Chitrakala Sakthivel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chitrakala Sakthivel has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Kumaran Pazhamalai
Department of Computer Science and Engineering, National Institute of Technology Puducherry, Karaikal, India
6 shared publications N. Moratanch
College of Engineering, Anna University
3 shared publicationsR. Priyatharshini
3 shared publications- Bharathi U
Department of Computer Science and Engineering, College of Engineering, Anna University, Guindy, Chennai, India
2 shared publications K. Aishwaryameenakshi
Department of Computer Science and Engineering, Easwari Engineering College, Chennai, India
2 shared publications- Kalaivani Anbarasan
Rajalakshmi Engineering College
2 shared publications
Latest Publications
- Open Access
- 8 May 2026
- Published by MDPI AG in Journal of Theoretical and Applied Electronic Commerce Research
- Vol. 21 (5) , 147
NFT-TRUST: Trust-Aware Social Signal Modeling for NFT Valuation Support in Electronic Commerce
Social media platforms such as X (formerly Twitter) increasingly shape attention formation, market visibility, and value signaling in electronic commerce, particularly in emerging digital asset markets such as Non-Fungible Tokens (NFTs). Prior work shows that social engagement correlates with NFT prices, suggesting its potential for valuation support. However, open social platforms exhibit heterogeneous user credibility, automated activity, and coordinated promotion, which can distort engagement-based inference. To address these challenges, we propose NFT-TRUST, a trust-aware social signal modeling framework that transforms raw engagement into credibility- and integrity-aware indicators for robust valuation support under manipulation-prone conditions. The framework integrates three components: (i) Credibility-Weighted Social Signal Aggregation (CW-SSA), (ii) Engagement Disproportionality Detection (EDD), and (iii) Integrity-Aware Signal Attenuation (IASA), which jointly reduce the influence of unreliable or manipulated signals while preserving informative engagement. Rather than estimating intrinsic NFT value from social signals alone, NFT-TRUST evaluates the reliability of social attention and converts it into trust-aware features. An XGBoost-based model is used to capture non-linear interactions among these features. Robustness is assessed through stress testing with RL-TweetGen-ST, a reinforcement learning–based synthetic tweet generator that simulates controlled engagement inflation. Experimental results show that NFT-TRUST achieves competitive predictive performance while demonstrating improved stability under simulated manipulation. Ablation analysis indicates that credibility and integrity components are complementary and jointly enhance the reliability of social-signal-based inference. Overall, this work advances trust-aware analytics in electronic commerce and supports more reliable social-driven valuation in emerging digital markets.
- 8 May 2026
- Published by MDPI AG in Journal of Theoretical and Applied Electronic Commerce Research
- Vol. 21 (5) , 147
Open AccessNFT-TRUST: Trust-Aware Social Signal Modeling for NFT Valuation Support in Electronic Commerce
Social media platforms such as X (formerly Twitter) increasingly shape attention formation, market visibility, and value signaling in electronic commerce, particularly in emerging digital asset markets such as Non-Fungible Tokens (NFTs). Prior work shows that social engagement correlates with NFT prices, suggesting its potential for valuation support. However, open social platforms exhibit heterogeneous user credibility, automated activity, and coordinated promotion, which can distort engagement-based inference. To address these challenges, we propose NFT-TRUST, a trust-aware social signal modeling framework that transforms raw engagement into credibility- and integrity-aware indicators for robust valuation support under manipulation-prone conditions. The framework integrates three components: (i) Credibility-Weighted Social Signal Aggregation (CW-SSA), (ii) Engagement Disproportionality Detection (EDD), and (iii) Integrity-Aware Signal Attenuation (IASA), which jointly reduce the influence of unreliable or manipulated signals while preserving informative engagement. Rather than estimating intrinsic NFT value from social signals alone, NFT-TRUST evaluates the reliability of social attention and converts it into trust-aware features. An XGBoost-based model is used to capture non-linear interactions among these features. Robustness is assessed through stress testing with RL-TweetGen-ST, a reinforcement learning–based synthetic tweet generator that simulates controlled engagement inflation. Experimental results show that NFT-TRUST achieves competitive predictive performance while demonstrating improved stability under simulated manipulation. Ablation analysis indicates that credibility and integrity components are complementary and jointly enhance the reliability of social-signal-based inference. Overall, this work advances trust-aware analytics in electronic commerce and supports more reliable social-driven valuation in emerging digital markets.
