Medical image analysis is essential in healthcare, guiding diagnosis, treatment, and monitoring. This study presents AACNet (Advanced Attention Capsule Network), a deep learning framework addressing the complexity of diverse medical images. AACNet incorporates a multi-feature extractor with SPP layer, multi-level capsule network, and dynamic channel attention modules. Trained on curated datasets, including chest X-rays and CT scans, augmented for enhanced generalization, AACNet achieves 92.43% accuracy on X-rays and 94.64% on CT scans, surpassing other models in multiple metrics. The model's interpretability, utilizing dynamic channel attention, underscores its capacity to emphasize crucial spatial features. The innovative integration of dynamic channel attention and capsule networks makes AACNet a pivotal solution for medical image analysis. The research findings underscore the model's adaptability, effectiveness, and interpretability. AACNet emerges as a pivotal solution for medical image analysis, exhibiting consistent superior performance and potential for real-world clinical applications.

Mobile ad hoc networks (MANETs) suffer from a major problem with the energy drainage of network nodes, as the mobile nodes rely on batteries and do not have a permanent power supply. Therefore, a new multipath routing technique, using a novel hybrid heuristic algorithm, is designed to solve the diverse metrics of a multi-objective function, including energy consumption, distance, routing overhead ratio, throughput, end-to-end delay and packet delivery ratio. This approach implements a new hybrid algorithm termed the modified aquila-firefly heuristic strategy (MA-FHS), which integrates the aquila optimizer and the firefly algorithm. This derived fitness function is applied to achieve optimal paths in multipath routing with minimization of the multi-objective function. The simulation demonstrates that the developed routing protocols outperformed traditional protocols under several network constraints.

Cloud storage technology is gaining increasing attention as a new network storage technology that extends the fog computing concept. Fog computing plays an important role in today's business world as computing resources are provided on demand via the Internet as a service to users. One of Fog Computing's increasingly well-liked services is cloud storage. The primary advantages of cloud storage for consumers are lower costs associated with owning and maintaining storage infrastructure, the freedom to scale up or down storage capacity, and only paying for the actual amount of storage used. One major issue with cloud storage systems is the exponential expansion of digital data. problem, as a lot of duplicate data in the storage system imposes additional load. Different applications generate and store large amounts of data, which creates problems regarding data storage and data access time. To solve the above problems, the proposed dynamic reduction of duplicate data (DRDD) saves storage space, reduces the amount of data transmission bandwidth, and provides better communication. Therefore, data deduplication technology is used to increase the cloud storage system's storage efficiency. Owing to the dynamic nature of cloud storage data, cloud data utilization is subject to alteration over time, with some data blocks potentially seeing frequent readings. To preserve redundancy for fault tolerance and increase storage efficiency, we suggest a dynamic data deduplication system. Experimental results show that using the Edge Pass algorithm to encrypt image passwords requires less internal storage space than existing password encryption technologies.

Social media sites are a popular medium for interaction in the modern, expanding globe, where everyone has a connection with social media in some way. The people are accustomed to reading reviews before making decisions, for instance reading comments for movies, eateries, online stores, and a variety of other products. Taking reviews entails being aware of what other people think. It can be described in one way as sentiment analysis or even as opinion mining. For correctly predicting sentiments from social corpus data, the turbulent flow optimized deep fused ensemble model is a novel and sophisticated approach for sentiment analysis. The preprocessed data were used to extract a variety of features, including bag of words, term frequency-inverse term frequency, word to vector, and Glove. Then, the contemporary turbulent flow of water-based optimization mechanism was used to select the features that would be most useful for training the classifier. In addition, the cutting-edge deep fused ensemble voting classifier is employed to construct a precise decision function in accordance with the average probability of the number of classifiers. This work uses the well-known benchmarking social corpus datasets from IMDB, Twitter, Airlines, Amazon, Crowded Flower, and Apple for system analysis and study.

