Dharmendra Dangi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Dharmendra Dangi has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Dheeraj Kumar Dixit
Department of Computer Science and Engineering, Madhav Institute of Technology and Science, Gwalior, Madhya Pradesh, India
7 shared publications - Amit Bhagat
Department of Computer Applications, Maulana Azad National Institute of Technology, Bhopal, Madhya Pradesh, India
4 shared publications - Amit Bhagat
Computer Applications, Maulana Azad National Institute of Technology, Bhopal, India
3 shared publications - Rashmi Gupta
Atal Bihari Vajpayee University
3 shared publications - Abhay Sharma
International Institute of Information Technology Hyderabad, Hyderabad, Telangana, India
2 shared publications Amit Bhagat
Department of Mathematics, Bioinformatics and Computer Applications, Maulana Azad National Institute of Technology, Bhopal, India
2 shared publications
Latest Publications
- 26 August 2026
- Published by Springer Nature in National Academy Science Letters
- p. 1-6
Lightweight Hybrid XGBoost-VAE for Zero-Day Intrusion Detection in VANETs: A Leakage-Free Approach
- 26 August 2026
- Published by Springer Nature in National Academy Science Letters
- p. 1-6
Lightweight Hybrid XGBoost-VAE for Zero-Day Intrusion Detection in VANETs: A Leakage-Free Approach
- Open Access
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 65819-65832
Performance Comparison of Static and Contextual Embedding Models for Opinion Mining
Transformer-based language models are widely adopted for sentiment analysis due to their strong contextual representation capabilities; however, their high computational complexity can limit practical deployment in resource-constrained environments. This work presents a systematic comparative study of static and contextual word representations for sentiment classification across architecturally distinct model families under standardized preprocessing and evaluation conditions. We evaluate Long Short-Term Memory (LSTM) networks with Word2Vec, GloVe, and FastText embeddings, and compare them with fine-tuned BERT-base and DistilBERT transformer baselines using the same preprocessing, training, and evaluation protocols across five publicly available datasets spanning formal reviews and noisy social media text. In addition to overall accuracy, we report macro- and weighted-F1 scores across three random seeds to estimate experimental variance, and apply McNemar’s test (with Bonferroni correction for multiple comparisons) to assess pairwise model differences on each dataset’s test set. Contingency tables required for each McNemar comparison are provided in the supplementary material. Detailed error analyses using confusion matrices and out-of-vocabulary (OOV) statistics examine the impact of lexical coverage on model performance. Experimental results indicate that FastText consistently outperforms other static embeddings, particularly on datasets with high lexical variability, while offering substantially lower computational overhead compared to the transformer baselines. The primary contribution of this study is a diagnostic multi-dataset evaluation framework that quantifies the relationship between lexical coverage and subword modeling benefit, and characterises the efficiency–accuracy trade-off across embedding paradigms. All architectural and training differences between model families are explicitly documented and their confounding effects discussed rather than assumed away. These findings provide practical guidance for selecting embedding strategies by jointly considering accuracy and deployment efficiency.
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 65819-65832
Open AccessPerformance Comparison of Static and Contextual Embedding Models for Opinion Mining
Transformer-based language models are widely adopted for sentiment analysis due to their strong contextual representation capabilities; however, their high computational complexity can limit practical deployment in resource-constrained environments. This work presents a systematic comparative study of static and contextual word representations for sentiment classification across architecturally distinct model families under standardized preprocessing and evaluation conditions. We evaluate Long Short-Term Memory (LSTM) networks with Word2Vec, GloVe, and FastText embeddings, and compare them with fine-tuned BERT-base and DistilBERT transformer baselines using the same preprocessing, training, and evaluation protocols across five publicly available datasets spanning formal reviews and noisy social media text. In addition to overall accuracy, we report macro- and weighted-F1 scores across three random seeds to estimate experimental variance, and apply McNemar’s test (with Bonferroni correction for multiple comparisons) to assess pairwise model differences on each dataset’s test set. Contingency tables required for each McNemar comparison are provided in the supplementary material. Detailed error analyses using confusion matrices and out-of-vocabulary (OOV) statistics examine the impact of lexical coverage on model performance. Experimental results indicate that FastText consistently outperforms other static embeddings, particularly on datasets with high lexical variability, while offering substantially lower computational overhead compared to the transformer baselines. The primary contribution of this study is a diagnostic multi-dataset evaluation framework that quantifies the relationship between lexical coverage and subword modeling benefit, and characterises the efficiency–accuracy trade-off across embedding paradigms. All architectural and training differences between model families are explicitly documented and their confounding effects discussed rather than assumed away. These findings provide practical guidance for selecting embedding strategies by jointly considering accuracy and deployment efficiency.
