Evolutionary Algorithms for Edge Server Placement in Vehicular Edge Computing
Article, IEEE Access, 2025, DOI Link
View abstract ⏷
Vehicular Edge Computing (VEC) is a critical enabler for intelligent transportation systems (ITS). It provides low-latency and energy-efficient services by offloading computation to the network edge. Effective edge server placement is essential for optimizing system performance, particularly in dynamic vehicular environments characterized by mobility and variability. The Edge Server Placement Problem (ESPP) addresses the challenge of minimizing latency and energy consumption while ensuring scalability and adaptability in real-world scenarios. This paper proposes a framework to solve the ESPP using real-world vehicular mobility traces to simulate realistic conditions. To achieve optimal server placement, we evaluate the effectiveness of several advanced evolutionary algorithms. These include the Genetic Algorithm (GA), Non-dominated Sorting Genetic Algorithm II (NSGA-II), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), and Teaching-Learning-Based Optimization (TLBO). Each algorithm is analyzed for its ability to optimize multiple objectives under varying network conditions. Our results show that ACO performs the best, producing well-distributed pareto-optimal solutions and balancing trade-offs effectively. GA and PSO exhibit faster convergence and better energy efficiency, making them suitable for scenarios requiring rapid decisions. The proposed framework is validated through extensive simulations and compared with state-of-the-art methods. It consistently outperforms them in reducing latency and energy consumption. This study provides actionable insights into algorithm selection and deployment strategies for VEC, addressing mobility, scalability, and resource optimization challenges. The findings contribute to the development of robust, scalable VEC infrastructures, enabling the efficient implementation of next-generation ITS applications.
Resource management in fog computing: Overview and mathematical foundation
Book chapter, Swarm Intelligence: Theory and Applications in Fog Computing, Beyond 5G Networks, and Information Security, 2025,
MATSFT: User query-based multilingual abstractive text summarization for low resource Indian languages by fine-tuning mT5
Article, Alexandria Engineering Journal, 2025, DOI Link
View abstract ⏷
User query-based summarization is a challenging research area of natural language processing. However, the existing approaches struggle to effectively manage the intricate long-distance semantic relationships between user queries and input documents. This paper introduces a user query-based multilingual abstractive text summarization approach for the Indian low-resource languages by fine-tuning the multilingual pre-trained text-to-text (mT5) transformer model (MATSFT). The MATSFT employs a co-attention mechanism within a shared encoder–decoder architecture alongside the mT5 model to transfer knowledge across multiple low-resource languages. The Co-attention captures cross-lingual dependencies, which allows the model to understand the relationships and nuances between the different languages. Most multilingual summarization datasets focus on major global languages like English, French, and Spanish. To address the challenges in the LRLs, we created an Indian language dataset, comprising seven LRLs and the English language, by extracting data from the BBC news website. We evaluate the performance of the MATSFT using the ROUGE metric and a language-agnostic target summary evaluation metric. Experimental results show that MATSFT outperforms the monolingual transformer model, pre-trained MTM, mT5 model, NLI model, IndicBART, mBART25, and mBART50 on the IL dataset. The statistical paired t-test indicates that the MATSFT achieves a significant improvement with a p-value of ≤ 0.05 compared to other models.
Swarm intelligence: Theory and applications in fog computing, beyond 5G networks, and information security
Book, Swarm Intelligence: Theory and Applications in Fog Computing, Beyond 5G Networks, and Information Security, 2025, DOI Link
View abstract ⏷
This book offers a comprehensive overview of the theory and practical applications of swarm intelligence in fog computing, beyond 5G networks, and information security. The introduction section provides a background on swarm intelligence and its applications in real-world scenarios. The subsequent chapters focus on the practical applications of swarm intelligence in fog-edge computing, beyond 5G networks, and information security. The book explores various techniques such as computation offloading, task scheduling, resource allocation, spectrum management, radio resource management, wireless caching, joint resource optimization, energy management, path planning, UAV placement, and intelligent routing. Additionally, the book discusses the applications of swarm intelligence in optimizing parameters for information transmission, data encryption, and secure transmission in edge networks, multi-cloud systems, and 6G networks. The book is suitable for researchers, academics, and professionals interested in swarm intelligence and its applications in fog computing, beyond 5G networks, and information security. The book concludes by summarizing the key takeaways from each chapter and highlighting future research directions in these areas.
