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)
Review
Medicine, General & Internal
Stephen Bacchi, Yiran Tan, Luke Oakden-Rayner, Jim Jannes, Timothy Kleinig, Simon Koblar
Summary: This review found significant variations in the performance of machine learning models for predicting total inpatient LOS in medical patients, influenced by factors such as different input datasets, LOS thresholds and outcome metrics. Common methodological shortcomings included a lack of reporting patient demographics and clinical details. Further research is needed to determine the utility of machine learning in predicting total inpatient LOS in medical patients.
INTERNAL MEDICINE JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Anders T. Sandnes, Bjarne Grimstad, Odd Kolbjornsen
Summary: Virtual flow metering (VFM) is a cost-effective and non-intrusive technology for inferring multiphase flow rates in petroleum assets. Data-driven VFM, which replaces mechanistic models with machine learning models, has gained attention for its promise of lower maintenance costs. Multi-task learning (MTL) has been shown to improve robustness over single-task methods in modeling 55 wells from four petroleum assets.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Biochemical Research Methods
Raquel Aoki, Frederick Tung, Gabriel L. Oliveira
Summary: This paper proposes a Multi-gate Mixture-of-Experts with Exclusivity (MMoEEx) approach to address the challenge of predicting multiple heterogeneous biological and medical targets. The method introduces more diversity among experts and adopts a two-step optimization to balance the tasks, aiming to tackle complex MTL tasks.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2022)
Article
Engineering, Electrical & Electronic
Dinghao Fan, Hengjie Lu, Shugong Xu, Shan Cao
Summary: This study introduces an end-to-end multi-task learning framework that utilizes depth modality to enhance the accuracy of gesture recognition. Experimental results demonstrate that the proposed method outperforms existing gesture recognition frameworks on three public datasets, and also achieves excellent accuracy improvement when applied to other 2D CNN-based frameworks.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Information Systems
Sang-woo Lee, Ryong Lee, Min-seok Seo, Jong-chan Park, Hyeon-cheol Noh, Jin-gi Ju, Rae-young Jang, Gun-woo Lee, Myung-seok Choi, Dong-geol Choi
Summary: Multi-task learning is an efficient method to tackle multiple tasks with a single model, but recent approaches struggle to outperform single-task learning. This study validates the effectiveness of MTL in low-data conditions and proposes a feature filtering module with minimal overheads. Empirical results demonstrate that MTL can significantly enhance performance under low-data conditions for all tasks.
Article
Forestry
Qigang Xu, Xiangdong Lei, Huiru Zhang
Summary: Guaranteeing the property of biological compatibility is crucial when estimating tree biomass in the context of global climate change. While traditional regression models successfully address this issue, machine learning methods have not. This study introduces a new approach using multi-task loss function to improve the compatibility of tree biomass estimation in Artificial Neural Network (ANN). Experimental results on two tree species biomass datasets demonstrate reduced RMSE and mean absolute relative difference, indicating improved compatibility when compared to classical loss function models. This method offers a trade-off solution for error accumulation and compatibility in tree biomass modelling using ANN, and shows promise for carbon accounting using machine learning methods.
FOREST ECOLOGY AND MANAGEMENT
(2022)
Article
Fisheries
Diogo Nunes Goncalves, Plabiany Rodrigo Acosta, Ana Paula Marques Ramos, Lucas Prado Osco, Danielle Elis Garcia Furuya, Michelle Tais Garcia Furuya, Jonathan Li, Jose Marcato Junior, Hemerson Pistori, Wesley Nunes Goncalves
Summary: This study proposes a new method for locating and counting fingerlings in a sequence of images using convolutional neural networks. The method employs a multi-task approach and utilizes temporal information to enhance the results. Experimental results demonstrate that the proposed method performs well in various scenarios and is capable of detecting fingerling contact.
