With the increasing use of satellite imagery for military, environmental, and commercial applications, the need for secure and efficient encryption techniques is also increasing. We present a Feistel-inspired encryption framework for satellite images, which uses two novel proposed chaotic maps Power-Reciprocal Cosine (PRC) and Logarithmic Cosine-Reciprocal (LCR) in combination with Data Encryption Standard (DES)-inspired permutation-diffusion algorithm, gives promising results by obtaining NPCR 99.60

Wireless Sensor Networks (WSNs) for multievent monitoring (industrial and environmental site surveillance, structural health monitoring) should provide different criticality levels of data. Most conventional transport-layer designs for WSNs either treat all traffic the same or are energy-or reliability-oriented only, leading to potential delay or loss of urgent events when they strive for contention. In this paper, we propose a Prioritized Transport Layer Protocol (PTLP) that offers differentiated priority-driven reliability and timeliness for multi-event WSNs but is lightweight enough to be executed by resource-constrained nodes. PTLP includes: (1) event-driven priority marking System architecture, suitable for emergency system, take advantage of LTE features including; early recognition on the occurrence of a future critical condition like bank robbery or cardiac arrest, and file high-priority reports with higher precision to maintain user quality of experience. We deploy PTLP on a popular sensor OS, and evaluate it through testbed experiments and ns-3 simulations with mixed-load, multi-event workloads. Equivalently, our experimental results demonstrate that PTLP decreases median end-to-end latency for critical events up to 30–45% and increases the packet delivery ratio on average by >20–60% under common such reliable transports and best-effort baselines, at an energy overhead of typically less than 12% per node under typical duty-cycles. Thus, PTLP provides a tunable and practical tradeoff among reliability, delay and energy which is suitable for event-driven sensor networks. The paper presents protocol state, header formats, algorithms, empirical assessment, example use cases, limitations and future work

Prompt diagnosis and timely treatment are essential to prevent pandemic effects to aggravate. To prevent this disease, a proper diagnosis is essential but in the case of the remote area, difficulties arise due to lack of facilities such as laboratory and well equipment setup. This paper introduces an approach that is centered on the automated analysis of this disease by using both voice sample and cough sound and some major common health issues samples of COVID-19. People may experience symptoms like cough, fever, tiredness, and difficulty breathing (several cases) in COVID-19. We have seen that it attacks mostly our respiratory system brutally and those people are suffering the most and it will take them to death. Most people infected with the COVID-19 virus will experience mild to moderate respiratory illness and recover without requiring special treatment. Older people and those with underlying medical problems like cardiovascular disease, diabetes, chronic respiratory disease, and cancer are more likely to develop serious illnesses. It hypothesized that in any disease in lungs or our respiratory system cough and voice carry vital information to diagnose pneumonia, and developed mathematical features and a pattern classifier system suited for the task. So we have suggested a way to collect cough sound and voice sample by using Non-contact devices like microphones kept by the patient’s bedside would be used for data acquisition. The features are extracted from cough sounds and voice sample and combined with other attributes such as fever data, and oxygen level data used them to train a classifier. Here we are suggesting MFCC for feature extraction and after that for classification CNN (Convolutional Neural Network), also with a novel approach as a solution to that issue. These results show that cough or voice sounds indeed carry critical information on the lower respiratory tract, and can be used to diagnose pneumonia. To the best of our knowledge, this is also one of the finest attempts in the world to diagnose COVID-19 in humans using cough sound and voice analysis.

The IoT-enabled smart pest control system for improved crop protection seeks to improve agricultural sustainability by utilizing Internet of Things (IoT) technologies for improved pest control. This research presents a novel method for leveraging IoT sensors and data analytics to identify and decrease insect infestation in real time. By incorporating superior sensing technologies coupled with predictive analysis, the system provides effective pest detection and control reducing crop losses and resource wastage. This work proposes and tests two simulation models while assessing the effectiveness of controlling pest populations with them comprehensively. Findings show enhanced effectiveness of detecting pests and undertaking appropriate intervention measures proving the effectiveness of the proposed system in improving crop protection measures. This paper adds to the development of the continuous field of precision farming (PF) by proving that IoT solutions can reduce agricultural risks and enhance productivity.