Traffic Classification in Dark Web Using Machine Learning Models
Conference paper, Lecture Notes in Networks and Systems, 2025, DOI Link
View abstract ⏷
The dark web is a collection of hidden content and web sites hosted on the darknet, which is not indexed by standard search engines and can only be accessed using specialized browsers like Tor, JonDonym, and I2P. As Internet technology advances, the threat to personal data security grows correspondingly, making the dark web a hub for malicious activities such as bank fraud, data theft, and security breaches. The content on the dark web is deliberately concealed from normal users, and its anonymity makes it a haven for illicit activities. Therefore, monitoring the darknet is crucial to detect data breaches and prevent serious consequences. Traffic classification plays a vital role in various areas such as security, service management, and research and development. In this experiment, traffic from dark web anonymity tools (Tor, JonDonym, and I2P) is classified at different levels of granularity, including network, traffic, and application levels. Initially, dark web traffic classification is conducted using four machine learning classifiers: naive Bayes, multinomial naive Bayes, decision tree, and random forest, utilizing a publicly available dataset. The impact of class imbalance within the dataset is also examined experimentally, employing the Synthetic Minority Oversampling TEchnique (SMOTE) to address the imbalance. Following this, the effectiveness of a neural network, specifically a multilayer perceptron, is evaluated for the classification task, and its performance is compared against the aforementioned classifiers.
Monitoring and Optimization of Machine Learning Workloads Using Kubernetes
Conference paper, Lecture Notes in Networks and Systems, 2025, DOI Link
View abstract ⏷
The demand for energy in cloud-native applications has increased considerably in recent years. With the rise of container-based deployments for delivering applications, understanding their power usage patterns is critical to lowering them. Unfortunately, cloud vendors do not provide their clients with power consumption details for individual workloads owing to virtualization-related limits inside the cloud infrastructure. This research paper compares the software and hardware-based tools available in the market to measure power consumption and discusses in detail about Kubernetes Efficient Power Level Exporter (Kepler), which addresses the above issue by estimating power metrics at the container level by using extended Berkeley Packet Filter (eBPF) and machine learning (ML) models. Since data-intensive workloads are power-hungry, we run the ML models on a simulated Graphical Processing Unit (GPU) accelerated Kubernetes (K8s) cluster. The metrics extracted by Kepler are carefully analyzed, and the ML workloads are tuned and optimized to use less energy.
CO2 Emissions of AI Applications: An Investigation on its Measurement
Conference paper, Lecture Notes in Networks and Systems, 2025, DOI Link
View abstract ⏷
The rapid expansion of Artificial Intelligence (AI) has led to a significant increase in the use of Data Centres (DCs), which are essential for processing and storing vast amounts of data. However, this surge in AI deployment has raised environmental concerns about increased Carbon Dioxide (CO2) emissions. Various solutions have been proposed to address the energy efficiency of DCs such as advanced cooling systems or selecting training locations with lower cooling needs or greener power supplies. To achieve further improvements, one needs to be able to measure actual emissions at the code level so that an optimization strategy can be designed and evaluated. To address the issue, we explore an innovative approach to precisely measure the CO2 emissions of AI applications. By introducing a linear regression energy estimation model based on Performance Monitoring Counters (PMCs) we calculate the CO2 emission of AI applications. PMCs such as the total number of instructions and the total number of cycles of the computer processor are considered ideal for energy estimation due to their strong correlation with the processor’s energy consumption and minimal overhead on resource utilisation. For this research, only the Central Processing Unit (CPU) and Dynamic Random Access Memory (DRAM) are considered, as they consume the maximum energy compared to other parts of the processor. This approach is easily extendable to GPUs. In the presented evaluation, the energy estimation model produced an error of only 0.158% for CPU and 0.272% for DRAM.
Autism Spectrum Disorder Prediction Using Particle Swarm Optimization and Convolutional Neural Networks
Conference paper, Lecture Notes in Networks and Systems, 2025, DOI Link
View abstract ⏷
The integration of PSO with CNN provides a promising approach for classifying ASD using sMRI data. ASD is a behavioral disorder that impacts a person’s lifetime tendency to reciprocate with society. The variability and intensity of ASD symptoms, in addition to the fact that they share symptoms with other mental disorders, make an early diagnosis difficult. The key limitation of CNN is selecting the best parameters. To overcome this, we use PSO as an optimization approach within the CNN to choose the most relevant parameters to train the network. In the proposed approach, we initialize a swarm of particles, where each particle represents a unique configuration of CNN hyperparameters, including the number of convolutional layers, learning rates, filter sizes, and batch sizes. To evaluate the swarm in PSO, we use a fitness function, such as accuracy, to measure each particle’s performance. The performance of the proposed approach for ASD prediction outperformed that of the other optimizers with a high convergence rate.