Computer-aided diagnosis has emerged as one of the main areas of study for radiology diagnosis and medical imaging in recent years. Also, developing a single prediction methodology for handling multiple types of medical images is remains one of the most significant issues in recent times. For handling various kinds of medical images, this research presents Smart Multimodal Disease Detection (SMD2), an innovative and powerful automated method. The proposed framework’s contribution is the ability to use various kinds of medical images to carry out an accurate and efficient disease diagnosis. The Woodpecker Mating Optimization Algorithm (WpMO) approach is used to optimally choose the most important features from the provided inputs, simplifying the classification process. In addition, the innovative Squeeze Excitation Capsule Network (SECNet) model is used to accurately identify and classify the disease class with a reduced computational time and complexity. A range of various medical imaging datasets, including X-ray, CT, and MRI, are considered for study in order to validate the performance outcomes of the proposed model. The results of the investigation indicate that the loss value of the proposed approach has dropped to 1.3, but its average accuracy has grown by 99

In response to growing security concerns and the increasing demand for face recognition (FR) technology in various sectors, this research explores the application of deep learning techniques, specifically pre-trained Convolutional Neural Network (CNN) models, in the field of FR. The study leverages five pre-trained CNN models, including DenseNet201, ResNet152V2, MobileNetV2, SeResNeXt, and Xception, for feature extraction, followed by SoftMax classification. A novel weighted average ensemble model, optimized through a grid search technique, is introduced to enhance feature extraction and classification performance. Robust data pre-processing, encompassing resizing, data augmentation, splitting, and normalization, is emphasized to ensure reliable FR systems. The research systematically investigates hyperparameters across deep learning models, fine-tuning network depth, learning rate, activation functions, and optimization methods. Comprehensive evaluations are conducted on diverse datasets, including ORL, GTAV, GTF, FEI, LFW, F_LFW, and YTF, to assess the effectiveness of the proposed models. Key contributions of this work include the utilization of pre-trained CNN models for feature extraction, extensive evaluation across multiple datasets, the introduction of a weighted average ensemble model, emphasis on robust data pre-processing, systematic hyperparameter tuning, and the use of comprehensive evaluation metrics. The results showcase the superior performance of the proposed method, consistently outperforming all other models across key metrics, including Recall, Precision, F1 Score, Matthews Correlation Coefficient (MCC), and Accuracy. Receiver Operator Characteristic (ROC) curves further highlight the models' classification abilities. Notably, the proposed method achieves an exceptional accuracy of 99.48% on the LFW dataset, surpassing state-of-the-art benchmarks. In conclusion, this research presents a significant advancement in FR technology, offering a reliable and accurate solution supported by empirical evidence. The proposed method demonstrates the potential of pre-trained CNN models, ensemble learning, robust data pre-processing, and hyperparameter tuning in enhancing the accuracy and reliability of FR systems, with implications for various real-world applications.

Tasks related to vision based action recognition are different human activities from the whole movements of those actions. It also helps predict how that individual will behave in the future by drawing conclusions from their present behaviour. It was a subject in past years since it tackles real-world problems including visual surveillance, driverless automobiles, entertainment, etc. A great deal of research has been done in this domain to develop an efficient human action recognizer. It is also expected that more work will be required. Thus, there are a plethora of applications for human action detection, such as video surveillance and patient monitoring. The Convolutional Neural Network (CNN) models are published in this piece. The results demonstrate strategy which outperforms the conventional two-stream CNN technique by at least 8% in terms of accuracy. Robots with wearable exoskeletons are becoming a promising technology to assist human movements in many activities. Real-time activity detection offers helpful data to improve the robot's control support for routine operations. With the help of two rotary encoders included into the exoskeleton robot and the activity signals from an inertial measurement unit (IMU), a real-time activity detection system is implemented in this study. For the purpose of recognizing activities, five deep learning models in real-time and assessed. Consequently, an edge device was used to assess a subset of refined deep learning models in real-time while using eight typical human actions, which include standing, bending, crouching, walking, sit-down, sit-up, and climbing and descending stairs. With the chosen edge device, these eight robot wearers' behaviours are identified in real-time testing with an average accuracy of 97.35%, an inference time of less than 10ms, and an overall latency of. 506 s per recognition

"Mobile Ad Hoc Network (MANET)" is a self-configurable, self-repairing, self-maintaining, highly mobile, decentralized, and independent wireless network, which has the liberty to move from one to another place. Such networks do not have any pre-existing infrastructure. The adoption of a smart environment in MANET requires new protocols to connect the gadgets to the internet. A smart environment with routing protocols should assure the following properties like connectivity among the nodes, "Quality of Service (QoS)", and fairness, both in access points and ad-hoc networks. Combination with the Internet of Things (IoT) and MANET generates a novel MANET-IoT system, which focuses on reducing the implementing costs of the network and providing better mobility for users. The necessity of these integrated networks is increasing in military operations, rescue operations, personal area networks, emergency rooms, and meeting rooms. Routing in MANETs is a not simple job and has projected a huge range of attention from researchers around the world. Thus, the intention of this task is a development of a security protocol in MANET for the IoT platform. For dealing with encryption and decryption strategies to handle MANET and IoT data, a new approach is suggested through the enhanced chaotic map. Here, three improved algorithms are implemented for proposing the optimized key management scheme under a chaotic map, which is the Modified Updating-based Harris Hawks Optimization Algorithm (MU-HHO), Mean Solution-based Averaging Sailfish Optimizer (MS-ASFO), Adaptive Basic Reproduction Rate-based Coronavirus Herd Immunity Optimizer (ABRR-CHIO). In the convergence evaluation, while taking the length of plain text as 40, ABRR-CHIO shows superior performance over other techniques at the 60th iteration, which is 96%, 95%, 93%, 96%, and 80% superior to HHO, SFO, CHIO, SA-SFO, and CHHSO. Finally, the performance evaluation is performed regarding "statistical analysis, convergence analysis, and communication overhead" to reveal the superiority of the designed model.

