safely repair it. After returning to the substation, the lineman can turn ON the power. By regulating the power supply on the electrical lines, this system protects the safety of the lineman and reduces the risk of electrocution injuries.

Handwritten character recognition is a very interesting and challenging branch of pattern recognition. It has an impressive range of applications, from filling up banking applications to digitizing a text document. Handwritten character recognition is difficult because of the huge variety of writing styles, the similarity between different handwritten characters, the interconnections, and overlapping between characters. The main motive of this study/review is to compare and summarize the performance of different models and techniques used for the recognition of Kannada handwritten characters. The paper focuses on three main classifiers—Convolutional Neural Network (CNN), Support Vector Machine (SVM), and the K-nearest neighbour classifier (KNN). This review paper also highlights the various pre-processing and feature extraction techniques that were implemented by other authors and identifies their respective research gaps. The subsequent aim of this survey is to develop a new powerful and efficient model that provides improved accuracy, efficiency, and the least error rates which can be applied over a large character set of the Kannada language.

The implementation of network functions is based on the separately configured devices. This implementation has a significant effect on the operational expenses and capital expenses. This separation will also reduce and facilitate the deployment of new services with better overhead and faster time. The developed IPv6 experimental testbed was modeled using Mininet network simulation version 2.2.2170321. The Mininet software was installed and configured on Ubuntu Linux version 14.04.4–server-i386 simulator operating system environment. The flow-visor protocol was used to create the network slices in the topology while the floodlight protocol is used to create the controller, virtual switches and virtual hosts within the Mininet network emulator. The prime focus of this study is to develop a mechanism for network function virtualization in an IPV6-enabled SDN. The analysis of the percentage line rate for IPv4 was 95.27% as compared to the developed model of IPv6 with a line rate of 54.55% for each network slice.

Health practice has to be accountable not only for expertise and nursing abilities but also for the processing of a broad variety of details on patient treatment. By successfully handling the knowledge, experts will consistently establish better welfare policy. The key intention of Decision Support Systems (DSSs) is to provide experts with knowledge where and when it is needed. Therefore, these systems have experience, templates and resources to enable professionals in different scenarios to make smarter decisions. It seeks to address numerous health-related challenges by having greater access to these services and supporting patients and their communities to navigate their health care. This article describes an in-depth examination of the classical intelligent DSSs. Also, it discusses the recent developments in smart systems to support healthcare decision-making. A comparative analysis is presented regarding their strengths and challenges in such DSSs to suggest a solution to make smarter decisions.

Air pollution is the major concern in urban areas due to the impacts of air pollution on health and environment. A number of studies reveal the importance to be aware of air pollution and air pollution monitoring systems. This paper is a review article based on different methods implemented by the researchers to know about the concentration levels of particles and gases in air. The paper focuses on the different networks that are used for the pollution monitoring system and how they work effectively.

Agriculture serves as the backbone of a country’s economy and is vital. Various tactics are being implemented in order to maintain awareness of good and disease-free yield creation. In the rural areas, steps are being done to aid ranchers with the best kind of insect sprays and pesticides. In a harvest, disease usually affects the leaves, causing the crop to lack proper nutrients and, as a result, its quality and quantity to suffer. In this study, we use programming to recognise the impacted region in a leaf organically and provide it with a better arrangement. We use several image processing algorithms to determine the impacted region of a leaf. It consists of several steps, including the acquisition of images. It consists of many processes, including image acquisition, image pre-processing, division, and highlights extraction.

The development in any field is the way to success. IoT is one of the ways to develop things in our day-to-day life which directly or indirectly helps in automation and energy conservation. IoT get connected to the devices through a sensor which helps in making things easy to work. This paper represents the remote controlling of the devices using IoT. In this paper, the luminaries are controlled remotely with the presence and absence of human beings. Additionally, the speed control of the fan is achieved as per the atmospheric conditions like humidity and temperature automatically through sensor. Controlling and monitoring the electric devices gets easier when connected to IoT. A microcontroller, sensor, relay and electronic devices are connected together to get the IoT work. ESP8266 microcontroller is used to connect the devices to Internet through Wi-Fi which provides data to and from cloud. Relays are used to receive data from cloud and sensors are used to send data to the cloud. These developed IoT devices help to improve the lifestyle and manage the use of electricity in daily life. The IoT and cloud can help to keep the record of daily electricity use for analysis and conservation purpose. The hardware has been developed successfully and the mobile app is used by connecting it to the microcontroller and adding conditions accordingly for the remote monitoring of the said devices at home. These devices can be controlled from anywhere through the mobile application. It is working satisfactorily and energy conservation is also possible due to automation.

A great nation is a nation that upholds the services of its predecessors, namely the nation's heroes who fought for the independence of this Indonesian state in 1945. The current generation is expected to appreciate the services of heroes by respecting this nation's history and the current generation's duty to fill this independence by continuing its values. It is essential for the transformation of knowledge to each generation to seriously study the history of this nation through the delivery of historical subject matter. Therefore in this paper, a web-based history learning application is developed which is limited to 6th-grade elementary school students where the proposed system is modeled using use case diagrams, and after that by using class diagrams, the relationship between database tables is displayed, and in the end, the user interface is shown as implementation using software Personal Home Pages (PHP) and MySQL database.

Paul, Amala Mary Salim, A.Text summarization is the process of generating a condensed text form from single or multiple text documents. Extractive summaries are generated by stringing together selected sentences taken from the input text document without any modification, whereas abstractive summaries convey the salient ideas in the input, may reuse phrases or clauses from the input text, and may add new phrases/sentences which are not part of the input text. Extractive summarization guarantees that the generated sentences will be grammatically correct, whereas abstractive methods can generate summaries that are coherent, at the expense of grammatical errors. To this end, we propose to integrate an extractive method based on lexical chains and an abstractive method that uses concept generalization and fusion. The former method tries to identify the most important concepts in the input document with the help of lexical chains and then extract the sentences that contain those concepts. The latter method identifies generalizable concepts in the input and fuses them to generate a shorter version of the input. We evaluated our method using ROUGE and the results show that the integrated approach was successful in generating summaries that are more close to human generated versions.

Smart automotive web applications facilitate the easy purchase of automotive accessories online and offer customers real-time automobile services. Such an application offers customers auto parts alongside a great user experience with first-rate quality and customer service. Our website project furnishes all the relevant information needed on the product, product type, model, company, order, items ordered, and the status of the order tracked. Auto parts retailers and online mechanics have long been able to rely on product quality and the niche nature of the said products to set themselves apart. The fierce growth of online competition, however, has been driving consumer-friendly branding strategies. Further, our website provides links to miscellaneous auto spares stores so customers can have access to a wide range of products to choose from and be able to compare prices as well. The user-friendly nature of the application’s UI makes it easy for customers to browse products and eliminates the need to re-specify the automobile type every time a user refreshes or opens another page.