Optimal deployment of multiple IoT applications on the fog computing: A metaheuristic-based approach
Macha S.S.R.K., Chinta P.K., Katakam P., Hussain M., Georgievski I., Reddy V.D.
Book chapter, Swarm Intelligence: Theory and Applications in Fog Computing, Beyond 5G Networks, and Information Security, 2025,
Leveraging Artificial Intelligence And Machine Learning For Advanced Customer Relationship Management In The Retail Industry
Girimurugan B., Gokul K., Sasank M.S.S., Pokuri V.N., Kurra N.K., Reddy V.D.
Conference paper, 2024 2nd International Conference on Disruptive Technologies, ICDT 2024, 2024, DOI Link
View abstract ⏷
Maintaining success in the ever-changing retail sector requires careful attention to customer interactions. Understanding and satisfying client expectations are crucial for growth in the retail industry, which is becoming increasingly competitive. The level of consumer awareness that is typically required for traditional customer relationship management (CRM) solutions to function properly is frequently in excess of what is possible. The present CRM systems' incapacity to process huge, complicated information places a cap on the insights that may be obtained from these data. Specifically, this importance is brought to light by the findings of the study. This is despite the fact that AI and ML have been widely adopted over the past several years. In order to fill in this knowledge vacuum, this study investigates how Deep Support Vector Machines (SVMs) might be utilised to turn consumer data into actionable insight for improved decision-making in retail customer relationship management (CRM). This paper investigates the challenges that can arise when attempting to improve customer relationship management (CRM) in the retail industry by employing AI and ML, more specifically through the application of Deep Support Vector Machines (Deep SVM). The capability of the model to anticipate the actions and preferences of customers will be trained and validated using data collected from actual customers shopping in a number of different retail situations. One of the outcomes that is anticipated is the development of a much improved customer relationship management system that has the capacity to give more accurate customer insights and predictions.
Energy efficient resource management in data centers using imitation-based optimization
Article, Energy Informatics, 2024, DOI Link
View abstract ⏷
Cloud computing is the paradigm for delivering streaming content, office applications, software functions, computing power, storage, and more as services over the Internet. It offers elasticity and scalability to the service consumer and profit to the provider. The success of such a paradigm has resulted in a constant increase in the providers’ infrastructure, most notably data centers. Data centers are energy-intensive installations that require power for the operation of the hardware and networking devices and their cooling. To serve cloud computing needs, the data center organizes work as virtual machines placed on physical servers. The policy chosen for the placement of virtual machines over servers is critical for managing the data center resources, and the variability of workloads needs to be considered. Inefficient placement leads to resource waste, excessive power consumption, and increased communication costs. In the present work, we address the virtual machine placement problem and propose an Imitation-Based Optimization (IBO) method inspired by human imitation for dynamic placement. To understand the implications of the proposed approach, we present a comparative analysis with state-of-the-art methods. The results show that, with the proposed IBO, the energy consumption decreases at an average of 7%, 10%, 11%, 28%, 17%, and 35% compared to Hybrid meta-heuristic, Extended particle swarm optimization, particle swarm optimization, Genetic Algorithm, Integer Linear Programming, and Hybrid Best-Fit, respectively. With growing workloads, the proposed approach can achieve monthly cost savings of €201.4 euro and CO2 Savings of 460.92 lbs CO2/month.
SONG: A Multi-Objective Evolutionary Algorithm for Delay and Energy Aware Facility Location in Vehicular Fog Networks
Hussain M.M., Azar A.T., Ahmed R., Umar Amin S., Qureshi B., Dinesh Reddy V., Alam I., Khan Z.I.
