DSpace Community:http://localhost:8080/xmlui/handle/123456789/37922026-06-23T06:31:49Z2026-06-23T06:31:49ZEMERGING AI-ENABLED SECURITY FOR INDUSTRY 4.0Dabbe, ChetanRakibe, PriyaAgarwal, NimishBarhate, BhaveshChoudhari, RuchaPawar, Sakshihttp://localhost:8080/xmlui/handle/123456789/38022025-06-12T08:23:42Z2023-12-05T00:00:00ZTitle: EMERGING AI-ENABLED SECURITY FOR INDUSTRY 4.0
Authors: Dabbe, Chetan; Rakibe, Priya; Agarwal, Nimish; Barhate, Bhavesh; Choudhari, Rucha; Pawar, Sakshi
Abstract: In the world of industry, where everything is going to be connected and automated. The expanding network of
interconnected devices and systems heightens their exposure to cyber-attacks and security breaches. For solving
such problems or to overcome such problems, combining AI with cybersecurity is essential, because AI is mostly
used for analyzing the huge amount of data from sensors and devices to detect and prevent cyber threats. The use
of Machine Learning algorithms is crucial for recognizing regular behavioral patterns and detecting any
deviations that may indicate potential security threats. Anomaly detection, predictive analysis and Intrusion
detection are the various techniques that are used in combination with cybersecurity measures i.e. intrusion
detection system and firewalls for providing the best approach to cybersecurity for Industry applications.
Additionally, the ideal AI-driven cybersecurity solution integrates advanced technologies for real-time anomaly
detection and comprehensive security response, ensuring proactive protection against evolving cyber threats.
Moreover, it seamlessly integrates with existing security infrastructure, enhancing overall security posture and
facilitating a unified approach to threat detection and response. The main aim to use AI with cybersecurity for
industry application is to reduce the increasing cyber-attacks.2023-12-05T00:00:00ZRamrajya in Kaliyug: Finding the Inner Ram with Modern Astrahttp://localhost:8080/xmlui/handle/123456789/38002025-06-12T08:18:36Z2023-11-15T00:00:00ZTitle: Ramrajya in Kaliyug: Finding the Inner Ram with Modern Astra2023-11-15T00:00:00ZReview on ML for recognition of Chat - GPT generated textDixit, Ishan SwapnilRakibe, Priyahttp://localhost:8080/xmlui/handle/123456789/37982025-06-12T08:15:30Z2024-01-15T00:00:00ZTitle: Review on ML for recognition of Chat - GPT generated text
Authors: Dixit, Ishan Swapnil; Rakibe, Priya2024-01-15T00:00:00ZCombining Multiple Feature Extraction and Classification Methods to Study Performance of Handwritten Sanskrit Character RecognitionShelke, Shraddha VChandwadkar, D.M.Ugale, S. P.http://localhost:8080/xmlui/handle/123456789/37952025-06-12T07:58:47Z2023-08-18T00:00:00ZTitle: Combining Multiple Feature Extraction and Classification Methods to Study Performance of Handwritten Sanskrit Character Recognition
Authors: Shelke, Shraddha V; Chandwadkar, D.M.; Ugale, S. P.
Abstract: The recognition of Sanskrit handwriting has been
found to be one of the most challenging research topics. The
Sanskrit language is written using the Devanagari Script. In
this paper, we implemented novel algorithm to recognize
handwritten characters using four different feature extraction
methods, resizing the image, Canny Edge detection, Hybrid
Discrete Wavelet-Discrete Cosine Transform (DWT-DCT),
Histogram of oriented Gradients (HOG). Classification is done
by using support vector machine with cubic kenrel and neural
network with ReLU activation function. When features are
extracted by HOG, the SVM provides classification accuracy of
97.10% while the neural network provides 91.40%. SVM has
been found to provide superior classification than neural
networks for all feature extraction strategies.2023-08-18T00:00:00Z