Santosh Kumar Banbhrani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Santosh Kumar Banbhrani has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Hongfei Lin
School of Computer Science and Technology, Dalian University of Technology, Dalian, China
6 shared publications - Bo Xu
School of Computer Science and Technology, Dalian University of Technology, Dalian, China
5 shared publications - Pir Dino Soomro
School of Information Science and Technology, Dalian Maritime University, Dalian, China
3 shared publications Arsalan Ali
2 shared publications- Chen Wei
School of Electrical Engineering, Shaoyang University, Shaoyang 422000, China
2 shared publications - Dileep Kumar Sajnani
School of Computer Science and Engineering, Southeast University, Nanjing 210096, China
2 shared publications
Latest Publications
- Open Access
- 9 October 2026
- Published by MDPI AG in Electronics
- Vol. 15 (20) , 4584
Trust-Aware Federated Learning for Privacy-Preserving IoT Intrusion Detection
The rapid growth of Internet of Things (IoT) networks has increased the need for intrusion detection mechanisms that provide accurate threat detection while preserving privacy, resisting malicious clients, and limiting communication overhead. Existing Federated Learning (FL)-based intrusion detection systems (IDS) remain challenged by heterogeneous non-IID client data, exposure of model updates, adversarial client participation, and frequent model transmission. To address these limitations, this paper proposes FLZT-IDS (Federated Learning with Zero-Trust for Intrusion Detection in IoT). The framework employs gradient-deviation monitoring to mitigate the effects of heterogeneous client updates, while Graph Neural Networks (GNN) and an Attention-based BiLSTM capture relational and temporal attack patterns, respectively. Secure Aggregation with Local Differential Privacy (SALDP) protects transmitted model updates, whereas dynamic trust-based client filtering limits the contribution of potentially malicious participants. An adaptive communication mechanism transmits local updates only when the model change exceeds a predefined threshold, thereby reducing unnecessary communication. Experiments on CICIDS2017 and Edge-IIoTset show that FLZT-IDS achieves 97.8% and 96.2% accuracy, respectively. Compared with FL-IDS, the adaptive communication and trust-filtering mechanisms reduce cumulative communication overhead by more than 30% after 100 communication rounds. Under model-poisoning experiments with 30% malicious clients, FLZT-IDS maintains accuracies of 89.3% on CICIDS2017 and 87.1% on Edge-IIoTset, demonstrating improved robustness under the evaluated adversarial setting.
- 9 October 2026
- Published by MDPI AG in Electronics
- Vol. 15 (20) , 4584
Open AccessTrust-Aware Federated Learning for Privacy-Preserving IoT Intrusion Detection
The rapid growth of Internet of Things (IoT) networks has increased the need for intrusion detection mechanisms that provide accurate threat detection while preserving privacy, resisting malicious clients, and limiting communication overhead. Existing Federated Learning (FL)-based intrusion detection systems (IDS) remain challenged by heterogeneous non-IID client data, exposure of model updates, adversarial client participation, and frequent model transmission. To address these limitations, this paper proposes FLZT-IDS (Federated Learning with Zero-Trust for Intrusion Detection in IoT). The framework employs gradient-deviation monitoring to mitigate the effects of heterogeneous client updates, while Graph Neural Networks (GNN) and an Attention-based BiLSTM capture relational and temporal attack patterns, respectively. Secure Aggregation with Local Differential Privacy (SALDP) protects transmitted model updates, whereas dynamic trust-based client filtering limits the contribution of potentially malicious participants. An adaptive communication mechanism transmits local updates only when the model change exceeds a predefined threshold, thereby reducing unnecessary communication. Experiments on CICIDS2017 and Edge-IIoTset show that FLZT-IDS achieves 97.8% and 96.2% accuracy, respectively. Compared with FL-IDS, the adaptive communication and trust-filtering mechanisms reduce cumulative communication overhead by more than 30% after 100 communication rounds. Under model-poisoning experiments with 30% malicious clients, FLZT-IDS maintains accuracies of 89.3% on CICIDS2017 and 87.1% on Edge-IIoTset, demonstrating improved robustness under the evaluated adversarial setting.
