International Conference on Innovative Computing and Communications
Proceedings of ICICC 2022, Volume 3
- 2023
- Book
- Editors
- Deepak Gupta
- Ashish Khanna
- Aboul Ella Hassanien
- Sameer Anand
- Ajay Jaiswal
- Book Series
- Lecture Notes in Networks and Systems
- Publisher
- Springer Nature Singapore
About this book
This book includes high-quality research papers presented at the Fifth International Conference on Innovative Computing and Communication (ICICC 2022), which is held at the Shaheed Sukhdev College of Business Studies, University of Delhi, Delhi, India, on February 19–20, 2022. Introducing the innovative works of scientists, professors, research scholars, students and industrial experts in the field of computing and communication, the book promotes the transformation of fundamental research into institutional and industrialized research and the conversion of applied exploration into real-time applications.
Advertisement
Table of Contents
-
Effective Data-Sharing Method for Multiple ICR Management in Autonomous Distributed Control Systems
Takaaki Kawano, Daiki Nobayashi, Takeshi IkenagaThe chapter discusses the challenges of managing multiple ICRs in autonomous distributed control systems, highlighting the need for efficient data-sharing methods. It introduces a sink node-based approach that aggregates and delivers data, reducing wireless communication loads and ensuring reliable information exchange. The proposed method, validated through simulations, demonstrates significant improvements in data packet arrival ratios and reduced communication overhead compared to existing methods.AI Generated
This summary of the content was generated with the help of AI.
AbstractIndustrial carrier robots (ICRs), which are designed to deliver packages to designated destinations automatically in automated and semi-automated facilities, can potentially contribute to resolving labor shortages and improving productivity. Conventional ICRs operate within a centralized system in which a remote server manages both general task assignments and collision avoidance. However, such systems entail significant infrastructure maintenance costs. This paper focuses on autonomous operations and autonomous distributed control methods in which ICRs first share task and location information, and then distribute upcoming tasks among themselves based on that shared information. However, when each ICR is required to communicate with all the other ICRs in a distributed system, the number of wireless communications will increase with the number of system ICRs, thereby wasting wireless communication resources. In this paper, we propose a method that reduces wireless communication loads by using a sink node to streamline communication, and then presents simulation evaluation results that show it can effectively achieve autonomous distributed control in ICR systems. -
Applicability of Communication Technologies in Internet of Things: A Review
Parul Jhingta, Amol Vasudeva, Manu SoodThe chapter 'Applicability of Communication Technologies in Internet of Things: A Review' delves into the diverse communication technologies essential for IoT, such as RFID, NFC, Bluetooth, Zigbee, LPWAN, Wi-Fi, and cellular communication. It offers a comprehensive analysis of each technology's communication range, frequency spectrum, power consumption, and security features. A comparative study of these technologies is presented, emphasizing their strengths and weaknesses in various IoT applications. The chapter also discusses the security challenges faced by these technologies and the need for enhanced security solutions in the future. This detailed exploration of IoT communication technologies provides valuable insights for professionals seeking to optimize their IoT applications.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe advancement in technology has made interaction among objects a reality. A network of devices can be created by linking them via the Internet and facilitating communication among these devices by sending and receiving the messages. This network of objects is called the Internet of Things (IoT). Various communication technologies are used for connecting devices in IoT; however, the selection of communication protocol depends on the requirement of the application. This paper discusses some of the most commonly used IoT communication technologies. A comparison has been made among these technologies on the basis of various parameters, such as communication range, amount of power consumed, the area covered, data transmission rate, frequency range, and the applications where they are used. Additionally, the pros and cons of these communication technologies have also been discussed. -
A KNN-Based Intrusion Detection Model for Smart Cities Security
Mohamed Abdedaime, Ahlam Qafas, Mounir Jerry, Azidine GuezzazThe chapter delves into the development of a K-NN-based intrusion detection model tailored for smart cities. It begins by highlighting the importance of big data and IoT in transforming urban services and the challenges they pose for security. The authors propose a hybrid approach using K-NN to distinguish between normal and abnormal activities, enhancing detection accuracy. The methodology involves data collection, preparation, and training, with the K-NN algorithm at its core. Experimental results demonstrate the model's superior performance compared to traditional methods like SVM and DT, showcasing its potential to secure smart city networks effectively. The chapter concludes with insights into future work, focusing on improving data quality techniques to bolster detection accuracy.AI Generated
This summary of the content was generated with the help of AI.