- Open Access
- 6 March 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1) , 115
ARE-GAN: Adaptive Regression and ROI-Enhanced Generative Adversarial Network for Alzheimer Disease Progression Prediction
- 6 March 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1) , 115
Open AccessARE-GAN: Adaptive Regression and ROI-Enhanced Generative Adversarial Network for Alzheimer Disease Progression Prediction
- Open Access
LEARNet: A Learning Entropy-Aware Representation Network for Educational Video Understanding
Educational videos contain long periods of visual redundancy, where only a few frames convey meaningful instructional information. Conventional video models, which are designed for dynamic scenes, often fail to capture these subtle pedagogical transitions. We introduce LEARNet, an entropy-aware framework that models educational video understanding as the extraction of high-information instructional content from low-entropy visual streams. LEARNet combines a Temporal Information Bottleneck (TIB) for selecting pedagogically significant keyframes with a Spatial–Semantic Decoder (SSD) that produces fine-grained annotations refined through a proposed Relational Consistency Verification Network (RCVN). This architecture enables the construction of EVUD-2M, a large-scale benchmark with multi-level semantic labels for diverse instructional formats. LEARNet achieves substantial redundancy reduction (70.2%) while maintaining high annotation fidelity (F1 = 0.89, mAP@50 = 0.88). Grounded in information-theoretic principles, LEARNet provides a scalable foundation for tasks such as lecture indexing, visual content summarization, and multimodal learning analytics.
Open AccessLEARNet: A Learning Entropy-Aware Representation Network for Educational Video Understanding
Educational videos contain long periods of visual redundancy, where only a few frames convey meaningful instructional information. Conventional video models, which are designed for dynamic scenes, often fail to capture these subtle pedagogical transitions. We introduce LEARNet, an entropy-aware framework that models educational video understanding as the extraction of high-information instructional content from low-entropy visual streams. LEARNet combines a Temporal Information Bottleneck (TIB) for selecting pedagogically significant keyframes with a Spatial–Semantic Decoder (SSD) that produces fine-grained annotations refined through a proposed Relational Consistency Verification Network (RCVN). This architecture enables the construction of EVUD-2M, a large-scale benchmark with multi-level semantic labels for diverse instructional formats. LEARNet achieves substantial redundancy reduction (70.2%) while maintaining high annotation fidelity (F1 = 0.89, mAP@50 = 0.88). Grounded in information-theoretic principles, LEARNet provides a scalable foundation for tasks such as lecture indexing, visual content summarization, and multimodal learning analytics.
- Open Access
Contextual Feature Fusion-Based Keyframe Selection Using Semantic Attention and Diversity-Aware Optimization for Video Summarization
Training-free video summarization tackles the challenge of selecting the most informative keyframes from a video without relying on costly training or complex deep models. This work introduces C2FVS-DPP (Contextual Feature Fusion Video Summarization with Determinantal Point Process), a lightweight framework that generates concise video summaries by jointly modeling semantic importance, visual diversity, temporal structure, and symmetry. The design centers on a symmetry-aware fusion strategy, where appearance, motion, and semantic cues are aligned in a unified embedding space, and on a reward-guided optimization logic that balances representativeness and diversity. Specifically, appearance features from ResNet-50, motion cues from optical flow, and semantic representations from BERT-encoded BLIP captions are fused into a contextual embedding. A Transformer encoder assigns importance scores, followed by shot boundary detection and K-Medoids clustering to identify candidate keyframes. These candidates are refined through a reward-based re-ranking mechanism that integrates semantic relevance, representativeness, and visual uniqueness, while a Determinantal Point Process (DPP) enforces globally diverse selection under a keyframe budget. To enable reliable evaluation, enhanced versions of the SumMe and TVSum50 datasets were curated to reduce redundancy and increase semantic density. On these curated benchmarks, C2FVS-DPP achieves F1-scores of 0.22 and 0.43 and fidelity scores of 0.16 and 0.40 on SumMe and TVSum50, respectively, surpassing existing models on both metrics. In terms of compression ratio, the framework records 0.9959 on SumMe and 0.9940 on TVSum50, remaining highly competitive with the best-reported values of 0.9981 and 0.9983. These results highlight the strength of C2FVS-DPP as an inference-driven, symmetry-aware, and resource-efficient solution for video summarization.
