ABSTRACTWireless Sensor Networks (WSNs) are extensively used in event monitoring and tracking, particularly in scenarios that require minimal human intervention. However, a key challenge in WSNs is the short lifespan of sensor nodes (SN), as continuous sensing leads to rapid battery depletion. In high‐traffic areas, sensors located near the sink node exhaust their energy quickly, creating an energy‐hole issue. As a result, optimizing energy usage is a significant challenge for WSN‐assisted applications. To address this, this paper proposes an Energy‐aware Routing and Cluster Head Selection in Wireless Sensor Network through an Attentive Dual Residual Generative Adversarial Network for Golden Search Optimization Algorithm in Wireless Sensor Network (EAR‐WSN‐ADRGAN‐GSOA). This method involves selecting the Cluster Head (CH) using Attentive Dual Residual Generative Adversarial Network (ADRGAN), minimizing energy consumption, and reducing a number of dead sensor nodes. Subsequently, Golden Search Optimization Algorithm (GSOA) is employed to determine an optimal path for data transmission to the sink node, maximizing energy efficiency, and elongating sensor node lifespan. The proposed EAR‐WSN‐ADRGAN‐GSOA method is simulated in MATLAB. The performance metrics, such as network lifetime, number of alive nodes, number of dead nodes, throughput, energy consumption, and packet delivery ratio is examined. The proposed EAR‐WSN‐ADRGAN‐GSOA demonstrates improved performance, achieving a higher average throughput of 0.93 Mbps, and lower average energy consumption of 0.39 mJ compared with the existing methods. These improvements have significant real‐world implications for enhancing the efficiency and longevity of WSNs in applications, such as environmental monitoring, smart cities, and industrial automation.

Background noise often distorts the speech signals obtained in a real-world environment. This deterioration occurs in certain applications, like speech recognition, hearing aids. The aim of Speech enhancement (SE) is to suppress the unnecessary background noise in the obtained speech signal. The existing approaches for speech enhancement (SE) face more challenges like low Source-distortion ratio and memory requirements. In this manuscript, Recalling-Enhanced Recurrent Neural Network (R-ERNN) optimized with Chimp Optimization Algorithm based speech enhancement is proposed for hearing aids (R-ERNN-COA-SE-HA). Initially, the clean speech and noisy speech are amassed from MS-SNSD dataset. The input speech signals are encoded using vocoder analysis, and then the Sample RNN decode the bit stream into samples. The input speech signals are extracted using Ternary pattern and discrete wavelet transforms (TP-DWT) in the training phase. In the enhancement stage, R-ERNN forecasts the associated clean speech spectra from noisy speech spectra, then reconstructs a clean speech waveform. Chimp Optimization Algorithm (COA) is considered for optimizing the R-ERNN which enhances speech. The proposed method is implemented in MATLAB, and its efficiency is evaluated under some metrics. The R-ERNN-COA-SE-HA method provides 23.74%, 24.81%, and 19.33% higher PESQ compared with existing methods, such as RGRNN-SE-HA, PACDNN-SE-HA, ARN-SE-HA respectively.

In this manuscript, an Adaptive and Efficient Hybrid In-loop Filter based on Enhanced Generative Adversarial Network Deblocking Filter (EGANDF) with Sample Adaptive Offset filter (EGANDF-SAO-HEVC) is proposed for High Efficiency Video Coding (HEVC)/H-265. In this, the proposed hybrid in-loop filter involves EGANDF and Sample Adaptive Offset (SAO) filter that lessens the blocking artifacts caused by block-wise processing for coding unit (CU), which is mainly used for improving the video quality. Initially, EGANDF is proposed for HEVC/H-265 for removing blocking artifacts along low computation. Here, the output of EGANDF is given to the SAO filter for reducing ringing artifacts by diminishing high-frequency components during quantization. Thus, the proposed method efficiently reduces artifacts for improving video quality performance. The proposed EGANDF-SAO-HEVC method is implemented in the working platform of HEVC reference software with MATLAB. Finally, the proposed EGANDF-SAO-HEVC model has attained 27.26%, 29.65%, 12.45% higher accuracy, 33.56%, 31.8%, 28.7% higher sensitivity, 34.7%, 33.5%, 32.6% higher specificity, 46.92%, 35.7%, 41.3% lower MSE, 25.7%, 29.7%, 35.6% higher PSNR, and 25.6%, 28.9%, 13.6% higher SSIM for using basketball video sequence when compared to the existing methods.

