Browse Items (14421 total)
Sort by:
-
A novel deep learning based multimedia video retrieval framework using may fly optimization
Developing a video retrieval framework in multimedia management is a main challenge due to the massive growth of video content on the internet. A major drawback of video retrieval is its long search response time and low accuracy. To tackle these issues, this paper introduces a novel deep learning-based Multimedia video retrieval system (DL-MVR) to minimize the search response time with high accuracy. The collected video is initially converted into key frames and pre-processed with contrast adaptive histogram equalization to remove noise artifacts thereby improving image quality. After pre-processing, the images are fed to Efficient Net to extract patch features. Finally, to retrieve the similar video, matching is done using may fly optimization (MFO), that compares the query frame features to the video database. Several performance metrics are analysed to measure the effectiveness of the proposed strategy in terms of accuracy and response time. Experimental results indicate that the proposed system has a search response time of 0.71s, which is lower than existing methods. The proposed DL-MVR method achieves 99.26% of accuracy. The proposed method improves the overall accuracy by 9.32%, 22.04%, and 19.40% which is better than CNN-AlexNet (convolutional neural network), Pyramid regional graph network and CBVR respectively. Bharati Vidyapeeth's Institute of Computer Applications and Management 2025. -
A novel discrete slash family of distributions with application to epidemiology informatics data
This study puts forward a new class of discrete distribution that can be used by the epidemiologists and medical scientists to model data relating to epidemiology informatics. The proposed distribution is superior to traditional discrete modeling alternatives, viz., discrete Weibull and geometric distributions in terms of its model fit and flexibility to handle heavy-tailed dataset. It is a flexible three-parameter discrete distribution, grounded in the slash family and can be considered as a refined extension to the geometric distribution. We explored the diverse properties of this novel distribution thoroughly by evaluating the mathematical properties. The models parameters are estimated using the maximum likelihood estimation method, where the methodology validity is confirmed through an extensive simulation study. Furthermore, the practical utility of the distribution to model epidemiology informatics was examined with the help of eight different datasets representing three different dimensions of the epidemiology informatics, viz., mortality, infection and medication statistics. The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024. -
A novel discrete slash family of distributions with application to epidemiology informatics data
This study puts forward a new class of discrete distribution that can be used by the epidemiologists and medical scientists to model data relating to epidemiology informatics. The proposed distribution is superior to traditional discrete modeling alternatives, viz., discrete Weibull and geometric distributions in terms of its model fit and flexibility to handle heavy-tailed dataset. It is a flexible three-parameter discrete distribution, grounded in the slash family and can be considered as a refined extension to the geometric distribution. We explored the diverse properties of this novel distribution thoroughly by evaluating the mathematical properties. The models parameters are estimated using the maximum likelihood estimation method, where the methodology validity is confirmed through an extensive simulation study. Furthermore, the practical utility of the distribution to model epidemiology informatics was examined with the help of eight different datasets representing three different dimensions of the epidemiology informatics, viz., mortality, infection and medication statistics. The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024. -
A Novel Dynamic Physical Layer Impairment-Aware Routing and Wavelength Assignment (PLI-RWA) Algorithm for Mixed Line Rate (MLR) Wavelength Division Multiplexed (WDM) Optical Networks
The ever-increasing global Internet traffic will inevitably lead to a serious upgrade of the current optical networks' capacity. The legacy infrastructure can be enhanced not only by increasing the capacity but also by adopting advance modulation formats, having increased spectral efficiency at higher data rate. In a transparent mixed-line-rate (MLR) optical network, different line rates, on different wavelengths, can coexist on the same fiber. Migration to data rates higher than 10 Gbps requires the implementation of phase modulation schemes. However, the co-existing on-off keying (OOK) channels cause critical physical layer impairments (PLIs) to the phase modulated channels, mainly due to cross-phase modulation (XPM), which in turn limits the network's performance. In order to mitigate this effect, a more sophisticated PLI-Routing and Wavelength Assignment (PLI-RWA) scheme needs to be adopted. In this paper, we investigate the critical impairment for each data rate and the way it affects the quality of transmission (QoT). In view of the aforementioned, we present a novel dynamic PLI-RWA algorithm for MLR optical networks. The proposed algorithm is compared through simulations with the shortest path and minimum hop routing schemes. The simulation results show that performance of the proposed algorithm is better than the existing schemes. 2016 by De Gruyter. -
