Artificial Intelligence in Internet of Things (IoT): Key Digital Trends

Internet of Things (IoT) plays a crucial role in automating systems, offering effectual and reliable services with minimal human intervention. To be precise, IoT-enabled smart agriculture is a vital factor in the modern digital world which ensures to provide various functionalities such as—water level monitoring, temperature monitoring, moisture sensing, and plant growth tracking. These functionalities of smart agriculture significantly simplify the work of farmers. But on the contrary, several security and privacy-related concerns were identified such as critical agriculture field data storage and management. Therefore, the evolution of integration of the IoT and blockchain (BIoT) came into the limelight. BIoT-based smart agriculture can enhance efficiency, sustainability, etc., leading to increased productivity, improved resource management, and secure data storing management in a decentralized manner. In this paper, we propose an architecture for a smart agriculture ecosystem based on the fusion of both IoT and blockchain. Primarily, our proposed architecture consists of three stages, PEGASIS-based chain construction phase, mutual authentication and key agreement phase, and blockchain-based data storage in base-station phase. Finally, this paper highlights on security analysis of our proposed architecture and found that it is well-secured against broadly known security attacks.

The incapacity of visually challenged people to see their immediate environment restricts their mobility. The World Health Organization estimates that 36 million people worldwide have completely lost their vision, 18 million of whom reside in India. The main purpose of the Raspberry Pi-powered chapeau is to help people who are blind read the text and to talkatively support them. The front part of the chapeau has a camera that records live photos of the wearer’s surroundings. An onboard computer processes these photos by using computer vision techniques for object recognition and important landmarks. With the help of this smart chapeau integrated with cutting-edge technologies, visually impaired people can navigate their surroundings more confidently and easily while also receiving real-time environmental information. GPS technology is incorporated into the smart chapeau to provide precise outdoor navigation. The smart chapeau makes use of sensors, NOIR cameras, and Artificial Intelligence algorithms to understand its surroundings. The smart chapeau design places a high priority on user comfort and uses breathable and light materials.

Machine-to-machine (M2M) communication has gained interest because of the Internet of Things’ potential market reach and the rapid development of wireless communication technology. It’s not just the most significant technological advancement of the twenty-first century, but it has also sparked promising futures in both business and education. M2M communications are growing in popularity as an autonomous means of connecting the internet’s cyber worlds and physical worlds. It may lower the overhead expenses of regular activities, encouraging their greater use on reliable mobile platforms with embedded CPUs, sensors, as well as devices. Here, we talk about the technology, obstacles, and opportunities in connection with machine-to-machine (M2M) communication. Additionally, depending on their network communication pattern and examined pattern, the researcher researched a thorough nomenclature of machine-to-machine classification based on communication over a network pattern as well as a scrutinized pattern. In this study researcher further studied existing home network projects to better understand how these systems are used in the real world. This study will assist in improving the understanding of existing machine-to-machine (M2M) network challenges and give innovative insight for future research directions.

Accurate drought prediction plays a pivotal role in water resource management and agricultural planning. This study delves into the realm of machine learning algorithms to enhance the accuracy of such predictions. The core focus centers on the integration of support vector neural networks (SVNNs) as a means to predict drought occurrences, leveraging data from diverse sources including meteorological, hydrological, and remote sensing. The unique characteristic of SVNNs lies in their amalgamation of support vector machines and neural networks, allowing for the nuanced capture of intricate data relationships. The refinement of feature engineering strategies is instrumental in optimizing the predictive models. These strategies address the challenges posed by imbalanced datasets through the implementation of resampling techniques, paired with careful selection of evaluation metrics. The performance evaluation of SVNNs is conducted through a rigorous assessment against historical drought events, further accentuated by a comparison against conventional methods. To expand the scope, the integration of remote sensing data enriches the models with comprehensive spatiotemporal insights, enhancing their predictive capabilities. Moreover, the research extends its exploration into ensemble techniques and hybrid models, showcasing the versatile potential of machine learning in the domain of drought prediction. The findings of this study unequivocally demonstrate the superiority of the projected method when compared to existing methodologies, particularly in terms of accuracy, precision, and F1-score. The novel drought prediction models put forward in this research hold the potential for unprecedented advancements, significantly enhancing the efficacy of drought mitigation strategies.