Human face recognition research in biometric applications is a popular research subject because of its various applications and challenges, including camera type, pose, light or illumination, resolutions, wearing or not wearing glasses, and expressions, among others. This study presents a novel hybrid biometric software application for facial recognition considering uncontrollable environmental conditions. The proposed system uses two features namely, Laplace of Gaussian filter-based Discrete Wavelet Transform (LGDWT) and Discrete Cosine Transform Compressed based Log Gabor Filter (DCTLGF). The combined LGDWT and DCTLGF features were used by a Multiclass Support Vector Machine (MSVM) classifier to create the desired class label of individual faces. Our work was tested on a face dataset comprising 25 people of 200 face images which are taken using a five-megapixel low-goal web camera and yielded good results in different bounds in contrast to existing techniques.

Security has been always a major concern in wireless network irrespective of evolving safety protocols, which motivates various researchers to explore an effective security solution. Existing encryption-based solution offers security but at the cost of resources which are sometime highly limited in communication devices. Therefore, this paper discusses about trust evaluation that is one of the critical operations for ascertaining the degree of security strength offered by the sensor nodes in Wireless Sensor Network (WSN). Existing research work has been carried out to find a strong connection between the resource efficiency and the critical security approaches; however, these approaches are not proven for lightweight energy efficient security scheme. Therefore, the proposed system developed using analytical approach offers a secured communication scheme that evaluates the comprehensive trust value for the target relay node followed by reputation value from the neighboring node in order to perform an effective selection of legitimate relay node. The authentication process has been carried out using progressive key-generation process while the resource efficiency is maintained by developing multi-dimensional trust computation. The essential contribution of the proposed model is to offer an effective balance between resource efficiency and trust-reputation based security strengthening features. The outcome shows that proposed model offers 75% of retention of energy-efficient nodes with more predictable energy dissipation trend. It also offers 82% of reduction of energy fluctuation during the entire operation which is again found to be 35% faster than existing approaches. The simulated outcome of study exhibits that proposed system offers better data transmission performance with significant energy efficiency in comparison to existing scheme.

Nowadays, the online recommender systems based collaborative filtering methods are widely employed to model long term user preferences (LTUP). The deep learning methods, like recurrent neural networks (RNN) have the potential to model short-term user preferences (STUP). There is no dynamic integration of these two models in the existing recommender systems. Therefore, in this article, a multi-preference integrated algorithm (MPIA) for deep learning based recommender framework (DLRF) is proposed to perform the dynamic integration of these two models. Moreover, the MPIA addresses improper data and to improve the performance for creating recommendations. This algorithm is depending on an enhanced long short term memory (LSTM) with additional controllers to consider relative information. Here, experiments are carried out by Amazon benchmark datasets, then obtained outcomes are compared with other existing recommender systems. From the comparison, the experimental outcomes show that the proposed MPIA outperforms existing systems under performance metrics, like area under curve, F1-score. Consequently, the MPIA can be integrated with real time recommender systems.

Smart healthcare systems have become smarter compared to traditional systems due to the advancement of communication technologies such as 5G and with the wide range of Internet of Things (IoT) devices such as sensors with blockchain technologies, evolving to the current trend of Healthcare 4.0. It is decided that 75% of the company will start using the blockchain concept within 2022 and the IoT adaptors are planning to implement blockchain for around 90% based on the Gartner report. Healthcare systems, which are vital for any society, store information about the patients and their diagnoses. So, it is important to secure and maintain the privacy of patient information in smart healthcare. An amalgamation of 5G, IoT, and blockchain in a smart healthcare system provides the necessary security and privacy of the data generated. 5G provides a reliable high-performance communication network with high throughput and large network coverage for data transfer. IoT provides remote patient monitoring and real-time status for quick reactions while blockchain provides the security and privacy of the data. The framework of the smart healthcare system is discussed along with comparisons of various framework models. The layer-wise security issues and applications in IoT are also discussed. A case study is discussed to provide a wide range of information about the techniques and plan used to provide security and privacy along with a comparison of the various technologies used.

The proposed work carried out to convert the Kannada speech signal to a text document using Sphinx tools. The system is implemented for the large vocabulary of the Kannada speech signal by using the acoustic model (AM) and language model (LM) with the decoder. The AM extracted the Mel frequency cepstral coefficients (MFCC) of the speech signal successfully and trained these coefficients using hidden Markov model (HMM) and tweak the estimation of the AM using Baum-Welch method. The required language model (LM) format is built for the decoder using n-gram count. The decoder is configured to create a text file to the corresponding input speech signal using Sphinx3. The proposed automatic speech recognition (ASR) system achieves a better recognition rate with less word error rate (WER) with AM and LM adaptation using Sphinx3 for large vocabulary and Pocket Sphinx implemented on RasberryPi3 results better accuracy than the other ASR system.