A novel dynamic Physical Layer Impairment-Aware Routing and Wavelength Assignment (PLI-RWA) algorithm for Mixed Line Rate (MLR) Wavelength Division Multiplexed (WDM) optical networks /
Journal of Optical Communications, Vol.37, Issue 4, pp.349-356, ISSN: 2191-6322 (Online) 0173-4911 (Print). -
A Novel Edge-Based Trust Management System for the Smart City Environment Using Eigenvector Analysis
The proposed Edge-based Trust Management System (E-TMS) uses an Eigenvector-based approach for eliminating the security threats present in the Internet of Things (IoT) enabled smart city environment. In most existing trust management systems, the trust aggregation process completely depends on the direct trust ratings obtained from both legitimate and malicious neighboring IoT devices. E-TMS possesses an edge-assisted two-level trust computation approach for ensuring the malicious free trust evaluation of IoT devices. The E-TMS aims at removing the false contribution on aggregated trust data. It utilizes the properties of the Eigenvector for identifying compromised IoT devices. The Eigenvector Analysis also helps to avoid false detection. The analysis involves a comparison of all the contributed trust data about every single connected device. A spectral matrix will be generated corresponding to the contributions and the received trust will be scaled based on the obtained spectral values. The absolute sum of obtained values will contain only true contributions. The accurate identification of false data will remove the effect of malicious contributions from the final trust value of a connected IoT device. Since the final trust value calculated by the edge node contains only the trustworthy data, the prediction about the malicious nodes will be accurate. Eventually, the performance of E-TMS has been validated. Throughput and network resilience are higher than the existing system. 2022 G. Nagarajan et al. -
A Novel Energy-Efficient Hybrid Optimization Algorithm for Load Balancing in Cloud Computing
In the field of Cloud Computing (CC), load balancing is a method applied to distribute workloads and computing resources appropriately. It enables organizations to effectively manage the needs of their applications or workloads by spreading resources across numerous PCs, networks, or servers. This research paper offers a unique load balancing method named FFBSO, which combines Firefly algorithm (FF) which reduces the search space and Bird Swarm Optimization (BSO). BSO takes inspiration from the collective behavior of birds, exhibiting tasks as birds and VMs as destination food patches. In the cloud environment, tasks are regarded as autonomous and non-preemptive. On the other hand, the BSO algorithm maps tasks onto suitable VMs by identifying the possible best positions. Simulation findings reveal that the FFBSO algorithm beat other approaches, obtaining the lowest average reaction time of 13ms, maximum resource usage of 99%, all while attaining a makespan of 35s. 2023 IEEE. -
A Novel Ensemble based Model for Intrusion Detection System
In the present interconnected world, the increasing reliance on computer networks has made them susceptible to multiple security threats and intrusions. Intrusion Detection Systems (IDS) is essential for shielding these networks by detecting and mitigating potential threats in real-time. This research paper presents an in-depth study of employing the Random Forest algorithm for building an effective intrusion detection System. The proposed IDS uses the power of the Random Forest algorithm, a popular ensemble learning technique, to detect various types of intrusions in network traffic effectively. The algorithm integrates more than one decision trees to produce a robust and accurate classifier, capable of handling large-scale and complex datasets typical of network traffic. The proposed system can be used in various industries and sectors to protect critical assets, ensuring the uninterrupted operation of computer networks. Evolving cyber threats have encouraged further research into ensemble analytics methods to increase the resilience of Intrusion Detection Systems in an ever-changing threat landscape. 2024 IEEE. -
A novel fibrinolytic enzyme producer from mangrove soil sediments: Screening, isolation, strain improvement, and fermentation
Fibrinolytic enzymes are used for addressing many cardiovascular disease conditions. However, current fibrinolytic enzymes are highly expensive with many side effects which necessitate the development of alternative cost-effective processes for low-cost production of these lifesaving enzymes. Since the availability of a suitable strain is considered the basic requirement for any process development effort, we started our work in this direction with screening and isolation of fibrinolytic enzyme producers. The goal of this study was to screen and isolate fibrinolytic enzyme producers from a relatively unexplored environment, i.e., the mangroves. Mangroves are wetlands and are one of the unique and less studied habitats for the production of therapeutic molecules. Microbiota that produces fibrinolytic enzymes from Coringa mangroves located in Kakinada District, Andhra Pradesh, India, is lacking. Therefore, in this study, fibrinolytic enzyme-producing bacterium was screened from samples obtained from Coringa mangroves. Out of 200, protease enzyme-producing isolates obtained from screening 30 mangrove soil samples, 7 isolates exhibiting fibrinolytic activity were selected. Out of these 7, the highest fibrinolytic enzyme-producing bacterial strain (AIBL_AMSB2) was characterized by biochemical and genomic methods, which was finally identified as Bacillus subtilis subsp. Inaquosorum by 16S rRNA analysis. The strain was also found to be an amylase producer. AIBL_AMSB2 was subjected to strain improvement using random mutagenesis techniques (i) Ultraviolent radiations (UV) and (ii) Ethyl methyl Sulphonate (EMS), which resulted in an improved mutant strain AIBL_AMSB2_M7E32 exhibiting 54.70% improvement in fibrinolytic activity. Batch fermentation in controlled experimental conditions using the obtained mutant strain resulted in a 133.54% increase in growth OD and a 391.11% increase in enzyme activity. Thus, the study reports an increased fibrinolytic enzyme activity producing mangrove isolate and its production by submerged fermentation. Further studies to prove the potential of the enzyme on blood clots are necessary to utilize for industrial application. 2024 Bhavana Sompalli and Alok Malaviya. -