- 19 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 72 (1) , 1836-1845
Post-Quantum Traceable Anonymous Cross-Domain Authentication for Blockchain-Based IoT
With the proliferation of Internet of Things (IoT) applications, secure and efficient cross-domain information sharing has become essential. Traditional cross-domain authentication approaches that rely on real device identities pose significant privacy risks, while fully anonymous schemes often lack accountability for malicious behavior. Additionally, emerging quantum computing capabilities threaten the security of classical cryptographic systems. To address these challenges, this paper proposes a post-quantum secure, traceable anonymous cross-domain authentication scheme based on blockchain technology. The scheme incorporates lattice-based certificateless cryptography and quantum-resistant hash functions to ensure resilience against quantum attacks. Devices are assigned multiple unlinkable pseudonymous identities with corresponding post-quantum public-private key pairs. A dynamic accumulator is employed to update domain information, and distinct pseudonyms are used for each authentication. Cross-domain credentials issued by a key generation center enable identity verification without exposing real identities. The system ensures both device privacy and traceability of malicious actors. Formal security proofs and BAN logic analysis confirm the scheme’s robustness against classical and quantum-era threats. Compared with existing classical approaches, the proposed scheme achieves strong post-quantum security with reduced computational and communication overhead during the authentication process.
- 19 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 72 (1) , 1836-1845
Post-Quantum Traceable Anonymous Cross-Domain Authentication for Blockchain-Based IoT
With the proliferation of Internet of Things (IoT) applications, secure and efficient cross-domain information sharing has become essential. Traditional cross-domain authentication approaches that rely on real device identities pose significant privacy risks, while fully anonymous schemes often lack accountability for malicious behavior. Additionally, emerging quantum computing capabilities threaten the security of classical cryptographic systems. To address these challenges, this paper proposes a post-quantum secure, traceable anonymous cross-domain authentication scheme based on blockchain technology. The scheme incorporates lattice-based certificateless cryptography and quantum-resistant hash functions to ensure resilience against quantum attacks. Devices are assigned multiple unlinkable pseudonymous identities with corresponding post-quantum public-private key pairs. A dynamic accumulator is employed to update domain information, and distinct pseudonyms are used for each authentication. Cross-domain credentials issued by a key generation center enable identity verification without exposing real identities. The system ensures both device privacy and traceability of malicious actors. Formal security proofs and BAN logic analysis confirm the scheme’s robustness against classical and quantum-era threats. Compared with existing classical approaches, the proposed scheme achieves strong post-quantum security with reduced computational and communication overhead during the authentication process.
- Open Access
- 13 August 2025
- Published by Springer Nature in National Academy Science Letters
- p. 1-5
Harnessing CNNs and Embedding Techniques for Enhanced Sentiment Classification
- 13 August 2025
- Published by Springer Nature in National Academy Science Letters
- p. 1-5
Open AccessHarnessing CNNs and Embedding Techniques for Enhanced Sentiment Classification
- 1 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Multilingual AI-Generated Text Detection with BERT and LSTM Model
The advent of AI-generated text, driven by advanced language models like GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers) has revolutionized content creation but also raised concerns about authenticity and misuse in various domains. This research proposes a system to detect whether the supplied text is written by human-being or it generated by AI algorithms, supporting both English and Hindi languages using two datasets with mixed human-authored and AI-generated content. After pre-processing steps such as tokenization, cleaning, and normalization, trained the models including BERT, LSTM (Long Short Term Memory), Logistic Regression, SVM (Support Vector Machine), Random Forest, and Naive Bayes, with BERT finetuned for contextual understanding and LSTM for sequential data, achieving higher accuracy in both languages. A userfriendly interface was developed to allow text file uploads for instant authenticity predictions, serving academic, journalistic, and digital media contexts, with the study highlighting transformer-based models' potential in multilingual detection to enhance digital content trustworthiness and mitigate AIgenerated text misuse. Using the proposed method, accuracies of 95.76 % in English text and 95.58 % in Hindi text have been obtained. The proposed system was found to be effective in detecting text generated by AI algorithms.
