Chiranji Lal Chowdhary
@vit.ac.in
Associate Professor
Vellore Institute of Technology Vellore, India
RESEARCH INTERESTS
Image Processing, Pattern Recognition, Deep Learning, Neural Networks, Computational Intelligence
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Subhranshu Sekhar Tripathy, Sujit Bebortta, Chiranji Lal Chowdhary, Tanmay Mukherjee, SeongKi Kim, Jana Shafi, and Muhammad Fazal Ijaz
Elsevier BV
Sivashankari Rajadurai, Kumaresan Perumal, Muhammad Fazal Ijaz, and Chiranji Lal Chowdhary
MDPI AG
Malignant lymphoma, which impacts the lymphatic system, presents diverse challenges in accurate diagnosis due to its varied subtypes—chronic lymphocytic leukemia (CLL), follicular lymphoma (FL), and mantle cell lymphoma (MCL). Lymphoma is a form of cancer that begins in the lymphatic system, impacting lymphocytes, which are a specific type of white blood cell. This research addresses these challenges by proposing ensemble and non-ensemble transfer learning models employing pre-trained weights from VGG16, VGG19, DenseNet201, InceptionV3, and Xception. For the ensemble technique, this paper adopts a stack-based ensemble approach. It is a two-level classification approach and best suited for accuracy improvement. Testing on a multiclass dataset of CLL, FL, and MCL reveals exceptional diagnostic accuracy, with DenseNet201, InceptionV3, and Xception exceeding 90% accuracy. The proposed ensemble model, leveraging InceptionV3 and Xception, achieves an outstanding 99% accuracy over 300 epochs, surpassing previous prediction methods. This study demonstrates the feasibility and efficiency of the proposed approach, showcasing its potential in real-world medical applications for precise lymphoma diagnosis.
Musiri Kailasanathan Nallakaruppan, Chiranji Lal Chowdhary, SivaramaKrishnan Somayaji, Himakshi Chaturvedi, Sujatha. R, Hafiz Tayyab Rauf, and Mohamed Sharaf
American Institute of Mathematical Sciences (AIMS)
<abstract><p>Fake face identity is a serious, potentially fatal issue that affects every industry from the banking and finance industry to the military and mission-critical applications. This is where the proposed system offers artificial intelligence (AI)-based supported fake face detection. The models were trained on an extensive dataset of real and fake face images, incorporating steps like sampling, preprocessing, pooling, normalization, vectorization, batch processing and model training, testing-, and classification via output activation. The proposed work performs the comparative analysis of the three fusion models, which can be integrated with Generative Adversarial Networks (GAN) based on the performance evaluation. The Model-3, which contains the combination of DenseNet-201+ResNet-102+Xception, offers the highest accuracy of 0.9797, and the Model-2 with the combination of DenseNet-201+ResNet-50+Inception V3 offers the lowest loss value of 0.1146; both are suitable for the GAN integration. Additionally, the Model-1 performs admirably, with an accuracy of 0.9542 and a loss value of 0.1416. A second dataset was also tested where the proposed Model-3 provided maximum accuracy of 86.42% with a minimum loss of 0.4054.</p></abstract>
Thandra Jithendra, Mohammad Zubair Khan, S. Sharief Basha, Raja Das, A. Divya, Chiranji Lal Chowdhary, Abdulrahman Alahmadi, and Ahmed H. Alahmadi
Institute of Electrical and Electronics Engineers (IEEE)
The adoption of adaptive neuro-fuzzy inference systems (ANFIS) and metaheuristic optimization approaches has been widely observed in recent research. Even so, integrating these methods improves the model’s capability to solve complex problems. A novel enhanced prediction method based on COOT bird optimization was developed for selecting the optimal parameters of ANFIS in the current study. This method combines COOT optimization with ANFIS to model the quality of service (QoS) characteristics of web services by using the adaptive neuro-fuzzy inference system COOT (ANFIS-COOT). In this instance, the quality of the web service (QWS) dataset was obtained from the GitHub database, which consists of 120 web services data, and then evaluated using the presented model on the dataset for estimating response time and throughput of web services. As significant evidence of ANFIS-COOT’s efficiency, the similar QWS data set is analyzed using four different prediction models: ANFIS, ANFIS-Beetle Antennae Search (ANFIS-BAS), ANFIS-Reptile Search Algorithm (ANFIS-RSA), and ANFIS-Snake Optimizer (ANFIS-SO). Moreover, the exploratory study used statistical benchmarks such as root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and determination coefficient (<inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula>) to emphasize the accuracy of the proposed model. Based on analysis results, the presented model achieved optimal values of RMSE (59.7473), MAE (15.8531), MAPE (0.0705), and <inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula> of 96.32 %, as well as RMSE (1.335), MAE (1.1255), MAPE (0.1818), and <inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula> of 97.12 % for modelling response time and throughput of web services, compared to other models. Eventually, this report demonstrates the viability of the ANFIS-COOT while tackling a complex problem and improving predictive performance.
