Since the open nature of Internet of Things (IoT), it is more vulnerable for various attacks that degrades the network topologies and functionalities. Rather than other attacks, Rank Attack (RA) becomes the most dangerous attack mainly affecting the rank values of routing process. Thus, it reaches more attention in “Routing Protocol for Low Power and Lossy Networks (RPL)” as well. Hence, the trust-based secured IoT network is a quite challenging process. The former methods are limited with overhead problem, more energy consumption and RA, which is a basic security attack on routing in IoT networks. In order to tackle and to detect the attack, the secured IoT routing against rank attacks framework is developed. Initially, the data is aggregated from benchmark datasets. Further, the aggregated data is given to the Multiscale Depth wise Separable One-Dimensional Convolutional Neural Network (MDS-1DCNN) model for rank attack detection. In addition to that, the nodes are mitigated while the routing process takes place. To validate the efficiency of the given network model during routing, the Golden Eagle Optimizer (GEO) is utilized to derive the objective function using the constraints such as shortest distance, energy, path loss and delay. Finally, the performance is validated using diverse parameters and compared against classical methodologies. Thus, the results illustrate that the proposed model has effectively detected the RA that facilitates the secured IoT routing against other models.

The Internet of Things (IoT) is the intelligent framework that connects smart objects through the Internet. The IoT framework is vulnerable to various attacks because the Internet is unsafe and untrustworthy. The IoT cyber attacks can create significant physical and economic changes that affect the supply chains, manufacturing processes, production lines, impact the vehicle’s physical safety, and affect people’s health. Numerous systems are being connected to the Internet, and the data from the IoT systems is employed in the decision-making process in complex environments such as the military, healthcare, and so on. Hence, it becomes highly significant to safeguard the IoT platform. Traditional authentication and encryption approaches often fail in the IoT-aided framework, and an intrusion may cause damage to the framework. Hence, it is significant to model an Intrusion Detection System (IDS) for a specific network. In this work, a new attack detection, mitigation, and routing system on IoT is suggested for recognizing different kinds of attacks on IoT. At first, the attack detection is carried out by a designed Serial Cascaded and Attention-based Hybrid Convolution Network (SCA-HCN), which is formed by integrating a convolutional autoencoder with Temporal Convolutional Networks (TCN). Especially, in the IoT attack detection model, the proposed SCA-HCN model primarily provides significant advancement in improving the model’s accuracy, efficiency and scalability. Moreover, the integration of cascaded mechanism excels in identifying and understanding the context of attack over time. Further, the attack mitigation and routing tasks are performed by the Enhanced Dung Beetle Optimizer (EDBO). Enabling the EDBO optimization algorithm helps in providing more efficient and stable solutions, which helps in managing the IoT network traffic more effectively. During the routing process, some of the objective functions, including the shortest path, energy, delay, path loss, and Packet Delivery Ratio (PDR), are derived. The simulation outcomes are performed for the implemented framework over existing deep learning approaches and algorithms to analyze the ability of a designed model. From the results, the developed SCA-HCN-EDBO model achieves high performance rates in terms of 97.18% accuracy, 2.91% FPR, 2.5% FNR and 99.1% NPV, respectively. Hence, it is guaranteed that the introduced new attack detection, mitigation, and routing framework achieve superior and promising results.

Single-model vision pipelines are also lacking, and it means that traditional automated attendance systems cannot reliably operate in unconstrained environments. The proposed paper presents a new deep model fusion architecture, a two-stage design, to create an extremely robust and accurate face recognition system that can be used in managing real-time attendance. We propose a two-specialized hybridization approach consisting of building two hybrids: 1) a Detection Fusion Model that is based on YOLOv8 in conjunction with RetinaFace through Weighted Box Fusion (WBF) to attain higher spatial resolution (estimated WIDER FACE mAP of 96.5) and constant thinking speed (estimated 35.2 FPS), decreasing false alarms and enhancing small face recognition; and 2) a Recognition Fusion Model, which relies on the synergies between ArcFace (angular margin This combination approach creates a maximum margin between matching and non-matching identities (maximum of 0.787), which produces a high verification reliability. Using a combination of these customized fused models, the resulting system can successfully deal with multi-person recognition in group photographs, confirming an entirely correct and lowlatency solution to overcome the major drawbacks of singlemodel face recognition strategies of that time and establishing a new record of automation rates of attendance.

The memory and cognitive abilities of older people are significantly impacted by Alzheimer's disease. Early and accurate identification is critical to improving patient care and enabling timely intervention. Electroencephalogram (EEG) signals are the most effective method of identification. Alzheimer's disease has been identified using a variety of machine learning and deep learning techniques. These algorithms, including Decision Tree, Random Forest, Support Vector Machine, Convolutional Neural Networks, Deep Belief Networks, ResNet50, and Light Gradient Boosting Machine (LightGBM) models, have been thoroughly examined by us. Experimental results show that LightGBM outperforms the other models in terms of classification accuracy. These findings suggest that LightGBM offers an effective, non-invasive framework for real-time Alzheimer's disease detection.