- 1 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Multilingual AI-Generated Text Detection with BERT and LSTM Model
The advent of AI-generated text, driven by advanced language models like GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers) has revolutionized content creation but also raised concerns about authenticity and misuse in various domains. This research proposes a system to detect whether the supplied text is written by human-being or it generated by AI algorithms, supporting both English and Hindi languages using two datasets with mixed human-authored and AI-generated content. After pre-processing steps such as tokenization, cleaning, and normalization, trained the models including BERT, LSTM (Long Short Term Memory), Logistic Regression, SVM (Support Vector Machine), Random Forest, and Naive Bayes, with BERT finetuned for contextual understanding and LSTM for sequential data, achieving higher accuracy in both languages. A userfriendly interface was developed to allow text file uploads for instant authenticity predictions, serving academic, journalistic, and digital media contexts, with the study highlighting transformer-based models' potential in multilingual detection to enhance digital content trustworthiness and mitigate AIgenerated text misuse. Using the proposed method, accuracies of 95.76 % in English text and 95.58 % in Hindi text have been obtained. The proposed system was found to be effective in detecting text generated by AI algorithms.
- 12 May 2025
- Published by Springer Nature in International Journal of Information Technology
- Vol. 17 (6) , 3389-3396
Utilization of hesitant and intuitionistic fuzzy sets (HFS-IFS) in computational intelligence for decision modeling
- 12 May 2025
- Published by Springer Nature in International Journal of Information Technology
- Vol. 17 (6) , 3389-3396
Utilization of hesitant and intuitionistic fuzzy sets (HFS-IFS) in computational intelligence for decision modeling
- 26 February 2025
- Published by Taylor & Francis
- p. 119-133
Novel Approaches to Pill Dispensing
Medication non-adherence is a major issue in healthcare, especially among older patients with chronic conditions who live at home. The purpose of this review is to comprehensively investigate automated dispenser treatments proposed in the literature to increase patient medication adherence. We emphasize the human-centered approach, taking into account patient acceptability and proper use, as well as caregiver and physician views. Our assessment emphasizes the need for resolving issues such as direct engagement with drug prescriptions, significant infrastructure requirements, and accessibility for the elderly. We also look into the possibility of cutting-edge technology like RFID tags and Arduino Mega controllers to create pharmaceutical dispensers that can store user data, track medication adherence, and send alerts and reminders. We also examine the role of artificial intelligence (AI) in healthcare, including its applications in personalized medicine, disease detection, clinical decision-making, and patient outcomes. Our analysis sheds light on the development of efficient automated dispenser treatments, as well as the potential for artificial intelligence to improve prescription adherence and healthcare outcomes in the older population.
- 26 February 2025
- Published by Taylor & Francis
- p. 119-133
Novel Approaches to Pill Dispensing
Medication non-adherence is a major issue in healthcare, especially among older patients with chronic conditions who live at home. The purpose of this review is to comprehensively investigate automated dispenser treatments proposed in the literature to increase patient medication adherence. We emphasize the human-centered approach, taking into account patient acceptability and proper use, as well as caregiver and physician views. Our assessment emphasizes the need for resolving issues such as direct engagement with drug prescriptions, significant infrastructure requirements, and accessibility for the elderly. We also look into the possibility of cutting-edge technology like RFID tags and Arduino Mega controllers to create pharmaceutical dispensers that can store user data, track medication adherence, and send alerts and reminders. We also examine the role of artificial intelligence (AI) in healthcare, including its applications in personalized medicine, disease detection, clinical decision-making, and patient outcomes. Our analysis sheds light on the development of efficient automated dispenser treatments, as well as the potential for artificial intelligence to improve prescription adherence and healthcare outcomes in the older population.