Sujit Bebortta, Subhranshu Sekhar Tripathy, Shakila Basheer, and Chiranji Lal Chowdhary
MDPI AG
In contemporary healthcare, the prediction and identification of cardiac diseases is crucial. By leveraging the capabilities of Internet of Things (IoT)-enabled devices and Electronic Health Records (EHRs), the healthcare sector can largely benefit to improve patient outcomes by increasing the accuracy of disease prediction. However, protecting data privacy is essential to promote participation and adhere to rules. The suggested methodology combines EHRs with IoT-generated health data to predict heart disease. For its capacity to manage high-dimensional data and choose pertinent features, a soft-margin L1-regularised Support Vector Machine (sSVM) classifier is used. The large-scale sSVM problem is successfully solved using the cluster primal–dual splitting algorithm, which improves computational complexity and scalability. The integration of federated learning provides a cooperative predictive analytics methodology that upholds data privacy. The use of a federated learning framework in this study, with a focus on peer-to-peer applications, is crucial for enabling collaborative predictive modeling while protecting the confidentiality of each participant’s private medical information.
Basanta Kumar Swain, Chiranji Lal Chowdhary, and Rakesh Gain
IGI Global
Sign language recognition is a worldwide concern across the globe. The use of technology has a scope in aiding the necessary help in the recognition of sign language. The major challenge lies in detecting and understanding signs, as the language differs across the various geographical regions, and there are no specific rules for understanding them. Hence, this research article uses a transfer learning algorithm with TensorFlow object detection to recognize Indian sign language. The proposed model has achieved an accuracy of around 97.87% for different types of sentences used in the experimentation. The main advantage of the proposed model is that it is feasible to identify Indian sign language and produce the corresponding voice output using speech synthesis system. The system is helpful to the deaf and dumb community's society and encourages such people's upliftment.
Harpreet Kaur Channi and Chiranji Lal Chowdhary
IGI Global
Quantum computing might accelerate diagnosis, personalize treatment, and optimize prices in healthcare. Quantum-enhanced machine learning is important. Quantum Computing and Healthcare are innovative partnerships. The healthcare sector advances with new technologies. Quantum computing was bound to revolutionize healthcare. With Quantum technology on the rise, a new age of computing is coming. Quantum technology and mechanics is an abstract technical subject, yet it might revolutionize healthcare and other sectors. Quantum computing is real. Quantum has great promise in healthcare. AI and other technologies are also significant in healthcare. Such technologies improve healthcare treatments, diagnoses, and assistance. Quantum Computing intends to change healthcare. Personalized healthcare hinges on genomes, physiology, and pharmacokinetics. Thus, more clinical data must be processed. Quantum Computing is the solution. This article explains quantum computing's influence on healthcare and its uses.