The increasing adoption of IoT devices has raised significant concerns about security and privacy. This paper proposes a blockchain-based approach for anomaly detection and intrusion prevention in IoT networks. The methodology combines blockchain technology with anomaly detection algorithms to enhance the security and trustworthiness of IoT systems. Through simulations and experiments using real-world IoT datasets, the effectiveness of the approach is evaluated. The results demonstrate improved accuracy in detecting anomalies and reduced false positives compared to traditional methods. The blockchain-based solution also provides tamper-proof and decentralized data storage, ensuring the integrity and availability of IoT network information. This research highlights the potential of blockchain technology as a robust solution for enhancing anomaly detection and intrusion prevention in IoT networks, addressing critical security challenges in the IoT ecosystem.

Nowadays, the current research trends in smart buildings plays a vital role and acts as an integral part of smart grids and smart cities. Recently, the need for sustainable energy and efficient power consumption has become very important across the world especially in domestic and industry zones. The challenges of global environment and energy sustainability can be addressed by the current thrust research area of smart buildings. This paper presents a power conservation system that utilizes deep learning techniques to detect and monitor human presence in order to enhance energy utilization in various environments. The proposed system credits open-CV algorithms and machine learning models to precisely identify humans and their movements within a given area, enabling intelligent control of power-utilizing devices. The Internet of Things (IoT) and deep learning techniques are used to control the operation of lights and fans and also enable a security feature in the form of telegram bot. Experimental results emphasize that the deep learning-based recognition can detect the persons in a particular area with an accuracy of 96% and 99% in dark and bright areas conditions, respectively.

The issues and challenges involved in the case of secondary distribution have been approached in a very limited number of research works. This paves a way for us to investigate the algorithms for planning of secondary distribution. In the current scenario, the use of renewable energy is widely preferred for the purpose of power generation as it is found to be highly beneficial to the environment. The main objective of any power distribution system is to minimize the cost which comprises of asset price, support substations, feeders and energy loss. When we deal with algorithms, a system and its objectives along with constraints are to be considered. The constraints usually considered are power flow equality, bus voltage or voltage drop limits, substation and feeder capacity limits, standard sizes for transformers and conductors, radial operation of the network, bus angle limits, and transformer tap limits and short-circuit current limit. The analysis toward the planning of secondary distribution in power system has been carried out through numerous algorithms. The sole purpose of utilizing algorithms is to eradicate the restrictions involved in secondary distribution. Thus, we have adopted a multifaceted diverse integer nonlinear optimization system.

Background: Continuous monitoring of patient health statistics becomes a difficult task in hospitals. Manually, it is difficult to monitor the health of the patients in the hospital continuously. Older and unconscious older people in particular need to be monitored regularly, and their relatives want to be informed about their health at every time. We, therefore, propose a revolutionary system that easily computerizes this task. Our device provides an intelligent device for monitoring patient status, which uses sensors to track hospital patients’ health status and informs their relatives in the event of a problem via the Internet. Our system uses temperature, glucose levels and heart rate detection to track health. This task has been proposed to improve the monitoring system by using the Internet of Things (IoT) for hospital applications. Result: The suggested system was developed by MAX30100, LM35, ultrasonic sensor and nodeMCU connected to the Internet. BLYNK IoT Android app has already been used to send the notification via Android Application. The remote healthcare monitoring system is also proposed with cloud service and data analytics as to the aiding features. The readings are captured by mobile phone, which acts as the graphical user interface to get the status of the patient’s health. The implemented hardware results illustrate that the suggested model can continuously observe the physiologic parameters and save lives promptly. Conclusion: ML classification algorithms like Regression tree, SVM, and RF analysis for prediction accuracy of patient health data. The proposed RF algorithm’s simulation results provide minimum prediction error and high accuracy compared with the existing Regression tree and SVM algorithm.