AbstractCurrently, information technologies are integrated to acquire, manage, and analyze data circulated within smart cities networks and systems. With the growth of technologies, security issues and privacy have been a significant field to anticipate attacks that infect resources. Therefore, many research works aim to include sophisticated techniques, such as artificial intelligence (AI), to monitor smart cities networks, improve their security and then protect data exchanged within their networks. This paper presents an enhanced approach for Internet of Thing (IoT) security in smart cities using AI techniques. Furthermore, we describe in details several suggested solutions to validate our approach. From experimental study, the proposed model gives robust results in terms of 98.4% accuracy (ACC), 96.1% detection rate (DR), and 2.9% false alarms (FAR). The obtained results prove that our approach makes accurate decisions compared with other models. -
Design of Asymmetric Microstrip Quad-Band Reconfigurable Antenna
D. P. Derish, G. Shine Let, C. Benin Pratap, J. John PaulThe chapter focuses on the design and analysis of an asymmetric microstrip quad-band reconfigurable antenna. The antenna incorporates ideal switches to achieve frequency reconfigurability, enabling operation across four distinct frequency bands: 6, 5.3, 3.38, and 2.84 GHz. The design utilizes a hook-shaped radiating strip and a partial ground plane, with the radiating strip length altered by the switching conditions. The chapter presents a comprehensive analysis of the antenna's performance, including reflection coefficient characteristics, current distribution, and radiation patterns under different switching states. The antenna's efficiency and gain are also evaluated, demonstrating its suitability for wireless communication applications such as WLAN and 5G. The use of ideal switches in the design is highlighted, with future work suggesting the integration of PIN diode RF switches for practical implementation.AI Generated
This summary of the content was generated with the help of AI.
AbstractFrequency reconfigurable antenna has the greatest demand in wireless communication applications. In this paper, a quad-band reconfigurable antenna is proposed. Asymmetric microstrip feed is provided to the antenna radiating strip. To provide reconfigurability, two switches are integrated with the antenna radiating strip. This provided a change in the antenna’s current distribution based on the switch condition. The designed antenna has an overall dimension of 22 × 12 × 1.57 mm3. Relying on the state of the switch, the antenna operates in 2.8, 3.4, 5.3, and 6 GHz. On all operating frequency bands, the radiation efficiency of the antenna is greater than 80%. -
COVID-19 and Associated Lung Disease Classification Using Deep Learning
Yogesh H. Bhosale, Priya Singh, K. Sridhar PatnaikThe chapter delves into the application of deep learning to diagnose lung diseases, particularly COVID-19, through chest X-ray images. It introduces the DenseNet169 architecture, which is employed to classify nine different lung diseases with high accuracy. The methodology involves data collection, preprocessing, and model training, with a focus on performance metrics such as accuracy, precision, recall, and specificity. The study highlights the potential of deep learning in enhancing diagnostic accuracy and efficiency, especially in the context of the COVID-19 pandemic. The chapter also discusses the limitations and future directions of the proposed model, making it a valuable resource for researchers and practitioners in the field of medical imaging and artificial intelligence.AI Generated
This summary of the content was generated with the help of AI.