Article, Sensors, 2023, DOI Link
View abstract ⏷
With the emergence of delay- and energy-critical vehicular applications, forwarding sense-actuate data from vehicles to the cloud became practically infeasible. Therefore, a new computational model called Vehicular Fog Computing (VFC) was proposed. It offloads the computation workload from passenger devices (PDs) to transportation infrastructures such as roadside units (RSUs) and base stations (BSs), called static fog nodes. It can also exploit the underutilized computation resources of nearby vehicles that can act as vehicular fog nodes (VFNs) and provide delay- and energy-aware computing services. However, the capacity planning and dimensioning of VFC, which come under a class of facility location problems (FLPs), is a challenging issue. The complexity arises from the spatio-temporal dynamics of vehicular traffic, varying resource demand from PD applications, and the mobility of VFNs. This paper proposes a multi-objective optimization model to investigate the facility location in VFC networks. The solutions to this model generate optimal VFC topologies pertaining to an optimized trade-off (Pareto front) between the service delay and energy consumption. Thus, to solve this model, we propose a hybrid Evolutionary Multi-Objective (EMO) algorithm called Swarm Optimized Non-dominated sorting Genetic algorithm (SONG). It combines the convergence and search efficiency of two popular EMO algorithms: the Non-dominated Sorting Genetic Algorithm (NSGA-II) and Speed-constrained Particle Swarm Optimization (SMPSO). First, we solve an example problem using the SONG algorithm to illustrate the delay–energy solution frontiers and plotted the corresponding layout topology. Subsequently, we evaluate the evolutionary performance of the SONG algorithm on real-world vehicular traces against three quality indicators: Hyper-Volume (HV), Inverted Generational Distance (IGD) and CPU delay gap. The empirical results show that SONG exhibits improved solution quality over the NSGA-II and SMPSO algorithms and hence can be utilized as a potential tool by the service providers for the planning and design of VFC networks.
Enhanced resource provisioning and migrating virtual machines in heterogeneous cloud data center
Article, Journal of Ambient Intelligence and Humanized Computing, 2023, DOI Link
View abstract ⏷
Data centers have become an indispensable part of modern computing infrastructures. It becomes necessary to manage cloud resources efficiently to reduce those ever-increasing power demands of data centers. Dynamic consolidation of virtual machines (VMs) in a data center is an effective way to map workloads onto servers in a way that requires the least resources possible. It is an efficient way to improve resources utilization and reduce energy consumption in cloud data centers. Virtual machine (VM) consolidation involves host overload/underload detection, VM selection, and VM placement. If a server becomes overloaded, we need techniques to select the proper virtual machines to migrate. By considering the migration overhead and service level of agreement (SLA) violation, we investigate design methodologies to reduce the energy consumption for the whole data center. We propose a novel approach that optimally detects when a host is overloaded using known CPU utilization and a given state configuration. We design a VM selection policy, considering various resource utilization factors to select the VMs. In addition, we propose an improved version of the JAYA approach for VM placement that minimizes the energy consumption by optimally pacing the migrated VMs in a data center. We analyze the performance in terms of energy consumption, performance degradation, and migrations. Using CloudSim, we run simulations and observed that our approach has an average improvement of 24% compared to state-of-the-art approaches in terms of power consumption.
Post-quantum distributed ledger technology: a systematic survey
Article, Scientific Reports, 2023, DOI Link
View abstract ⏷
Blockchain technology finds widespread application across various fields due to its key features such as immutability, reduced costs, decentralization, and transparency. The security of blockchain relies on elements like hashing, digital signatures, and cryptography. However, the emergence of quantum computers and supporting algorithms poses a threat to blockchain security. These quantum algorithms pose a significant threat to both public-key cryptography and hash functions, compelling the redesign of blockchain architectures. This paper investigates the status quo of the post-quantum, quantum-safe, or quantum-resistant cryptosystems within the framework of blockchain. This study starts with a fundamental overview of both blockchain and quantum computing, examining their reciprocal influence and evolution. Subsequently, a comprehensive literature review is conducted focusing on Post-Quantum Distributed Ledger Technology (PQDLT). This research emphasizes the practical implementation of these protocols and algorithms providing extensive comparisons of characteristics and performance. This work will help to foster further research at the intersection of post-quantum cryptography and blockchain systems and give prospective directions for future PQDLT researchers and developers.
Sentiment Analysis for Real-Time Micro Blogs using Twitter Data
Banu R., Ahammed G.F.A., Divya G., Reddy V.D., Bhaskar N., Kanthi M.
Conference paper, 2023 2nd International Conference for Innovation in Technology, INOCON 2023, 2023, DOI Link
View abstract ⏷
The basic purpose of sentiment analysis is to determine how someone feels when they comment or express their feelings or emotions. Positive, neutral, and negative emotions are the three categories into which emotions are divided. Everyone will use and apply this analysis on social media; online; everyone expresses their opinions by clicking on the like, remark, or share buttons. Using the Random Forest, SVM, and Nave Bayes algorithms, the Twitter tweets in this study were identified as positive or negative, with F1-Scores of 0.224, 0.410, and 0.702, respectively, and accuracy values of 50%, 52%, and 73%.