Harpreet Kaur Channi and Chiranji Lal Chowdhary
IGI Global
Numerous industries, including e-healthcare, are capitalizing on and using blockchain and internet of things (IoT) technology. IoT devices may collect patient vitals and other sensory information in real-time, which medical professionals can then examine. All information gathered from the internet of things is stored, processed, and computed in one place. Such concentration raises concerns since it increases the likelihood of a catastrophic failure, distrust, tampering with data, and even the circumvention of privacy protections. By offering decentralized processing and storage for IoT data, blockchain has the potential to address these critical issues. As a result, designing a decentralized IoT-based e-healthcare system that incorporates IoT and blockchain technology might be a viable option. First, the authors provide some context about blockchain in this essay. The viability of blockchain systems for the internet of things-based e-healthcare is then assessed.
Sabrina Manickam, Laasya Yarlagadda, Shynu Padinjappurathu Gopalan, and Chiranji Lal Chowdhary
Institute of Electrical and Electronics Engineers (IEEE)
Digital Twins possess the capability to create virtual representations of a device’s components and dynamics. They transcend static images or blueprints, offering intricate models that reveal the entire lifecycle of system design, construction, and operation. Digital Twins now spearhead the virtual revolution, equipped to faithfully replicate each component through sensor-driven data collection. This replication aids in informed decision-making, monitoring complex systems, and validating novel products and services. Numerous companies already leverage digital twins within these domains to detect issues and enhance productivity. Conversely, accurate data collection and analysis from digital twins can pose challenges, potentially introducing ambiguity in decision-making and complicating object lifecycle management. Consequently, ongoing debates and discussions revolve around the fundamental concepts, frameworks, and technologies of digital twins. In this work, we delve into the realm of Industrial Applications of Digital Twins, exploring their merits and limitations.
Sandeep Kumar Sharma, Vijay Shankar Sharma, Shakila Basheer, Amit Chaurasia, and Chiranji Lal Chowdhary
Institute of Electrical and Electronics Engineers (IEEE)
Object formation is imperative to the recent computer vision, pattern recognition, healthcare, and automation applications. The objects are generated from images by defining edges and the segmentation process. This article introduced a novel method, Outer Totality Cellular Automata (OTCA), for defining actual and continuous edges of the image objects. The OTCA analysis nearby 25 neighbourhood pixels of all the pixels and generate a unique and efficient threshold. The proposed method has three primary functions, i.e. vitality, rule mapping, and improved morphological functions. The key objectives are image smoothing, neighbourhood analysis, defining game of life rule, and edges smoothing. Notably, the proposed method aimed to segment different coloured images, i.e., RGB, HSV, and YUV. The proposed method also aimed to produce more truthful results on blurred, reflected, shaded night vision images. The experimental process demonstrates using standard open-source datasets and validated using image quality assessment parameters, i.e., entropy, PSNR, SSIM, and MSE. The results claim 3% – 12% more structural analogous, factual, and accurate than existing classical methods and recent searches.
Sandeep Kumar Sharma, Amit Chaurasia, Vijay Shankar Sharma, Chiranji Lal Chowdhary, and Shakila Basheer
Institute of Electrical and Electronics Engineers (IEEE)
Resource selection, sharing, and aggregation are the key functions of grid computing. However, managing the resources in a grid-based environment is a stimulating task. It is necessary to update the topographical dispersal of the resources possessed by the various organisations with proper load distribution, and availability patterns. Different types of Users and servers have specific objectives and needs that could be achieved using a grid environment. This article suggests a cost-effective efficient framework for resource management in grid computing to look at and address the resource management difficulties. The proposed framework has three main functions, which help in grid construction, load balancing, and resource allocation. A Genetic engineering approach has been implemented to establish a relationship between the resource pool and the jobs of the nodes that improve resource utilization. The proposed methodology also optimizes the overall cost by minimizing turnaround time. The results of the proposed research are compared with commonly used algorithms and claim 1.5 to 10% better results.