AbstractCoronavirus 2019, well familiar as COVID-19, is a virus that causes significant pneumonia and has varying degrees of severity based on the patient’s capability. The coronavirus infection was initially discovered in the Chinese town of Wuhan in Dec. 2019 and quickly spread around the world as a worldwide pandemic. Early detection of positive cases and prompt treatment of infected individuals is required to prevent viral transmission. The necessity of testing kits for COVID-19 has grown, and most of the growing nations are encountering a scarcity of testing kits as new cases emerge daily. In this case, the current study is with the help of radiology imaging techniques, including X-ray, to help in detecting COVID-19. In several disease diagnoses and decision-making circumstances, the information provided in a chest X-ray sample is sufficient to assist medical experts. With the help of a Deep Convolutional Neural Network (CNN), the research proposes an intelligent method to classify various nine diseases, including coronavirus disease 2019, with the help of X-ray instances applying pre-trained DenseNet169 architecture. The fundamental goal of this paper is to classify lung diseases with COVID-19. The used datasets are collected from online repositories, i.e., Kaggle and NIH contained X-ray images of all nine classes. This dataset consists of 1200 images for each class. Various rotations and scaling operations have been applied to the dataset, and the data in the dataset are divided into the test, train, and validation sets. In comparison to other studies in the literature, our models performed well. The highest accuracy attained by DenseNet169 is for COVID-19 with an accuracy of 99.4%, F1-score of 97.5%, precision of 97%, recall of 98%, and specificity of 99.6%. The highest True Positive rate we got in this is 99% for COVID-19, followed by 97% for Cardiomegaly. The minimal rate we got is 88% in Atelectasis. DesnseNet169 proved to be more robust and reliable in classifying nine classes, including COVID-19, after adopting a testing strategy proposed in the literature, making them suitable methods for classification using chest X-ray samples. Which in the future will be helpful for radiologists and physicians during the pandemic of Coronavirus 2019. -
Type 2 Diabetes Prediction Using Machine Learning and Validation Using Weka Tool
Govind Madhav, Shalini GoelThe chapter delves into the growing prevalence of Type 2 Diabetes (T2D) and its associated risk factors, emphasizing the importance of early detection through machine learning techniques. It explores various machine learning algorithms, including logistic regression, decision trees, and support vector machines, to predict T2D using a dataset from Vanderbilt University. The study compares the performance of these algorithms using both Python's sklearn library and the Weka tool, highlighting the superior accuracy of logistic regression. The chapter also discusses the implications of T2D and the potential for developing web-based applications to predict and manage the disease, offering valuable insights for healthcare professionals and researchers alike.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe purpose of this research is to figure out who is at risk for diabetes based on their lifestyle and family history. Accurate and timely predictions would be beneficial to people seeking ways to include a healthy lifestyle and therapy into their plans. To forecast the risk of type 2 diabetes, various machine learning algorithms are applied. These algorithms have undergone extensive testing to ensure the greatest levels of accuracy, which is now a must in the medical profession. After that, the WEKA tool is used to verify the algorithms that have been developed. Weka is a data mining toolkit that includes several machine learning algorithms. Data pre-processing, classification, regression, clustering, association rules and visualization are all available through Weka. Of all the approaches investigated in this study, we determined that logistic regression had the greatest accuracy. Individuals can self-evaluate their diabetes risk once the model has been trained to a high level of accuracy. -
DroidApp: An Efficient Android Malware Detection Technique for Smartphones
Manish Kumar, Kakali Chatterjee, Ashish SinghThe chapter 'DroidApp: An Efficient Android Malware Detection Technique for Smartphones' introduces a novel method for detecting malicious Android applications. By employing a graph-based approach, the DroidApp model reduces computational costs and execution times, making it a highly efficient tool for malware detection. The model is validated using the Drebin dataset, demonstrating superior performance in accuracy, precision, recall, and AUC compared to existing methods. This chapter provides a comprehensive analysis of the model's algorithms and results, highlighting its potential to revolutionize the field of mobile malware detection.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe huge development of Internet interconnectivity has brought about an extensive expansion in digital assault occasions, a considerable lot of which have decimating and serious impacts. Malware is one type of cyber assault that is becoming more prevalent day by day. The conflict between security researchers and malware creators is an ongoing battle with the quick evolution of malware as technological innovation develops. The aim of this research work is to detect Android malware using a recommendation system with less space and time complexity. This detection technique uses an app similarity graph (ASG) for Android application analysis. With this analysis, we achieved an accuracy of 98.22%. -
A Hybrid Approach to Optimize Handover Margin in UWSN by Integration of ACO with PSO and MVO: A Comparative Analysis
Seema Rani, Anju, Anupma SangwanThe chapter delves into the optimization of handover margin in Underwater Wireless Sensor Networks (UWSNs) using a hybrid approach that combines Ant Colony Optimization (ACO) with Particle Swarm Optimization (PSO) and Multi-Verse Optimizer (MVO). The introduction outlines the critical role of UWSNs in monitoring underwater environments and the challenges they face, such as high costs and equipment failures. The optimization techniques, including PSO, MVO, and ACO, are explained in detail, highlighting their potential to enhance network performance. The proposed model integrates these techniques to optimize handover margin, reduce training time, and increase accuracy. The results and discussions showcase the effectiveness of the hybrid approach, with a particular focus on energy efficiency. The chapter concludes by emphasizing the scalability and flexibility of the proposed solution and its potential for future research in underwater wireless sensor networks.AI Generated
This summary of the content was generated with the help of AI.