- Open Access
- 5 June 2026
- Published by Frontiers Media SA in Frontiers in Big Data
- Vol. 9, 1796969
TCMB: cross-model multi-level cross-attention network with Taylor-based loss for multimodal fake news detection
Introduction: The rapid spread of misinformation across social media platforms, websites, and online communication channels has made fake news detection a critical task in the digital era. Although various computational approaches have been developed to identify fake news, many existing methods suffer from limitations such as biased training datasets and high rates of false positives and false negatives. To address these challenges, this study proposes a Multimodal Cross Attention Network with Taylor-based Cross Entropy Mean Bias (MMCN_TCMB) model for detecting multimodal fake news. Methods: The proposed approach utilizes multimodal inputs consisting of textual and visual content obtained from fake news datasets. The textual information in news posts is first tokenized using Bidirectional Encoder Representations from Transformers (BERT). Feature extraction is then performed using Word2Vec and Term Frequency–Inverse Gravity Moment (TF-IGM). Simultaneously, images associated with news posts undergo preprocessing through Contrast Limited Adaptive Histogram Equalization and Histogram Equalization (CLAHE-HE), followed by feature extraction using ResNet. The extracted textual and visual features are combined and processed through the MMCN framework. The learning mechanism of the network is enhanced using the Taylor-based Cross Entropy Mean Bias (TCMB) loss function to improve classification performance. Results: Experimental results demonstrate that the proposed MMCN_TCMB model achieves superior performance in multimodal fake news detection. The model attains a recall of 97.988%, precision of 96.223%, F1-score of 97.098%, and overall accuracy of 97.436%, outperforming existing methods. Discussion: The findings indicate that integrating multimodal feature extraction with cross-attention mechanisms and the TCMB loss function significantly enhances the reliability and accuracy of fake news detection. The proposed framework effectively captures both textual and visual inconsistencies, making it a promising approach for combating misinformation in modern digital platforms. The code is available on: https://github.com/banbhrani84/MMCN_TCMB-Fake-News- .
- 5 June 2026
- Published by Frontiers Media SA in Frontiers in Big Data
- Vol. 9, 1796969
Open AccessTCMB: cross-model multi-level cross-attention network with Taylor-based loss for multimodal fake news detection
Introduction: The rapid spread of misinformation across social media platforms, websites, and online communication channels has made fake news detection a critical task in the digital era. Although various computational approaches have been developed to identify fake news, many existing methods suffer from limitations such as biased training datasets and high rates of false positives and false negatives. To address these challenges, this study proposes a Multimodal Cross Attention Network with Taylor-based Cross Entropy Mean Bias (MMCN_TCMB) model for detecting multimodal fake news. Methods: The proposed approach utilizes multimodal inputs consisting of textual and visual content obtained from fake news datasets. The textual information in news posts is first tokenized using Bidirectional Encoder Representations from Transformers (BERT). Feature extraction is then performed using Word2Vec and Term Frequency–Inverse Gravity Moment (TF-IGM). Simultaneously, images associated with news posts undergo preprocessing through Contrast Limited Adaptive Histogram Equalization and Histogram Equalization (CLAHE-HE), followed by feature extraction using ResNet. The extracted textual and visual features are combined and processed through the MMCN framework. The learning mechanism of the network is enhanced using the Taylor-based Cross Entropy Mean Bias (TCMB) loss function to improve classification performance. Results: Experimental results demonstrate that the proposed MMCN_TCMB model achieves superior performance in multimodal fake news detection. The model attains a recall of 97.988%, precision of 96.223%, F1-score of 97.098%, and overall accuracy of 97.436%, outperforming existing methods. Discussion: The findings indicate that integrating multimodal feature extraction with cross-attention mechanisms and the TCMB loss function significantly enhances the reliability and accuracy of fake news detection. The proposed framework effectively captures both textual and visual inconsistencies, making it a promising approach for combating misinformation in modern digital platforms. The code is available on: https://github.com/banbhrani84/MMCN_TCMB-Fake-News- .