The growth of internet become more development in communication medium to provide various services. Information sharing ad security is mostly suffered by crime attackers because of different models of cyber-attacks are carried out by attackers. Attackers creates jamming principles, communication delays, packet dropping, and information hacking, duplicate injection to do so many activities to destroy the security. Based on the communication data analysis and features are non-identified and difficult to find the malicious activities. So the development of cyber security needs advancement to find the attackers based on the communication breaking activities. To resolve this problem, we propose a Spectral entity feature selection based Cyber Crypto Proof Security Protocol (C2PSP) to improve the cyber security. The Defect Scaling Rate (DSR) is used to estimate the communication defect rate. By marginalize the scaling rate using Spectral entity feature selection approach (SEFSA) is applied to select the features and trained to identify with Artificial neural network classifier (ANN). Based on the attack principles and activities in communication medium, the Cyber Crypto Proof Security Protocol (C2PSP) is applied to ensure the security verification and validation to process the data safer and securely. The proposed system produce high performance compared to other system as well to identify the malicious activities to improve the security against the cyber-attacks

Low cost, low form factor and highly energy efficient VLSI design is the key for the success of internet of things (IoT) paradigm. Approximate computing is one of the major techniques used to achieve high performance and energy efficiency in error resistant computationally intense applications. Low power VLSI design is one of the important factors in the designing of new IoT system or reconstructing the existed IoT system. An inexact reverse carry select adder (IRCSLA) with back carry propagation is presented in this work. Three different types of adder implementations were presented in IRCSLA. The method of back carry propagation is applied to the design both 16-bit ripple carry adder (RCA) & 16-bit carry select adders. These adders were designed in CADENCE schematic tool and simulations were done in Analog Design Environment with 45 nm CMOS technology. The design parameters such as delay and power of the three IRCSLA designs were compared with the existed back carry propagate full adders. IRCSLA-III gives 34.84% reduction in power and 56.91% improvement in delay compared to conventional CSLA adder and also improves the energy at the rate of 86.77% and 71.92% compared to the conventional RCA and a CSLA adder respectively.

WSN (Wireless Sensor Network) is gradually evolving into the most prevalent technology adopted in business and industrial sectors as a result of major developments in processing, communication, and low-power consumption of embedded computer devices. WSNs are quickly evolving into a cutting-edge technology that may be used in a variety of contexts. In wireless sensor networks, the most critical difficulty is often seen as being the use of energy. Researchers have investigated a variety of approaches in order to find a solution to this significant challenge posed by wireless sensor networks. One of these approaches, a routing strategy that is founded on clustering, has been shown to be useful in research studies and is currently regarded as one of the finest solutions to resolve the challenge of excessive energy expenditure. The intention of this study was to find a way to reduce the amount of energy that was used while maintaining acceptable levels of performance. At the beginning, the algorithm will separate the network into individual cells or clusters. The genetic algorithm was then brought into the picture, and it was utilised to determine the optimal number of nodes that should be present in a network. Following the placement of the nodes in the surroundings, the chromosomal length is adjusted to be equal to the quantity of nodes in order to facilitate the process of gradual convergence. As a consequence of this, the length of the chromosomes is reduced, and we are able to reach convergence on the optimal solution more quickly. The cluster heads found inside each chromosome, on the other extreme, are passed to the K-Means method as starting points in order to facilitate a rapid clustering process.