AbstractUnderwater Wireless Sensor Network (UWSN) in the ocean is becoming more and more popular as a tool for marine monitoring and data collection. Sensor nodes’ mobility models for UWSN vary from WSN devices on the ground. This variation complicates handover prediction in these networks, which is a key difficulty. As a result, the current study focuses on handover optimization. UWSN handover and optimization in UWSN handover have received only sporadic attention. Thus, this paper offers a simulation of sensor nodes’ movement calculated data. The speed and direction of the water flow between the data points are included in this dataset. Sensor nodes and base stations in a UWSN are used to simulate the suggested simulation. For the handover optimization job, all of the handover events that occur throughout the simulation are collected. Handover events are optimized using PSO, MVO, and ACO techniques based on historical data obtained from previous handovers. This paper provides the ideal option to increase reliability in the case of UWSN. Performance analysis of the proposed model indicates the excellent quality in the case of the measured evolution scores. -
Cyber Risks and Security—A Case Study on Analysis of Malware
Moulik Agrawal, Karan Deep Singh Mann, Rahul Johari, Deo Prakash VidyarthiThe chapter delves into the intricate world of malware, with a particular focus on Keylogger and Adware. It begins by defining malware and its various types, setting the stage for an in-depth analysis of Keylogger and Adware. The authors demonstrate how these malicious software programs can be used to monitor user activity and display unwanted advertisements, respectively. Real-world case studies, such as the Anthem data breach and the Slammer adware incident, are highlighted to underscore the severe consequences of malware attacks. The chapter also provides a step-by-step guide on how to create and disguise these malware programs, offering a unique perspective on their functionalities. Furthermore, it discusses the social implications of cyber threats, particularly in the context of the COVID-19 pandemic. The authors conclude by proposing prevention techniques to safeguard against such malware, making this chapter a valuable resource for anyone looking to understand and combat these cybersecurity threats.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe automation of business enterprises, the bulk computer storage to store sensitive information, various distributed applications being accessed via the Internet, all these have become critical for the government, financial institutions, and millions of users. Cyber security plays an important role to identify different types of risks and to overcome the challenges of securing the information thereby preventing financial and reputational damage to the organization and its customers. This work introduces some known threats to Cyber Security—Keylogger and Adware, and how they are spoofed and sent to a victim, with which an attacker can surreptitiously break into a network system. This study shows how anyone on the Internet can fall prey to such malware attacks, and how a user needs to protect himself/herself with such increasing number of Internet users. Approaches to prevent these malware programs are also discussed in this paper. -
Hybrid Technique for Human Activities and Actions Recognition Using PCA, Voting, and K-means
Navjot Kaur Sekhon, Gurpreet SinghThe chapter delves into the critical role of human activity recognition in various domains, such as senior citizen monitoring and smart home technology. It introduces a hybrid technique that leverages Principal Component Analysis (PCA) for dimensionality reduction, K-means for clustering, and a voting classifier for robust classification. The method addresses the challenge of high-dimensional feature vectors by employing filter and wrapper methods for feature selection. The proposed framework is validated through experiments, demonstrating superior accuracy, precision, and recall compared to traditional logistic regression models. The chapter also provides a detailed review of existing human activity recognition techniques, setting the stage for the innovative hybrid approach presented.AI Generated
This summary of the content was generated with the help of AI.
