arXiv subjects

Kathiravan Srinivasan

Publications and source records attributed to Kathiravan Srinivasan.

5 recordsLinked to original sources

arXiv2026

Quantum inspired qubit qutrit neural networks for real time financial forecasting

This research investigates the performance and efficacy of machine learning models in stock prediction, comparing Artificial Neural Networks (ANNs), Quantum Qubit-based Neural Networks (QQBNs), and Quantum Qutrit-based Neural Networks (QQTNs). By outlining methodologies, architectures, and training procedures, the study highlights significant differences in training times and performance metrics across models. While all models demonstrate robust accuracies above 70%, the Quantum Qutrit-based Neural Network consistently outperforms with advantages in risk-adjusted returns, measured by the Sharpe ratio, greater consistency in prediction quality through the Information Coefficient, and enhanced robustness under varying market conditions. The QQTN not only surpasses its classical and qubit-based counterparts in multiple quantitative and qualitative metrics but also achieves comparable performance with significantly reduced training times. These results showcase the promising prospects of Quantum Qutrit-based Neural Networks in practical financial applications, where real-time processing is critical. By achieving superior accuracy, efficiency, and adaptability, the proposed models underscore the transformative potential of quantum-inspired approaches, paving the way for their integration into computationally intensive fields.

cs.AI↗

arXiv2022

Early Diagnosis of Retinal Blood Vessel Damage via Deep Learning-Powered Collective Intelligence Models

Early diagnosis of retinal diseases such as diabetic retinopathy has had the attention of many researchers. Deep learning through the introduction of convolutional neural networks has become a prominent solution for image-related tasks such as classification and segmentation. Most tasks in image classification are handled by deep CNNs pretrained and evaluated on imagenet dataset. However, these models do not always translate to the best result on other datasets. Devising a neural network manually from scratch based on heuristics may not lead to an optimal model as there are numerous hyperparameters in play. In this paper, we use two nature-inspired swarm algorithms: particle swarm optimization (PSO) and ant colony optimization (ACO) to obtain TDCN models to perform classification of fundus images into severity classes. The power of swarm algorithms is used to search for various combinations of convolutional, pooling, and normalization layers to provide the best model for the task. It is observed that TDCN-PSO outperforms imagenet models and existing literature, while TDCN-ACO achieves faster architecture search. The best TDCN model achieves an accuracy of 90.3%, AUC ROC of 0.956, and a Cohen kappa score of 0.967. The results were compared with the previous studies to show that the proposed TDCN models exhibit superior performance.

eess.IV↗

arXiv2018

NHAD: Neuro-Fuzzy Based Horizontal Anomaly Detection In Online Social Networks

Use of social network is the basic functionality of today's life. With the advent of more and more online social media, the information available and its utilization have come under the threat of several anomalies. Anomalies are the major cause of online frauds which allow information access by unauthorized users as well as information forging. One of the anomalies that act as a silent attacker is the horizontal anomaly. These are the anomalies caused by a user because of his/her variable behaviour towards different sources. Horizontal anomalies are difficult to detect and hazardous for any network. In this paper, a self-healing neuro-fuzzy approach (NHAD) is used for the detection, recovery, and removal of horizontal anomalies efficiently and accurately. The proposed approach operates over the five paradigms, namely, missing links, reputation gain, significant difference, trust properties, and trust score. The proposed approach is evaluated with three datasets: DARPA'98 benchmark dataset, synthetic dataset, and real-time traffic. Results show that the accuracy of the proposed NHAD model for 10% to 30% anomalies in synthetic dataset ranges between 98.08% and 99.88%. The evaluation over DARPA'98 dataset demonstrates that the proposed approach is better than the existing solutions as it provides 99.97% detection rate for anomalous class. For real-time traffic, the proposed NHAD model operates with an average accuracy of 99.42% at 99.90% detection rate.

cs.NI↗

arXiv2018

QoS-Aware Routing in Wireless Networks Using Aerial Vehicles

The next generation wireless networks need efficient mechanisms for data dissemination that should support users with better Quality of Service (QoS). Nevertheless, the existing solutions are unable to handle this demand and require either network redeployment or replanning. Moreover, this upsurges the overall operational cost and complexity of the network. This problem can be addressed by deploying Unmanned Aerial Vehicles (UAVs), which can act as on-demand relays in next generation wireless networks. In this work, a novel strategy comprising a series of algorithms based on neural networks is devised, which resolves the issues related to data dissemination, QoS, capacity, and coverage. When compared with the existing methods, the proposed approach demonstrates better outcomes for various parameters, namely, throughput, message disseminations, service dissemination rate, UAV allocation time, route acquisition delay, link utilization and signal to noise ratio for end users. The experimental results exhibit the fact that the proposed approach utilizes 39.6%, 41.6%, 43.5%, 44.4%, and 46.9% lesser iterations than the EEDD, A-Star, OCD, GPCR, and GyTAR, respectively. Therefore, it is evident that the proposed approach surpasses the existing methods by means of superior performance and augmented efficiency.

cs.NI↗

arXiv2017

Managing Service-Heterogeneity using Osmotic Computing

Computational resource provisioning that is closer to a user is becoming increasingly important, with a rise in the number of devices making continuous service requests and with the significant recent take up of latency-sensitive applications, such as streaming and real-time data processing. Fog computing provides a solution to such types of applications by bridging the gap between the user and public/private cloud infrastructure via the inclusion of a "fog" layer. Such approach is capable of reducing the overall processing latency, but the issues of redundancy, cost-effectiveness in utilizing such computing infrastructure and handling services on the basis of a difference in their characteristics remain. This difference in characteristics of services because of variations in the requirement of computational resources and processes is termed as service heterogeneity. A potential solution to these issues is the use of Osmotic Computing -- a recently introduced paradigm that allows division of services on the basis of their resource usage, based on parameters such as energy, load, processing time on a data center vs. a network edge resource. Service provisioning can then be divided across different layers of a computational infrastructure, from edge devices, in-transit nodes, and a data center, and supported through an Osmotic software layer. In this paper, a fitness-based Osmosis algorithm is proposed to provide support for osmotic computing by making more effective use of existing Fog server resources. The proposed approach is capable of efficiently distributing and allocating services by following the principle of osmosis. The results are presented using numerical simulations demonstrating gains in terms of lower allocation time and a higher probability of services being handled with high resource utilization.

cs.DC↗