M. Lawanya Shri, E. Gangadevi, K. Santhi, and Chiranji Lal Chowdhary
Apple Academic Press
Mathew D. A. Steve, Shree N. Durga, and Lal Chowdhary Chiranji
International Hellenic University
Devika Menon, Bharath Anand, and Chiranji Lal Chowdhary
Institute of Electrical and Electronics Engineers (IEEE)
The potential of digital twin technology to generate virtual models and simulations of real assets and processes has contributed to the widespread adoption of this technology across a variety of business sectors. As a result, performance, cost savings, and overall efficiency have all seen significant improvements. By conducting a study of the academic literature and previous research, this article offers readers an introduction to the origins, evolution, and applications of digital twin technology. This paper looks at the different kinds of digital twins, the advantages, and disadvantages of using them, and the causes that have contributed to their rising popularity. Case examples illustrating effective implementations of digital twin technology in industry and healthcare are included in the article. An overview of digital twin technology and its prospective applications in several industries is provided in this paper. This paper intends to contribute to the current understanding of digital twin technology and its potential impact by discussing the advantages, limitations, and prospects for further study and development.
Aditi Sharma, Vishal Goar, Manoj Kuri, and Chiranji Lal Chowdhary
Springer Nature Singapore
Saksham Arora, Pranav Gupta, Vishal Goar, Manoj Kuri, Harpreet Kaur Channi, and Chiranji Lal Chowdhary
Springer Nature Singapore
Amit Chaurasia, Vijay Shankar Sharma, Chiranji Lal Chowdhary, Shakila Basheer, and Thippa Reddy Gadekallu
Institute of Electrical and Electronics Engineers (IEEE)
Networks-on-Chip (NoCs) provides a packet-based communication model for the System-on-Chip (SoC) architecture to achieve objectives of lower power, higher performance and optimized area. To evaluate NoC performance and explore architectural design options, synthetic traffic models provide better solution in terms of simulation flexibility and faster simulation. In this synthetic traffic, models are generated for the simulation to optimize the computational resources requirements which will be placed inside NoC’s architecture before the early design process. In this paper, Wavelet-based Rosenblatt synthetic traffic [RST] is designed and examined which is a non-Gaussian process based on the $2^{nd}$ -order Hermite Process. The proposed traffic is applied to SPLASH-2 benchmarks and compared with Gaussian and Non-Gaussian traffic on the parameters of latency, power and buffer-loss. We applied the synthetic traffic on multicore architecture to capture parameters which would be helpful for network designers to choose optimized network resources during the early design architecture. We demonstrate our traffic model: first, how it can be used to describe and acquire non-gaussian burstier traffic on NoC; second, how it can be used to produce synthetic traffic traces that can drive exploration of the early design space for NoCs. Our traffic model helps the chip network designer to choose optimized queue storage inside the router in early design process.
Sujit Bebortta, Subhranshu Sekhar Tripathy, Shakila Basheer, and Chiranji Lal Chowdhary
Institute of Electrical and Electronics Engineers (IEEE)
Basanta Kumar Swain, Mohammad Zubair Khan, Chiranji Lal Chowdhary, and Abdullah Alsaeedi
Computers, Materials and Continua (Tech Science Press)
N. Rajagopal Reddy, Mohammad Zubair Khan, S. Sharief Basha, Abdulrahman Alahmadi, Ahmed H. Alahmadi, and Chiranji Lal Chowdhary
Computers, Materials and Continua (Tech Science Press)
Decision-making (DM) is a process in which several persons concurrently engage, examine the problems, evaluate potential alternatives, and select an appropriate option to the problem. Technique for determining order preference by similarity to the ideal solution (TOPSIS) is an established DM process. The objective of this report happens to broaden the approach of TOPSIS to solve the DM issues designed with Hesitancy fuzzy data, in which evaluation evidence given by the experts on possible solutions is presents as Hesitancy fuzzy decision matrices, each of which is defined by Hesitancy fuzzy numbers. Findings: we represent analytical results, such as designing a satellite communication network and assessing reservoir operation methods, to demonstrate that our suggested thoughts may be used in DM. Aim: We studied a new testing method for the artificial communication system to give proof of the future construction of satellite earth stations. We aim to identify the best one from the different testing places. We are also finding the best operation schemes in the reservoir. In this article, we present the concepts of Laplacian energy (LE) in Hesitancy fuzzy graphs (HFGs), the weight function of LE of HFGs, and the TOPSIS method technique is used to produce the hesitancy fuzzy weighted-average (HFWA). Also, consider practical examples to illustrate the applicability of the finest design of satellite communication systems and also evaluation of reservoir schemes.