In recent years, heterogeneous wireless networks have been established to maximize data rates through the use of several protocols and application optimization algorithms for effective data gathering and routing. To improve wireless network power consumption, researchers developed the low power adaptive agglomeration hierarchy (LEACH) protocol, which enables effective data collecting via efficient routing. For heterogeneous networks, we suggest the Quadrature-LEACH (Q-LEACH) protocol in order to increase throughput and routing effectiveness while preserving the best possible network lifespan characteristics. For real-time applications, heterogeneous networks like Wi-Max, Wi-Fi, and LTE are strong, dependable, and efficient, enabling packets to be transferred across the network with little latency. To enhance data sharing and efficient routing efficiency in heterogeneous networks, we adopt the enhanced fractional Darwinian particle swarm optimization (EFOFDPSO) optimization technique. The radio connection quality stability and radio routing pathways’ bandwidth utilization form the basis of the optimization algorithm. Experiments demonstrate that effective network routing may reduce data transfer time while preserving low latency and good connection quality.

Router energy consumption has an impact on the lifetime of a wireless sensor network (WSN). Small sensor node uploading can be challenging after installation. To save energy or lower the total amount of data produced by the WSN, data gathering is used redundantly to reduce or fully eliminate data redundancy at individual nodes. Because of resource constraint, wireless sensor networks confront a significant problem in determining solutions to improve resource efficiency and accomplish effective load balancing. The graph-based cat salp swarm algorithm (Graph-CSSA) is presented in this research as a multi-stage routing strategy for wireless sensor networks (WSNs) with the purpose of prolonging network lifetime by uniformly distributing energy consumption among clusters. The proposed CSSA graph is utilized to determine the best hop. Multi-hop routing is enabled by group head (CH) selection and data forwarding implemented in two operations. After the cluster vertices are distributed, blocks are formed centrally in the aggregation phase, which is similar to low-energy adaptive clustering hierarchy (LEACH). Finally, simulations are done to evaluate the proposed routing method’s performance and compare it to other energy-aware routing approaches. Our findings show that the proposed technique efficiently reduces data volume while increasing the lifetime of WSNs.

One significant challenge encountered in the process industry pertains to the management of fluid levels within tanks and the transportation of fluids between them. The focus of this study will be the examination of the interaction between two tanks. Certain accidents occur as a result of individuals failing to exercise vigilance over specific physical entities. The resolution of this issue necessitates the utilisation of concepts pertaining to data communication. Certain firms utilise various types of networks such as RS485 and RS232. In contrast, these technologies significantly reduce the amount of distance data transmitted. This project aims to develop a device capable of retrieving data from remote input/output (I/O) locations through the use of Wi-Fi technology. The UDP protocol is utilised for wireless communication in this context. Wireless technology is employed to monitor the fluid levels of two interconnected tanks in the system. A wireless fidelity (Wi-Fi) transmitter node is responsible for receiving level data and subsequently performing data processing. Individuals who possess a smartphone or tablet device equipped with a wireless fidelity (Wi-Fi) connection are also able to access data. The level of the tank is periodically measured using a smartphone, and the resulting data is visually represented in a graph. The Simulink result was compared to the data that was collected on mobile devices to make sure they were the same thing. The utilisation of Wi-Fi as a means of transmitting data is advantageous due to its expeditious and precise nature.

This study presents a computational fluid dynamics (CFD) simulation of an earth tube heat exchanger (ETHX) integrated into a building heating, ventilation, and air-conditioning system. The objective is to investigate the impact of varying materials and airflow rates on the performance of the ETHX. The ETHX is a passive cooling and heating technology that utilizes the stable ground temperature to pre-condition the air entering the building. A three-dimensional (3D) model of the building and the ETHX system is developed using CAD software. The geometry includes the earth tubes, heat exchangers, and other relevant components. A fine mesh is generated to accurately capture the flow features and thermal gradients within the system. The fluid properties of the airflow through the ETHX and the surrounding soil are defined, considering factors such as density, specific heat capacity, and thermal conductivity. Boundary conditions are applied to simulate real-world scenarios, including inlet and outlet conditions for airflow, as well as wall conditions for the earth tubes. A suitable CFD solver is selected, and the simulation parameters are set up, including turbulence models, discretization schemes, and convergence criteria. The simulations are executed, and the results are analysed to assess the performance of the ETHX under different conditions. The fluid thermal variations are monitored and controlled by Internet of things. This study contributes to understanding the design and optimization of earth tube heat exchangers in building HVAC systems.

