Crop diseases pose significant challenges to global food security and agricultural sustainability. Timely and accurate disease detection is crucial for effective disease management and minimizing crop losses. In recent years, hyperspectral imaging has emerged as a promising technology for non-destructive and early disease detection in crops. This research paper presents an advanced deep learning approach for enhancing crop disease detection using hyperspectral imaging. The primary objective is to propose a hybrid Autoencoder-Generative Adversarial Network (AE-GAN) model that effectively extracts meaningful features from hyperspectral images and addresses the limitations of existing techniques. The hybrid AE-GAN model combines the strengths of the Autoencoder for feature extraction and the Generative Adversarial Network for synthetic sample generation. Through extensive evaluation, the proposed model outperforms existing techniques, achieving exceptional accuracy in crop disease detection. The results demonstrate the superiority of the hybrid AE-GAN model, offering substantial advantages in terms of feature extraction, synthetic sample generation, and utilization of spatial and spectral information. The proposed model’s contributions to sustainable agriculture and global food security make it a valuable tool for advancing agricultural practices and enhancing crop health monitoring. With its promising implications, the hybrid AE-GAN model represents a significant advancement in crop disease detection, paving the way for a more resilient and food-secure future.

Patient-centered AI solutions for dealing with Alzheimer's ailment is a research-based totally article that explores the ability of synthetic intelligence (AI) in aiding the management and remedy of Alzheimer's disease (AD). Alzheimer's disorder is a revolutionary neurodegenerative sickness that impacts thousands and thousands of people worldwide. And not using a recognized treatment, managing advert calls for a comprehensive and personalized technique. This text highlights the key demanding situations in cutting-edge advert control and introduces the function of AI in addressing those demanding situations. It additionally discusses the potential benefits of patient-targeted AI answers in improving early detection, analysis, and remedy of advert. Through an assessment of existing studies, this article provides promising AI applications which include advanced imaging, biomarker evaluation, and predictive modeling for identifying individuals prone to ad and monitoring disorder development.

The combination of artificial intelligence, 5G technology, and cloud computing has altered energy conversion processes, most notably the use of agricultural waste for sustainable energy generation. This book chapter digs into AI, 5G, and cloud computing research and development for efficient energy conversion, environmental concerns, and the viability of agricultural waste as a renewable energy resource. AI technologies provide real-time monitoring and control, while cloud computing enables data analytics and optimization. The synergistic method increases the efficiency of energy conversion, predictability, flexibility, optimization, grid integration, energy storage, and cost reduction. Compatibility, data security, and financial sustainability, on the other hand, must be addressed. The chapter emphasises the importance of this integrated strategy in addressing global energy and environmental challenges.

A new era in communication has been ushered in by MANET networks, in which users (nodes) interact with one another through a self-configuring network of handheld devices linked by wireless links. Nodes are capable of participating and enthusiastic about sending packets to other nodes. Consequently, the need for a routing protocol materializes. The most difficult aspect is dealing with the network's dynamic topology as a result of node mobility. This is because limited resources like storage space, battery life, and bandwidth require a protocol that can quickly adapt to topology changes while periodically updating messages. On the other hand, security is another important aspect of routing since the involvement of attackers will exhaust the network resources. This paper addresses the main issue of designing a routing protocol that handles all the adversaries and achieves better efficiency. For that, we proposed a Hybrid Machine Learning (HyML) model which evaluates the. Initially, the network is segregated by the Secure Stable Clustering (SSC) approach which first verifies the node's legacy and forms clusters based on stability. The HyML is designed by combining two important ML techniques such as ANN and fuzzy-C Means (FCM) algorithm. The ANN model learns multiple attributes of the trust value and computes the cumulative trust score. Next, FCM determines the node position upon trust score. After the computation of the trust value, optimal route selection is performed by the Spider Monkey Optimization (SMO) technique. The overall work is evaluated through comprehensive simulations based on network longevity, throughput, energy usage, PDR, attack detection efficiency, and delay.