In recent years, computer networks have grown significantly in size and complexity, and Intrusion Detection Systems (IDS) have become an integral part of the system foundation. An IDS must overcome obstacles such as a low detection rate and a high computational load. Insufficient feature selection in IDS can have a negative impact on the accuracy of machine learning methods, resulting in errors in the form of False Negatives (FN) and False Positives (FP), which must be minimised. The research presents an effective feature selection and classification technique for intrusion detection by combining the Hybrid Grey Wolf optimizer Cuckoo Search Optimization (HGWCSO) with the Enhanced Transductive Support Vector Machine (ETSVM). The proposed strategies are capable of selecting the top eight features from a total of 41 features without sacrificing precision or recall. The experimental results reveal that the proposed system outperforms the current system in terms of accuracy, precision, recall, and F-measure.

The practise of recognising unauthorised abnormal actions on computer systems is referred to as intrusion detection. The primary goal of an Intrusion Detection System (IDS) is to identify user behaviours as normal or abnormal based on the data they communicate. Firewalls, data encryption, and authentication techniques were all employed in traditional security systems. Current intrusion scenarios, on the other hand, are very complex and capable of readily breaching the security measures provided by previous protection systems. However, current intrusion scenarios are highly sophisticated and are capable of easily breaking the security mechanisms imposed by the traditional protection systems. Detecting intrusions is a challenging aspect especially in networked environments, as the system designed for such a scenario should be able to handle the huge volume and velocity associated with the domain. This research presents three models, APID (Adaptive Parallelized Intrusion Detection), HBM (Heterogeneous Bagging Model) and MLDN (Multi Layered Deep learning Network) that can be used for fast and efficient detection of intrusions in networked environments. The deep learning model has been constructed using the Keras library. The training data is preprocessed and segregated to fit the processing architecture of neural networks. The network is constructed with multiple layers and the other required parameters for the network are set in accordance with the input data. The trained model is validated using the validation data that has been specifically segregated for this purpose.

The broad increase make use of digital cameras, by hand wound imaging has turn out to be common practice in experimental place. There is in malice of still a condition for a reasonable device for accurate wound curing consideration between dimensional facility and tissue categorization in a exacting simple to exploit technique We achieved the major unit of this plan by computing a 3-D model for wound dimensions using un calibrated revelation techniques. We highlight at this point on tissue classification from color and eminence region descriptors computed after unverified segmentation. As a result of perception distortions, unconstrained lighting provisions and viewpoints, wound assessments modify commonly in the middle of patient review. The majority significant separation of this article is to overcome this trouble by means of a multi inspection approach for tissue classification, relying on a 3-D model onto which tissue labels are mapped and categorization result merged. The investigational categorization tests communicate that improved repeatability and robustness are obtained and that metric assessment is attain through appropriate region and degree dimensions and wound chart origin. In this manuscript we proposed wound image segmentation, tissue classification in grouping with the Random Forest (RF). These methodology are helpful for classifying the rate of injured tissue in a segmented element and improved accuracy.

Mobile Ad-Hoc Network (MANET) is a structure less and emerging technology in recent years. Generally, this structure forms a network with nodes with inherent characteristics, including resource heterogeneity, node reliability, etc. In this manuscript, we proposed a Multi-Agent-Based Zone Routing (MAZR) protocol for enhancing the performance of MANET. Our proposed MAZR is works based on the principle of packet forwarding through intermediate and zone leaders. It consists of multiple agents, which include static and dynamic mobile agents. The proposed implementation is done as follows: Initially discovering the zone leader’s .The discovered zone leaders are connected to the communication nodes. The communication nodes and zone leaders are associated for building the network backbones for achieving multicast routing .To the multicast, zone members are connected .The zone managements, backbone and highly mobile nodes are initiated. The proposed MAZR protocol comprises five types of agents: Path agent, Network control agent, Multicast control agent, Network launch agent, and Multicast control agents. The Path agent, Network control agent, and Multicast control agent are static, and Network launch agents and Multicast control agents are mobile. The future protocol's performance is determined using the experimental work based on the evaluation metrics like delay, power consumption, and network lifetime. The obtained results prove the future MAZR is far improved than the Zone-based Hierarchical Link Protocol and Zone Routing Protocol in all aspects and ensures flexibility with versatile multicast service.

Developing an automated brain tumor diagnosis system is a highly challenging task in current days, due to the complex structure of nervous system. The Magnetic Resonance Imaging (MRIs) are extensively used by the medical experts for earlier disease identification and diagnosis. In the conventional works, the different types of medical image processing techniques are developed for designing an automated tumor detection system. Still, it remains with the problems of reduced learning rate, complexity in mathematical operations, and high time consumption for training. Therefore, the proposed work intends to implement a novel segmentation-based classification system for developing an automated brain tumor detection system. In this framework, a Convoluted Gaussian Filtering (CGF) technique is used for normalizing the medical images by eliminating the noise artifacts. Then, the Sparse Space Segmentation (S3) algorithm is implemented for segmenting the pre-processed image into the non-overlapping regions. Moreover, the multi-feature extraction model is used for extracting the contrast, correlation, mean, and entropy features from the segmented portions. The Deep Recurrent Long-Short Term Memory (DRLSTM) technique is utilized for predicting the classified label as normal of disease affected. During results analysis, the performance of the proposed system is tested and compared by using various evaluation measures.