Real-Time Hand Gesture Recognition Using Convolutional Neural Networks: A Robust Approach for Diverse Applications. Hand gestures are fundamental to human communication and find extensive utility across various domains. However, the real-time recognition of hand gestures using computer vision algorithms poses significant challenges. While several algorithms have incorporated color and depth cameras to facilitate gesture recognition, achieving robust classification across diverse individuals remains a notable hurdle. In this paper, we present a novel algorithm that leverages Convolutional Neural Networks (CNNs) for real-time hand gesture recognition. Our CNN model is trained on a comprehensive dataset consisting of nine distinct hand gestures, each comprising 500 images. Through rigorous evaluation, our proposed algorithm achieves an impressive average accuracy of 98.76%, underscoring its potential to establish secure and user-friendly interfaces for a wide range of applications.

Breast cancer is often curable if discovered in its early stages. Machine learning algorithms are used to automate disease identification. To increase the likelihood of recognizing the condition at an early stage, an effective classifier for automated diagnosis of breast cancer is needed. This research attempts to introduce a mixed machine learning model for predicting breast cancer. To outperform other strategies, it requires enormous amounts of data. Moreover, the intricate data models increase the training cost. For enhancing the efficiency of basic classifiers, ensemble learning holds great promise. A rapid discrete wavelet transforms using the wrapping approach is then used to extract the characteristics from the Region of Interest (ROI) mammography pictures. In addition to being too high to be categorized, the extracted wavelet coefficients also have incredibly high run-time complexity. The modified whale optimization method, which employs swarm intelligence, has been presented to lower time complexity and select the significant characteristics. Ensemble learning has been applied for the requisite efficiency in the suggested technique. Three machine learning (ML) classifiers—the extreme gradient boost classifier (XGB), support vector machine (SVM), and enhanced granular neural network (E-GNN)—form the ensemble voting system.

AI and robotics have emerged as revolutionary technologies influencing the future of different sectors and our daily lives. If robotics is to be intelligent, artificial intelligence must be at the forefront of the field since it deals with the relationship between perception and action. This review article investigates the current development of AI and robotics, their applications in many fields, and their societal influence. We look at advances in machine learning, the convergence of AI and robotics, ethical concerns, and potential future issues. This study provides insights into how AI and robotics are becoming humanity's new frontier by reviewing current advancements and their ramifications.

The safety of mining professionals working in underground mines is of paramount importance. To enhance the security of these professionals, this research paper proposes the use of an Internet of Things (IoT)-based safety system to monitor the underground environment. We have used an Arduino board and a collection of sensors to monitor parameters like temperature, humidity, air pressure, etc., as part of our safety system. The sensors are set to a threshold value and connected to an Arduino kit, which processes the data and sounds an alarm in case of any abnormal conditions. This research paper discusses the implementation of this system and its effectiveness in detecting potentially hazardous situations in underground mines. A device like this one could help alert miners and give them sufficient time to get to safety or call for help. The experiment results show that the system is able to detect the presence of harmful gasses that could potentially result in a fire. This system is reliable and can help prevent accidents and fatalities in underground mines.

Network congestion poses challenges for internet users, diminishing the utility of accessed information due to reduced speeds. To mitigate this, various strategies such as web mining, caching, and server prefetching have been proposed to enhance internet performance. We introduced a novel prefetching approach tailored for high-traffic environments with minimal server idle times. This method constructs an online navigation graph from preprocessed log data, offering insights into user navigation patterns across the web. Our primary objective was to refine web prefetching techniques for congested digital landscapes. We evaluated the model using log files from specific domain client groups. Our proposed web clustering method surpasses conventional prefetching techniques, especially after a short-lived acceleration when server idle times are sufficient for prefetching across all user predictions. This method, when synergized with web caching, can predict subsequent related web items following a particular web object request.