Yusera Farooq Khan, Baijnath Kaushik, Chiranji Lal Chowdhary, and Gautam Srivastava
MDPI AG
Alzheimer’s is one of the fast-growing diseases among people worldwide leading to brain atrophy. Neuroimaging reveals extensive information about the brain’s anatomy and enables the identification of diagnostic features. Artificial intelligence (AI) in neuroimaging has the potential to significantly enhance the treatment process for Alzheimer’s disease (AD). The objective of this study is two-fold: (1) to compare existing Machine Learning (ML) algorithms for the classification of AD. (2) To propose an effective ensemble-based model for the same and to perform its comparative analysis. In this study, data from the Alzheimer’s Diseases Neuroimaging Initiative (ADNI), an online repository, is utilized for experimentation consisting of 2125 neuroimages of Alzheimer’s disease (n = 975), mild cognitive impairment (n = 538) and cognitive normal (n = 612). For classification, the framework incorporates a Decision Tree (DT), Random Forest (RF), Naïve Bayes (NB), and K-Nearest Neighbor (K-NN) followed by some variations of Support Vector Machine (SVM), such as SVM (RBF kernel), SVM (Polynomial Kernel), and SVM (Sigmoid kernel), as well as Gradient Boost (GB), Extreme Gradient Boosting (XGB) and Multi-layer Perceptron Neural Network (MLP-NN). Afterwards, an Ensemble Based Generic Kernel is presented where Master-Slave architecture is combined to attain better performance. The proposed model is an ensemble of Extreme Gradient Boosting, Decision Tree and SVM_Polynomial kernel (XGB + DT + SVM). At last, the proposed method is evaluated using cross-validation using statistical techniques along with other ML models. The presented ensemble model (XGB + DT + SVM) outperformed existing state-of-the-art algorithms with an accuracy of 89.77%. The efficiency of all the models was optimized using Grid-based tuning, and the results obtained after such process showed significant improvement. XGB + DT + SVM with optimized parameters outperformed all other models with an efficiency of 95.75%. The implication of the proposed ensemble-based learning approach clearly shows the best results compared to other ML models. This experimental comparative analysis improved understanding of the above-defined methods and enhanced their scope and significance in the early detection of Alzheimer’s disease.
Akshat Mishra, Swetank Kaushik, Srinivasa Perumal R., and Chiranji Lal Chowdhary
IGI Global
The notion of agile supply chains is gaining traction in academia and has been enthusiastically adopted by private corporations. A variety of factors differentiate agile supply networks. They should not only be network-based but also market-sensitive, with tightly linked virtual and crucial operations. If agile supply chains are to adapt for ever-faster turnaround time towards both volume and variety changes, they must integrate supply and demand. The agile supply chain must be able to swiftly modify the output to satisfy customer needs and move from one version to the next. Of course, information technology is essential to the smooth running of agile teams. However, this chapter will focus on two additional essential facilitators of supply chains. Agility, which has gotten less emphasis yet is vital to the success of these kinds of procedures, has gotten less attention.