Article
Biochemistry & Molecular Biology
Abdelkader A. Metwally, Amira A. Nayel, Rania M. Hathout
Summary: This study successfully predicted the in vivo efficacy of siRNA nanoparticles using computational simulation. By combining cheminformatics with machine learning techniques, the study utilized a dataset and an evolutionary algorithm for modeling, and achieved good predictive results.
FRONTIERS IN MOLECULAR BIOSCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Jing Xia, Nanguang Chen, Anqi Qiu
Summary: This study proposes a multi-level and joint attention network for learning high-order representations of brain functional connectivities to predict different cognitive tasks. The experiments demonstrate the effectiveness of attention modules and identify specific and shared brain functional connectivities and regions. The joint attention module significantly improves the prediction of cognitive functions. The network outperforms existing machine learning techniques on the ABCD dataset.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Engineering, Electrical & Electronic
Juan Cervino, Juan Andres Bazerque, Miguel Calvo-Fullana, Alejandro Ribeiro
Summary: Reinforcement learning optimizes an agent's policy using rewards, with the collaborative cross-learning approach aiding in adapting quickly to various tasks in different environments.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2021)
Article
Environmental Sciences
Shanshan Sui, Qilong Han
Summary: Accurate air quality prediction is crucial for intelligent cities, but complex correlations make it challenging. Previous work focused on spatial or temporal modeling, but we propose a multi-view multi-task spatiotemporal graph convolutional network (M2) that considers logical semantic, temporal, and spatial relations for air quality prediction. Our experimental results show that our model outperforms state-of-the-art methods.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Computer Science, Artificial Intelligence
Jiejie Zhao, Bowen Du, Leilei Sun, Weifeng Lv, Yanchi Liu, Hui Xiong
Summary: This paper introduces a novel deep multi-task learning method with relational attention, which uses attention modules to specify features for different tasks and learns relationships among tasks to transfer knowledge effectively.
PATTERN RECOGNITION
(2021)
Article
Construction & Building Technology
Chien-Liang Liu, Chun-Jan Tseng, Tzu-Hsuan Huang, Jie-Si Yang, Kai -Bin Huang
Summary: Buildings are significant energy consumers worldwide, and accurate forecasting of building electricity loads can have substantial environmental and economic benefits. This study proposes a deep learning model based on multi-task learning architecture to predict the electricity loads of commercial buildings. The proposed model outperforms other methods in terms of prediction performance, and simple ensemble techniques further enhance its performance.
ENERGY AND BUILDINGS
(2023)
Article
Biology
Amine Amyar, Romain Modzelewski, Pierre Vera, Vincent Morard, Su Ruan
Summary: In this study, a multi-task, multi-scale learning framework is proposed to predict patient survival and treatment response. The results show that this framework can extract meaningful and powerful features, improving the performance of radiomics. The subsidiary tasks provide an inductive bias, enabling the model to better generalize.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Information Systems
Sungkwang Eom, Byungkook Oh, Sangjin Shin, Kyong-Ho Lee
Summary: Multi-task learning is increasingly popular for improving prediction accuracy and cost savings, especially in predicting event types from social data. The proposed deep learning framework SEP integrates event attribute type prediction, attention mechanism, and location representation sharing method, effectively addressing data sparsity and incompleteness.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Hao Miao, Jiaxing Shen, Jiannong Cao, Jiangnan Xia, Senzhang Wang
Summary: This paper studies the problem of simultaneously predicting crowd flow and flow Origin-Destination (OD) locations, and proposes a Multi-task Bayes-enhanced Adversarial Spatial Temporal Network (MBA-STNet) to effectively address it. MBA-STNet adopts a shared-private framework and incorporates an adversarial loss on shared feature extraction to reduce information redundancy. Bayesian heterogeneous Spatio-temporal Attention Network and an attentive temporal queue are designed to learn complex correlations and capture temporal dependency. Extensive evaluations demonstrate the superiority of MBA-STNet over existing methods.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Pharmacology & Pharmacy
Daiqiao Ai, Hanxuan Cai, Jiajia Wei, Duancheng Zhao, Yihao Chen, Ling Wang
Summary: Cytochrome P450 (CYP) is a superfamily of oxidizing enzymes involved in the metabolism of various compounds. In this study, a deep learning method called FP-GNN was used to develop classification models for predicting the inhibitory activity of molecules against five CYP isoforms. The evaluation results showed that the multi-task FP-GNN model achieved the best predictive performance compared to other existing models. The developed online webserver DEEPCYPs can be used to detect potential inhibitory activity of compounds against CYPs, aiding in drug-drug interaction prediction and early-stage drug discovery.