Applications of Mobile Ad-Hoc Networks under Wireless Sensor Networks are drastically growing for various purposes in recent days. One of the major and important real-time applications is monitoring and predicting human and objects' abnormal activities. Children missing, older people participating, and unknown people involving in a family or private party should be monitored and identified to take care of all. Some of the applications like strange people, children, and old age people need to be watched to generate alert messages to save them. In this paper, motion sensors interconnected into concentric's IoT sensor network is considered as the background network and surveillance application is deployed. Then mobile nodes are deployed and connected to the network to receive the alert message to know the abnormal activity and its location. It helps to provide immediate prevention to save the people and avoid dangers. New IoT gateway products are launched with battery-powered sensors and wireless suites. All the motion sensors are connected with Node.js software development kit for broadcasting alerts whenever an abnormal activity happens. The experimental results are verified and evaluated through Twilio API, where it interconnects anyone from anywhere. The experimental results show that this kind of application is very much useful in real-time.

Face recognition is a significant biometric application in Image Processing. In the research zone, the Face recognition topic persistently continued due to the most significant challenge such that illumination effects. This may occur due to camera type, focus, resolutions, illumination directions, Face pose conditions, aging, expression type, and so forth. To improve the performance of Face Recognition System [FRS] different face detection, Illumination Pre-processing, feature extraction, classification techniques are needed to be utilized in a hybrid manner. This paper reviews various face recognition methods, and also their effective performance on different combinations.

In research work, human face recognition is an essential biometric symbol persistently continued so far due to its different levels of applications in society. Since the appearance of the human faces can have many variations due to issues like the effect of illumination, expression and face pose. These differences are correlated with one another, which results in a helpless ability to recognize a particular person's face. The motivation behind our work in this paper is to give a new framework for face recognition based on frequency analysis that contributes to solving the distinguishing proof issues with enormous varieties of boundaries like the effect of illumination, expression, and face pose. Here three algorithms combined for provable results: i) Difference of Gaussian filtered discrete wavelet transform (DDWT) for feature extraction; ii) Log Gabor (LG) filter for feature extraction; and iv) Multiclass support vector machine classifier, where feature coefficients of DDWT and LG filter are fused for classification and parameters evaluation. The evaluation of our experiment is carried out on a large database consisting of 15 persons of each 200-face image which are captured using a 5-megapixel low-resolution web camera and yielding satisfactory results on various parameters compared to existing methods.

The challenging task is protecting the data which are uploaded to the cloud becomes bigger worries in a cloud environment system. In this type of security is needed for monitoring of data access in a cloud environment and is getting more and more attention in recent days. Few strategies which can be afford for top-secret and an unknown authentication for delicate information and it is more efficient than doing the encrypting data first and then sign or doing the sign first then encrypting the data. However, in so many previous work, delicate information of data users can be reveal to authority, and only the authority is responsible to answer to that type of attribute management and generation of key in the system. The proposed system states that confidentiality and protective of data access control over the cipher text scheme based on cloud security. It is provide a control measure, attribute confidentiality and guard the data’s of user concurrently in a multiple authority cloud system. Both the attributes of designcryptor and signcryptor can be kept secret by not knowing to the authorities and cloud storage server. Besides, decryption in the clouds for users as becomes meaningfully reduced by outsourcing the unwanted bilinear pairing process to the cloud server without humiliating the attribute privacy. The planned scheme is confirmed for protecting the standard model and has the skill to provide top secret, unforged, unknown authentication, and verifiability of public. The security analysis which are relating to comparison of difficulty and results of execution will indicate that the proposed system has the capacity to balance the security issues with respect to computation in hypothetical efficiency.

Continuous speech segmentation and its recognition is playing important role in natural language processing. Continuous context based Kannada speech segmentation depends on context, grammer and semantics rules present in the kannada language. The significant feature extraction of kannada speech signal for recognition system is quite exciting for researchers. In this paper proposed method is divided into two parts. First part of the method is continuous kannada speech signal segmentation with respect to the context based is carried out by computing average short term energy and its spectral centroid coefficients of the speech signal present in the specified window. The segmented outputs are completely meaningful segmentation for different scenarios with less segmentation error. The second part of the method is speech recognition by extracting less number Mel frequency cepstral coefficients with less number of codebooks using vector quantization .In this recognition is completely based on threshold value.This threshold setting is a challenging task however the simple method is used to achieve better recognition rate.The experimental results shows more efficient and effective segmentation with high recognition rate for any continuous context based kannada speech signal with different accents for male and female than the existing methods and also used minimal feature dimensions for training data.

