Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
1,418
result(s) for
"Kumar, Umesh"
Sort by:
Groundwater fluoride contamination, probable release, and containment mechanisms: a review on Indian context
Fluoride contamination in the groundwater has got great attention in last few decades due to their toxicity, persistent capacity and accumulation in human bodies. There are several sources of fluoride in the environment and different pathways to enter in the drinking water resources, which is responsible for potential effect on human health. Presence of high concentration of fluoride ion in groundwater is a major issue and it makes the water unsuitable for drinking purpose. Availability of fluoride in groundwater indicates various geochemical processes and subsurface contamination of a particular area. Fluoride-bearing aquifers, geological factors, rate of weathering, ion-exchange reaction, residence time and leaching of subsurface contaminants are major responsible factors for availability of fluoride in groundwater. In India, several studies have reported that the groundwater of several states are contaminated with high fluoride. The undesirable level of fluoride in groundwater is one of the most natural groundwater quality problem, which affects large portion of arid and semiarid regions of India. Rajasthan, Andhra Pradesh, Telangana, Tamil Nadu, Gujarat, and West Bengal are the relatively high-fluoride-contaminated states in India. Chronic ingestion of high doses of fluoride-rich water leads to fluorosis on human and animal. Over 66 million Indian populations are at risk due to excess fluoride-contaminated water. Therefore, groundwater contamination subject to undesirable level of fluoride needs urgent attention to understand the role of geochemistry, hydrogeology and climatic factors along with anthropogenic inputs in fluoride pollution.
Journal Article
Yukawa–Casimir Wormholes in f(Q) Gravity
Casimir energy is always suggested as a possible source to create a traversable wormhole. It is also used to demonstrate the existence of negative energy, which can be created in a lab. To generalize this idea, Yukawa modification of a Casimir source has been considered in Remo Garattini (Eur. Phys. J. C 81 no.9, 824, 2021). In this work, we explore the Yukawa–Casimir wormholes in symmetric teleparallel gravity. We have taken four different forms of f(Q) to obtain wormhole solutions powered by the original Casimir energy source and Yukawa modification of the Casimir energy source. In power law form f(Q)=αQ2+β and quadratic form f(Q)=αQ2+βQ+γ, where α,β,γ are constants and Q is non-metricity scalar, we analyze that wormhole throat is filled with non-exotic matter. We find self-sustained traversable wormholes in the Casimir source where null energy conditions are violated in all specific forms of f(Q), while after Yukawa modification, it is observed that violation of null energy conditions is restricted to some regions in the vicinity of the throat.
Journal Article
A precise model for skin cancer diagnosis using hybrid U-Net and improved MobileNet-V3 with hyperparameters optimization
Skin cancer is a frequently occurring and possibly deadly disease that necessitates prompt and precise diagnosis in order to ensure efficacious treatment. This paper introduces an innovative approach for accurately identifying skin cancer by utilizing Convolution Neural Network architecture and optimizing hyperparameters. The proposed approach aims to increase the precision and efficacy of skin cancer recognition and consequently enhance patients' experiences. This investigation aims to tackle various significant challenges in skin cancer recognition, encompassing feature extraction, model architecture design, and optimizing hyperparameters. The proposed model utilizes advanced deep-learning methodologies to extract complex features and patterns from skin cancer images. We enhance the learning procedure of deep learning by integrating Standard U-Net and Improved MobileNet-V3 with optimization techniques, allowing the model to differentiate malignant and benign skin cancers. Also substituted the crossed-entropy loss function of the Mobilenet-v3 mathematical framework with a bias loss function to enhance the accuracy. The model's squeeze and excitation component was replaced with the practical channel attention component to achieve parameter reduction. Integrating cross-layer connections among Mobile modules has been proposed to leverage synthetic features effectively. The dilated convolutions were incorporated into the model to enhance the receptive field. The optimization of hyperparameters is of utmost importance in improving the efficiency of deep learning models. To fine-tune the model's hyperparameter, we employ sophisticated optimization methods such as the Bayesian optimization method using pre-trained CNN architecture MobileNet-V3. The proposed model is compared with existing models, i.e., MobileNet, VGG-16, MobileNet-V2, Resnet-152v2 and VGG-19 on the “HAM-10000 Melanoma Skin Cancer dataset\". The empirical findings illustrate that the proposed optimized hybrid MobileNet-V3 model outperforms existing skin cancer detection and segmentation techniques based on high precision of 97.84%, sensitivity of 96.35%, accuracy of 98.86% and specificity of 97.32%. The enhanced performance of this research resulted in timelier and more precise diagnoses, potentially contributing to life-saving outcomes and mitigating healthcare expenditures.