FRONTIERS IN PHARMACOLOGY
(2023)
Article
Computer Science, Information Systems
Qunjian Chen, Xiaoliang Ma, Yanan Yu, Yiwen Sun, Zexuan Zhu
Summary: This paper proposes a new multi-objective evolutionary multi-task optimization (EMTO) algorithm by introducing cross-dimensional variable search and prediction-based individual search for efficient knowledge transfer. The algorithm is tested on benchmark problems and the experimental results demonstrate its effectiveness and efficiency.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Jiqian Mo, Zhiguo Gong
Summary: This article proposes a novel Cross-city Multi-Granular Adaptive Transfer Learning method (MGAT) for traffic prediction. By training the model on multiple source cities and obtaining multi-granular features, the Adaptive Transfer module selects the most appropriate features to improve traffic prediction.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Engineering, Civil
Chizhan Zhang, Fenghua Zhu, Xiao Wang, Leilei Sun, Haina Tang, Yisheng Lv
Summary: This article investigates the importance of accurate and real-time taxi demand prediction for pre-allocating taxi resources in cities, and proposes a multi-task learning model to co-predict taxi pick-up and drop-off demands. Experimental results demonstrate the effectiveness of the proposed model.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Ao Wang, Yongchao Ye, Xiaozhuang Song, Shiyao Zhang, James J. Q. Yu
Summary: This paper proposes a graph-based spatio-temporal autoencoder for traffic speed prediction with missing values. The model outperforms state-of-the-art methods and demonstrates stable performance in different missing scenarios and prediction horizons.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Chen Wan, Wenzhong Li, Wangxiang Ding, Zhijie Zhang, Qingning Lu, Lin Qian, Ji Xu, Jixiang Lu, Rongrong Cao, Baoliu Ye, Sanglu Lu
Summary: This paper proposes a multi-task sequence learning approach that combines LSTM and Seq2Seq models to simultaneously achieve performance prediction and KPI mining. Experimental results show that the method achieves lower errors and outperforms existing algorithms on two real-world DBMS datasets.
INFORMATION SCIENCES
(2021)
Editorial Material
Biochemistry & Molecular Biology
C. Liu, D. Saffen, T. G. Schulze, M. Burmeister, P. C. Sham, Y-g Yao, P-H Kuo, C. Chen, Y. An, J. Dai, W. Yue, M. X. Li, H. Xue, B. Su, L. Chen, Y. Shi, M. Qiao, T. Liu, K. Xia, R. C. K. Chan
MOLECULAR PSYCHIATRY
(2016)
Article
Computer Science, Information Systems
Hengjie Song, Yonghui Xu, Huaqing Min, Qingyao Wu, Wei Wei, Jianshu Weng, Xiaogang Han, Qiang Yang, Jialiang Shi, Jiaqian Gu, Chunyan Miao, Nishida Toyoaki
ACM TRANSACTIONS ON THE WEB
(2016)
Editorial Material
Computer Science, Hardware & Architecture
Qiang Yang
Article
Computer Science, Artificial Intelligence
Chuanren Liu, Kai Zhang, Hui Xiong, Guofei Jiang, Qiang Yang
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2016)
Article
Computer Science, Information Systems
Ying Wei, Yangqiu Song, Yi Zhen, Bo Liu, Qiang Yang
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2016)
Article
Multidisciplinary Sciences
Siu-Kin Ng, Taobo Hu, Xi Long, Cheuk-Hin Chan, Shui-Ying Tsang, Hong Xue
SCIENTIFIC REPORTS
(2016)
Article
Computer Science, Artificial Intelligence
Chen Luo, Jia Zeng, Mingxuan Yuan, Wenyuan Dai, Qiang Yang
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2016)
Article
Integrative & Complementary Medicine
Rui Li, Wingman Chan, Waikin Mat, Yiucheong Ho, Rigil K. Yeung, Shuiying Tsang, Hong Xue
EVIDENCE-BASED COMPLEMENTARY AND ALTERNATIVE MEDICINE
(2017)
Article
Medicine, Research & Experimental
Sophia Yui Kau Fong, Chenrui Li, Yiu Cheong Ho, Rui Li, Qian Wang, Yin Cheong Wong, Hong Xue, Zhong Zuo
MOLECULAR PHARMACEUTICS
(2017)
Article
Multidisciplinary Sciences
Han Yu, Zhiqi Shen, Chunyan Miao, Cyril Leung, Yiqiang Chen, Simon Fauvel, Jun Lin, Lizhen Cui, Zhengxiang Pan, Qiang Yang
Article
Multidisciplinary Sciences
Han Yu, Chunyan Miao, Cyril Leung, Yiqiang Chen, Simon Fauvel, Victor R. Lesser, Qiang Yang
SCIENTIFIC REPORTS
(2016)
Article
Oncology
Zhenggang Wu, Xi Long, Shui Ying Tsang, Taobo Hu, Jian-Feng Yang, Wai Kin Mat, Hongyang Wang, Hong Xue
Article
Genetics & Heredity
Xi Long, Hong Xue
Summary: Genetic variants are unevenly distributed in the human genome, forming hotspots and clusters associated with different functional genomic features and diseases. Hotspots and clusters of genetic variants can lead to both positive and negative genomic changes, offering a potential approach to address the missing heritability problem.
Review
Biology
Hong Xue, J. Tze-Fei Wong
Article
Chemistry, Analytical
Timothy Yiu-Cheong Ho, Hong Xue