Article
Computer Science, Information Systems
Jian Liang, Jinjun Tang, Fan Gao, Zhe Wang, Helai Huang
Summary: Accurate regional travel demand forecasting is beneficial for urban traffic management and service operations. This study proposes a multi-task adaptive recurrent graph attention network that combines prior knowledge-driven graph learning with a novel recurrent graph attention network to capture dynamic spatiotemporal dependencies. The method divides demand forecasting into different learning tasks based on region function distributions and improves prediction accuracy.
INFORMATION SCIENCES
(2023)
Article
Engineering, Electrical & Electronic
Li Chen, Cong Peng, Bingchao Zhao
Summary: This paper proposes a novel motion magnification approach that fuses Lagrangian and Eulerian methods through multi-task learning, achieving accurate perception and magnification of tiny variations. Qualitative and quantitative experiments demonstrate that the proposed method outperforms previous approaches in terms of robustness and artifacts.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Clinical Neurology
Cheng-Chang Yang, Oluwaseun Adebayo Bamodu, Lung Chan, Jia-Hung Chen, Chien-Tai Hong, Yi-Ting Huang, Chen-Chih Chung
Summary: This study developed an artificial neural network model to predict prolonged length of hospital stay after acute ischemic stroke by identifying risk factors and using parameters at the time of hospitalization. The key factors associated with prolonged length of stay included National Institutes of Health Stroke Scale scores at admission, atrial fibrillation, receiving thrombolytic therapy, history of hypertension, diabetes, and previous stroke. The proposed model can assist in clinically assessing the risk of prolonged hospitalization, informing decision-making, and developing individualized medical care plans for patients with acute ischemic stroke.
FRONTIERS IN NEUROLOGY
(2023)
Article
Orthopedics
Tony Lin -Wei Chen, Anirudh Buddhiraju, Timothy G. Costales, Murad Abdullah Subih, Henry Hojoon Seo, Young -Min Kwon
Summary: This study developed machine learning models using a national-scale dataset to predict prolonged lengths of stay following total hip arthroplasty. The models demonstrated excellent performance and identified age, laboratory tests, and surgical variables as the strongest predictors of prolonged stay.
JOURNAL OF ARTHROPLASTY
(2023)
Article
Green & Sustainable Science & Technology
Zhikai Xing, Yigang He
Summary: Wind power is a clean and effective energy source for electricity generation, but the abnormality, multi-modal, and uncertainty in wind power data are undesirable. To address these issues, a multi-modal multi-step wind power forecasting model is proposed. It improves the density-based spatial clustering of applications with noise (DBSCAN) by using the k-dimensional tree (kd-tree) to detect abnormal data, and fuses wind speed, wind direction, and air density modalities for a unified representation. To increase accuracy, a stacking deep learning model (SDLM) is introduced, which includes the bidirectional gated recurrent unit (BGRU) and leaky echo state network (LESN) to overcome uncertainty. The final forecasting results are obtained using a meta-learning operator. The model is validated using both inland and offshore wind farm datasets, and the results show that it outperforms in multi-step wind power prediction.
Article
Construction & Building Technology
In Kuk Kang, Tae Yong Shin, Jae Hong Kim
Summary: This study aims to substitute human sensory and slump tests with artificial intelligence, by using observation-informed modeling and artificial neural networks to predict the fluidity and bleeding of concrete. This approach can improve the quality and efficiency of construction processes.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Computer Science, Information Systems
Feihu Zhang, Xujia Hou
Summary: This paper proposes an improved network for ship detection, which achieves better performance and robustness by improving the deep layer aggregation network, lightweight convolution module, and activation function. Experimental results demonstrate outstanding performance of the proposed approach in tiny object detection and significant improvements compared to current advanced methods.