In this study, a unique ECG slotted patch antenna loaded with split ring resonator is designed and analyzed for ECG monitoring. The antenna is fed with conductor backed coplanar feed to obtain low dispersion and attenuation characteristics. The operating frequency of the designed antenna is in the Industrial Scientific medical band (2.4 to 2.5) GHz. Performance analysis is made for both FR4 and PDMS substrate. The results of the proposed antenna’s specific absorption ratio and return loss are 0.487 W/kg and21. S7dB for FR4 and 0.2604 W/kg and -31.4S dB for PDMS. A comparison on gain, directivity, return loss and SAR is presented.

Early Alzheimer’s disease detection is essential for facilitating prompt intervention and enhancing the quality of care provided to patients. This research presents a novel strategy for the diagnosis of Alzheimer’s disease that makes use of sophisticated sampling methods in conjunction with a hybrid model of deep learning. We use stratified sampling, ADASYN (Adaptive Synthetic Sampling), and Cluster- Centroids approaches to ensure a balanced representation of Alzheimer’s and non-Alzheimer’s cases during model training in order to meet the issues posed by imbalanced data distributions in clinical datasets. This allows us to solve the challenges posed by imbalanced data distributions in clinical datasets. A strong hybrid architecture is constructed by combining a Residual Neural Network (ResNet) with Residual Neural Network (ResNet) units. This architecture makes the most of both the feature extraction capabilities of ResNet and the capacity of LSTM to capture temporal dependencies. The findings demonstrate that the model is superior to traditional approaches to machine learning and single-model architectures in terms of accuracy, sensitivity, and specificity. The hybrid deep learning model demonstrates exceptional capabilities in identifying early indicators of Alzheimer’s disease with a high degree of accuracy, which paves the way for early diagnosis and treatment. In addition, an interpretability study is carried out in order to provide light on the decision-making process underlying the model. This helps to contribute to a better understanding of the characteristics and biomarkers that play a role in the identification of Alzheimer’s disease. In general, the strategy that was provided provides a promising foundation for accurate and reliable Alzheimer’s disease identification. It does this by harnessing the capabilities of hybrid deep learning models and sophisticated sampling approaches to improve clinical decision support and, as a result, eventually improve patient outcomes.

Rapid and erratic electrical firing in the brain is what causes seizures. This may result in momentary anomalous behaviors, movements (such as jerky, alternately stiffened arms and legs), sensations, or unconsciousness or an altered degree of consciousness. According to a survey, approximately 50 million people around the world suffer from epilepsy, making it one of the most common neurological diseases on a global scale. Despite modern pharmacological and surgical treatment options, more than a quarter of epilepsy patients experience uncontrollable seizures. Early detection of seizures aids in the prevention of SUDEP (Sudden Unexpected Death in Epilepsy) This model proposed a machine learning approach to detect the seizure. The Random Forest Classifier algorithm was used to diagnose the seizure that was brought to our attention. A pretrained model with a machine learning and supervised classification approach is built with the datasets received from the EEG (electroencephalogram) and ECG (electrocardiogram) to detect seizures in the pre-ictal stage. The model has been trained with existing datasets, and the research shows that there are several causes of epilepsy. Even if the causes differ, the solution is the same. In this case, the model predicts the seizure and alerts the hospital management, nurses, and carers before it occurs. Which would be extremely beneficial to doctors in treating it.