Scoliosis is a medical condition that causes an abnormal curve in the spine, which can result in vertebral compression fractures (VCFs). Identifying VCFs accurately is crucial for managing scoliosis effectively and preventing further complications. This review aims to analyze the latest imaging techniques for precise identification of VCFs in patients with scoliosis. The study discusses various imaging methods, such as radiography, CT, MRI, D-EXA, bone scintigraphy, ultrasonography, and CBCT, as potential techniques for identifying VCFs. The challenges and constraints associated with these techniques are also analyzed. The review emphasizes integrating these imaging techniques to enhance scoliosis diagnosis and management, compares their accuracy and effectiveness, and highlights their clinical implications for patient outcomes and quality of life. This provides an overview of the latest advancements in imaging techniques for the accurate identification of VCFs in patients with scoliosis and their potential impact on patient care and future research directions.

Graphs are effective mathematical models for analyzing a variety of specific real-world issues. As a generalization of a graph, semigraph has also a pivotal role in graph theory. Because of its structure the idea of domination creates novel contributions in the field of network. In this article, we are trying to bring the concept of distance domination in connected semigraphs by defining l distance a-domination and l distance e-domination. The characterization of minimal l distance a-dominating set of connected semigraphs is also been discussed. Additionally l distance a-domination number, l distance e-domination number of some particular classes of semigraphs are determined.

In the current era, the world is propelled by the rapid advancements of next-generation technologies, which play a pivotal role in shaping various aspects of our lives. This research paper aims to delve into the intricate nature of indoor wireless communication channels operating at 2.5 GHz for wireless local area networks. The central objective of this study is to meticulously examine the prevailing elements that wield influence over signal transmission among sensor nodes strategically positioned within indoor environments. By comprehensively analysing these factors, we aim to gain a deeper understanding of the dynamics at play within indoor wireless networks.

Whenever it comes to road pavements, asphalt and its mixture are used to improve the performance and durability of the surface. SMA Mix (also known as Stone mastic asphalt or Stone matrix asphalt) is a great alternative to bituminous concrete or thick graded mix for this application because of its durability (DGM). Countries in Europe and North America were the primary users of this term. Stone Mix is an asphalt blend that has been gap-graded. Different materials (natural or manufactured) are employed as stabilisers, and Stone or Slag is utilised as coarse aggregate to make high-bituminous material with a high degree of bituminous content. In this study, a variety of alternate methods for improvement are explored, including the use of waste materials as fillers, such as coconut shell charcoal powder, glass powder, and bagasse fibre, to lower costs while simultaneously improving roadway quality and safety. The primary goal of the study is to compare the outcomes obtained with these fillers to the results obtained with the conventional mix, which is the baseline. Crushers and pavement fillers must have certain qualities to function properly. These features include crushing, surface moisture, grading, and freezing.

When the complexity and range of computer system hardware increases, and its appropriateness as a pedagogical tool in computer organization/architecture courses reduces. The Teachers or instructors are turning to simulators as teaching aids, but valuable teaching/research time spent to constructing simulator (Dhamdhere in Systems Programming and Operating Systems. McGraw Hill Education [1]) Microprogramming is generally not available to programmers because it may engross alteration of a machine's native language (Wolffe et al. in Teaching computer organization/architecture with limited resources using simulators. SIGCSE Bull. 34, 1(March 2002), 176–180, [2]) A hypothetical computer can provide a simulator for microprogramming projects and add considerably to one's understanding of the subject of microprogramming and the concept of a multilevel machine. This research paper presents, the design of new instruction set which will be further useful for better understanding of system programming so that one can understand microprogramming, machine-level language programming, simulations, and concept of hypothetical machine.