- 23 February 2026
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 133
Federated learning based deep learning framework for robust object detection in indoor and outdoor environments
- 23 February 2026
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 133
Federated learning based deep learning framework for robust object detection in indoor and outdoor environments
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 170910-170928
A Trust-Aware Federated Learning Framework With Multi-Source Data Fusion for Robust IoT Intrusion Detection
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 170910-170928
Open AccessA Trust-Aware Federated Learning Framework With Multi-Source Data Fusion for Robust IoT Intrusion Detection
- Open Access
- 1 January 2026
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 17 (9) , 1821-1830
Sentiment Classification on IMDb Movie Reviews: A Controlled Comparative Study of Classical, Deep-learning, Feature-fusion, and Fine-tuned Transformer Models
Sentiment analysis is one of the most important tasks in natural language processing, as it allows opinions expressed in text to be automatically categorized. This study presents a systematically controlled comparative analysis of classical machine-learning, deep-learning, feature-fusion, and fully fine-tuned transformer models for binary sentiment classification on the Internet Movie Database (IMDb) Movie Reviews dataset. While the individual components of the framework, including Term Frequency-Inverse Document Frequency (TF-IDF), Bidirectional Encoder Representations from Transformers (BERT) embeddings, feature fusion, and Multi-Layer Perceptron (MLP) classification, are established techniques, this study contributes a comprehensive empirical evaluation of their combined effectiveness for the target classification task, providing insights into the practical benefits of integrating lexical and contextual representations. Under a single experimental framework, all models are evaluated on a commonly held-out test set with 95% bootstrap confidence intervals, paired McNemar significance testing, confusion-matrix and error analysis, and a computational-complexity comparison. The fully fine-tuned transformers achieve the highest performance Robustly Optimized BERT Pretraining Approach (RoBERTa), F1-Score = 0.9427. The TF-IDF and BERT feature-fusion model is significantly more accurate than the classical, deep-learning, and BERT-only baselines (all p < 0.001), but significantly less accurate than the fine-tuned transformers (all p < 0.01); furthermore, concatenating the [CLS] token and mean-pooled representations does not significantly improve upon mean pooling alone ( p = 0.48). The study provides a transparent, evidence-based account of the accuracy and cost trade-offs among these model families.
- 1 January 2026
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 17 (9) , 1821-1830
Open AccessSentiment Classification on IMDb Movie Reviews: A Controlled Comparative Study of Classical, Deep-learning, Feature-fusion, and Fine-tuned Transformer Models
Sentiment analysis is one of the most important tasks in natural language processing, as it allows opinions expressed in text to be automatically categorized. This study presents a systematically controlled comparative analysis of classical machine-learning, deep-learning, feature-fusion, and fully fine-tuned transformer models for binary sentiment classification on the Internet Movie Database (IMDb) Movie Reviews dataset. While the individual components of the framework, including Term Frequency-Inverse Document Frequency (TF-IDF), Bidirectional Encoder Representations from Transformers (BERT) embeddings, feature fusion, and Multi-Layer Perceptron (MLP) classification, are established techniques, this study contributes a comprehensive empirical evaluation of their combined effectiveness for the target classification task, providing insights into the practical benefits of integrating lexical and contextual representations. Under a single experimental framework, all models are evaluated on a commonly held-out test set with 95% bootstrap confidence intervals, paired McNemar significance testing, confusion-matrix and error analysis, and a computational-complexity comparison. The fully fine-tuned transformers achieve the highest performance Robustly Optimized BERT Pretraining Approach (RoBERTa), F1-Score = 0.9427. The TF-IDF and BERT feature-fusion model is significantly more accurate than the classical, deep-learning, and BERT-only baselines (all p < 0.001), but significantly less accurate than the fine-tuned transformers (all p < 0.01); furthermore, concatenating the [CLS] token and mean-pooled representations does not significantly improve upon mean pooling alone ( p = 0.48). The study provides a transparent, evidence-based account of the accuracy and cost trade-offs among these model families.
