Alzheimer's disease (AD) is a type of brain disorder that is becoming more prevalent worldwide. It is a progressive and irreversible condition that gradually impairs memory and cognitive abilities, eventually making it difficult to perform even basic tasks. While the symptoms may not be noticeable until the disease has progressed significantly, early diagnosis can help slow its progression. Unfortunately, there is currently no cure for AD, and although medications and therapies can help manage its symptoms, they cannot reverse the disease. This article proposes a SpinalNet-Rider Neural Network (Spinal-RideNN) algorithm for AD classification. The Spinal-RideNN is formed by the SpinalNet and Rider Neural Network (RideNN) mixture. Here, an input brain image is forwarded to the preprocessing stage. The preprocessing is done by the Kalman filter and Rate of Interest (ROI) extraction. Then, the image segmentation is accomplished by Psi-Net. Later, feature extraction is done for extracting the Speeded Up Robust Features (SURF), the Haralick features, and the Local Binary Pattern (LBP). Eventually, the AD classification is done by using Spinal-RideNN. Furthermore, the Spinal-RideNN is evaluated by using evaluation measures like sensitivity, specificity, accuracy, Positive Predictive Value (PPV) as well as Negative Predictive Value (NPV) and it obtained the best values of 0.948, 0.928, and 0.909correspondingly.

Wireless Sensor Networks (WSNs) are pivotal in enabling real-time Internet of Things (IoT) applications through sensor nodes that communicate both with each other and their environment. Despite their potential, WSNs face significant challenges due to limited energy resources, which are crucial for sustaining long-term operations. One of the most pressing issues is unbalanced energy utilization during data packet routing, which can lead to premature network failure. This paper addresses these challenges by introducing an Enhanced Zone Stable Election Multipath Routing Protocol that leverages Binary Gray Wolf Optimization (BGWO) and Sugeno Fuzzy Logic. The proposed protocol aims to enhance energy efficiency, load balancing, and network scalability through an optimized clustering and routing approach. By employing multipath routing, the protocol creates multiple paths between source and destination, thereby improving data delivery probability and network resilience. Simulation results demonstrate that our approach outperforms existing methods, such as LEACH and DFLC, in terms of packet delivery ratio, energy consumption and network life time. The findings suggest that the proposed solution significantly extends network lifetime and improves overall performance, offering a robust alternative to conventional WSN routing strategies.

This paper presents a mixed algorithm approach for real-time image processing on air and land based robotic drones that operate in highly deterministic environments such as automated warehouses. A combination of heuristic, multi state algorithmic solution based on Canny Edge and a CNN deep learning-based solution is proposed to ensure maximum performance out of low power embedded hardware. A heuristic i.e., rule-based approach is used for fixed, simple tasks such as navigation, docking, charging, identifying racks etc. On detecting an edge case or an anomaly beyond the scope of heuristics, the program switches to a deep learning-based approach in real time for extracting context and navigating the complex scenario. This computationally intense mode only lasts for short bursts and switches back to an appropriate, power efficient algorithm. The paper aims to study the effects of different embedded computer vision methodologies taking into account the context switching time and their effect on the computational resources such as CPU, RAM and ROM along with variations in CPU temperature and verify the effectiveness of a mixed algorithm approach on a Raspberry Pi 4 single board computer running “Raspbian Bookworm” a 64bit Debian based operating system interfaced with a CSI Camera for visual feed.

In this survey paper, we discuss various techniques that can be employed to enhance isolation between multiple-input and multiple-output (MIMO) antennas. In this modern world, the MIMO antenna system is an important technique used in wireless technology. The channel capacity in a multipath environment can be improved by deploying multiple antenna elements, i.e., the MIMO technique at both the transmitter and receiver terminals. To have an efficient MIMO technique, the isolation between the multiple antenna elements must be as high as possible. In the past decade, many research works have proposed techniques to enhance isolation in MIMO antennas. In this survey, we examined various mutual coupling reduction techniques employed to improve isolation in multiple antenna elements and compared them based on various performance metrics. Isolation enhancement techniques such as stubs, filters, defected ground structure, decoupling networks, orientation of the radiating elements, parasitic elements, periodic structures, neutralization lines, metamaterials, etc., are discussed in this paper.