A Novel Framework for Harnessing AI for Evidence-Based Policymaking in E-Governance Using Smart Contracts
Harnessing AI for evidence-based policymaking in e-governance has the potential to revolutionize the way governments formulate and implement policies. By leveraging AI technologies, governments can analyze vast amounts of data, extract valuable insights, and make informed decisions based on evidence. This chapter explores the various ways in which AI can be employed in e-governance to facilitate evidence-based policymaking. It discusses the use of AI algorithms for data analysis and prediction, enabling governments to identify patterns, trends, and emerging issues from diverse data sources. Moreover, AI-powered tools can enhance citizen engagement and participation, by facilitating data-driven decision-making processes and providing personalized services. Additionally, AI can assist in policy evaluation and impact assessment, by automating the collection and analysis of data, thus enabling governments to measure the effectiveness of their policies in real-time. Furthermore, AI can contribute to enhancing transparency and accountability in e-governance, by automating processes such as fraud detection and risk assessment. Despite the immense potential, the adoption of AI in e-governance must address challenges such as data privacy, algorithmic bias, and ethical considerations. This chapter concludes by emphasizing the importance of building trust, ensuring fairness, and promoting responsible AI practices to maximize the benefits of AI in evidence-based policymaking for e-governance. The Author(s), under exclusive license to Springer Nature Switzerland AG 2023. -
A Novel Framework for Integrating Machine Learning in CSR to Accelerate Sustainability in the Indian Automobile Sector
This paper aims at determining the suitability of using machine learning in CSR in enhancing sustainability of the Indian automobile industry. Prominent automobile companies are known to be major sources of environmental pollution together with wastage of various natural resources. There is a challenge of incorporating sustainability policies in the sector due to the rising regulation and consumers' awareness. Machine learning contains new approaches to managing resources more effectively, minimizing emissions and providing transparency of goods to clients. This study scrutinizes the previous literature, outlines the machine learning-based framework system of CSR activities, and validates the applicability of the system using case studies and qualitative data. The results show that learning from data can improve sustainability at an extensive scale and that the changes are sustainable and financially advantageous. 2025 IEEE. -
A novel free space communication system using nonlinear InGaAsP microsystem resonators for enabling power-control toward smart cities
Nowadays, the smart grid has demonstrated a great ability to make life easier and more comfortable given recent advances. This paper studies the above issue from the perspective of two important and very useful smart grid applications, i.e., the advanced metering infrastructure and demand response using the instrumentality of a set of well-known scheduling algorithms, e.g., best-channel quality indicator, log rule, round robin, and exponentialproportional fairness to validate the performance. To increase the data transmission bandwidth, a new concept of optical wireless communication known as free-space optical communication (FSO) system based on microring resonator (MRR) with the ability to deliver up to gigabit (line of sight) transmission per second is proposed for the two studied smart grid applications. The range between 374.7 and 374.79THz frequency band was chosen for the generation of 10 successive-carriers with a free spectral range of 8.87GHz. The ten multi-carriers were produced through drop port of the MRR. The results show up to 10 times bandwidth improvement over the radius as large as 600m and maintain receive power higher than the minimum threshold (? 20dBm) at the controller/users, so the overall system is still able to detect the FSO signal and extract the original data without detection. 2019, Springer Science+Business Media, LLC, part of Springer Nature. -
A Novel Fuzzy-Based Thresholding Approach for Blood Vessel Segmentation from Fundus Image