- Open Access
- 2 July 2025
- Published by Knowledge Creation and Dissemination Centre in Social Science Review Archives
- Vol. 3 (3) , 1762-1773
Auslan Sign Language Image Recognition Using Deep Neural Network
Sign language recognition improves accessibility for the deaf and hard-of-hearing by translating hand gestures into machine-interpretable labels. This paper presents a hybrid pipeline for static Auslan digit recognition (classes 0–2) that combines convolutional neural networks (CNNs) for automated feature extraction with classical classifiers, Support Vector Machine (SVM) and Random Forest (RF). A grayscale dataset of 6,000 images (2,000 per class) was pre-processed using Canny edge detection to emphasize contour information, then resized for model inputs. Two CNN feature-extractors were trained and their flattened feature vectors fed to an RBF-kernel SVM and a 100-tree Random Forest. Experimental evaluation shows the CNN + Random Forest hybrid attained the highest validation accuracy (99.75%), outperforming the baseline end-to-end CNN (≈95%) and the CNN+SVM (99.67%). The trained pipeline was also integrated into a Mediapipe-based real-time testing setup to demonstrate practical applicability. Results indicate that combining deep feature extraction with ensemble/classical classifiers improves robustness and generalization for static gesture recognition. Future work will expand class coverage, incorporate dynamic gesture modelling, and investigate model compression for embedded deployment.
- 2 July 2025
- Published by Knowledge Creation and Dissemination Centre in Social Science Review Archives
- Vol. 3 (3) , 1762-1773
Open AccessAuslan Sign Language Image Recognition Using Deep Neural Network
Sign language recognition improves accessibility for the deaf and hard-of-hearing by translating hand gestures into machine-interpretable labels. This paper presents a hybrid pipeline for static Auslan digit recognition (classes 0–2) that combines convolutional neural networks (CNNs) for automated feature extraction with classical classifiers, Support Vector Machine (SVM) and Random Forest (RF). A grayscale dataset of 6,000 images (2,000 per class) was pre-processed using Canny edge detection to emphasize contour information, then resized for model inputs. Two CNN feature-extractors were trained and their flattened feature vectors fed to an RBF-kernel SVM and a 100-tree Random Forest. Experimental evaluation shows the CNN + Random Forest hybrid attained the highest validation accuracy (99.75%), outperforming the baseline end-to-end CNN (≈95%) and the CNN+SVM (99.67%). The trained pipeline was also integrated into a Mediapipe-based real-time testing setup to demonstrate practical applicability. Results indicate that combining deep feature extraction with ensemble/classical classifiers improves robustness and generalization for static gesture recognition. Future work will expand class coverage, incorporate dynamic gesture modelling, and investigate model compression for embedded deployment.
- Open Access
- 13 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (20) , 10292
TDO-Spider Taylor ChOA: An Optimized Deep-Learning-Based Sentiment Classification and Review Rating Prediction
Modern review websites, namely Yelp and Amazon, permit the users to post online reviews for numerous businesses, services and products. Currently, online reviewing is an imperative task in the manipulation of shopping decisions produced by customers. These reviews afford consumers experience and information regarding the superiority of the product. The prevalent method of strengthening online review evolution is the performance of Sentiment Classification, which is an attractive domain in industrial and academic research. The review helps various domains, and it is problematic to collect interpreted training data. In this paper, an effectual Review Rating Prediction and Sentiment Classification was developed. Here, a Gated Recurrent Unit (GRU) was employed for the Sentiment Classification process, whereas a Hierarchical Attention Network (HAN) was applied for Review Rating Prediction. The significant features, such as statistical, SentiWordNet and classification features, were extracted for the Sentiment Classification and Review Rating Prediction process. Moreover, the GRU was trained by the designed TD-Spider Taylor ChOA approach, and the HAN was trained by the designed Jaya-TDO approach. The experimental results show that the proposed Jaya-TDO technique attained a better performance of 0.9425, 0.9654 and 0.9538, and that TD-Spider Taylor ChOA achieved 0.9524, 0.9698 and 0.9588 in terms of the precision, recall and F-measure.
- 13 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (20) , 10292
Open AccessTDO-Spider Taylor ChOA: An Optimized Deep-Learning-Based Sentiment Classification and Review Rating Prediction
Modern review websites, namely Yelp and Amazon, permit the users to post online reviews for numerous businesses, services and products. Currently, online reviewing is an imperative task in the manipulation of shopping decisions produced by customers. These reviews afford consumers experience and information regarding the superiority of the product. The prevalent method of strengthening online review evolution is the performance of Sentiment Classification, which is an attractive domain in industrial and academic research. The review helps various domains, and it is problematic to collect interpreted training data. In this paper, an effectual Review Rating Prediction and Sentiment Classification was developed. Here, a Gated Recurrent Unit (GRU) was employed for the Sentiment Classification process, whereas a Hierarchical Attention Network (HAN) was applied for Review Rating Prediction. The significant features, such as statistical, SentiWordNet and classification features, were extracted for the Sentiment Classification and Review Rating Prediction process. Moreover, the GRU was trained by the designed TD-Spider Taylor ChOA approach, and the HAN was trained by the designed Jaya-TDO approach. The experimental results show that the proposed Jaya-TDO technique attained a better performance of 0.9425, 0.9654 and 0.9538, and that TD-Spider Taylor ChOA achieved 0.9524, 0.9698 and 0.9588 in terms of the precision, recall and F-measure.