Journal Article
A Hybrid Intrusion Detection Model Using EGA-PSO and Improved Random Forest Method
Due to the rapid growth in IT technology, digital data have increased availability, creating novel security threats that need immediate attention. An intrusion detection system (IDS) is the most promising solution for preventing malicious intrusions and tracing suspicious network behavioral patterns. Machine learning (ML) methods are widely used in IDS. Due to a limited training dataset, an ML-based IDS generates a higher false detection ratio and encounters data imbalance issues. To deal with the data-imbalance issue, this research develops an efficient hybrid network-based IDS model (HNIDS), which is utilized using the enhanced genetic algorithm and particle swarm optimization(EGA-PSO) and improved random forest (IRF) methods. In the initial phase, the proposed HNIDS utilizes hybrid EGA-PSO methods to enhance the minor data samples and thus produce a balanced data set to learn the sample attributes of small samples more accurately. In the proposed HNIDS, a PSO method improves the vector. GA is enhanced by adding a multi-objective function, which selects the best features and achieves improved fitness outcomes to explore the essential features and helps minimize dimensions, enhance the true positive rate (TPR), and lower the false positive rate (FPR). In the next phase, an IRF eliminates the less significant attributes, incorporates a list of decision trees across each iterative process, supervises the classifier’s performance, and prevents overfitting issues. The performance of the proposed method and existing ML methods are tested using the benchmark datasets NSL-KDD. The experimental findings demonstrated that the proposed HNIDS method achieves an accuracy of 98.979% on BCC and 88.149% on MCC for the NSL-KDD dataset, which is far better than the other ML methods i.e., SVM, RF, LR, NB, LDA, and CART.
Journal Article
Design and Implementation of an ML and IoT Based Adaptive Traffic-Management System for Smart Cities
The rapid growth in the number of vehicles has led to traffic congestion, pollution, and delays in logistic transportation in metropolitan areas. IoT has been an emerging innovation, moving the universe towards automated processes and intelligent management systems. This is a critical contribution to automation and smart civilizations. Effective and reliable congestion management and traffic control help save many precious resources. An IoT-based ITM system set of sensors is embedded in automatic vehicles and intelligent devices to recognize, obtain, and transmit data. Machine learning (ML) is another technique to improve the transport system. The existing transport-management solutions encounter several challenges resulting in traffic congestion, delay, and a high fatality rate. This research work presents the design and implementation of an Adaptive Traffic-management system (ATM) based on ML and IoT. The design of the proposed system is based on three essential entities: vehicle, infrastructure, and events. The design utilizes various scenarios to cover all the possible issues of the transport system. The proposed ATM system also utilizes the machine-learning-based DBSCAN clustering method to detect any accidental anomaly. The proposed ATM model constantly updates traffic signal schedules depending on traffic volume and estimated movements from nearby crossings. It significantly lowers traveling time by gradually moving automobiles across green signals and decreases traffic congestion by generating a better transition. The experiment outcomes reveal that the proposed ATM system significantly outperformed the conventional traffic-management strategy and will be a frontrunner for transportation planning in smart-city-based transport systems. The proposed ATM solution minimizes vehicle waiting times and congestion, reduces road accidents, and improves the overall journey experience.