- 5 February 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (2) , 1-13
Efficient Deep Learning Model for Analyzing Muscle Activity Patterns in Biomechanical Simulations
- 5 February 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (2) , 1-13
Efficient Deep Learning Model for Analyzing Muscle Activity Patterns in Biomechanical Simulations
- Open Access
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2900 (1) , 020014
A comparative analysis for detecting fake news using supervised learning algorithms
Fake news is a type of essential problem on social media. The rapid circulate of fake news has an ability for disastrous influences on human beings and the soci Fake news is a type of essential problem on social media. The rapid circulate of fake news has an ability for disastrous influences on human beings and the soci
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2900 (1) , 020014
Open AccessA comparative analysis for detecting fake news using supervised learning algorithms
Fake news is a type of essential problem on social media. The rapid circulate of fake news has an ability for disastrous influences on human beings and the soci Fake news is a type of essential problem on social media. The rapid circulate of fake news has an ability for disastrous influences on human beings and the soci
- 23 November 2022
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 35 (1)
An accurate fake news detection approach based on a Levy flight honey badger optimized convolutional neural network model
Summary: People can quickly acquire the news through a variety of sources, including websites, blogs, and social media, among others. The spread of fake news has become easier as a result of the availability of these platforms. Anybody with access to these networks generates and distributes fake news for professional or personal gain. Numerous studies relying on supervised and unsupervised learning techniques are available to address the issue of recognizing fake news. All of those studies, though, have one flaw: they all deliver mostly inaccurate or unmatched results. Poor accuracy is attributed to a variety of factors, including imbalanced datasets, inefficient parameter tuning, poor feature selection, and so on. To tackle these issues, we proposed a novel approach for fake news detection. Initially, the data were obtained from the ISOT dataset and data cleaning is performed. After that, preprocessing is done which includes three major steps such as stemming, stop word removal, and tokenization are carried out. Next to preprocessing, various features that involve name entity recognition‐based features are selected during feature extraction. From this, the short dimensionality features are selected with the help of the ensemble modified independent component analysis model. Finally, the hybrid convolutional neural network‐based Levy flight‐based honey badger algorithm detects fake news. The experiments are simulated using python software with various performance metrics such as accuracy, specificity, sensitivity, precision, and F‐scores to validate the performance of the proposed method. The proposed model offers a precision, recall, and accuracy value of 95%, 97%, and 98% when evaluated with the ISOT dataset. When compared to the existing state‐of‐art methods, the proposed method yielded superior detection results and higher accuracy rates.
- 23 November 2022
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 35 (1)
An accurate fake news detection approach based on a Levy flight honey badger optimized convolutional neural network model
Summary: People can quickly acquire the news through a variety of sources, including websites, blogs, and social media, among others. The spread of fake news has become easier as a result of the availability of these platforms. Anybody with access to these networks generates and distributes fake news for professional or personal gain. Numerous studies relying on supervised and unsupervised learning techniques are available to address the issue of recognizing fake news. All of those studies, though, have one flaw: they all deliver mostly inaccurate or unmatched results. Poor accuracy is attributed to a variety of factors, including imbalanced datasets, inefficient parameter tuning, poor feature selection, and so on. To tackle these issues, we proposed a novel approach for fake news detection. Initially, the data were obtained from the ISOT dataset and data cleaning is performed. After that, preprocessing is done which includes three major steps such as stemming, stop word removal, and tokenization are carried out. Next to preprocessing, various features that involve name entity recognition‐based features are selected during feature extraction. From this, the short dimensionality features are selected with the help of the ensemble modified independent component analysis model. Finally, the hybrid convolutional neural network‐based Levy flight‐based honey badger algorithm detects fake news. The experiments are simulated using python software with various performance metrics such as accuracy, specificity, sensitivity, precision, and F‐scores to validate the performance of the proposed method. The proposed model offers a precision, recall, and accuracy value of 95%, 97%, and 98% when evaluated with the ISOT dataset. When compared to the existing state‐of‐art methods, the proposed method yielded superior detection results and higher accuracy rates.