- Open Access
- 19 April 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (9) , 1354
Taylor-ChOA: Taylor-Chimp Optimized Random Multimodal Deep Learning-Based Sentiment Classification Model for Course Recommendation
Course recommendation is a key for achievement in a student’s academic path. However, it is challenging to appropriately select course content among numerous online education resources, due to the differences in users’ knowledge structures. Therefore, this paper develops a novel sentiment classification approach for recommending the courses using Taylor-chimp Optimization Algorithm enabled Random Multimodal Deep Learning (Taylor ChOA-based RMDL). Here, the proposed Taylor ChOA is newly devised by the combination of the Taylor concept and Chimp Optimization Algorithm (ChOA). Initially, course review is done to find the optimal course, and thereafter feature extraction is performed for extracting the various significant features needed for further processing. Finally, sentiment classification is done using RMDL, which is trained by the proposed optimization algorithm, named ChOA. Thus, the positively reviewed courses are obtained from the classified sentiments for improving the course recommendation procedure. Extensive experiments are conducted using the E-Khool dataset and Coursera course dataset. Empirical results demonstrate that Taylor ChOA-based RMDL model significantly outperforms state-of-the-art methods for course recommendation tasks.
- 19 April 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (9) , 1354
Open AccessTaylor-ChOA: Taylor-Chimp Optimized Random Multimodal Deep Learning-Based Sentiment Classification Model for Course Recommendation
Course recommendation is a key for achievement in a student’s academic path. However, it is challenging to appropriately select course content among numerous online education resources, due to the differences in users’ knowledge structures. Therefore, this paper develops a novel sentiment classification approach for recommending the courses using Taylor-chimp Optimization Algorithm enabled Random Multimodal Deep Learning (Taylor ChOA-based RMDL). Here, the proposed Taylor ChOA is newly devised by the combination of the Taylor concept and Chimp Optimization Algorithm (ChOA). Initially, course review is done to find the optimal course, and thereafter feature extraction is performed for extracting the various significant features needed for further processing. Finally, sentiment classification is done using RMDL, which is trained by the proposed optimization algorithm, named ChOA. Thus, the positively reviewed courses are obtained from the classified sentiments for improving the course recommendation procedure. Extensive experiments are conducted using the E-Khool dataset and Coursera course dataset. Empirical results demonstrate that Taylor ChOA-based RMDL model significantly outperforms state-of-the-art methods for course recommendation tasks.
- Open Access
- 22 March 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (7) , 3211
Spider Taylor-ChOA: Optimized Deep Learning Based Sentiment Classification for Review Rating Prediction
The prediction of review rating is an imperative sentiment assessment task that aims to discover the intensity of users’ sentiment toward a target product from several reviews. This paper devises a technique based on sentiment classification for predicting the review rating. Here, the review data are taken from the database. The significant features, such as SentiWordNet-based statistical features, term frequency–inverse document frequency (TF-IDF), number of capitalized words, numerical words, punctuation marks, elongated words, hashtags, emoticons, and number of sentences are mined in feature extraction. The features are mined for sentiment classification, which is performed by random multimodal deep learning (RMDL). The training of RMDL is done using the proposed Spider Taylor-ChOA, which is devised by combining spider monkey optimization (SMO) and Taylor-based chimp optimization algorithm (Taylor-ChOA). Concurrently, the features are considered input for the review rating prediction, which determines positive and negative reviews using the hierarchical attention network (HAN), and training is done using proposed Spider Taylor-ChOA. The proposed Spider Taylor-ChOA-based RMDL performed best with the highest precision of 94.1%, recall of 96.5%, and highest F-measure of 95.3%. The proposed spider Taylor-ChOA-based HAN performed best with the highest precision of 93.1%, recall of 95.4% and highest F-measure of 94.3%.
