<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>DSpace Community:</title>
    <link>http://localhost:8080/xmlui/handle/123456789/3792</link>
    <description />
    <pubDate>Tue, 23 Jun 2026 07:39:13 GMT</pubDate>
    <dc:date>2026-06-23T07:39:13Z</dc:date>
    <item>
      <title>EMERGING AI-ENABLED SECURITY FOR INDUSTRY 4.0</title>
      <link>http://localhost:8080/xmlui/handle/123456789/3802</link>
      <description>Title: 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&#xD;
interconnected devices and systems heightens their exposure to cyber-attacks and security breaches. For solving&#xD;
such problems or to overcome such problems, combining AI with cybersecurity is essential, because AI is mostly&#xD;
used for analyzing the huge amount of data from sensors and devices to detect and prevent cyber threats. The use&#xD;
of Machine Learning algorithms is crucial for recognizing regular behavioral patterns and detecting any&#xD;
deviations that may indicate potential security threats. Anomaly detection, predictive analysis and Intrusion&#xD;
detection are the various techniques that are used in combination with cybersecurity measures i.e. intrusion&#xD;
detection system and firewalls for providing the best approach to cybersecurity for Industry applications.&#xD;
Additionally, the ideal AI-driven cybersecurity solution integrates advanced technologies for real-time anomaly&#xD;
detection and comprehensive security response, ensuring proactive protection against evolving cyber threats.&#xD;
Moreover, it seamlessly integrates with existing security infrastructure, enhancing overall security posture and&#xD;
facilitating a unified approach to threat detection and response. The main aim to use AI with cybersecurity for&#xD;
industry application is to reduce the increasing cyber-attacks.</description>
      <pubDate>Tue, 05 Dec 2023 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">http://localhost:8080/xmlui/handle/123456789/3802</guid>
      <dc:date>2023-12-05T00:00:00Z</dc:date>
    </item>
    <item>
      <title>Ramrajya in Kaliyug: Finding the Inner Ram with Modern Astra</title>
      <link>http://localhost:8080/xmlui/handle/123456789/3800</link>
      <description>Title: Ramrajya in Kaliyug: Finding the Inner Ram with Modern Astra</description>
      <pubDate>Wed, 15 Nov 2023 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">http://localhost:8080/xmlui/handle/123456789/3800</guid>
      <dc:date>2023-11-15T00:00:00Z</dc:date>
    </item>
    <item>
      <title>Review on ML for recognition of Chat - GPT generated text</title>
      <link>http://localhost:8080/xmlui/handle/123456789/3798</link>
      <description>Title: Review on ML for recognition of Chat - GPT generated text
Authors: Dixit, Ishan Swapnil; Rakibe, Priya</description>
      <pubDate>Mon, 15 Jan 2024 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">http://localhost:8080/xmlui/handle/123456789/3798</guid>
      <dc:date>2024-01-15T00:00:00Z</dc:date>
    </item>
    <item>
      <title>Combining Multiple Feature Extraction and Classification Methods to Study Performance of Handwritten Sanskrit Character Recognition</title>
      <link>http://localhost:8080/xmlui/handle/123456789/3795</link>
      <description>Title: 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&#xD;
found to be one of the most challenging research topics. The&#xD;
Sanskrit language is written using the Devanagari Script. In&#xD;
this paper, we implemented novel algorithm to recognize&#xD;
handwritten characters using four different feature extraction&#xD;
methods, resizing the image, Canny Edge detection, Hybrid&#xD;
Discrete Wavelet-Discrete Cosine Transform (DWT-DCT),&#xD;
Histogram of oriented Gradients (HOG). Classification is done&#xD;
by using support vector machine with cubic kenrel and neural&#xD;
network with ReLU activation function. When features are&#xD;
extracted by HOG, the SVM provides classification accuracy of&#xD;
97.10% while the neural network provides 91.40%. SVM has&#xD;
been found to provide superior classification than neural&#xD;
networks for all feature extraction strategies.</description>
      <pubDate>Fri, 18 Aug 2023 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">http://localhost:8080/xmlui/handle/123456789/3795</guid>
      <dc:date>2023-08-18T00:00:00Z</dc:date>
    </item>
  </channel>
</rss>