Open AccessContextual Feature Fusion-Based Keyframe Selection Using Semantic Attention and Diversity-Aware Optimization for Video Summarization
Training-free video summarization tackles the challenge of selecting the most informative keyframes from a video without relying on costly training or complex deep models. This work introduces C2FVS-DPP (Contextual Feature Fusion Video Summarization with Determinantal Point Process), a lightweight framework that generates concise video summaries by jointly modeling semantic importance, visual diversity, temporal structure, and symmetry. The design centers on a symmetry-aware fusion strategy, where appearance, motion, and semantic cues are aligned in a unified embedding space, and on a reward-guided optimization logic that balances representativeness and diversity. Specifically, appearance features from ResNet-50, motion cues from optical flow, and semantic representations from BERT-encoded BLIP captions are fused into a contextual embedding. A Transformer encoder assigns importance scores, followed by shot boundary detection and K-Medoids clustering to identify candidate keyframes. These candidates are refined through a reward-based re-ranking mechanism that integrates semantic relevance, representativeness, and visual uniqueness, while a Determinantal Point Process (DPP) enforces globally diverse selection under a keyframe budget. To enable reliable evaluation, enhanced versions of the SumMe and TVSum50 datasets were curated to reduce redundancy and increase semantic density. On these curated benchmarks, C2FVS-DPP achieves F1-scores of 0.22 and 0.43 and fidelity scores of 0.16 and 0.40 on SumMe and TVSum50, respectively, surpassing existing models on both metrics. In terms of compression ratio, the framework records 0.9959 on SumMe and 0.9940 on TVSum50, remaining highly competitive with the best-reported values of 0.9981 and 0.9983. These results highlight the strength of C2FVS-DPP as an inference-driven, symmetry-aware, and resource-efficient solution for video summarization.
- Open Access
- 26 August 2025
- Published by MDPI AG in Journal of Theoretical and Applied Electronic Commerce Research
- Vol. 20 (3) , 218
RL-TweetGen: A Socio-Technical Framework for Engagement-Optimized Short Text Generation in Digital Commerce Using Large Language Models and Reinforcement Learning
In the rapidly evolving landscape of digital marketing and electronic commerce, short-form content—particularly on platforms like Twitter (now X)—has become pivotal for real-time branding, community engagement, and product promotion. The rise of Non-Fungible Tokens (NFTs) and Web3 ecosystems further underscores the need for domain-specific, engagement-oriented social media content. However, automating the generation of such content while balancing linguistic quality, semantic relevance, and audience engagement remains a substantial challenge. To address this, we propose RL-TweetGen, a socio-technical framework that integrates instruction-tuned large language models (LLMs) with reinforcement learning (RL) to generate concise, impactful, and engagement-optimized tweets. The framework incorporates a structured pipeline comprising domain-specific data curation, semantic classification, and intent-aware prompt engineering, and leverages Parameter-Efficient Fine-Tuning (PEFT) with LoRA for scalable model adaptation. We fine-tuned and evaluated three LLMs—LLaMA-3.1-8B, Mistral-7B Instruct, and DeepSeek 7B Chat—guided by a hybrid reward function that blends XGBoost-predicted engagement scores with expert-in-the-loop feedback. To enhance lexical diversity and contextual alignment, we implemented advanced decoding strategies, including Tailored Beam Search, Enhanced Top-p Sampling, and Contextual Temperature Scaling. A case study focused on NFT-related tweet generation demonstrated the practical effectiveness of RL-TweetGen. Experimental results showed that Mistral-7B achieved the highest lexical fluency (BLEU: 0.2285), LLaMA-3.1 exhibited superior semantic precision (BERT-F1: 0.8155), while DeepSeek 7B provided balanced performance. Overall, RL-TweetGen presents a scalable and adaptive solution for marketers, content strategists, and Web3 platforms seeking to automate and optimize social media engagement. The framework advances the role of generative AI in digital commerce by aligning content generation with platform dynamics, user preferences, and marketing goals.