Deep face recognition has achieved near-saturated performance on several controlled benchmarks, yet its robustness in unconstrained real-world scenarios remains a critical challenge. This paper presents a comparative analysis of three backbone architectures,a classification-based SE-ResNet-50 and two metric-learning-based models, IR-ResNet-50 and IR-SE-ResNet-50 trained with ArcFace loss on the large-scale VGGFace2 dataset and evaluated on the challenging IJB-C verification benchmark. All models are trained from scratch on a 4,605-identity subset of VGGFace2, achieving strong in-domain performance with validation accuracies in the 94-96% range and verification AUC of approximately 0.955 on VGGFace2 validation pairs. However, when evaluated on the IJB-C 1:1 verification protocol, the same models exhibit a dramatic drop in performance. IR-ResNet-50 with ArcFace achieves only 1.10% true accept rate (TAR) at false accept rate (FAR) 10-3 and 0.36% at FAR 10-4. IR-SE-ResNet-50 with alignment and MTCNN-based cropping marginally improves TAR to 1.75% at FAR 10-3 and 0.57% at FAR 10-4, while SE-ResNet-50 trained with softmax classification surprisingly performs best among the three, reaching 28.02% TAR at FAR 10-3 and 11.99% at FAR 10-4. These results highlight a severe generalization gap between curated training data and unconstrained benchmarks and suggest that strong margin-based losses alone are insufficient to guarantee cross-domain robustness. We further analyze failure modes related to pose, alignment mismatch, and template noise, and motivate a Pose-Aware Feature Rectification Network (PAFR-Net) as a future direction to improve pose robustness by learning pose-conditioned residual corrections in feature space.

Optical character recognition (OCR) is a process that recognizes and converts data from scanned images, including both handwritten and printed documents, into an accessible format. The challenges in Telugu OCR arise from compound characters, an extensive character set, limited datasets, character similarities, and difficulties in segmenting overlapping characters. To tackle these segmentation complexities, an algorithm has been developed, prioritizing the preservation of essential features during character segmentation. For distinguishing between structurally similar characters, we used convolutional neural networks (CNN) due to their feature-extracting properties. We have employed the CNN model, the SqueezeNet for feature extraction, resulting in an impressive character recognition rate of 94% and a word recognition rate of 80%.

A secured IoT routing model against different attacks has been implemented to detect attacks like replay attacks, version attacks, and rank attacks. These attacks cause certain issues like energy depletion, minimized packet delivery, and loop creation. By mitigating these issues, an advanced attack detection approach for secured IoT routing techniques with a deep structured scheme is promoted to attain an efficient attack detection rate over the routing network. In the starting stage, the aggregation of data is done with the help of IoT networks. Then, the selected weighted features are subjected to the Multiscale Depthwise Separable 1-Dimensional Convolutional Neural Networks (MDS-1DCNN) approach for attack detection, in which the parameters in the 1-DCNN are tuned with the aid of Fused Grasshopper-aided Lemur Optimization Algorithm (FG-LOA). The parameter optimization of the FG-LOA algorithm is used to enlarge the efficacy of the approach. Especially, the MDS-1DCNN model is used to detect different attacks in the detection phase. The attack nodes are mitigated during the routing process using the developed FG-LOA by formulating the fitness function based on certain variables such as shortest distance, energy, path loss and delay, and so on in the routing process. Finally, the performances are examined through the comparison with different traditional methods. From the validation of outcomes, the accuracy value of the developed attack detection model is 96.87%, which seems to be better than other comparative techniques. Also, the delay analysis of the routing model based on FG-LOA is 17.3%, 12.24%, 10.41%, and 15.68% more efficient than the classical techniques like DHOA, HBA, GOA, and LOA, respectively. Hence, the effectualness of the offered approach is more enriched than the baseline approaches and also it has mitigated diverse attacks using secured IoT routing and different attack models.

Nowadays, heart diseases have become a leading cause of mortality worldwide and it affects a huge number of individuals. The early and accurate prediction of heart disease risk factors plays a crucial role in preventing opposing results. Additionally, it is necessary to recognize heart disease quickly and accurately by analyzing patient’s data. This paper proposed a novel approach for predicting heart disease through machine learning techniques. The proposed Bat Algorithm (BA) and Particle Swarm Optimization (PSO) based Random Forest (RF), named BAPSO-RF is utilized for selecting optimum features that can enhance the heart-disease prediction accuracy. The proposed BAPSO-RF is evaluated on UCI heart disease dataset which contains 14 attributes and 270 records. The proposed BAPSO-RF model attains better results by utilizing metrics like accuracy, precision, recall, and f1-score values of about 98.71%, 98.67%, 98.23%, and 98.45% correspondingly which ensures early and accurate prediction of heart disease compared to existing techniques like hybrid of Genetic Algorithm and Particle Swarm Optimization (PSO) with Random Forest (GAPSO-RF), stacked Genetic Algorithm (GA) and Genetic Algorithm with Radial Basis Function (GA-RBF).

Organizations with field employees face the challenge of maintaining high-quality standards while optimizing costs. Analyzing, Classifying, Predicting, and Monitoring the Field Employee's Regular Activities, Work Productivity and Performance is the challenging objective for Management in any Organization. Research study suggests using Android Application and machine learning predictive analytic model by using decision tree algorithm to analyze and classify field employee work productivity and performance. This aims to achieve a higher accuracy rate and better insights into employee performance. To track field employees, a GPS tracking app is used on mobile devices. As part of Mobile Computing implementation, Android Mobile device transfers the data in the form of text, voice and images to the web server and vice-versa. It generates location data with secured communication through cryptography techniques and stores captured data in a database server for further analysis. Furthermore, a web-based application is proposed for monitoring and generating reports for individuals and groups of field employees, including route maps and time sheets. This proposed solution is going to be a complete one-point automated software solution for any business organization for managing their field employees.

Optical character recognition (OCR) technology is indispensable for converting and analyzing text from various sources into a format that is editable and searchable. Telugu handwriting presents notable challenges due to the resemblance of characters, the extensive character set, and the need to segment overlapping characters. To segment the overlapping characters, we assess the width of small characters within a word and segment the overlapping characters accordingly. This method is well suited for the segmentation of overlapping compound characters. To address the recognition of similar characters with less training periods we have used ResNet 18 and SqueezeNet models which have achieved character recognition rates of 95% and 94% respectively.