- 22 March 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (7) , 3211
Open AccessSpider Taylor-ChOA: Optimized Deep Learning Based Sentiment Classification for Review Rating Prediction
The prediction of review rating is an imperative sentiment assessment task that aims to discover the intensity of users’ sentiment toward a target product from several reviews. This paper devises a technique based on sentiment classification for predicting the review rating. Here, the review data are taken from the database. The significant features, such as SentiWordNet-based statistical features, term frequency–inverse document frequency (TF-IDF), number of capitalized words, numerical words, punctuation marks, elongated words, hashtags, emoticons, and number of sentences are mined in feature extraction. The features are mined for sentiment classification, which is performed by random multimodal deep learning (RMDL). The training of RMDL is done using the proposed Spider Taylor-ChOA, which is devised by combining spider monkey optimization (SMO) and Taylor-based chimp optimization algorithm (Taylor-ChOA). Concurrently, the features are considered input for the review rating prediction, which determines positive and negative reviews using the hierarchical attention network (HAN), and training is done using proposed Spider Taylor-ChOA. The proposed Spider Taylor-ChOA-based RMDL performed best with the highest precision of 94.1%, recall of 96.5%, and highest F-measure of 95.3%. The proposed spider Taylor-ChOA-based HAN performed best with the highest precision of 93.1%, recall of 95.4% and highest F-measure of 94.3%.
- Open Access
- 8 March 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Conditional Probability Joint Extraction of Nested Biomedical Events: Design of a Unified Extraction Framework Based on Neural Networks (Preprint)
BACKGROUND Event extraction is essential for natural language processing. In the biomedical field, the nested event phenomenon (event A as a participating role of event B) makes extracting this event more difficult than extracting a single event. Therefore, the performance of nested biomedical events is always underwhelming. In addition, previous works relied on a pipeline to build an event extraction model, which ignored the dependence between trigger recognition and event argument detection tasks and produced significant cascading errors. OBJECTIVE This study aims to design a unified framework to jointly train biomedical event triggers and arguments and improve the performance of extracting nested biomedical events. METHODS We proposed an end-to-end joint extraction model that considers the probability distribution of triggers to alleviate cascading errors. Moreover, we integrated the syntactic structure into an attention-based gate graph convolutional network to capture potential interrelations between triggers and related entities, which improved the performance of extracting nested biomedical events. RESULTS The experimental results demonstrated that our proposed method achieved the best F1 score on the multilevel event extraction biomedical event extraction corpus and achieved a favorable performance on the biomedical natural language processing shared task 2011 Genia event corpus. CONCLUSIONS Our conditional probability joint extraction model is good at extracting nested biomedical events because of the joint extraction mechanism and the syntax graph structure. Moreover, as our model did not rely on external knowledge and specific feature engineering, it had a particular generalization performance.
- 8 March 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessConditional Probability Joint Extraction of Nested Biomedical Events: Design of a Unified Extraction Framework Based on Neural Networks (Preprint)
BACKGROUND Event extraction is essential for natural language processing. In the biomedical field, the nested event phenomenon (event A as a participating role of event B) makes extracting this event more difficult than extracting a single event. Therefore, the performance of nested biomedical events is always underwhelming. In addition, previous works relied on a pipeline to build an event extraction model, which ignored the dependence between trigger recognition and event argument detection tasks and produced significant cascading errors. OBJECTIVE This study aims to design a unified framework to jointly train biomedical event triggers and arguments and improve the performance of extracting nested biomedical events. METHODS We proposed an end-to-end joint extraction model that considers the probability distribution of triggers to alleviate cascading errors. Moreover, we integrated the syntactic structure into an attention-based gate graph convolutional network to capture potential interrelations between triggers and related entities, which improved the performance of extracting nested biomedical events. RESULTS The experimental results demonstrated that our proposed method achieved the best F1 score on the multilevel event extraction biomedical event extraction corpus and achieved a favorable performance on the biomedical natural language processing shared task 2011 Genia event corpus. CONCLUSIONS Our conditional probability joint extraction model is good at extracting nested biomedical events because of the joint extraction mechanism and the syntax graph structure. Moreover, as our model did not rely on external knowledge and specific feature engineering, it had a particular generalization performance.