Underwater Wireless Sensor Networks (UWSNs) are employed in various applications ranging from observing the underwater environment to military applications, which leads to attaining interest for many investigators in the UWSNs area. They experience more problematic issues because they are deployed underwater. Some of the common difficulties involve the assessment of battery, installation, energy consumption, and long delay. To overcome this bridge, an effectual scheme is developed for the internet of UWSNs named Archimedes Chicken Swarm Optimization (ACSO). Here, ACSO is obtained by the fusion of Archimedes Optimization Algorithm (AOA) and Chicken Swarm Optimization (CSO). The underwater sensor network IoT module (IoUT) nodes are simulated and the energy model and mobility model are considered for the following progress. The energy prediction is achieved by employing a Deep Recurrent Neural Network (DRNN), which is trained by the proposed ACSO. The Cluster Head (CH) selection is performed utilizing the Energy Efficient Clustering Protocol. Lastly, the routing is carried out by the ACSO algorithm, where the best route is determined based on various parameters namely, energy, distance, delay, throughput, and Packet Delivery Ratio (PDR).

Streetlights are crucial for public safety, especially for those traveling at night. Unfortunately, many areas encounter non-functioning streetlights due to various issues, which can lead to significant safety hazards. To address this problem, an optimized artificial intelligence (AI)-enhanced explainable Random Forest model, referred to as OptiX-AI-RF, has been developed for fault detection in streetlight systems. Initially, various machine learning (ML) models are trained using publicly available street light fault prediction dataset. Since the random forest (RF) model outperformed the others, it is utilized for optimization. Key RF model hyperparameters are adjusted using Bayesian optimization to improve the detection capabilities of the model. The experimental results demonstrated that the OptiX-AI-RF model effectively identified faults in streetlight systems, achieving an accuracy of 82.88%, a precision of 86.30%, a recall of 82.88%, and an F1-score of 78.98%. The predictions of the suggested model are further analyzed using explainable artificial intelligence (XAI) methods. OptiX-AI-RF enables authorities to evaluate the predictions of the model and gain insights into the various factors contributing to streetlight failures by utilizing XAI techniques such as permutation importance, partial dependence plots, and LIME (Local Interpretable Model-agnostic Explanations). This dual capability of accurate fault detection and explainability makes OptiX-AI-RF a valuable tool for maintaining streetlight infrastructure, ultimately aiding in the implementation of more effective maintenance strategies and enhancing public safety in urban areas.

The growth of wireless communication technologies demands advancement in designing antennas. The essential need for efficient and low-profile antennas are required for wireless communication. The development of antenna structures(compact) with performances is considerably enhanced over traditional antenna structures and methodologies. A compact printed and planar multiple-input multiple-output (MIMO) for ultra wideband (UWB) communications is presented. Two circular disc monopole antenna elements constitute the proposed UWB-MIMO antenna, operating over the frequency band of 4-10 GHz. The required antenna performance in terms of frequency response, gain, S-parameters, and voltage standing wave ratio (VSWR) can be achieved in the range of 3-7 GHz gain with minimum attenuation. The proposed antenna is simulated using computer simulation technology (CST) microwave studio software, and the designed antenna will operate for wireless communication application.

