K. Gowsic
K. Gowsic has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- P. Vijayalakshmi
Department of Computer Science and Engineering, Knowledge Institute of Technology, Salem, India
3 shared publications - K. Selvi
Department of IT, Paavai Engineering College, Pachal, Namakkal, India
2 shared publications Siranjeevi S
Department of Computer Science and Engineering, Mahendra Engineering College, Tamil Nadu, India
2 shared publications- K. Muthumanickam
Department of Information Technology, Kongunadu College of Engineering and Technology, Tholurpatti, India
1 shared publication Mohammed Farook R
UG Students, Department of Computer Science and Engineering, Mahendra Engineering College
1 shared publicationMugunthan S
UG Students, Department of Computer Science and Engineering, Mahendra Engineering College
1 shared publication
Latest Publications
- Open Access
- 31 May 2024
- Published by Granthaalayah Publications and Printers in ShodhKosh: Journal of Visual and Performing Arts
- Vol. 5 (5)
THEFT DETECTION WITH CRIMINAL IDENTIFICATION USING MACHINE LEARNING
One of the main goals of video surveillance research and practical implementations is abnormal event detection. In order to improve public safety, the usage of surveillance cameras in public spaces—such as roadways, crosswalks, banks, retail centers, etc.—is expanding. One of the most important tasks in video surveillance is the detection of anomalous occurrences, such as criminal activity, traffic accidents, or crimes. In general, abnormal events are rare in comparison to normal activities. A useful anomaly detection system aims to pinpoint the anomaly's temporal range and instantly notify users when any behavior deviates from expected norms. Consequently, it is possible to think of anomaly identification as coarse-grained video knowledge that separates anomalies from regular patterns. Classification techniques can be used to further categories an anomaly into one of the specific activities once it has been recognized. An overview of anomaly detection is provided in this work, with a particular emphasis on applications in banking operations. Banking operations involve a wide range of daily, weekly, and monthly tasks and exchanges carried out by or impacting several parties, including staff members, clients, debtors, and outside organizations. Events could develop gradually, and early identification greatly reduces the likelihood of negative consequences and, in certain situations, even completely prevents them. Finding people at unfavorable periods is accomplished using anomaly detection based on time series. This research offers a machine learning based anomaly detection technique to discriminate between normal and abnormal occurrences. A comparison is made between the biometric identity of the captured face and the biometric identities of known criminals. If a match is found, we can identify and capture the culprit right away.
- 31 May 2024
- Published by Granthaalayah Publications and Printers in ShodhKosh: Journal of Visual and Performing Arts
- Vol. 5 (5)
Open AccessTHEFT DETECTION WITH CRIMINAL IDENTIFICATION USING MACHINE LEARNING
One of the main goals of video surveillance research and practical implementations is abnormal event detection. In order to improve public safety, the usage of surveillance cameras in public spaces—such as roadways, crosswalks, banks, retail centers, etc.—is expanding. One of the most important tasks in video surveillance is the detection of anomalous occurrences, such as criminal activity, traffic accidents, or crimes. In general, abnormal events are rare in comparison to normal activities. A useful anomaly detection system aims to pinpoint the anomaly's temporal range and instantly notify users when any behavior deviates from expected norms. Consequently, it is possible to think of anomaly identification as coarse-grained video knowledge that separates anomalies from regular patterns. Classification techniques can be used to further categories an anomaly into one of the specific activities once it has been recognized. An overview of anomaly detection is provided in this work, with a particular emphasis on applications in banking operations. Banking operations involve a wide range of daily, weekly, and monthly tasks and exchanges carried out by or impacting several parties, including staff members, clients, debtors, and outside organizations. Events could develop gradually, and early identification greatly reduces the likelihood of negative consequences and, in certain situations, even completely prevents them. Finding people at unfavorable periods is accomplished using anomaly detection based on time series. This research offers a machine learning based anomaly detection technique to discriminate between normal and abnormal occurrences. A comparison is made between the biometric identity of the captured face and the biometric identities of known criminals. If a match is found, we can identify and capture the culprit right away.