A Computer Vision based Facial Denoising Alignment using Convolution Neural Network Model
Vidyullatha P., Reddy V.D., Dasaradha Ram K., Reddy D.S., Shaik A., Ramya K.R.
Conference paper, Proceedings of the 8th International Conference on Communication and Electronics Systems, ICCES 2023, 2023, DOI Link
View abstract ⏷
For most higher-level face evaluation applications, including liveliness, human activity identification, and personal contact, facial organization is a significant task. The real-world usefulness of such models is constrained since the utilization of present approaches can significantly deteriorate when handling images under particularly uncontrolled circumstances. This is true even though the best-in-class accuracy has significantly improved thanks to new access to large datasets and potent deep learning algorithms. In this study, a composite recurrent tracker that can simultaneously find single image facial arrangement and deformable facial following in nature, has been suggested. The multi-facet LSTMs are combined to illustrate real-world scenarios with varied length, and an internal denoiser that focuses on enhancing the information images to increase the resiliency of the general model, is offered. Face positioning is important in the majority of face examination frameworks. It emphasizes locating a few prominent features of human faces in images or recordings. The planning strategies and implementations described in this research, are based on information expansion and programming enhancement techniques, and they allow for working on a wide range of models with a place for specific continuous computations for face arrangement. A sophisticated set of evaluation metrics that enables new assessments to lessen the frequent issues seen in actual opportunity-following contexts, is proposed. The exploratory results show that the models created utilizing the approaches are more accurate, faster and more robust in defined testing environments, and more flexible in global positioning frameworks is the proposed challenge.
Classification of Autism Spectrum Disorder Based on Brain Image Data Using Deep Neural Networks
Lakshmi P.B., Reddy V.D., Ghosh S., Sengar S.S.
Conference paper, Smart Innovation, Systems and Technologies, 2023, DOI Link
View abstract ⏷
Autism spectrum disorder (ASD) is a neuro-developmental disorder that affects 1% of children and has a lifetime effect on communication and interaction. Early prediction can address this problem by decreasing the severity. This paper presents a deep learning-based transfer learning applied to resting state fMRI images for predicting the autism disorder features. We worked with CNN and different transfer learning models such as Inception-V3, Resnet, Densenet, VGG16, and Mobilenet. We performed extensive experiments and provided a comparative study for different transfer learning models to predict the classification of ASD. Results demonstrated that VGG16 achieves high classification accuracy of 95.8% and outperforms the rest of the transfer learning models proposed in this paper and has an average improvement of 4.96% in terms of accuracy.
Image Description Generator using Residual Neural Network and Long Short-Term Memory
Article, Computer Science Journal of Moldova, 2023, DOI Link
View abstract ⏷
Human beings can describe scenarios and objects in a picture through vision easily whereas performing the same task with a computer is a complicated one. Generating captions for the objects of an image helps everyone to understand the scenario of the image in a better way. Instinctively describing the content of an image requires the apprehension of computer vision as well as natural language processing. This task has gained huge popularity in the field of technology and there is a lot of research work being carried out. Recent works have been successful in identifying objects in the image but are facing many challenges in generating captions to the given image accurately by understanding the scenario. To address this challenge, we propose a model to generate the caption for an image. Residual Neural Network (ResNet) is used to extract the features from an image. These features are converted into a vector of size 2048. The caption generation for the image is obtained with Long Short-Term Memory (LSTM). The proposed model is experimented on the Flickr8K dataset and obtained an accuracy of 88.4%. The experimental results indicate that our model produces appropriate captions compared to the state of art models.
A discrete cosine transform-based intelligent image steganography scheme using quantum substitution box
Article, Quantum Information Processing, 2023, DOI Link
View abstract ⏷
Everyday dealing with enormous amounts of sensitive data requires its protection and communication over the insecure network. The field of ‘Steganography’ always attracted researchers for significant amount of scientific attention to protect and communicate sensitive data. This paper presents a secure steganography scheme for hiding Gray-scale secret image into a Color cover image by replacing cover image bits in frequency domain using modified quantum substitution box (S-Box). The inclusion of modified quantum S-Box for concealing secret bits in randomly selected any of the two channels of cover image ensures enhanced security. In the proposed scheme, we first performed discrete cosine transform (DCT) on the cover image. Then, quantum S-box is applied to locate the position of DCT coefficients where least significant bits are substituted intelligently based on the relative ordering of DCT frequencies. This relative ordering is achieved by traversing DCT coefficients in a zigzag manner where less important pixels have been altered more effectively without any major loss in image quality. The security of proposed method is examined by key space, key sensitivity parameters and robustness analysis. Additionally, the conducted simulation results demonstrate that our proposed steganography scheme has better visual image quality in terms of MSE, PSNR, UQI, SSIM, RMSE parameters as compared to other state-of-the-art works.