Obesity is a significant health concern linked to severe medical conditions. Obesity increases the risk of diabetes, thyroid issues, cardiac disease, liver tumors, and stroke. Early prediction of obesity risk is essential for improving public health and well-being. To address this, an optimized explain-able CatBoost model, referred to as OptiX-CatBoost, has been developed. Initially, various machine learning (ML) models are trained using the publicly available dhaka obesity dataset. Among these, the categorical boosting (CatBoost) model emerged as the top performer and is selected for optimization. Bayesian optimization is employed to fine-tune key hyperparameters of the CatBoost model, enhancing its performance. The experimental results demonstrated that the OptiX-CatBoost model outperformed existing methods, achieving an accuracy of 95.60%, a precision of 94.60%, a recall of 93.12%, an F1-score of 98.15%, a Jaccard score of 96.14%, and a Kappa score of 87.14%. Additionally, the predictions made by the proposed model are further analyzed using explainable artificial intelligence (XAI) techniques. Healthcare professionals can evaluate the predictions of the proposed model and learn more about the different factors driving obesity by using XAI techniques such as partial dependence graphs, permutation significance, and LIME (Local Interpretable Model-agnostic Explanations). This dual capability of accurate prediction and interpretability renders OptiX-CatBoost a valuable tool for early obesity risk assessment, ultimately aiding in the development of better public health strategies and interventions.

This paper proposes an Internet of Things (IoT) based answer to address the issue of under-loading and overloading of railroad carts at Coal India Limited (CIL) sidings. The carts, stacked through legally binding means by payloaders, frequently bring about overloading or under-loading. While punishments for overloading are borne by the buyer, under-loading brings about inactive cargo costs, which are borne by the CIL. The framework's essential parts incorporate burden sensors introduced on every cart, a focal handling unit for information collection and examination, and easy to understand interface for observing and control. The load sensors ceaselessly measure the heaviness of the freight in every cart and send this information to the focal handling unit. The focal handling unit examines this information, recognizes any examples of underloading or overloading, and cautions the significant faculty through the UI. The proposed advanced arrangement includes the utilization of sensors/IoT gadgets to screen and control the stacking of carts. This framework plans to guarantee ideal stacking, accordingly forestalling punishments and diminishing inactive cargo costs. By resolving this issue, the undertaking can altogether improve functional productivity and cost-adequacy in coal transportation at CIL sidings.

This paper introduces a novel design and optimization approach for a compact K-band Multiple Input Multiple Output (MIMO) antenna, catering to the requirements of high-speed wireless communication systems. It addresses challenges like compactness, high gain, and mutual coupling effects in MIMO setups by utilizing advanced simulation techniques and optimization algorithms. Through analyzing frequency needs and radiation characteristics, it explores various antenna configurations and feed network architectures. The focus is on achieving compactness, efficient power distribution, and impedance matching while evaluating metrics like radiation pattern, impedance bandwidth, envelope correlation coefficient (ECC), and diversity gain. The resulting design is optimized for integration into diverse high-speed wireless communication systems like 5G networks, satellite communication, radar systems, and wireless backhaul links, offering valuable insights for researchers and engineers in the field.

Alzheimer's Disease (AD) is a well-recognized cause of dementia among the elderly population, affecting an increasing number of individuals. The origins and progression mechanisms of AD remain intricate and not yet fully comprehended. Magnetic Resonance Imaging (MRI) is a neuroimaging technique that enables in-depth and precise investigations of the disease, providing a valuable tool for both diagnosis and early detection of AD. However, handling extensive sets of clinical images poses a significant challenge, prompting researchers to explore machine learning methods. Machine learning encompasses a range of computer-assisted techniques that adapt their outcomes toward predefined objectives. This study incorporates various machine learning techniques and conducts a comparative analysis to determine the most effective approach for Alzheimer's Disease detection. Additionally, a web application has been developed, enabling physicians to predict a patient's condition automatically.

Artificial intelligence (AI) is that encompasses machine learning (ML) combined with human intelligence had begun to reform medical practices into a new dimension. Advancements and developments of AI molds improved diagnostics in the field of cardiology. Electrocardiogram (ECG) is a simple and cost-effective tool to identify cardiac disorder and which is its reason for being into practice till date. Increasing the population of ECG big data annually requires automatic analysis and immediate interpretation for improved diagnosis. Modern AI techniques like deep learning (DL)-based convolutional neural networks (CNNs) provide an improved way of cardiac disease management and diagnosis. This review throws a light over application of AI in ECG analysis and its necessity. Rich sets of clinical ECG data curated carefully as private and public access developed for various cardiac and extra-cardiac diseases management. Rather than human ECG interpretation, AI can move modern medicine toward more personalized patient care. The intention of this review article is to assess clinical and research possibilities, gaps, and jeopardies involved in cardiac anomalies detection using ECG measurement.