Cancer of the breast is a malignant tumour that originates in the cells of the breast tissue. It is by far the most common kind of cancer found in females around the world, with a projected 2.3 million new cases will be discovered in the year 2020 alone. It is projected that one in eight women will be diagnosed with breast cancer at some point in their life, despite the fact that breast cancer can also occur in men. Breast cancer is a complex condition that can arise from a diverse set of factors, express itself in a variety of ways, and can be treated in a variety of ways. Ductal carcinoma in situ, invasive ductal carcinoma, and invasive lobular carcinoma are all different subtypes. Both the available treatment options and the expected outcome of breast cancer are very variable depending on the particular subtype of the illness. Breast cancer risk factors include drinking alcohol and not getting enough exercise, as well as getting older, having a family history of the disease, having genetic mutations, being exposed to estrogens, and having a family history of the disease. There is not always a connection between having risk factors and developing breast cancer, despite the fact that there can be a link between the two. The prognosis and treatment options for breast cancer are highly dependent on the stage of the disease at the time of diagnosis. During staging, the extent to which the cancer has spread throughout the body and how far it has progressed are both measured. The TNM system, the IAFCM system, the ACM system, and the MPIG system are just few of the staging systems that are used to classify breast cancer. These staging systems consider not only the size of the tumor but also whether or not lymph nodes are involved and whether or not distant metastases are present. The severity of breast cancer symptoms can vary widely, depending not only on the subtype of the disease but also on how far along it has progressed. Alterations in the size or shape of the breast, discharge from the nipple, and alterations in the skin of the breast (such as redness or dimpling) are all common indications. On the other hand, not all cases of breast cancer present themselves in a visible manner, and mammography and other forms of routine screening may be able to detect some of these cases. Options for treating breast cancer vary depending on the patient's condition and the stage of the disease, as well as the patient's overall health and their preferences towards therapy. Common examples of medical interventions include surgery, radiotherapy, chemotherapy, hormone therapy, and targeted therapy. Other examples include. In certain cases, it may be appropriate to participate in more than one form of treatment.

The Internet of Things (IoT), which has revolutionized many industries in recent years, including agriculture, has been growing quickly. This abstract describes an IoT-based system for tracking paddy growth, an important crop in many parts of the world. The suggested system is made up of numerous sensors that gather information about the environment in real-time, including temperature, humidity, soil moisture, and water levels. This information is wirelessly transferred to a cloud-based platform, where it is analyzed and processed to offer farmers useful insights to increase crop output and use less water. A vital tool for precision agriculture, the system's low cost and simplicity allow farmers to maximize their resources while reducing their environmental impact.

Non-Orthogonal Multiple Access (NOMA) is a new technology that has a good prospect for increasing channel use without increasing bandwidth. NOMA provides a higher spectrum efficiency, reduced latency, and can accommodate a greater number of users per cluster than Orthogonal Multiple Access (OMA). Receiver complexity, an appropriate power allocation method, the requirement for perfect Channel State Information (CSI) for detection, and so on are all implementation issues. Support Vector Machine (SVM) based NOMA signal detection is proposed in this paper to detect the signal over a fading channel and analyzed using a different number of receiver antennas. The simulation results reveal that the suggested technique needs about 5 dB higher SNR than the complex Maximum Likelihood (ML) -based receiver with receiver diversity order two to achieve closer performance. However, increasing the receiver diversity results in increased BER performance of the proposed system over slow, frequency non-selective fading channel. This proves that the proposed SVM learning-based NOMA receiver without CSI could achieve complex ML based detector performance over the wireless channel by increasing receiver diversity.

Polyether ether ketone (PEEK) is a biocompatible alternative to metallic biomaterials because of its unique properties and biocompatibility. Its bioinert nature may lead to implant failure from inadequate osseointegration. Therefore, this research aims to develop the nSiO 2 ceramic particle-reinforced PEEK (nSiO 2 @PEEK) polymer nanocomposite. The particle size of nanoparticles was measured as 43.6 nm using the particle size analyzer (PSA). The morphology of the fabricated composite was analyzed using FESEM. The structural characteristic of nSiO 2 @PEEK was investigated using XRD and FTIR. Thermal stability was examined using TGA thermograms and DSC curves. Minimum toxic level (grade: slight, 1–20%) was observed by in vitro cytotoxicity assessment using direct and indirect methods. Excellent cell viability was found as 83.6% through MTT assay. The MG-63 cell adhesion study was conducted subsequently excellent cell growth and cell morphology were monitored using SEM analysis. This investigation found the nanocomposite to be biocompatible. It is a promising biomaterial for medical implants.