There is a big challenge in speech recognition system due to variability of the spoken languages and also speech signal is degraded due the environmental noise.Therefore speech recognition system requires pre-processing, which plays vital role to restore speech signal more effectively.Many challenges are there to restore the speech from different noisy environment.In this paper, proposed method is divided into two parts.First part is Kannada speech restoration, the modified wiener filter is proposed to restore the Kannada speech signal with very good speech quality.The experimental results are verified for different types of noise by varying input Signal to Noise Ratio (SNR) from -20dB to 5 decibels (dB).Second part is Autocorrelation based Kannada speech recognition system.Autocorrelation technique gives better output SNR for degraded input SNR with -20dB.The Autocorrelation is the simple method to recognize the isolated Kannada word in speech signal.This proposed technique results 100% recognition rate for male, female, with different accents.

The new technology of video compression standard - High Efficiency Video Coding has got more popularity as the world is going completely digital through video applications like Internet streaming, Digital video broadcasting, Video conferencing, Video surveillance, etc. So it is necessary to have very high video quality with reasonable complexity. This is achievable with In-Loop Filter of HEVC decoder containing two filters put one after the other, Deblocking Filter and Sample Adaptive Offset Filter. These filters together will build the visual and objective quality of the video. This paper helps in understanding the basics of the filters and summarizes the important methods, techniques proposed by various authors.

Speech is the main mode of communication between human beings and man-machine environment. Due to large use of mobile communication to long distance the speech in mobile communication plays a vital role. The mobile speech suffers from more number of noises due to surrounding environment and makes the person in conversation complex to hear. Hence there is a need for enhancing mobile speech for better understanding. In this paper various stationary noises like car noise, airport noise, exhibition noise, restaurant noise etc are analyzed with spectral subtraction and additive White Gaussian noise for the clean speech and noisy speech. The energy of the various samples are compared by calculating the energy of the speech content and compared. The noisy speech is filtered and analyzed for improving the quality, with speech data alone without the silent area.

In the recent development the Internet of Things (IoT) brings all electronics objects in to a single domain and it is easy to access everything through internet. The applications of IoT are Smart agriculture, Smart Home, Smart City, Smart health monitoring system etc. The automation of health care is one of the application which monitors the patient health status using IoT to make medical equipments more efficient by monitoring the patient's health, in which identifies the body conditions and reduces the human error. A health care monitoring system is used to monitor patient's body parameters for the particular disese and obtain the various values about it. The heart rate monitor is one of the in system using IoT to recognize the cardic patients condition and monitor the status in emergency situations. It monitors the heart rate of the patient with long term cardiovascular disease. Here the Arduino based microcontroller is used to communicate to the sensors such as pulse sensor and ECG Sensor. The system can analyze the signal, extract features from it, detect the normal or abnormal conditions with the help of Raspberry Pi and the results of the ECG signals is sent to the web server. It ensures the signal transmission of heart rate signal to the database through IoT. This also suggests doctors to care the patient follow-up their patient using the patient's data stored in the database. Thus IoT brings one of the solution for cardiac patient monitoring and also reduces the complexity between patient outcome and technology.

This paper represents a brief description about design of rectangular microstrip patch antenna and its parameter effects in size, efficiency and compactness and parametric analysis in terms of return loss, bandwidth, directivity and gain by using same and different dielectric substrate materials with same and different thickness of rectangular microstrip patch antenna. The important parameters of patch such as L, W, ε r and h has its own impact in antenna characteristics. This parametrical impact is studied and verified. As thickness of dielectric substrate increases, the gain & directivity of rectangular microstrip patch antenna decreases and bandwidth increases. As ε r increases, the size of the antenna decreases but when height of dielectric substrate increase antenna size also increases. There will be always a compromise between miniaturization and other antenna characteristics. This antenna is designed for microstrip feed line technique and with center frequency (f 0 ) at 4 GHz. The parametric analysis is obtained by comparing the simulated results of rectangular microstrip patch antenna for different cases. The proposed antenna is simulated using HFSS tool at resonance frequency of 4 GHz.