Proper waste management in urban areas is very important for the development of smart cities, hence the need to adopt effective, efficient, and sustainable technologies. Some common problems associated with ordinary waste management services include but not limited to; improper collection frequency, spillover events, and high resource utilization. In the following paper, we present an IoT framework for waste management that utilizes sensors and machine learning approaches to improve supervision and collection trips while at the same time increasing productivity. The system under consideration provides for the use of sensors to constantly measure the waste and environment parameters as well as forwarding the obtained data to a special server for further identification of specifics. For advancing predictions and route planning, artificial intelligent models are used and collection schedules and routes are transformed according to new data received. A detailed analysis of the implementation of the proposed system is presented through simulation experiments as well as real-life applications, proving significant increases in the efficiency of waste collection, decreased costs, and improvements in environmental impact. From the findings made from the study, it is understood that IoT and machine learning innovations have the possibility to greatly revolutionize the nature of urban waste management and, therefore, advance smart cities.

The authors presented a holistic AI-augmented cybersecurity protocol architecture for trustworthy multi-hop wireless communication system in 6G networks. They follow an approach that builds secure and efficient communication in dynamic and resource constraint settings from implementing Deep Learning, Federated Learning, and Reinforcement Learning. The combination of these techniques helps ensure prompt detection of threats, flexible management of security controls, and cost-effective use of resources. Extensive simulations and evaluations confirm that the protocol provides improved performance in terms of detection accuracy, low latency, and scalability. The results highlight that AI-driven techniques can provide holistic solutions to secure future wireless communicational systems, thus offering dynamic and long-lasting security solutions.

Recently, the rapid growth of Renewable Energy Resources(RER)in power generation has resulted in the frequent occurrence of Power Quality Disturbances(PQDs)within the power system. The timely and accurate detection of these PQDs is critical for maintaining good power quality while integrating RER into hybrid power systems to make them more robust and stable. In this paper, a multi-view dimensionality reduction approach based on Canonical Correlation Analysis(CCA) is proposed to differentiate different types of PQDs. Here, a dataset of 29 types of PQDs which include nine single types and twenty multiple types of PQDs have been generated using their mathematical model in MATLAB for experimentation. CCA being multi-view dimensionality reduction technique maximizes the correlation between two different views of the data. Here two cases of datasets have been considered for further exploration, Case 1: PQDs without noise and with 20 dB noise, Case 2: PQDs with 20 dB and 30 dB noise. Furthermore, to test the efficacy of CCA in both cases, the extracted features have been tested using four different classifiers i.e. K-Nearest Neighbour(KNN), Support Vector Machine (SVM), Naive Bayes(NB), and Random Forest (RF). The performance of each of the classifiers has been tested on five different performance metrics such as precision, recall, F1 score, hamming loss and accuracy and the results shows that the proposed technique of multi-view dimensionality reduction is capable of classifying the PQDs with two different views at a time

The revolution of microgrids (MGs) in the modern world has impacted the power systems to deal with the loads with optimal use of renewable energy resources (RERs). In the models consisting of energy management systems (EMS) and generation sources, there will be power fluctuations between the source and the load under certain conditions due to the unpredictable behavior of RERs. Therefore, a reliable scheme has to be implemented between the source and the load to ensure optimal performance of direct current (DC)-MGs. This article has presented a review of the EMS models introduced by various researchers to enable optimal power supply and efficient operation of the DC-MGs. A thorough illustration of the schemes adopted to provide efficient operations under grid-connected and islanded mode of operations are provided. The effects and advantages of centralized and decentralized EMSs are discussed. The role of a battery energy storage system (BESS) in microgrid scheduling is presented and compared with a few other energy storage systems. The scheduling strategies implemented for optimal EMS using different algorithms and techniques are elaborated. In addition, the effects of battery degradation and the formulated solutions to improve the degraded models with improved battery life are also provided with cycle life and calendar life. Then, the lithium ion and lead acid BESS effect on microgrid EMS is presented. Finally, the energy management methods for DC-MGs end with challenges, research gaps, and future direction.