Smart vehicle monitoring and tracking system powered by active radio frequency identification and Internet of Things (SVMT-ARFIoT) technology is proposed, which is cost-effective and more secured. The system gives tracking assistance over the connected devices. The advantage of smart vehicle monitoring system powered by active radio frequency identification tag and Internet of Things (SVM-ARFIoT) technology over global positioning system (GPS) is that GPS is very costly and its functionality is not secured, that is, prone to hack. When a GPS-enabled device is switched off, the device is out of the tracking/coverage area; hence, it can be driven unmonitored. Hence, there is a need for a system that is more secured by continuous tracking and cost-effective. The layout of the total area is initially gridded based on the geographical area. The active radio frequency identification (RFID) transmitters are equipped in a mobile fashion, and they have been housed in the vehicle. The RF wireless sensors serve as stationary active RFID receivers that are placed as per the range of detection on the basis of the geographical gridding. The stationary active RFID receivers are retained in the range of specified zones. The wireless sensor network modules with the Internet of Things (IoT) transceiver module (ESP8266) push the data that have been harvested from the field to the IoT domain for monitoring webpage support. The database encompasses the information concerning location, recorded date and time, and time stamp in that particular zone for security purpose. Lending customers have access to all the vehicles by attaching via SVMT-ARFIoT. Therefore the vehicles are readily made for monitoring and tracking purposes with less cost and high security.

. In this research work, the Ti-6Al-4V material was used for the investigation of machining parameters by means of hybrid micro electrical discharge machining to improve the machining process and reduce the negative effects of debris accumulation in the drilled hole. L9 orthogonal array was used in the Taguchi based grey relational analysis to optimize the parameters such as material removal rate and dia-metrical accuracy of the machining process for Ti-6Al-4V. This work encompasses the design, development, and calibration of the work piece vibration platform and experimental analysis of the process parameters by means of the hybrid micro electrical discharge machining process. The maximum material removal rate and minimum surface roughness was observed at the current value of 2.5 A, pulse on time is 2 µ s and pulse off time is 14.5 µ s. The maximum material removal rate was observed for the increase in pulse on time with 14.4 µ s and 4 A current level. The diametrical accuracy of the microholes was increased while increasing the pulse off time and decreasing the pulse on time. The fluid flow simulation has been conducted to find out the pressure drop and to know the velocity of the flow inside the hole for the effective flushing of the debris during machining.

In this paper, an antenna with L shaped slots adjacent to each other is presented. The return loss and the VSWR have been found to be ideal which are less than -10dB and 1.5dB respectively. The antenna resonates between 1GHz to 3GHz by displaying acute antenna characteristics at 1.6GHz, 2.0GHz and 2.5GHz. Due to low frequency range they are compatible for medical purposes.

A rectangular patch array antenna of size 2*1 and 4*1 with inset feed for S band applications are designed. The main objectives of this work are to improve the gain and return loss of the antenna. Both the arrays are designed to operate at the resonant frequency of 2. 45GHz. The antenna is designed by using a substrate called Poly tetra fluoro ethylene (Teflon). It is a flexible material. It is chemically inert, highly insoluble and thermally stable. The performance of two arrays are compared out of which 4*1 array is found to be better in terms of gain and return loss.

Sorting of fruit into different grade is essential to fetch high price in the market. The fruits are graded based on height, size, area and weight. Each and every fruit changes the skin’s color in their life span. Hence, it is appropriate to grade them by processing color images of them and then applying estimation or recognition techniques on those images. Citrus (plant) grows even in temperature lands and it does not penetrate its root too deep. It is a precious commodity and used for various day to day activities. In this paper, Machine vision technique is used to sort citrus based on variety and quality. Primarily, the image is captured by a camera, placed at a particular distance. Then captured citrus image is classified into different categories, based on their color, size and quality. During the processing, the attributes are determined based on their defects in the surface of the citrus. Finally, the quality and breed are determined based on the three-color planes of color image and gray scale image respectively.

A rectangular antenna, to work in the operating frequency of L band is designed with capacitive disc fed for GPS application. The antenna gain aimed to have 2dBi. The capacitive disc is utilized for the increment of impedance bandwidth. It is designed using CADFEKO 7.0 and obtained the output with improved bandwidth and good return loss. Moreover, much improved reflection coefficient of the proposed antenna is obtained and it has been analyzed. With reference to simulation results, reflection coefficient at 1.13 GHz is attained as -34.18 dB with bandwidth of 140 MHz and at 1.34 GHz is -26.13 dB with the bandwidth of 230 MHz.