The concept of Virtual Power Plant (VPP) has become an attractive solution to optimize the integration of renewable energy sources into the grid. However, the operation and transaction system of VPPs still face several challenges, such as the lack of transparency, security, and efficiency. In this learning, we propose a new operation and transaction system built on blockchain technology for VPPs. The proposed system contains of two layers, the blockchain layer and the application layer. The blockchain layer is responsible for ensuring the security and transparency of transactions, while the application layer provides an interface for VPP operators and users. We implemented the proposed system using Ethereum, one of the most popular blockchain platforms. We also conducted a case study to evaluate the routine of the proposed system in terms of transaction throughput, latency, and scalability. The outcomes show that the proposed system can handle a large quantity of transactions with low latency and high scalability. Our study demonstrates the possible of blockchain technology to enhance the operation and transaction system of VPPs, which can contribute to the integration of renewable energy bases into the grid.

Netflix, the leading global streaming service, has revolutionized the entertainment industry by providing an extensive library of content to millions of subscribers. This research\paper presents an exploratory data analysis (EDA) of Netflix's vast dataset, aiming to uncover valuable insights into user behavior and content trends. By employing descriptive statistics, data visualization, and pattern recognition, this study delves into viewing patterns, content popularity, user demographics, and regional variations in user engagement. The findings of this analysis shed light on the factors driving Netflix's success and offer crucial implications for enhancing user experience and content duration on the platform.

Machine learning helps the organization to find the limitations and to develop higher interaction with the existing customers. This helps the organization to identify the things that could increase the customer satisfaction level. The concept of machine learning and its effect on the process of business development. The inputted data of the ML are related to the business data and it helps to analyse the upcoming situation of the existing market. Primary and secondary data collection methods have been applied. Quantitative process like SPSS has been used and qualitative analysis has helped to increase the knowledge of machine learning and its utilization in businesses. The steps of the customer interaction in the business model that help to understand the mechanism of sales. The steps of machine learning have represented for better understanding of the ML processes. Google use ML for customer interaction, Apple uses innovation technology to increase interaction and satisfaction level of the customers, and Microsoft use the hybrid approach to provide better product and services to customers. Quantitative and qualitative analysis has been done for a better understanding of the result. The implementation of ML helps businesses to interact with customers. This increases the successive factors of the businesses. The implication of ML is appreciative as these analyses all the business conditions as per data and represents the results based on the algorithm analysis and computerized technology.

The usage of chatbots advanced swiftly in various fields in current years, inclusive of advertising, supporting systems, training, healthcare, cultural background, and leisure. In this paper, we first gift an ancient review of the evolution of the worldwide network’s hobby in chatbots. Subsequent, we discuss the motivations that drive the usage of chatbots, and we say that chatbots usefulness in a most of areas. After clarifying necessary technological standards, we pass on to a chatbot category-based totally on diverse standards, consisting of the location of expertise they check with, the need they serve and others. Furthermore, we present the overall architecture of cutting-edge chatbots whilst also bringing up the principle systems for his or her advent. Our engagement with the problem to date, reassures us of the possibilities of chatbots and encourages us to have a look at them in more extent and intensity. This research focuses on the development and application of a medical chatbot designed to optimize appointment scheduling, saving time and improving accuracy. The chatbot utilizes machine learning to access a vast amount of user data, offering a personalized experience. HealthBot, the chatbot, employs natural language processing (NLP) to understand user intents and matches them with symptoms. It also collects daily health data through APIs, utilizing a regression model to identify potential diseases and trigger notifications.

Smart microcontroller-based automation system for garden maintenance is specially designed to improve the conditions of public garden by controlling plant watering, lighting and gate opening and closing without any human interference. The garden is taking care of itself through automated electronics devices, hence it is called smart automated garden. This system avoids the wastage of electricity and water in public gardens. Arduino is used to control entire functionality of system. Real Time Clock (RTC), soil moisture sensor, buzzer, motor required for water supply and motor required for gate control interfaced to ATMEGA328 microcontroller. Lamps in the garden are switched ON/OFF depending upon time set in RTC device and the lamps remain functional till the garden remains open. Soil moisture sensor is used to analyze moisture contents in the soil. Depending on moisture contents of the soil, water pump will turn ON and OFF. The gate is opened and closed by motor with closing indication controlled through ATMEGA328 microcontroller. The designed system is deployed and tested which has performed well and satisfactory with 88% and above accuracy and reduced the efforts of human in public gardens.