A secure IoT-based micro-payment protocol for wearable devices
Article, Peer-to-Peer Networking and Applications, 2022, DOI Link
View abstract ⏷
Wearable devices are parts of the essential cost of goods sold (COGS) in the wheel of the Internet of things (IoT), contributing to a potential impact in the finance and banking sectors. There is a need for lightweight cryptography mechanisms for IoT devices because these are resource constraints. This paper introduces a novel approach to an IoT-based micro-payment protocol in a wearable devices environment. This payment model uses an “elliptic curve integrated encryption scheme (ECIES)” to encrypt and decrypt the communicating messages between various entities. The proposed protocol allows the customer to buy the goods using a wearable device and send the mobile application’s confidential payment information. The application creates a secure session between the customer, banks and merchant. The static security analysis and informal security methods indicate that the proposed protocol is withstanding the various security vulnerabilities involved in mobile payments. For logical verification of the correctness of security properties using the formal way of “Burrows-Abadi-Needham (BAN)” logic confirms the proposed protocol’s accuracy. The practical simulation and validation using the Scyther and Tamarin tool ensure that the absence of security attacks of our proposed framework. Finally, the performance analysis based on cryptography features and computational overhead of related approaches specify that the proposed micro-payment protocol for wearable devices is secure and efficient.
Non-invertible Cancellable Template for Fingerprint Biometric
Kavati I., Kumar G.K., Gopalachari M.V., Babu E.S., Cheruku R., Reddy V.D.
Conference paper, Lecture Notes in Networks and Systems, 2022, DOI Link
View abstract ⏷
In this work we propose an approach for generation of secure and non-invertible fingerprint templates. Firstly, we have to find the points around the reference point and select the n points sorted in ascending order. Then we have to construct a n sided polygon from the n selected points. The polygon created will have all its points connected to the reference minutia which will in turn divide the polygon into n triangles. The area and semi perimeter of the triangle, the angle between the two lines joining the reference minutiae from the two points is calculated and the orientation of the points in the triangle is taken. These all features together constitute the feature vector. This feature vector will be projected onto the 4D-space and the binary string will be generated from it. Then Discrete Fourier Transform (DFT) will be applied on the generated binary string. To achieve non invertibility the obtained DFT matrix will be multiplied by a user key. At last, the proposed work will be inspected by using the FVC databases and various metrics will be used to check the performance.
A Dynamic Model and Algorithm for Real-Time Traffic Management
Teja M.N.V.M.S., Sree N.L., Harshitha L., Bhargav P.V., Bhaskar N., Reddy V.D.
Conference paper, Smart Innovation, Systems and Technologies, 2022, DOI Link
View abstract ⏷
The work portrays a summary of traffic congestion which has been a persistent problem in many cities in India. The major problems that lead to traffic congestion in India are primarily associated with one or combination of the factors such as signal failures, inadequate law enforcement and relatively poor traffic management practices. The traffic congestion shall be treated as a grave issue as it significantly reduces the freight vehicles speed, increases wait time at the checkpoints and toll plazas, uncountable loss of productive man-hours spending unnecessary journey time, physical and mental fatigue of humans. In addition, the cars that are waiting in traffic jams contribute to 40% increased pollution than those which are normally moving on the roads by way of increased fuel wastage and therefore causing excessive carbon dioxide emissions which would result in frequent repairs and replacements. To avoid such unwarranted and multi-dimensional losses to mankind, we developed a technological solution and our experiments on real-time data show that proposed approach is able to reduce the waiting time and travelling time for the users.
Analyzing Student Performance in Programming Education Using Classification Techniques
Conference paper, ASSIC 2022 - Proceedings: International Conference on Advancements in Smart, Secure and Intelligent Computing, 2022, DOI Link
View abstract ⏷
Programming Skills play a crucial role in any computer engineering student's life to apply the concepts in solving any real world problem as well to crack a secure job in the dream company. To achieve this they should assess their performance in programming, analyze and improve their skills regularly. Many students are even undergoing mental stress and depression and even attempting suicides out of the stress if the considered scores and performance are not met. With the help of analyzing the programming skills one can enhance their scores and performance on a regular basis, introspect and can deliberately practice for better improvement. This reduces the stress, anxiety and depression on students' minds in securing good scores in their academics and in building their career to achieve the goal. This analysis helps even professors to improvise the teaching and learning outcomes of students and increase their performance in whichever field they are working in. We made a comparison of different machine learning algorithms based on 200 classification instances. This analysis helped us in analyzing the statistics of students' performance.