Journal Article
A novel approximation of underwater robotic vehicle controller exploiting multi-point matching
This proposed work is presenting the approximation of higher-order (HO) underwater robotic vehicle (URV) controller with the help of multi-point matching technique by incorporating greywolf optimization algorithm (GWOA). The performance of URV system is affected by external and internal dynamics. The proper momentum of URV system is achieved by designing a controller. The URV can be effectively operated by control action of controller. The URV controller is approximated to comparatively lower-order (LO) to propose an efficient, effective and economical controller for HOURV system. The approximation is accomplished with the help of expansion parameters of HOURV controller and its desired LOURV controller. The errors between these expansion parameters of HOURV controller and its desired LOURV controller are minimized using multi-point matching. The multi-point matching is depicted in the form of objective function (OF). The constructed OF is minimized by exploiting GWOA by fulfilling the steady-state matching condition and Hurwitz stability criterion, as constraints. The effectiveness of proposed approach of multi-point matching is verified by comparing the proposed LOURV model with LOURV models obtained with the help of other approximation approaches. The applicability of proposed LOURV controller is evaluated and validated by analyzing responses and tabulated data obtained in the results. Additionally, the statistical data of performance error values (PEVs) are provided in tabulated form along with its bar plot.
Journal Article
New Tsallis holographic dark energy
Tsallis entropy is a generalization of the Boltzmann–Gibbs entropy in statistical theory which uses a parameter δ to measure the deviation from the standard scenario quantitatively. Using concepts of Tsallis entropy and future event horizon, we construct a new Tsallis holographic dark energy model. The parameters c and δ will be used to characterize various aspects of the model. Analytical expressions for various cosmological parameters such as the differential equation describing the evolution of the effective dark energy density parameter, the equation of state parameter and the deceleration parameter are obtained. The equation of state parameter for the current model exhibits the pure quintessence behaviour for c>1, quintom behaviour for c<1 whereas the ΛCDM model is recovered for c=1. To analyze the thermal history of the universe, we obtained the expression for the deceleration parameter and found that for z≈0.6, the phase transits from deceleration to acceleration.
Journal Article
HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification
Optical Coherence Tomography (OCT) plays a crucial role in diagnosing ocular diseases, yet conventional CNN-based models face limitations such as high computational overhead, noise sensitivity, and data imbalance. This paper introduces HDL-ACO, a novel Hybrid Deep Learning (HDL) framework that integrates Convolutional Neural Networks with Ant Colony Optimization (ACO) to enhance classification accuracy and computational efficiency. The proposed methodology involves pre-processing the OCT dataset using discrete wavelet transform and ACO-optimized augmentation, followed by multiscale patch embedding to generate image patches of varying sizes. The hybrid deep learning model leverages ACO-based hyperparameter optimization to enhance feature selection and training efficiency. Furthermore, a Transformer-based feature extraction module integrates content-aware embeddings, multi-head self-attention, and feedforward neural networks to improve classification performance. Experimental results demonstrate that HDL-ACO outperforms state-of-the-art models, including ResNet-50, VGG-16, and XGBoost, achieving 95% training accuracy and 93% validation accuracy. The proposed framework offers a scalable, resource-efficient solution for real-time clinical OCT image classification.
Journal Article
Autonomous object tracking with vision based control using a 2DOF robotic arm
The tracking of moving object by implementing robot manipulator is one of the challenging task for many applications such as manufacturing, agriculture, logistics, healthcare, space, military, entertainment, etc. In the deployment of robotic manipulators with real-time object tracking for aforementioned important applications, the proper sensor surveillance and ensuring stability are major challenges. The purpose of this study is to design a precise and responsive object-tracking system by eliminating the complexities related to tedious mechanisms, rigidity, requirement of multiple sensors, etc. which are commonly associated with traditional systems. The robotic arms can be effectively designed to track moving objects autonomously with vision-based control. In comparison with different classical and traditional servoing approaches, the image-based visual servoing (IBVS) is more advantageous in vision-based control. The present article describes a new approach for IBVS-based tracking control of 2-degree-of-freedom (DOF) robotic arm by including object identification and trajectory tracking based crucial components. To solve the issues associated with IBVS, an accurate deep learning-based object detection framework is employed. The presented framework is utilized to detect and locate the objects in real-time. Further, an effective vision-based control technique is designed to control the 2-DOF robotic arm with the help of real-time response of object detection system. The validation of proposed control strategy is done by performing a simulation and experimental investigations with CoppeliaSim robot simulator and 2-DOF robotic arm, respectively. The findings reveal that the proposed deep learning controller for the vision-based 2-DOF robotic arm achieves good levels of accuracy and response time while performing visual servoing tasks. Furthermore, thorough discussion on possibility of using data-driven learning technique has been explored to improve the robustness and adaptability of the presented control scheme.
Journal Article