An efficacious energy model based on Gaussian minimum shift keying (GMSK) for cooperative communication is proposed in this paper. The influence of the rate at which data are transmitted, distance, severity of fading, and quantity of participating nodes on the energy expended for communication by the proposed model is investigated through simulations. The influence of the rate at which data are transmitted and the quantity of participating nodes on the energy expended in circuitry is also studied. Through the simulations, it is apparent that the energy consumed by the circuit dominates the energy consumed for transmission for all of the transmission data rates, path loss exponents, bit error rates, and transmission distances considered.

Alzheimer's Disease (AD), the most common form of dementia, is a neurodegenerative condition which evolves over time. Patients experience short-term memory lapses at the start of this process, and by the end, they depend exclusively on signs. While there is no cure for AD, Medical treatments can be pursued for premature patients. Individuals suffering from early-stage Alzheimer's disease have signs of linguistic impairment, including issues with word recall and word seeking. In this paper, we use Stacking, an ensemble Machine Learning algorithm that learns how to combine the best predictions from multiple high-performing Machine Learning models, such as the K-Nearest Neighbors algorithm, Random Forest algorithm, Decision Tree algorithm, Support Vector Machine algorithm, and Multi-Layer Perceptron algorithm, to accurately predict AD. The data-set is gathered from the dementia Pitt corpus repository. Our methodology focuses on utilizing extracted Features from speech signals to detect abnormalities and deduce whether a patient has AD. 78% of AD sufferers and Healthy participants can be distinguished using the proposed technique. This data set demonstrates the ability to detect AD using only audio information.

There are numerous goals in next-generation cellular networks (5G), which is expected to be available soon. They want to increase data rates, reduce end-to-end latencies, and improve end-user service quality. Modern networks need to change because there has been a significant rise in the number of base stations required to meet these needs and put the operators' low-cost constraints to the test. Because it can withstand interference from other wireless networks, and Adaptive Complex Multicarrier Modulation (ACMM) system is being looked at as a possible choice for the 5th Generation (5G) of wireless networks. Many arithmetic units need to be used on the hardware side of multicarrier systems to do the pulse-shaping filters and inverse FFT. The main goal of this study is to adapt complex multicarrier modulation (ACMM) for baseband transmission with low complexity and the ability to change it. We found that this is the first recon-figurable architecture that lets you choose how many subcarriers a subband has while still having the same amount of hardware resources as before. Also, under the new design with a single selection line, it selects from a set of filters. The baseband modulating signal is evaluated and tested using a Field-Programmable Gate Array (FPGA) device. This device is available from a commercial source. New technology outperforms current technology in terms of computational com-plexity, simple design, and ease of implementation. Additionally, it has a higher power spectrum density, spectral efficiency, a lower bit error rate, and a higher peak to average power ratio than existing technology.

Alzheimer's Disease (AD), the most common form of dementia, is a neurodegenerative condition which evolves over time. Patients experience short-term memory lapses at the start of this process, and by the end, they depend exclusively on signs. While there is no cure for AD, Medical treatments can be pursued for premature patients. Individuals suffering from early-stage Alzheimer's disease have signs of linguistic impairment, including issues with word recall and word seeking. In this paper, we use Stacking, an ensemble Machine Learning algorithm that learns how to combine the best predictions from multiple high-performing Machine Learning models, such as the K-Nearest Neighbors algorithm, Random Forest algorithm, Decision Tree algorithm, Support Vector Machine algorithm, and Multi-Layer Perceptron algorithm, to accurately predict AD. The data-set is gathered from the dementia Pitt corpus repository. Our methodology focuses on utilizing extracted Features from speech signals to detect abnormalities and deduce whether a patient has AD. 78% of AD sufferers and Healthy participants can be distinguished using the proposed technique. This data set demonstrates the ability to detect AD using only audio information.