Techniques for Solving Shortest Vector Problem
Article, International Journal of Advanced Computer Science and Applications, 2021, DOI Link
View abstract ⏷
Lattice-based crypto systems are regarded as secure and believed to be secure even against quantum computers. lattice-based cryptography relies upon problems like the Shortest Vector Problem. Shortest Vector Problem is an instance of lattice problems that are used as a basis for secure cryptographic schemes. For more than 30 years now, the Shortest Vector Problem has been at the heart of a thriving research field and finding a new efficient algorithm turned out to be out of reach. This problem has a great many applications such as optimization, communication theory, cryptography, etc. This paper introduces the Shortest Vector Problem and other related problems such as the Closest Vector Problem. We present the average case and worst case hardness results for the Shortest Vector Problem. Further this work explore efficient algorithms solving the Shortest Vector Problem and present their efficiency. More precisely, this paper presents four algorithms: the Lenstra-Lenstra-Lovasz (LLL) algorithm, the Block Korkine-Zolotarev (BKZ) algorithm, a Metropolis algorithm, and a convex relaxation of SVP. The experimental results on various lattices show that the Metropolis algorithm works better than other algorithms with varying sizes of lattices.
CybSecMLC: A Comparative Analysis on Cyber Security Intrusion Detection Using Machine Learning Classifiers
Conference paper, Communications in Computer and Information Science, 2021, DOI Link
View abstract ⏷
With the rapid growth of the Internet and smartphone and wireless communication-based applications, new threats, vulnerabilities, and attacks also increased. The attackers always use communication channels to violate security features. The fast-growing of security attacks and malicious activities create a lot of damage to society. The network administrators and intrusion detection systems (IDS) were also unable to identify the possibility of network attacks. However, many security mechanisms and tools are evolved to detect the vulnerabilities and risks involved in wireless communication. Apart from that machine learning classifiers (MLCs) also practical approaches to detect intrusion attacks. These MLCs differentiated the network traffic data as two parts one is abnormal and other regular. Many existing systems work on the in-depth analysis of specific attacks in network intrusion detection systems. This paper presents a comprehensive and detailed inspection of some existing MLCs for identifying the intrusions in the wireless network traffic. Notably, we analyze the MLCs in terms of various dimensions like feature selection and ensemble techniques to identify intrusion detection. Finally, we evaluated MLCs using the “NSL-KDD” dataset and summarize their effectiveness using a detailed experimental evolution.
Extended Graph Convolutional Networks for 3D Object Classification in Point Clouds
Article, International Journal of Advanced Computer Science and Applications, 2021, DOI Link
View abstract ⏷
Point clouds are a popular way to represent 3D data. Due to the sparsity and irregularity of the point cloud data, learning features directly from point clouds become complex and thus huge importance to methods that directly consume points. This paper focuses on interpreting the point cloud inputs using the graph convolutional networks (GCN). Further, we extend this model to detect the objects found in the autonomous driving datasets and the miscellaneous objects found in the non-autonomous driving datasets. We proposed to reduce the runtime of a GCN by allowing the GCN to stochastically sample fewer input points from point clouds to infer their larger structure while preserving its accuracy. Our proposed model offer improved accuracy while drastically decreasing graph building and prediction runtime.
Meta-heuristic approaches to solve shortest lattice vector problem
Article, Journal of Discrete Mathematical Sciences and Cryptography, 2021, DOI Link
View abstract ⏷
We present the aptness of population based meta-heuristic approaches to compute a shortest non-zero vector in a lattice for solving the Shortest lattice Vector Problem (SVP). This problem has a great many applications such as optimization, communication theory, cryptography, etc. At the same time, SVP is notoriously hard to predict, both in terms of running time and output quality. The SVP is known to be NP-hard under randomized reduction and there is no polynomial time solution for this problem. Though LLL algorithm is a polynomial time algorithm, it does not give the optimal solutions. In this paper, we present the application of Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) to solve the SVP on an appropriate search space. We have implemented the PSO, GA and LLL algorithm for the SVP. The comparison results shows that our algorithm works for all instances.