Article
Engineering, Electrical & Electronic
Sreenath Chalil Madathil, Emre Yamangil, Harsha Nagarajan, Arthur Barnes, Russell Bent, Scott Backhaus, Scott J. Mason, Salman Mashayekh, Michael Stadler
IEEE TRANSACTIONS ON SMART GRID
(2018)
Review
Computer Science, Interdisciplinary Applications
Lu He, Sreenath Chalil Madathil, Amrita Oberoi, Greg Servis, Mohammad T. Khasawneh
COMPUTERS & INDUSTRIAL ENGINEERING
(2019)
Article
Infectious Diseases
Kamran Azimi, Michael D. Honaker, Sreenath Chalil Madathil, Mohammad T. Khasawneh
SURGICAL INFECTIONS
(2020)
Article
Clinical Neurology
Renee M. Hendricks, Mohammad T. Khasawneh
Summary: Parkinson's disease is a common neurodegenerative disorder with a lack of consensus on quantifying its progression and severity. Confusion among patients and misuse by clinicians and researchers of the rating scales indicate a need for comprehensive evaluation to identify gaps.
PARKINSONS DISEASE
(2021)
Article
Computer Science, Interdisciplinary Applications
Farouq Halawa, Sreenath Chalil Madathil, Mohammad T. Khasawneh
Summary: A proposed non-linear multi-objective model utilizing Genetic Algorithm is effective in optimizing outpatient clinic design by maximizing natural daylight exposure and minimizing total walking distance for patients. Efficient algorithms are identified to tackle challenges in computational complexity and area constraints approximation for spaces with wide bounds in clinic design. Sensitive analysis reveals that the main factors affecting algorithm performance are the selection mechanism for best Pareto points, number of spaces requiring lighting, and lighting dataset used, with adapted Genetic Algorithm proving superior in achieving better results for a multi-objective problem compared to other optimization algorithms.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Farouq Halawa, Sreenath Chalil Madathil, Mohammad T. Khasawneh
Summary: This paper introduces a three-phase framework for designing healthcare layouts using hospital tracking data, with the use of process mining and simulation modeling to extract important patient pathways and improve prediction accuracy.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Mai Abdulla, Mohammad T. Khasawneh
Summary: Silent diseases refer to a range of chronic illnesses that are usually diagnosed at advanced stages, and current diagnostic strategies lack specific clinical tests. The proposed MIP models offer a solution for selecting low-cost and informative features, improving accuracy and reducing costs in medical diagnosis.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Abbas Safaei, Mohammad T. Khasawneh
Summary: The major challenges in the pharmaceutical industry involve optimizing global expenditure on medicines and maximizing the effectiveness of pharmaceutical products while minimizing R&D costs. The lack of comprehensive Multi-Criteria Decision Making (MCDM) methodologies leads to ineffective decisions and a decline in R&D productivity. To address this, a type-2 fuzzy logic MCDM methodology called PE&PAP-AHP is developed, which improves the accuracy and precision of decision-making in pharmaceutical R&D.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Khalid Y. Aram, Sarah S. Lam, Mohammad T. Khasawneh
Summary: This article introduces the Alternated Sorting Method Genetic Algorithm (ASMGA), which is a hybrid wrapper-filter algorithm for simultaneous feature selection and model selection for Support Vector Machine (SVM) classifiers. ASMGA approximates a set of Pareto optimal feature subsets based on three objectives: cost-sensitive error rate, feature subset size, and Max-Margin Feature Selection (MMFS)-based estimates of feature relevance and redundancy. The proposed algorithm outperforms canonical GA and NSGA-II on benchmark datasets, showing the potential of ASMGA in cost-sensitive feature selection.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Asala N. Erekat, Mohammad T. Khasawneh
Summary: This paper introduces a novel feature selection algorithm S3LR that focuses on improving the accuracy of breast cancer recurrence prediction. By effectively handling censored, event, and unlabeled data, S3LR demonstrates significant improvements in predictive performance. Furthermore, this algorithm has a versatile application and can be applied to address other survival and recurrence problems.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Social Sciences, Mathematical Methods
Amro Khasawneh, Kapil Chalil Madathil, Kevin M. Taaffe, Heidi Zinzow, Amal Ponathil, Sreenath Chalil Madathil, Siddhartha Nambiar, Gaurav Nanda, Patrick J. Rosopa
Summary: The use of social media has increased among adolescents and young adults, exposing them to various risks. This paper explores the impact of educational intervention programs on reducing participation in viral social media challenges at different levels - family, school, and community. The study also compares the effectiveness of these interventions with social media-based policy interventions.