Retinal vessel segmentation is a vital part of pathological analysis in Fundus imaging. The automatic detection of blood vessels resolves several issues in the manual segmentation process. Most unsupervised segmentation methods depend on conventional thresholding techniques for final vessel extraction. It may lead to the loss of some vessel pixels, leading to inaccurate analysis of retinal diseases. In this work, we incorporate fuzzy concepts into two threshold-based vessel detection methods, namely mean-c thresholding and Iso-Data thresholding, which results in a mask consisting of membership values rather than binary values. The two fuzzy-based thresholding algorithms are applied independently on each image, and the resultant membership image (mask) is fused to get a single membership mask. The fusion is performed using fuzzy union operation. Experiments are carried out with Fundus images from DRIVE, STARE and CHASE_DB1 databases.ses. The proposed fusion framework gives a 3%, 6%, and 5% increase in sensitivity compared to traditional thresholding methods when applied to the DRIVE, STARE, and CHASE_DB1 databases, respectively. The accuracy obtained for the datasets is 96.02%, 94.57%, and 94.34%, respectively. 2023 by the authors. -
A Novel Generative Adversarial Network-Based Approach for Automated Brain Tumour Segmentation
Background: Medical image segmentation is more complicated and demanding than ordinary image segmentation due to the density of medical pictures. A brain tumour is the most common cause of high mortality. Objectives: Extraction of tumorous cells is particularly difficult due to the differences between tumorous and non-tumorous cells. In ordinary convolutional neural networks, local background information is restricted. As a result, previous deep learning algorithms in medical imaging have struggled to detect anomalies in diverse cells. Methods: As a solution to this challenge, a deep convolutional generative adversarial network for tumour segmentation from brain Magnetic resonance Imaging (MRI) images is proposed. A generator and a discriminator are the two networks that make up the proposed model. This network focuses on tumour localisation, noise-related issues, and social class disparities. Results: Dice Score Coefficient (DSC), Peak Signal to Noise Ratio (PSNR), and Structural Index Similarity (SSIM) are all generally 0.894, 62.084 dB, and 0.88912, respectively. The models accuracy has improved to 97 percent, and its loss has reduced to 0.012. Conclusions: Experiments reveal that the proposed approach may successfully segment tumorous and benign tissues. As a result, a novel brain tumour segmentation approach has been created. 2023 by the authors. -
A Novel Georouting Potency based Optimum Spider Monkey Approach for Avoiding Congestion in Energy Efficient Mobile Ad-hoc Network
Mobile Ad-hoc Network (MANET) is one of the recent fields in wireless communication that involves a large number of wireless nodes, which could be changed arbitrarily with the ability to link or exit the system anytime. Nevertheless, network congestion and energy management is a major problem in MANET. Consequently, the infrastructure of a network changes frequently which results in data loss and communication overheads. Therefore, in this paper, a novel Georouting Potency based Optimum Spider Monkey algorithm has been proposed for energy management and network congestion. The proposed technique in MANET is implemented using Network Simulator2 platform and the proposed outcomes show that the node energy, overload, and delay are minimized by increasing the quantity of packets transmitted through the network. Moreover, the delay in routing overhead and congestion is decreased by the proposed protocol. Consequently, the energy management is enhanced based on constraints of delay, energy consumption, and routing overhead of the nodes. Thus the effectiveness of the proposed protocol is enhanced by selecting the optimal path within the network, decreasing the consumption of energy, and congestion avoidance. Sequentially, the performance of the proposed routing algorithm is compared to existing protocols in terms of end-to-end delay, throughput, Packet Delivery Ratio, energy consumption, etc. Thus the result shows that the lifetime of the nodes have been enhanced by a high 98% of throughput ratio, less 0.01% of energy consumption, and congestion avoidance using the proposed network. 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. -
A Novel Hybrid Ensemble Architecture for Stroke Risk Prediction Using Healthcare Data
Stroke is the reason for an alarming number of disabilities worldwide, further emphasising the critical need for early and accurate prediction of risks to inform clinical management. This paper presents a novel hybrid ensemble architecture that leverages the superiority of multiple machine learning models for stroke health risk prediction using health data. In this novel hybridisation, decision tree classifiers belonging to the Random Forest and XGBoost families are effectively combined with support vector machines and a shallow neural network within a Stacked ensemble strategy that uses a hard vote technique. To improve model generalizability and avoid overfitting, feature selection and dimensionality reduction methods like Recursive Feature Elimination (RFE) and Principal Component Analysis (PCA) have been included expertly without compromising performance. After extensive training and testing on a real-world health repository covering a broad range of demographic, lifestyle, and clinical features, the model obtained an outstanding F1-score of 0.9427 and an exemplary ROC-AUC value of 0.9872, much higher than the performance of the individual models. Statistical significance was assessed using the Friedman and Wilcoxon signed-rank test. The model is a strong candidate for incorporation into clinical decision support systems and is fully deployable and EHR-compatible. The Author(s) 2026. -
A Novel Hybrid Model for Time Series Forecasting Using Artificial Neural Network and Autoregressive Integrated Moving Average Models