Alzheimer’s Disease (AD), the most common form of dementia, is a neurodegenerative condition which evolves over time. Patients experience short-term memory lapses at the start of this process, and by the end, they depend exclusively on signs. While there is no cure for AD, Medical treatments can be pursued for premature patients. Individuals suffering from early-stage Alzheimer’s disease have signs of linguistic impairment, including issues with word recall and word seeking. In this paper, we use stacking, an ensemble Machine Learning algorithm that learns how to combine the best predictions from multiple high-performing Machine Learning models, such as the K-Nearest Neighbors algorithm, Random Forest algorithm, Decision Tree algorithm, Support Vector Machine algorithm and Multi-Layer Perceptron algorithm, to accurately predict AD. The data-set is gathered from the dementia Pitt corpus repository. Our methodology focuses on utilizing extracted features from speech signals to detect abnormalities and deduce whether a patient has AD. 78% of AD sufferers and Healthy participants can be distinguished using the proposed technique. The average test accuracy using stacking classifier is 64%. Machine Learning algorithms employ 13 dimensionality reduction technique and an average accuracy reported by Neighborhood Component Analysis is 73%. 97% accuracy was attained using stacking classifier in machine learning algorithms. This data set demonstrates the ability to detect AD using only audio information.

This paper presents the design and analysis of a thin film MEMS based sensor for perceiving humidity. Humidity instruments measure the quantities such as temperature, pressure, volume of air or gas, etc. The main motivation behind this work is to fulfill the need for sensing humidity in automotive, food/beverages, cosmetics, and pharmaceutical industries. Here, the sensor structure holds a very thin conducting film which detects the presence of gases such as ethanol, propane, steam, hydrogen, etc. The whole sensor structure was then mounted on a silicon substrate. COMSOL Multiphysics was used to design the Humidity sensor. Simulation of humidity sensor was analyzed for moisture detection in the atmosphere. The presence of gases and water vapor can be calculated with the variation of parameters such as temperature, resistance, potential difference across sensing electrodes. These parameters are better optimized by using MEMS CAD tool for better performance of the sensor

Speech and Gesture recognition systems constitute an ideal aid for the disabled with speech and hearing impairments. Approximately, there are 466 million people in the world with hearing impairment and around 16 million with speech impairment. They require an external aid to recognize their speech and gestures, to express their thoughts and ideas to the world. The proposed Speech and Gesture Recognition System (SGRS) takes forward to solve the communication barriers faced by the disabled subjects, by recognizing both the speech and gestures of the subjects with promising accuracy using the convolutional neural network. The proposed SGRS model is competent to convert the sign-language into pictures and speech to text as well with high accuracy. Thus, SGRS can be a suitable aid for the subjects with speech and hearing impairment. SGRS has been evaluated with standard evaluation scores such as validation accuracy, validation loss, recall, precision and F1-score and has been proved to be proficient.

Device-to-Device (D2D) communication is one of the prominent and key technique in the next-generation wireless network. In D2D communication, resources are share between Device-to-Device users and cellular users. If the resource allocation is not shared properly then, there is an interference between device-to-device users and cellular users in the network. In D2D communication to mitigate the interference and improve the channel capacity is one of the challenging tasks. So, in this paper underlay as well as overlay scenarios in Long Term Evolution-Advanced (LTE-A) using uplink resource allocation scheme is proposed. In this analysis, orthogonal frequency resources are utilized and thereby reducing the interference in the channel, but at the cost of some throughput of cell-edge users. The proposed method makes use of the same orthogonal frequency resources and simultaneously allows the D2D users to reuse the left-over frequency from the cellular users. As a result, the throughput of the cellular users, as well as the cell-edge users, remains the same whereas the throughput of the D2D users increases significantly, thereby increasing the overall system throughput.