- Open Access
- 31 May 2024
- Published by Granthaalayah Publications and Printers in ShodhKosh: Journal of Visual and Performing Arts
- Vol. 5 (5)
IMAGE FORGERY DETECTION USING CONVOLUTIONAL NEURAL NETWORK ALGORITHM
The validity of photos is being called into doubt because to the availability of strong image modification tools. This is particularly problematic where images hold significant influence, such as in legal proceedings, news articles, or insurance claims. The rapid advances in science and technology have made it easier than ever to access a wealth of knowledge through a range of multimedia platforms. However, because it is so easy to alter the contents using a variety of editing programs, the authenticity and integrity of multimedia content are in jeopardy. Forensics technology is being developed to address this issue. We focus on blind image forensics tools for copy-move forgeries in this survey. Copy-move forgeries are among the most used methods for manipulating images. They usually entail adding objects to the same image or covering them with flat regions. Image forensic techniques use a variety of complex procedures that have been documented in the literature to ascertain the integrity of a photograph. To conceal particular objects or provide the appearance of a duplicate, a section of an image is copied, then pasted back onto the original. One study concentrates on a specific type of image faking. Next, build the architecture for a convolutional neural network to determine whether or not the image is fake.
- 31 May 2024
- Published by Granthaalayah Publications and Printers in ShodhKosh: Journal of Visual and Performing Arts
- Vol. 5 (5)
Open AccessIMAGE FORGERY DETECTION USING CONVOLUTIONAL NEURAL NETWORK ALGORITHM
The validity of photos is being called into doubt because to the availability of strong image modification tools. This is particularly problematic where images hold significant influence, such as in legal proceedings, news articles, or insurance claims. The rapid advances in science and technology have made it easier than ever to access a wealth of knowledge through a range of multimedia platforms. However, because it is so easy to alter the contents using a variety of editing programs, the authenticity and integrity of multimedia content are in jeopardy. Forensics technology is being developed to address this issue. We focus on blind image forensics tools for copy-move forgeries in this survey. Copy-move forgeries are among the most used methods for manipulating images. They usually entail adding objects to the same image or covering them with flat regions. Image forensic techniques use a variety of complex procedures that have been documented in the literature to ascertain the integrity of a photograph. To conceal particular objects or provide the appearance of a duplicate, a section of an image is copied, then pasted back onto the original. One study concentrates on a specific type of image faking. Next, build the architecture for a convolutional neural network to determine whether or not the image is fake.
- Open Access
- 31 March 2024
- Published by Granthaalayah Publications and Printers in ShodhKosh: Journal of Visual and Performing Arts
- Vol. 5 (3) , 647–653
WEB SPOOFING DEFENSE EMPOWERING USERS WITH PHISHCATCHER'S MACHINE LEARNING
The threat of malicious URLs and websites poses a frequent and serious risk to online safety. Search engines naturally serve as the foundation of information management. However, the proliferation of fake websites on these platforms puts our users in grave danger. Many current methods for identifying rogue websites focus on specific attacks, leaving numerous websites unaffected by widely available blacklist-based browser updates. It's imperative to properly disguise any data leaving the client side, as the server cannot extract meaningful information from masked data. This paper proposes an initial Privacy-Preserving Secure Browsing (PPSB) service, offering robust security assurances lacking in existing Secure Browsing (SB) services. The suggested method utilizes blacklist storage to detect malicious URL access, employing SVM classification to analyze user-provided input URLs. SVM, a class of machine learning algorithm, reliably assesses the safety or riskiness of a URL while safeguarding user privacy, browsing history, and the proprietary information of the blacklist provider. The paper introduces a technique for encrypting critical data to protect user privacy from external analysts and service providers, while fully supporting selected aggregate functionalities for analyzing user online activities and ensuring differential privacy. The ABE Encryption method encrypts user behavior data, enhancing secure history access.