Enhancing forecast accuracy while using time series is a potential area of research. Evidences exist in the literature to show that hybrid models can significantly improve the forecasting performance, as they combine the exclusive strengths of different models. This paper presents a novel hybrid model by combining forecasts from Autoregressive Integrated Moving Average (ARIMA) and artificial neural network (ANN) models with suitable weights, thereby improving the forecast accuracy. The methodology employs appropriate error metrics to construct the weights. The paper further demonstrates the efficiency of the proposed methodology through an empirical study, based on two real-world time series data sets. Thus, the new methodology can be used for enhancing the forecast accuracy in a number of fields of research. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
A novel image compression method using wavelet coefficients and Huffman coding
Compressing medical images to reduce their size while maintaining their clinical and diagnostic information is crucial. Because medical images can be large and demand a lot of storage and transmission capacity, effective compression methods aid medical institutions in better storing and transmitting medical images, reducing costs, speeding up data transfer, and simplifying managing image databases. However, it is essential to note that image compression in medical imaging can also introduce drawbacks, such as loss of information and poor output image quality. Therefore, a suitable compression algorithm and parameter must be chosen to balance file size and visual fidelity. This paper suggests an effective image compression method employing the Discrete Wavelet Transform (DWT), followed by a reduction operation and Huffman coding to produce a mere lossless encoding to transmit the images over a channel. The extracted DWT coefficients are mapped to the nearest integral value. All four sub-bands of DWT are joined, and then a window of 3 3 is selected for reduction operation by choosing the origin as the pivot element. The Huffman coding algorithm is used to compress the processed image. The pivot origin element is used in the reversible reduction while uncompressing the image. When sending compressed data across an unreliable route, the window size and pivot element selection keep the compressed data secure. Standard measures such as bits per pixel (BPP) and compression ratio (CR) are used to assess the suggested approach. The efficiency of the suggested course of action is supported by the research's findings, which use a peak signal-to-noise ratio (PSNR) of 54.66 dB. 2023 The Authors -
A novel image compression method using wavelet coefficients and Huffman coding
Compressing medical images to reduce their size while maintaining their clinical and diagnostic information is crucial. Because medical images can be large and demand a lot of storage and transmission capacity, effective compression methods aid medical institutions in better storing and transmitting medical images, reducing costs, speeding up data transfer, and simplifying managing image databases. However, it is essential to note that image compression in medical imaging can also introduce drawbacks, such as loss of information and poor output image quality. Therefore, a suitable compression algorithm and parameter must be chosen to balance file size and visual fidelity. This paper suggests an effective image compression method employing the Discrete Wavelet Transform (DWT), followed by a reduction operation and Huffman coding to produce a mere lossless encoding to transmit the images over a channel. The extracted DWT coefficients are mapped to the nearest integral value. All four sub-bands of DWT are joined, and then a window of 3 3 is selected for reduction operation by choosing the origin as the pivot element. The Huffman coding algorithm is used to compress the processed image. The pivot origin element is used in the reversible reduction while uncompressing the image. When sending compressed data across an unreliable route, the window size and pivot element selection keep the compressed data secure. Standard measures such as bits per pixel (BPP) and compression ratio (CR) are used to assess the suggested approach. The efficiency of the suggested course of action is supported by the research's findings, which use a peak signal-to-noise ratio (PSNR) of 54.66 dB. 2023 The Authors -
A Novel Investigation on p-GaN GATE with and without AlGaN Back Barrier for AlGaN/GaN High Electron Mobility Transistors
p-GaN layers are relatively mature and controllable, making p-GaN HEMTs the leading structure that is most likely to be commercialized. The analysis of the gate design parameters, such as transconductance, breakdown voltage, threshold voltage, Johnson Figure of Merit (JFOM), and gate turn-on current of p-GaN devices, which determine the on-state characteristics, needs to be investigated. The AlGaN barrier, p-GaN gate, GaN, AlGaN back barrier, and SiC substrate constitute the structure of p-GaN, which is operated in the E-mode. The use of an AlGaN back barrier reduces the punch-through current. Silicon carbide (SiC) is used as a substrate to have lower lattice mismatch with the nitride layer. The transfer characteristics, transconductance, threshold voltage, breakdown voltage, and JFOM are analyzed. The device demonstrates a positive threshold voltage that varies linearly with changes in ambient temperature. In addition, the device featuring an AlGaN back barrier shows a higher breakdown voltage of 105 V, in contrast to the device lacking a back barrier. 2025, Society for Communication and Computer Technologies. All rights reserved.