In the context of network traffic analysis, this review study offers a thorough examination of the integration of deep learning and evolutionary algorithms for intrusion detection system (IDS) optimization. The importance of network security and the shortcomings of traditional intrusion detection systems are examined. The study emphasizes the possible advantages of integrating evolutionary algorithms for feature selection and input layout optimization with deep learning methods like Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. The goals and research gaps are described, as well as the suggested technique. The anticipated outcomes—better accuracy, lower false alarm rates, better zero-day attack detection, and useful recommendations for network security experts—are given. This survey paper aims to contribute to the field of network security by providing a comprehensive overview of the state-of-the-art approaches and identifying future research directions.

Semantic scene understanding in computer vision image/video analysis involves assigning semantic labels to each pixel in an image. The main aim of this paper is to partition an image into meaningful scenes and objects and mapping to a specific class. For semantic scene understanding and segmentation, the encoder-decoder approach with UNet is presented in this paper. Encoder network down-sample the image feature and decoder network up-sample the feature map to obtain segmentation mask. The segmentation model is developed that is trained on public Standford dataset images consisting of objects and scenes. The segmented classes used are building, tree, sky, road, grass, river, mountain and foreground objects. The result shows that objects and scenes in the images are partitioned and classified into different classes with an average accuracy of 76.83%. The significance of this research is to recognize, partition and classify the objects and scenes for understanding the segmented contents in video. It can be further used for content-based video retrieval, browsing and summarization. Researchers, Government agencies and Automation industries will benefit from this study.

A Verilog implementation is made towards pattern recognition using convolutional neural network (CNN). The implementation derived demonstrates detection of a given pattern by revealing—‘number of times the particular pattern is being detected’. This is devised using adders, look-up-table (LUT) logics and flip-flops (FF) in a manner which satisfies the CNN architecture. This brief studies about reduction in the resources required for compute intensive processes like processing of the video/ graphics. An implementation of neural network is made using adders in an attempt to perform the compute intensive processes on CPU itself. In this way the requirement of GPUs could be avoided for some of the applications. The Verilog implementation in the devised architecture resulted in overall 11% less resource consumption while running simulations considering a 200 MHz clock frequency. It is observed that devised architecture consumed 2798 LUT count and 1652 FF count as opposed to one of the existing designs which shows a consumption of 10,292 LUT and 10,827 FF.

Driving under the influence of alcohol and drowsiness are significant contributors to motorcycle accidents. Consider a case, a man rides his bike despite consuming alcohol, which can lead to two possible outcomes. One possibility is that, by luck, he reaches his destination safely. The other, unfortunately, involves the high consumption of alcohol impairing his abilities, causing drowsiness and slowed reactions. As a result, he loses control of the motorbike and collides with a pedestrian. Sustaining a severe head injury, he is hospitalized, and due to a damaged phone, his family remains unaware of the accident. Concerned about his drinking habits, the family members worry for his well-being. However, due to the severity of the head injury, he passes away, and the family is informed after 24 h. From above it can be understood that drinking and driving can harm individuals, pedestrians, other drivers, and families. If the person had been wearing a helmet, he could have avoided the injury and loss of life. However, if the individual had been using a smart helmet equipped with an alcohol detector and drowsiness detector, the outcome may have been different. Additionally, if the helmet had GPS functionality, the family could have received an alert message with the location. So here comes the idea for a smart helmet—an alcohol and drowsiness detector. The smart helmet alcohol detector is a device that can be worn by motorcycle riders. If the riders would wear the helmet, then the vehicle would start, or else it would not. Two infrared sensors and an alcohol sensor will be built into the helmet. One infrared sensor will detect the rider’s face, and if he wears the helmet, the bike will start. A second infrared sensor will detect drowsiness, and if the rider is sleepy, the alarm will beep. If someone is wearing a helmet, the alcohol sensor will determine whether they are under the influence of alcohol or not. If he drinks alcohol beyond the threshold then the helmet will alert the rider with a voice alarm and turn off the vehicle’s ignition system. Also, notify the rider’s location to his family member by sending a message and a call, letting them know he is drunk.