SummaryLocation‐based underwater communication applications such as strategic surveillance, disaster prevention, marine research, and mine detection have given the field of underwater wireless sensor networks (UWSN) a head start. Node localization is a prerequisite for accurate data collection, target monitoring, and network management in UWSNs. However, the unique characteristics of the underwater environment, such as signal attenuation, multipath propagation, and variable acoustic properties, pose a major challenge to effective node localization. Accurate sensor node location data is essential for successful underwater data collection, but difficult to achieve as the GPS system cannot be used in an underwater environment. In this paper, existing node localization techniques such as ALS, SLUM, MASL, SLMP, UDB, USP, etc., and recent advances such as the fusion of range‐based and range‐free techniques, the fusion of RSSI and AoA to improve localization accuracy by using directional information in addition to signal strength, and the use of optimization techniques such as PSO, COA, and WOA algorithms to improve the accuracy of the applied node localization algorithm, e.g., TP‐TSFLA, and challenges related to UWSN are discussed. Also, different localization algorithms that affect the accuracy of UWSN localization techniques have been evaluated and compared with NS2 in terms of localization error, localization coverage, energy consumption, and average communication cost metrics. In addition, this paper also provides an up‐to‐date investigation of localization techniques. Finally, the tools available for simulation are presented, followed by open research questions that need to be addressed in the localization of nodes.

Significant obstacles to financial security have arisen as a result of the quick uptake of Unified Payments Interface (UPI) for online transactions and a commensurate rise in fraudulent activity. This paper suggests a novel fraud detection method that makes use of cutting-edge machine learning (ML) algorithms to address this urgent issue. It focuses on integrating a Hidden Markov Model (HMM) into the UPI transaction process. In order to enable the system to identify departures from these learnt behaviors as possibly fraudulent, the HMM is trained to predict the typical transaction patterns for particular cardholders. The suggested system uses a variety of contemporary approaches, such as Kmeans Clustering, Auto Encoder, Local Outlier Factor, and artificial neural networks, to improve algorithmic diversity and flexibility to changing fraud patterns. In addition to addressing issues like test data creation for training and validation, the system emphasizes a heuristic approach to solving high-complexity computational problems, guaranteeing efficacy in a variety of settings. This study, which is positioned as a proactive and adaptable solution, emphasizes how crucial it is to stop UPI fraud and provides a thorough foundation for reliable fraud detection in the ever-changing world of online transactions.

In today's automotive industry, Electronic Control Units (ECUs) control a large number of functions in vehicles. Increasing cyberattacks on ECUs pose a danger to vehicle safety and security due to the rising dependence on automation and Electronic Control Units (ECUs). This study proposes a new way to find ECU attacks by using Python's large library and tools for automotive security. The three main parts of the approach are collecting and processing data, and finding outliers. To gather data, an Arduino and a CAN bus shield are used to make a CAN network and record the data that the ECUs send and receive. Among the preprocessing tasks is the determination of the time intervals for message reception among nodes and the standardization of data to account for variances caused by hardware constraints. Examining the slope of data plots is a technique used for anomaly detection. The compromised Electronic Control Unit (ECU) is detected by a noticeable change in the slope, which indicates a potential attack. A proof-of-concept illustrates the strategy's efficacy. By inserting an adversarial Electronic Control Unit (ECU), which interferes with normal ECU communication patterns, we can simulate real-life attack scenarios. This Python-based method finds different threats successfully and with high accuracy. This study makes a big contribution to the fields of cyberphysical systems and automotive cybersecurity by showing a reliable way to detect attacks on Electronic Control Units (ECUs) that using Python.