Forecasting energy consumption using deep echo state networks optimized with genetic algorithm
Reddy V.D., Nilavan K., Gangadharan G.R., Fiore U.
Book chapter, Artificial Intelligence, Machine Learning, and Data Science Technologies: Future Impact and Well-Being for Society 5.0, 2021, DOI Link
Energy-aware virtual machine allocation and selection in cloud data centers
Dinesh Reddy V., Gangadharan G.R., Rao G.S.V.R.K.
Article, Soft Computing, 2019, DOI Link
View abstract ⏷
Data centers evolve constantly in size, complexity, and power consumption. Energy management in cloud data centers is a critical and challenging research issue. It becomes necessary to minimize the operational costs as well as environmental impact and to guarantee the service-level agreements for the services provided by the data centers. We propose a modified discrete particle swarm optimization based on the characteristic particle swarm optimization for the initial placement of virtual machines and a novel virtual machine selection algorithm for optimizing the current allocation based on memory utilization, bandwidth utilization, and size of the virtual machine. By means of simulations, we observe that the proposed method not only saves the energy significantly than the other approaches, but also minimizes the violations of service-level agreements.
Best Practices for Sustainable Datacenters
Dinesh Reddy V., Setz B., Rao S.V.R.K., Gangadharan G.R., Aiello M.
Article, IT Professional, 2018, DOI Link
View abstract ⏷
Datacenters are an essential utility of most modern organizations. These huge computing infrastructures consume large amounts of power, and their total energy consumption is estimated to be 2 percent of global consumption. Thus, it is important to minimize power usage in the design and operation of datacenters. The authors analyzed seven datacenters in India and the Netherlands and, based on their findings and industry standards, present a set of best practices to improve the datacenters energy efficiency. Following some of these best practices, these datacenters have achieved 10 to 20 percent improvements in their energy consumption.
Metrics for Sustainable Data Centers
Reddy V.D., Setz B., Rao G.S.V.R.K., Gangadharan G.R., Aiello M.
Article, IEEE Transactions on Sustainable Computing, 2017, DOI Link
View abstract ⏷
There are a multitude of metrics available to analyze individual key performance indicators of data centers. In order to predict growth or set effective goals, it is important to choose the correct metric and be aware of their expressivity and potential limitations. As cloud based services and the use of ICT infrastructure are growing globally, continuous monitoring and measuring of data center facilities are becoming essential to ensure effective and efficient operations. In this work, we explore the diverse metrics that are currently available to measure numerous data center infrastructure components. We propose a taxonomy of metrics based on core data center dimensions. Based on our observations, we argue for the design of new metrics considering factors such as age, location, and data center typology (e.g., co-location center), thus assisting in the strategic data center design and operations processes.
Energy efficient virtual machine placement in cloud data centers using modified intelligent water drop algorithm
Verma C.S., Dinesh Reddy V., Gangadharan G.R., Negi A.
Conference paper, Proceedings - 13th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2017, 2017, DOI Link
View abstract ⏷
Cloud Computing is an emerging distributed computing paradigm for the dynamic provisioning of computing services on demand over the internet. Due to heavy demand of various IT services over the cloud, energy consumption by data centers is growing significantly worldwide. The intense use of data centers leads to high energy consumptions, excessive CO2 emission and increase in the operating cost of the data centers. Although many virtual machine (VM) placement approaches have been proposed to improve the resource utilization and energy efficiency, most of these works assume a homogeneous environment in the data centers. However, the physical server configurations in heterogeneous data centers lead to varying energy consumption characteristics. In this paper, we model and implement a modified Intelligent Water Drop algorithm (MIWD) algorithm for dynamic provisioning of virtual machines on hosts in homogeneous and heterogeneous environments such that total energy consumption of a data center in cloud computing environment can be minimized. Experimental results indicate that our proposed MIWD algorithm is giving superior results.
Towards an Internet of Things framework for financial services sector
Conference paper, 2016 3rd International Conference on Recent Advances in Information Technology, RAIT 2016, 2016, DOI Link
View abstract ⏷
The ability to apply state-of-the-art Internet of Things (IoT) technology to extract customer insights through analytics by shaping the information into consumables for other connected systems is creating a lot of opportunities for banking and financial services. This paper presents an architecture based on Internet of Things for banking and finance sector by managing, mobile, household devices, wearable sensors and other sensing devices for various applications including retail banking, insurance, and investments. We have presented a case study of different banking applications flow with IoT-intelligence by analyzing users' data. In addition, we have a mapping of the proposed architecture onto the various applications of banks and financial services.