- 26 August 2025
- Published by MDPI AG in Journal of Theoretical and Applied Electronic Commerce Research
- Vol. 20 (3) , 218
Open AccessRL-TweetGen: A Socio-Technical Framework for Engagement-Optimized Short Text Generation in Digital Commerce Using Large Language Models and Reinforcement Learning
In the rapidly evolving landscape of digital marketing and electronic commerce, short-form content—particularly on platforms like Twitter (now X)—has become pivotal for real-time branding, community engagement, and product promotion. The rise of Non-Fungible Tokens (NFTs) and Web3 ecosystems further underscores the need for domain-specific, engagement-oriented social media content. However, automating the generation of such content while balancing linguistic quality, semantic relevance, and audience engagement remains a substantial challenge. To address this, we propose RL-TweetGen, a socio-technical framework that integrates instruction-tuned large language models (LLMs) with reinforcement learning (RL) to generate concise, impactful, and engagement-optimized tweets. The framework incorporates a structured pipeline comprising domain-specific data curation, semantic classification, and intent-aware prompt engineering, and leverages Parameter-Efficient Fine-Tuning (PEFT) with LoRA for scalable model adaptation. We fine-tuned and evaluated three LLMs—LLaMA-3.1-8B, Mistral-7B Instruct, and DeepSeek 7B Chat—guided by a hybrid reward function that blends XGBoost-predicted engagement scores with expert-in-the-loop feedback. To enhance lexical diversity and contextual alignment, we implemented advanced decoding strategies, including Tailored Beam Search, Enhanced Top-p Sampling, and Contextual Temperature Scaling. A case study focused on NFT-related tweet generation demonstrated the practical effectiveness of RL-TweetGen. Experimental results showed that Mistral-7B achieved the highest lexical fluency (BLEU: 0.2285), LLaMA-3.1 exhibited superior semantic precision (BERT-F1: 0.8155), while DeepSeek 7B provided balanced performance. Overall, RL-TweetGen presents a scalable and adaptive solution for marketers, content strategists, and Web3 platforms seeking to automate and optimize social media engagement. The framework advances the role of generative AI in digital commerce by aligning content generation with platform dynamics, user preferences, and marketing goals.
- Open Access
- 5 August 2025
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e3069
Multifeature fusion for claim scope-aware litigation risk prediction for patent drafts
The ‘claim scope’, or the ‘legal boundaries’ defined by patent claims, has been considered crucial for determining a patent’s value and its associated litigation risk. However, no direct claim semantics-based indicators currently exist to quantify patent claim scope, and existing scope measures are primarily indirect, which limits their ability to capture the semantic nuances of claim text. Additionally, the reliance on post-grant features restricts the applicability of existing litigation prediction models to patent drafts. These limitations complicate the patent drafting process, during which claims are formulated without feedback on scope and litigation risk. This often leads to suboptimal claim articulation, resulting in inadequate protection, increased legal vulnerabilities, or reduced patent grant probability. To address this gap, the hyponym tree score (HTS) is proposed as a novel indicator for quantifying claim scope by analysing hyponym counts, sentence structure, and dependency relations within patent claims. Building on this, early-stage litigation risk prediction has been achieved using a new deep learning model, the Multifeature BERT-Powered Fusion for Author-level Patent Litigation Risk Analysis (MAPRA). The MAPRA model restricts its input features to those available at early stages, such as indicators derived from claim text, inventor information, assignee details, and HTS, ensuring applicability to both draft-stage and granted patents. Despite excluding all post-grant or acquired data, MAPRA achieves a superior area under the receiver operating characteristic curve (AUC) of 0.878, outperforming the most comparable prior study, which reports an AUC of 0.822 using both early-stage and immediate post-grant features. By quantifying claim scope and enabling early-stage litigation risk prediction, this research offers a valuable screening tool for patent drafters, examiners, attorneys, and innovators. It supports informed decision-making during drafting and helps mitigate potential litigation risks. Furthermore, it lays a foundation for future research on claim scope modeling and the development of predictive tools for intellectual property litigation management.
- 5 August 2025
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e3069
Open AccessMultifeature fusion for claim scope-aware litigation risk prediction for patent drafts
The ‘claim scope’, or the ‘legal boundaries’ defined by patent claims, has been considered crucial for determining a patent’s value and its associated litigation risk. However, no direct claim semantics-based indicators currently exist to quantify patent claim scope, and existing scope measures are primarily indirect, which limits their ability to capture the semantic nuances of claim text. Additionally, the reliance on post-grant features restricts the applicability of existing litigation prediction models to patent drafts. These limitations complicate the patent drafting process, during which claims are formulated without feedback on scope and litigation risk. This often leads to suboptimal claim articulation, resulting in inadequate protection, increased legal vulnerabilities, or reduced patent grant probability. To address this gap, the hyponym tree score (HTS) is proposed as a novel indicator for quantifying claim scope by analysing hyponym counts, sentence structure, and dependency relations within patent claims. Building on this, early-stage litigation risk prediction has been achieved using a new deep learning model, the Multifeature BERT-Powered Fusion for Author-level Patent Litigation Risk Analysis (MAPRA). The MAPRA model restricts its input features to those available at early stages, such as indicators derived from claim text, inventor information, assignee details, and HTS, ensuring applicability to both draft-stage and granted patents. Despite excluding all post-grant or acquired data, MAPRA achieves a superior area under the receiver operating characteristic curve (AUC) of 0.878, outperforming the most comparable prior study, which reports an AUC of 0.822 using both early-stage and immediate post-grant features. By quantifying claim scope and enabling early-stage litigation risk prediction, this research offers a valuable screening tool for patent drafters, examiners, attorneys, and innovators. It supports informed decision-making during drafting and helps mitigate potential litigation risks. Furthermore, it lays a foundation for future research on claim scope modeling and the development of predictive tools for intellectual property litigation management.
