Hitkarini College of Engineering and Technology

Because of the heavy data and communication advances, the utilization of Internet of Things (IoT) gadgets has expanded dramatically. In the improvement of IoT, Wireless Sensor Network (WSN) plays out a crucial part and involves easy keen gadgets for data gathering. In any case, such savvy gadgets have requirements regarding calculation, preparing, memory, and energy assets. Alongside such requirements, the major difficulties for WSN are to accomplish dependability with the security of communicated information in a weak climate alongside pernicious nodes. This paper intends to build up an Anomalous Intrusion Detection Protocol and Intrusion Prevention Protocol for interruption evasion in IoT dependent on WSN to expand the network time frame and information reliability. The proposed framework makes dissimilar energy-efficient groups dependent on the natural characteristics of nodes. Also, in view of the (k, n) limit related Shamir mystery sharing plan, the unwavering quality also, the security of the tangible data within the Base Station and group head are accomplished. The proposed security conspires demonstrates a trivial answer to adapt to interruptions produced by malignant nodes. The trial results utilizing the network test system Network Simulator-2 show that the proposed directing convention accomplished improvement as far as network lifetime, end-to-end delay as 24%, packet delay ratio as 30%, when contrasted and the current work under unique network characteristics.

The cheap materials such as tea powder and sawdust were used as adsorbents. These Sawdust (SD) and tea powder waste (TP) have been used to remove phenol from synthetic aqueous solutions. After the H3PO4 chemical activation process, the removal percentage and adsorption capacity of Saw Dust Tea Powder (SDTP) adsorbent were calculated. After that, the adsorption isotherms of phenol on the adsorbents were evaluated and correlated with linear and non-linear forms of isotherm models such as Langmuir and the Freundlich models. Optimum conditions for phenol removal as well as the kinetics of that process, were established. From the results of adsorption isotherm models, the Langmuir model has the best fit with the highest correlation coefficient (R2 = 0.9672), which indicates that the adsorption of phenol occurred through adsorption. In the Pseudo-First-Order model, the rate constant k1 is 0.0475 with qe is 78.11 mg/g with and R2 of 0.9551 were obtained, whereas Pseudo-Second-Order offers a rate constant k2 of 2.85 × 10⁻⁴ g/mg min and qe of 83.64 mg/g with R2 of 0.8492. From the kinetic model results, the higher correlation coefficient implies that phenol adsorption follows the first-order kinetics, which is more surface diffusion with an accurate fit.

Early detection of cataract is crucial for thwarting visual impairment worldwide, and the utilization of automated cataract detection through medical images has shown increased growth for several years. The automated detection model comprises image processing, feature extraction and classification process to ensure accurate identification of infected cataract eye images. However, the recent detection model endures various challenges, including complex computing requirements, feature redundancy, inadequate precision, generalization and less data diversity. To overcome these challenges, a Chaotic Adaptive Poplar-Bacteria Optimization (Cha-PO) based Cataract VisionNet (CVNet) method is proposed to enhance diagnostic accuracy and operational efficiency. The Cha-PO model is specifically used for optimal feature selection of fundus images by reducing the dimension of the images, which ensures acute diagnostic data preservation. CVNet model used for classifying the cataract images by applying the deep hierarchical learning mechanisms alongside optimized network parameters to boost accuracy levels and operational reliability. The proposed approach is validated using the Eye Cataract Kaggle dataset, and it outperforms the traditional models with 99.10% accuracy, 99% precision, 99.21% recall and 99.10% of F1-Score. With a 99s execution time, it requires fewer computational resources than other baseline models, making it suitable for medical diagnosis.

Diabetic foot ulcers (DFUs) pose a significant complication of diabetes with the potential to lead to amputation if not effectively managed. Current DFU treatments require rigorous monitoring by both healthcare professionals and patients, which is challenging due to the high costs associated with diagnosis, treatment and long-term care. A major limitation of these approaches is their limited capacity to identify highly relevant pattern connections and broad contextual correlations resulting inaccuracies in classifying regions of interest. This research introduces an attention enhanced deep learning-based automated approach for assessing DFUs using images to expedite the investigation process and offer optimal recommendations. Adaptive thresholding is employed to enhance the contrast and uniformity of DFU images and thereby improves the feature extraction. A hybrid model incorporating coordinate attention enhanced ConvNeXt is used for effective DFU image classification to enhance the representation of complex patterns through efficient parameter utilization. The ConvNeXt architecture is designed to scale efficiently across various sizes by utilizing depthwise separable convolutions and improved image normalization. This model is augmented with coordinate attention, which captures spatial information in both horizontal and vertical directions, aiding in the extraction of long-range dependency features for more accurate classification of DFU images. Experimental results demonstrate that the model achieves an accuracy of 97.16% and F1-score of 0.97.

The optimal placement and sizing of distributed generation (DG) units and Static VAR Compensators (SVCs) are essential for enhancing the efficiency and reliability of radial distribution networks (RDN). Existing methods often rely on shunt capacitors, sensitivity-based techniques, which may not address the multi-objective challenges of minimizing power losses, reducing voltage deviations, and improving voltage stability. This paper proposes a Pareto front-based multi-objective chaotic particle swarm optimization with sigmoid-based acceleration coefficients (MO-CPSOS) for optimal placement and sizing of DGs and SVCs. The framework employs adaptive, real-time adjustment of cognitive and social parameters, promoting efficient exploration and faster convergence. Simulation results on IEEE 33-bus, 69-bus, and 119-bus test systems show that MO-CPSOS consistently achieves substantial reductions in power losses, improves voltage profiles, and enhances voltage stability compared to conventional approaches. The optimal solution involves three devices for the 33-bus and 69-bus networks, and six to seven for the 119-bus system, with diminishing returns beyond these points. MO-CPSOS demonstrates scalability and computational efficiency, making it suitable for modern RDNs. Future research may focus on incorporating dynamic load models and extending the approach to integrate economic, environmental, and operational factors for even broader applicability.