Genetic Algorithm (GA) is an excellent optimization algorithm which has attracted the attention of researchers in various fields. Many papers have been published on works done on GA, but no single paper ever utilized this algorithm for misbehavior detection in VANETs. This is because GA requires manual definition of fitness function and defining a fitness function for VANETs is a complex task. Automating the creation of these fitness functions is still a difficulty, even though studies have found several successful applications of GA. In this study, a neuro-genetic security framework has been built with ANN classifier for detecting misbehavior in VANETs. It leverages a genetic algorithm for feature reduction with ANN as a dynamic fitness function, considering both node behaviors and contextual GPS data. Deployed at the Roadside Unit (RSU) level, the framework detects misbehaving nodes, broadcasting alerts to RSUs, Central Authority and the vehicles. The ANN based fitness function has been employed in GA that enabled the GA to select the best results. The 10- fold CV used enabled the whole system to be unbiased giving a precision accuracy of 0.9976 with recall and F1 scores as 0.9977, and 0.9977 respectively. Comparative evaluations, using the VeReMi Extension dataset, demonstrate the framework's superiority in precision, recall, and F1 score for binary and multiclass classification. This hybrid genetic algorithm with ANN fitness function presents a robust, adaptive solution for VANET misbehavior detection. Its context-aware nature accommodates dynamic scenarios, offering an effective security framework for the evolving threats in vehicular environments.

Agriculture remains the primary source of income for many countries around the world. However, the industry has continued to suffer difficulties brought on by climate change, which has led to food insecurity. Extreme weather events brought on by climate change negatively influence crop yields and create uncertainty in agricultural production. Even though it is hard to eradicate these natural occurrences, farmers could greatly benefit from early knowledge of future conditions when planning and managing their crops. Crop yield prediction enables farmers to make informed decisions about planting, resource allocation, and general farm management. Conventional forecasting techniques frequently depend on historical data and oversimplified models, which may not adequately represent the complex interactions between environmental variables affecting crop development. The development of Machine Learning (ML) and Deep Learning (DL) techniques in recent years has demonstrated promise in producing precise, data-driven agricultural output projections. This study presents a review of how researchers have used ML-DL-based techniques to anticipate crop yields, assessing their efficacy and highlighting any inherent drawbacks. The necessity of addressing changing difficulties and encouraging the adoption of cutting-edge solutions in agriculture is emphasized, underscoring the significance of promoting multidisciplinary collaboration between academics and industry specialists.

Abstract: In this paper, speed control of induction motor using fuzzy logic controller is proposed. Speed control of induction motor takes place by, Direct torque control(DTC) method i.e. by directly controlling torque. Here we have used Voltage/Frequency speed control method of induction motor. The fuzzy logic controller (FLC) solves the problem of non linearity’s and parameter variation of induction motor. Unlike the conventional standard controllers, the proposed controller has much less computationally demanding. Direct torque control scheme of induction motor is firstly used. Then, the specified rule and their membership functions of proposed fuzzy logic system will be represented. The performance of a controller is evaluated under various operating conditions. A simplified FLC with relatively fewer rules will be implemented for perfect speed control.

The use of digital twins (DT) has made important improvements not just from the beginning of the process of automobile development through the final phases of vehicle building, but additionally during its usage, collecting essential information from its everyday activities to make traveling more joyful, relaxed, and secure. This study organizes the DT development history, fundamental principles, and essential technologies, as well as summarizing current research methodologies and problems in battery simulation, state estimate, remaining useful life (RUL) projection, battery protection, and management. In addition, study provide methods for batteries digital simulation, real-time status calculation, variable charging supervision, dynamic heat leadership, and energetic leveling regulation in the smart battery management system (BMS) using DT. The study also provides prospects for DT growth in the industry of battery. Lastly, the article concludes with an examination of the technological economic effects of DT technology, which will revolutionize conventional automobile manufacturing, as well as the barriers to continued growth.

A VANET is a collection of wireless vehicle nodes that may connect with one another without the need of fixed infrastructure or centralized management. Vehicular ad hoc networks (VANETs) function in a dynamic and unpredictably changing environment that brings numerous potential security risks. One of the types of attacks that affect VANETs the most is the Denial of Service (DoS) attack. Additionally, VANETs can't be secured by following the conventional approaches to protecting wired or wireless networks because of the ever changing network topology. Because preventative methods are insufficient, using an intrusion detection system (IDS) is crucial to the VANET's defense. In this paper, a new intrusion detection system has been proposed by using an Artificial Neural Network-Fitness function based Genetic Algorithm and Support Vector Machines (SVM) for vehicular ad hoc networks to detect the denial-of-service attack.