- 31 March 2024
- Published by Granthaalayah Publications and Printers in ShodhKosh: Journal of Visual and Performing Arts
- Vol. 5 (3) , 647–653
Open AccessWEB SPOOFING DEFENSE EMPOWERING USERS WITH PHISHCATCHER'S MACHINE LEARNING
The threat of malicious URLs and websites poses a frequent and serious risk to online safety. Search engines naturally serve as the foundation of information management. However, the proliferation of fake websites on these platforms puts our users in grave danger. Many current methods for identifying rogue websites focus on specific attacks, leaving numerous websites unaffected by widely available blacklist-based browser updates. It's imperative to properly disguise any data leaving the client side, as the server cannot extract meaningful information from masked data. This paper proposes an initial Privacy-Preserving Secure Browsing (PPSB) service, offering robust security assurances lacking in existing Secure Browsing (SB) services. The suggested method utilizes blacklist storage to detect malicious URL access, employing SVM classification to analyze user-provided input URLs. SVM, a class of machine learning algorithm, reliably assesses the safety or riskiness of a URL while safeguarding user privacy, browsing history, and the proprietary information of the blacklist provider. The paper introduces a technique for encrypting critical data to protect user privacy from external analysts and service providers, while fully supporting selected aggregate functionalities for analyzing user online activities and ensuring differential privacy. The ABE Encryption method encrypts user behavior data, enhancing secure history access.
- Open Access
- 31 January 2024
- Published by Granthaalayah Publications and Printers in ShodhKosh: Journal of Visual and Performing Arts
- Vol. 5 (1)
ENHANCED UNSUPERVISED K-MEANS CLUSTERING ALGORITHM
K-Means clustering is an unsupervised learning algorithm for distinguishing data into separate groups called clusters based on similarity. However, the need to specify the cluster count (K) beforehand highly affects the effectiveness of the algorithm, which can be challenging in practice. In our manuscript, we introduce an improved iteration of the K-Means algorithm, which incorporates the elbow method to autonomously identify the required number of clusters during the clustering procedure. Our approach also incorporates optimization techniques to improve computational efficiency. The experimental findings substantiate the efficacy of our refined algorithm in automatically identifying the precise count of clusters while reducing computational overhead compared to traditional methods.
- 31 January 2024
- Published by Granthaalayah Publications and Printers in ShodhKosh: Journal of Visual and Performing Arts
- Vol. 5 (1)
Open AccessENHANCED UNSUPERVISED K-MEANS CLUSTERING ALGORITHM
K-Means clustering is an unsupervised learning algorithm for distinguishing data into separate groups called clusters based on similarity. However, the need to specify the cluster count (K) beforehand highly affects the effectiveness of the algorithm, which can be challenging in practice. In our manuscript, we introduce an improved iteration of the K-Means algorithm, which incorporates the elbow method to autonomously identify the required number of clusters during the clustering procedure. Our approach also incorporates optimization techniques to improve computational efficiency. The experimental findings substantiate the efficacy of our refined algorithm in automatically identifying the precise count of clusters while reducing computational overhead compared to traditional methods.
- 3 November 2022
- Published by Springer Nature in Wireless Personal Communications
- Vol. 128 (4) , 2619-2636
A Random Waypoint Model for Route Avoidance with Zone Routing Protocol in Wireless Sensor Network
- 3 November 2022
- Published by Springer Nature in Wireless Personal Communications
- Vol. 128 (4) , 2619-2636
A Random Waypoint Model for Route Avoidance with Zone Routing Protocol in Wireless Sensor Network
- 15 July 2021
- Published by Springer Nature in Wireless Networks
- Vol. 27 (6) , 3845-3856
A misdirected route avoidance using random waypoint mobility model in wireless sensor network
- 15 July 2021
- Published by Springer Nature in Wireless Networks
- Vol. 27 (6) , 3845-3856
A misdirected route avoidance using random waypoint mobility model in wireless sensor network
- 11 March 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 119 (3) , 2725-2754
An Effective Traffic Management System Using Connected Dominating Set Forwarding (CDSF) Framework for Reducing Traffic Congestion in High Density VANETs
- 11 March 2021
- Published by Springer Nature in Wireless Personal Communications
- Vol. 119 (3) , 2725-2754
An Effective Traffic Management System Using Connected Dominating Set Forwarding (CDSF) Framework for Reducing Traffic Congestion in High Density VANETs