AbstractBecause of the proclivity for providing information about a group’s character and mental state, human activities are considered to be important in people-to-people communication and social relations. It is really tough to abstract this kind of complex data. The technical fields of computer vision and machine learning are built on a person’s capacity to track the behaviors of others, and the term “activity” refers to a set of acts performed by the human body that engage multiple portions of the body at the same time. Any form of observation is compared to a pre-defined pattern in computer vision, and the action is then detected and labeled for further identification. In this study, a hybrid technique for recognizing human activities is proposed. Principal Component Analysis, K-means, and voting categorization have all been combined in this hybrid technique. It has been observed that in terms of precision and recall, the voting classification outperforms the present logistic regression classification. The average results shown the proficiency level of about 96% for the identification of different human activities. -
Efficient Authenticated Key Agreement Protocol for Cloud-Based Internet of Things
V. Muthukumaran, V. Vinoth Kumar, Rose Bindu Joseph, Meram Munirathnam, I. S. Beschi, V. R. NivedithaThe chapter delves into the critical need for secure and efficient data transmission in cloud-based Internet of Things (IoT) systems. It introduces an innovative authenticated key agreement protocol that integrates encryption and digital signatures, thereby reducing computational costs and enhancing security. The protocol is based on the intractability of the Discrete Logarithm Problem (DLP) and extends the principle of authenticated key agreement to elliptic curve cryptography. The methodology focuses on safeguarding IoT devices and systems, addressing the unique security challenges posed by IoT data storage architecture. The proposed scheme is compared with existing methods, demonstrating superior performance in terms of security features and computational cost. The chapter concludes by highlighting the practical implementation of the protocol in a standard CIoT-based network, showcasing its effectiveness in maintaining data integrity and secrecy.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe key agreement with an authenticated key protocol is a cryptographic primitive that, in theory, combines the operations of digital signature and public-key encryption in one step, resulting in a reduced computational cost than the usual signature-then-encryption technique. Authentication is another method for achieving simultaneity of secrecy and validation throughout the Internet of Things (IoT). We introduce a new authenticated key agreement protocol approach in this paper, which is based on the intractability of a group-based polynomial decomposition issue and can be employed in CIoT-based systems for secure data transfer. -
Atamnirbhar Gaon—An Inhouse Employment Tool for Migrant Workers
Bhawna Suri, Shweta Taneja, Gaurav Dhingra, Ankush Goyal, Bhavay SharmaThe chapter delves into the pressing issue of rural-to-urban migration driven by lack of job opportunities and low agricultural returns. It introduces the Atamnirbhar Gaon application, a innovative tool designed to connect rural job seekers with local employers. The application supports multiple languages and voice commands, making it accessible to a broad audience. It also provides essential information on current market trends, expert agricultural advice, and vaccination awareness. The chapter includes a case study from Bakkas village in Uttar Pradesh, demonstrating the application's potential to transform rural employment landscapes. The successful pilot test highlights the application's feasibility and potential impact on reducing urban migration and promoting self-reliant villages.AI Generated
This summary of the content was generated with the help of AI.
AbstractIndia is a country where majority of the population resides in rural areas. For the development of India, it is necessary to focus on the core of India, i.e., the villages. Now, for developing villages, demand needs to be generated and supply chains to be put in place for ensuring fast-paced development. There are a plethora of employment opportunities and a million plus one can be created but villagers generally tend to relocate to metro cities for better facilities, resulting in overburdening of cities as well as slow development of villages. During the pandemic, India witnessed a large-scale migrant crisis. To bridge the gap between employers and employees, primarily focused on villages, we have developed an application—Atamnirbhar Gaon. Using this application, the workers can get equitable employment prospects like entrepreneurship, businesses, and skill set enhancement in their respective hometown. This venture can boost the development of villages and hence the development of the nation. This is a bilingual application—supports both Hindi and English; any illiterate person can also avail the functionality of this application through voice, know about the places near him where a person can learn new technologies or update his skills, weather updates for sowing the crops, latest updates in farming, and lastly can also get the importance of vaccination against Covid-19 and the available slots for vaccination. -
Deep Learning Approach for Early Diagnosis of Jaundice
Dhananjay Kalbande, Anuradha Majumdar, Pradeep Dorik, Prachi Prajapati, Samira DeshpandeThe chapter delves into the significance of early diagnosis of jaundice, a condition characterized by elevated bilirubin levels, affecting both newborns and adults. It provides an in-depth look at the pathophysiology and global impact of jaundice, highlighting its severe consequences such as kernicterus. The authors introduce two advanced deep learning models—ResNet50 and Detectron2—for detecting jaundice in eye images. These models demonstrate high accuracy and precision, offering a promising, non-invasive approach to early diagnosis. The chapter concludes by emphasizing the potential of these AI-based tools to enhance medical interventions and improve patient outcomes.AI Generated
This summary of the content was generated with the help of AI.