Recently, the communication systems have been propelled toward the fifth generation (5G) due to the huge demands of compact, fast, and wide bandwidth systems. Researchers are still intrigued by the challenge of creating an effective, small antenna with superior return loss and bandwidth for 5G applications. The foundation of this research is an H-shaped slotted rectangular patch antenna that operates at 28 GHz single frequency band (5G). Performance score error (PSE) has been used to observe the influences of the antenna parameter variation on the performance of the antenna during the manual parametric optimization. The best performance of the proposed antenna (after tuning) has been found as S11 = − 62.91 dB, BW = 5.36 GHz, VSWR=1.001 which outperformed all existing works. Even if the gain of the antenna is slightly low, it can be considered as a good candidate for the 5G communication at 28 GHz frequency band by considering overall performance.

This research work proposes a small (16 × 10 × 1.6) mm3 planner antenna for broadband (3.5–11 GHz) operation. The antenna is designed using FR-4 epoxy substrate at minimal cost with 0.02 loss tangent and dielectric constant (εr) of 4.4. The proposed geometry shows − 10 dB impedance bandwidth of 7.5 GHz with a percentage bandwidth of 103%, bandwidth dimension ratio (BDR) of 4682 and peak gain of 1dBi at 4.42 GHz. Quarter-wave transformer feeding with rectangular slit and defective ground structure (DGS) are used for achieving wideband characteristics. The proposed antenna is intended for WLAN, Wi-MAX and C-band (n79) for IoT applications. In parallel this antenna can also be used for INSAT that operate at 6.725–7.025 GHz for transmission, LTE 46 band (5.15–5.925 GHz), remote sensing and military applications.

Nowadays, high power and high frequency devices have various reliability issues due to which their performance is limited. The main cause is self-heating in gate drain region and E-field crowding near gate edge of AlGaN/GaN HEMT. In this work, our aim is to study and analyze the self-heating effects of field plate AlGaN/GaN-based high-electron mobility transistors (HEMTs) grown on sapphire substrates employing a dual AlN/SiN passivation using electro-thermal simulations. It is observed that the temperature of the proposed device is reduced from 578 to 439 K by incorporating the passivation layer with field plate in AlGaN/GaN which is $$\sim $$ ∼ 24% reduction in device temperature. The proposed device with dual passivation layer has $$\sim $$ ∼ 41% improvement in drain current, $$\sim $$ ∼ 14% in transconductance, and $$\sim $$ ∼ 87% reduction in E-field at the edge of device.

High-efficiency klystrons are the need of the hour, as they are essential to meet the demands for high-power applications. High-efficiency klystrons use multiple beams and extended interaction cavities. An 8-beam extended interaction intermediate cavity with high R/Q has been designed for the application of a high-efficiency klystron in the C-band. The 8-beam input cavity and extended interaction output cavity with slot coupling have also been represented. Special attention has also been given to the design so that the gap of each of the 8 beamlets has equal coupling. External quality factors of both the input and output cavities have also been optimized. Parametric analysis of the external quality factor with respect to the dimensions of the coupling slot has been investigated to get an idea of suitable dimensions for high-efficiency output. All simulations have been done using CST Microwave suite.

Getting highly accurate output in biomedical data processing concerning biomedical signals and images is impossible because biomedical data are generated from various electronic and electrical resources that can deliver the data with noise. Filtering is widely used for signal and image processing applications in medical, multimedia, communications, biomedical electronics, and computer vision. The biggest problem in biomedical signal and image processing is developing a perfect filter for the system. Digital filters are more advanced in precision and stability than analog filters. Digital filters are getting more attention due to the increasing advancements in digital technologies. Hence, most medical image and signal processing techniques use digital filters for preprocessing tasks. This paper briefly explains various filters used in medical image and signal processing. MATLAB is a famous mathematical, analytical software with a platform and built-in tools to design filters and experiment with different inputs. Even though this paper implements filters like mean, median, weighted average, Gaussian, and bilateral in Python to verify their performance in terms of mean square error (MSE) and similarity index (SI), a suitable filter can be selected for biomedical applications by comparing their performance.