- Open Access
ARE-PaLED: Augmented Reality-Enhanced Patch-Level Explainable Deep Learning System for Alzheimer’s Disease Diagnosis from 3D Brain sMRI
Structural magnetic resonance imaging (sMRI) is a vital tool for diagnosing neurological brain diseases. However, sMRI scans often show significant structural changes only in limited brain regions due to localised atrophy, making the identification of discriminative features a key challenge. Importantly, the human brain exhibits inherent bilateral symmetry, and deviations from this symmetry—such as asymmetric atrophy—are strong indicators of early Alzheimer’s disease (AD). Patch-based methods help capture local brain changes for early AD diagnosis, but they often struggle with fixed-size limitations, potentially missing subtle asymmetries or broader contextual cues. To address these limitations, we propose a novel augmented reality (AR)-enhanced patch-level explainable deep learning (ARE-PaLED) system. It includes an adaptive multi-scale patch extraction network (AMPEN) to adjust patch sizes based on anatomical characteristics and spatial context, as well as an informative patch selection algorithm (IPSA) to identify discriminative patches, including those reflecting asymmetry patterns associated with AD; additionally, an AR module is proposed for future immersive explainability, complementing the patch-level interpretation framework. Evaluated on 1862 subjects from the ADNI and AIBL datasets, the framework achieved an accuracy of 92.5% (AD vs. NC) and 85.9% (AD vs. MCI). The proposed ARE-PaLED demonstrates potential as an interpretable and immersive diagnostic aid for sMRI-based AD diagnosis, supporting the interpretation of model predictions for AD diagnosis.
Open AccessARE-PaLED: Augmented Reality-Enhanced Patch-Level Explainable Deep Learning System for Alzheimer’s Disease Diagnosis from 3D Brain sMRI
Structural magnetic resonance imaging (sMRI) is a vital tool for diagnosing neurological brain diseases. However, sMRI scans often show significant structural changes only in limited brain regions due to localised atrophy, making the identification of discriminative features a key challenge. Importantly, the human brain exhibits inherent bilateral symmetry, and deviations from this symmetry—such as asymmetric atrophy—are strong indicators of early Alzheimer’s disease (AD). Patch-based methods help capture local brain changes for early AD diagnosis, but they often struggle with fixed-size limitations, potentially missing subtle asymmetries or broader contextual cues. To address these limitations, we propose a novel augmented reality (AR)-enhanced patch-level explainable deep learning (ARE-PaLED) system. It includes an adaptive multi-scale patch extraction network (AMPEN) to adjust patch sizes based on anatomical characteristics and spatial context, as well as an informative patch selection algorithm (IPSA) to identify discriminative patches, including those reflecting asymmetry patterns associated with AD; additionally, an AR module is proposed for future immersive explainability, complementing the patch-level interpretation framework. Evaluated on 1862 subjects from the ADNI and AIBL datasets, the framework achieved an accuracy of 92.5% (AD vs. NC) and 85.9% (AD vs. MCI). The proposed ARE-PaLED demonstrates potential as an interpretable and immersive diagnostic aid for sMRI-based AD diagnosis, supporting the interpretation of model predictions for AD diagnosis.
- 12 September 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (7) , 10661-10679
Robust human detection system in flood related images with data augmentation
- 12 September 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (7) , 10661-10679
Robust human detection system in flood related images with data augmentation
- 18 June 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (3) , 4569-4597
Anaphora resolved abstractive text summarization (AR-ATS) system
- 18 June 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (3) , 4569-4597
Anaphora resolved abstractive text summarization (AR-ATS) system