AbstractJaundice is a yellow discoloration of the body caused by an increased level of bilirubin. Globally, newborns and adults are both affected by this condition. Newborns are highly prone to jaundice due to immature liver having unbalanced metabolism. Late diagnosis of jaundice in newborns results in kernicterus and provides a site for other complications too. Nevertheless, early diagnosis with smartphone Artificial intelligence (AI)-based application can be a promising tool. This proposed intervention is having low-cost, non-invasive, and easy to use. With the growing demand of Artificial intelligence (AI) in medical field, it has been recognized that AI can also be useful in the medical field. We developed the jaundice classification system by using deep learning algorithm. We used two deep learning models viz. ResNet50 and masked RCNN (Detectron2 implementation) to predict jaundice from the image of jaundice affected eyes. Our dataset consists of 98 images of jaundice affected eyes and 50 images of normal eyes. The Mask-RCNN model can segment and classify jaundice affected eyes images accurately. The experimental analysis shows that the Mask-RCNN Deep learning model is more accurate than ResNet50 model. -
Recent Trends in Opinion Mining using Machine Learning Techniques
Sandeep Kumar, Nand KumarThe chapter delves into the evolution of opinion mining, a critical aspect of data mining that focuses on extracting and understanding public sentiments. It reviews various machine learning techniques, such as Naive Bayes, Support Vector Machines, and deep learning models, and their applications in sentiment classification. The authors discuss the challenges faced in opinion mining, including spam detection and data imbalance, and highlight the potential of advanced deep learning models to address these issues. The chapter also explores the wide-ranging applications of opinion mining, from product and service improvements to policy-making and market analysis, making it a valuable resource for professionals seeking to leverage sentiment analysis in their fields.AI Generated
This summary of the content was generated with the help of AI.
AbstractOpinion mining is a sub-field of data mining and natural language processing that concerns extracting users’ opinions and attitudes towards products or services from their comments on the web. Human beings rely heavily on their perceptions. When making a choice, other people’s perspectives are taken into account. Currently, billions of Internet users communicate their opinions on several disciplines via journals, discussion forums, and social media sites. Companies and institutions are constantly interested in hearing what the general public thinks regarding their services and goods. It is critical in e-commerce and e-tourism to dynamically evaluate the vast number of user data available on the Internet; as a result, it is essential to establish ways for analysing and classifying it. Opinion mining, also known as sentiment classification, autonomously extracts opinions, views, and feelings through literature, audio, and data inputs using natural language processing. This paper provides an understanding of the machine learning strategies for classifying comments and opinions. This paper compares various machine learning-based opinion mining techniques such as Naive Bayes, SVM, genetic algorithm, decision tree, etc. -
Auto Surveillance Using IoT
Eldho Paul, M. S. Kalepha, T. Naveenkumar, Mugeshbabu ArulmaniThe chapter delves into the advancements of IoT in security systems, highlighting the increasing demand for surveillance due to rising theft rates. It discusses the integration of PIR sensors and GPS for real-time monitoring and alert systems, showcasing a smart surveillance solution that detects unwanted movements and sends alerts to users. The proposed system, using the Esp8266 NodeMCU module, analyzes data from sensors and sends it to the ThingSpeak website, enabling users to monitor and receive notifications via SMS. The chapter also provides a comparative analysis of existing systems and explores the future potential of IoT in security, including video recording and remote monitoring.AI Generated
This summary of the content was generated with the help of AI.
AbstractUsers can connect things, systems, network, services, and, in particular, control systems using the Internet of Things (IoT). The design and implementation of an IoT-based security surveillance system employing Node MCUs and Wi-Fi network connectivity is described in this study. Adding wireless fidelity to embedded systems offers up a world of possibilities, such as worldwide monitoring and control, secure data storage, and much more. Sensor nodes and a controller part make up this surveillance system. Remote user alerts and mobility are two of the system’s primary features. When a Wi-Fi connected microcontroller is integrated with a PIR sensor, the sensor looks for object movements and sends an alert to the user via an online cloud platform (ThingSpeak). This surveillance system is made up of sensor nodes and a controller. Two of the system’s main characteristics are remote user alerts and mobility. -
Density-Based Traffic Control System Using Artificial Intelligence