Abstract : The main aim of Engineering education is to impart intellectual development and promote technical skills to engineering students. Teaching methodology plays a major role in the teachinglearning process. The basic goal of engineering students is to nurture knowledge in the relevant areas. Engineering education is technology-oriented; the learners should apply his/her knowledge to a specific application. To develop their technical skills, the students should identify suitable learning styles for their potentialities. The proper teaching methodology is a key point to success in engineering education. The industry expects the students to be high-quality engineers and industry-ready after completing their courses. Due to lagging in technical training and syllabus provided by the university doesn't match with the real- time industry projects. To achieve these outcomes technical-based activity needs to be enhanced in engineering education. In this paper, we proposed a Tool Based Technical Activity (TBTA) teaching method that converges traditional teaching methods which improve the student's attention in learning. Students' feedback with TBTA improves students' learning, communication, technical skills, and knowledge. Ke ywo r d s : Kn owl e d g e , P r e s e n t a t i o n , Communication, Technical, Teaching-learning, Feedback

This Because of significant advancements in processor, communication, and low-power utilization of embedded computer devices, WSN (Wireless Sensor Network) is quickly becoming the most common technology used in commercial and industrial applications. WSNs are becoming an advanced technology applied in various fields. In Wireless sensor networks, the usage of energy is seen as the most significant challenge. In this work, a new method based on a genetic algorithm was developed to reduce energy use. Initially, the algorithm separates the network into clusters or individual cells. The evolutionary algorithm was then applied to the problem of determining the optimal size of a network in terms of its number of nodes. Once the nodes are distributed around the environment, the chromosomal length is adjusted to be equal to the total number of nodes to allow for gradual convergence. This shortens the chromosomes and helps us locate the optimal option more quickly. Meanwhile, the K-Means algorithm is given the cluster heads from each chromosome as input, facilitating a rapid iteration of the clustering process. Results from an implementation of the proposed method in the NS2 simulator demonstrate that it improves upon prior algorithms in terms of both network longevity and throughput.

Mobile Ad-hoc network is decentralized and composed of various individual devices for communicating with each other. Its distributed nature and infrastructure deficiency are the way for various attacks in the network. On implementing Intrusion detection systems (IDS) in ad-hoc node securities were enhanced by means of auditing and monitoring process. This system is composed with clustering protocols which are highly effective in finding the intrusions with minimal computation cost on power and overhead. The existing protocols were linked with the routes, which are not prominent in detecting intrusions. The poor route structure and route renewal affect the cluster hardly. By which the cluster are unstable and results in maximization processing along with network traffics. Generally, the ad hoc networks are structured with battery and rely on power limitation. It needs an active monitoring node for detecting and responding quickly against the intrusions. It can be attained only if the clusters are strong with extensive sustaining capability. Whenever the cluster changes the routes also change and the prominent processing of achieving intrusion detection will not be possible. This raises the need of enhanced clustering algorithm which solved these drawbacks and ensures the network securities in all manner. We proposed CBIDP (cluster based Intrusion detection planning) an effective clustering algorithm which is ahead of the existing routing protocol. It is persistently irrespective of routes which monitor the intrusion perfectly. This simplified clustering methodology achieves high detecting rates on intrusion with low processing as well as memory overhead. As it is irrespective of the routes, it also overcomes the other drawbacks like traffics, connections and node mobility on the network. The individual nodes in the network are not operative on finding the intrusion or malicious node, it can be achieved by collaborating the clustering with the system.

The transmission line is the most vulnerable element of any electrical power system due to its large physical dimension.This paper focused on identification of simple power system fault using wavelet based analysis of transmission line parameter disturbances for quick and reliable operation of protection schemes.The fault detection is disbursed by the assay of the detail coefficients activity of appearance currents.Discrete Wavelet Transform (DWT) examination of the transient aggravation created as an aftereffect of event shortcomings is performed.The result shows that the proposed method detects the fault very quickly and accurately.Simulation results are presented showing the selection of proper threshold value for fault detection.An embedded intelligence is inserted into the power-electronics to facilitate the reconfiguration of the system, and thereby ensuring security.