R. S. Sabeenian, R. Ramapriya, S. SwethaThe chapter delves into the pressing issue of traffic congestion, highlighting the inefficiencies of current traffic control methods. It introduces a novel density-based traffic control system that leverages AI and real-time data from CCTV cameras to optimize traffic signal timing. The proposed system uses the YOLO model for vehicle detection and a custom algorithm for signal time scheduling. Extensive simulations demonstrate the system's superior performance compared to existing static systems, with improvements of up to 38% in certain scenarios. The chapter also discusses potential enhancements and future directions for the system, making it a valuable resource for professionals seeking innovative solutions to traffic management challenges.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe road traffic management system and its inconsistencies are one of issues to be addressed. According to Google surveys and reports every year, people face many difficulties on road. Traffic congestions due to inefficient signal management systems which not only causes time delay and stress but also costs health of traffic police due to inhalation of polluted air. Therefore, inefficient traffic management causes unwanted wait times and congestion which produces a lot of CO2, a huge amount practically. Due to inefficient traffic management system, Emergency vehicles such as Ambulance, Fire Engines, and Rescue vehicles may tend to lose lots of valuable seconds. During absence or error in the system causes the signals to go offline, thus causing chaos and accidents. It is a necessity to calculate the real time road traffic density for improved traffic management due to the ever-increasing population of vehicles every day. One of the most impacting elements is the efficiency of the traffic controller as a result there are lot of opportunities for improvement and its demand increases. In our proposed system, live CCTV footage is given as input and vehicles are detected with the help of artificial intelligence. The input undergoes image processing techniques, and the vehicle density is calculated. The green signal time is also computed from the obtained traffic density to avoid long waiting time at road intersections. -
Crypto-Economic Model for Data Security in IoT Network
Sonam, Rahul JohariThis chapter introduces a Crypto-Economic Model designed to bolster data security in IoT networks. It begins by explaining the Internet of Things (IoT) and its various applications, highlighting the need for robust security measures. The literature survey discusses existing cryptographic techniques and their effectiveness against attacks. The core of the chapter focuses on securing routing in IoT, particularly through the MQTT protocol, and introduces two novel cryptography algorithms to enhance security. The proposed model not only ensures data integrity and confidentiality but also measures the economic value of records, making it a standout solution in the field of IoT security. The chapter concludes by emphasizing the reliability and efficiency of the proposed model, encouraging further exploration and implementation in real-world IoT applications.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe Internet of things (IoT) is the future research area in the networking domain. IoT is the Internet of things that connects everyday objects. It is the Internetwork of objects that enables these objects to collect the information from the environment and forward the information to the central server for further processing using several communication technologies. IoT is a new emerging technology that is used in variety of applications such as smart-building, smart-city, artificial intelligence, tracking, remote sensing, online emergency healthcare services. Routing plays a significant role in IoT network. This paper proposes a crypto-economic model for improving the security of data and determining the economic value of records in IoT Network. -
Speedy and Secure Remote Management Protocol Using Virtualization
K. Sudharson, S. Balaji, A. Deepak Reddy, V. Sai RamThe chapter introduces a framework for secure remote management of computers using virtualization, specifically focusing on the use of VNC for remote desktop access. It discusses the advantages of this approach, such as high-quality screen capturing and minimal latency, and compares it to existing solutions like Microsoft RDP. The experimental outcomes demonstrate the effectiveness of the proposed solution in handling multiple clients efficiently, highlighting its potential for various applications, including remote support and virtual teaching methods.AI Generated
This summary of the content was generated with the help of AI.
AbstractRemote capturing is a popular method for remotely assisting any equipment. Also, through Intranet-based classroom instruction and learning, virtualization principles can help in facilitating instructor–student collaboration. The present protocol, Microsoft remote desktop protocol (RDP), has significant flaws, including remote screen locking, no restarting, and the inability to handle several sessions at once. To overcome the existing issues, we designed the secure remote management protocol (SRMP) to assure the quality of service, to assist students, and to measure their progress. The study’s main contribution is the development of a reference model that can let instructors monitor and even influence student activity via remote messages delivered to the student via a chat application. SRMP is a platform-agnostic administrative tool designed to make it easier for server administrators to install and troubleshoot issues. We will compare and contrast the performance of our solution with RDP in this article, as well as how it may help with the creation of future solutions.
- Title
- International Conference on Innovative Computing and Communications
- Editors
-
Deepak Gupta
Ashish Khanna
Aboul Ella Hassanien
Sameer Anand
Ajay Jaiswal
- Copyright Year
- 2023
- Publisher
- Springer Nature Singapore
- Electronic ISBN
- 978-981-19-3679-1
- Print ISBN
- 978-981-19-3678-4
- DOI
- https://doi.org/10.1007/978-981-19-3679-1
Accessibility information for this book is coming soon. We're working to make it available as quickly as possible. Thank you for your patience.