JOURNAL OF COMPUTATIONAL SOCIAL SCIENCE
(2022)
Review
Health Policy & Services
Farouq Halawa, Sreenath Chalil Madathil, Alice Gittler, Mohammad T. Khasawneh
HEALTH CARE MANAGEMENT SCIENCE
(2020)
Article
Engineering, Industrial
Ala Qattawi, Sreenath Chalil Madathil
PRODUCTION AND MANUFACTURING RESEARCH-AN OPEN ACCESS JOURNAL
(2019)
Article
Computer Science, Artificial Intelligence
Jin Zhang, Zekang Bian, Shitong Wang
Summary: This study proposes a novel style linear k-nearest neighbor method to extract stylistic features using matrix expressions and improve the generalizability of the predictor through style membership vectors.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Qifeng Wan, Xuanhua Xu, Jing Han
Summary: In this study, we propose an innovative approach for dimensionality reduction in large-scale group decision-making scenarios that targets linguistic preferences. The method combines TF-IDF feature similarity and information loss entropy to address challenges in decision-making with a large number of decision makers.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Hegui Zhu, Yuchen Ren, Chong Liu, Xiaoyan Sui, Libo Zhang
Summary: This paper proposes an adversarial attack method based on frequency information, which optimizes the imperceptibility and transferability of adversarial examples in white-box and black-box scenarios respectively. Experimental results validate the superiority of the proposed method and its application in real-world online model evaluation reveals their vulnerability.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Jing Tang, Xinwang Liu, Weizhong Wang
Summary: This paper proposes a hybrid generalized TODIM approach in the Fine-Kinney framework to evaluate occupational health and safety hazards. The approach integrates CRP, dynamic SIN, and PLTSs to handle opinion interactions and incomplete opinions among decision makers. The efficiency and rationality of the proposed approach are demonstrated through a numerical example, comparison, and sensitivity studies.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Shigen Shen, Chenpeng Cai, Zhenwei Li, Yizhou Shen, Guowen Wu, Shui Yu
Summary: To address the damage caused by zero-day attacks on SIoT systems, researchers propose a heuristic learning intrusion detection system named DQN-HIDS. By integrating Deep Q-Networks (DQN) into the system, DQN-HIDS gradually improves its ability to identify malicious traffic and reduces resource workloads. Experiments demonstrate the superior performance of DQN-HIDS in terms of workload, delayed sample queue, rewards, and classifier accuracy.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Song Deng, Qianliang Li, Renjie Dai, Siming Wei, Di Wu, Yi He, Xindong Wu
Summary: In this paper, we propose a Chinese text classification algorithm based on deep active learning for the power system, which addresses the challenge of specialized text classification. By applying a hierarchical confidence strategy, our model achieves higher classification accuracy with fewer labeled training data.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Kaan Deveci, Onder Guler
Summary: This study proves the lack of robustness in nonlinear IF distance functions for ranking intuitionistic fuzzy sets (IFS) and proposes an alternative ranking method based on hypervolume metric. Additionally, the suggested method is extended as a new multi-criteria decision making method called HEART, which is applied to evaluate Turkey's energy alternatives.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Fu-Wing Yu, Wai-Tung Ho, Chak-Fung Jeff Wong
Summary: This research aims to enhance the energy management in commercial building air-conditioning systems, specifically focusing on chillers. Ridge regression is found to outperform lasso and elastic net regression when optimized with the appropriate hyperparameter, making it the most suitable method for modeling the system coefficient of performance (SCOP). The key variables that strongly influence SCOP include part load ratios, the operating numbers of chillers and pumps, and the temperatures of chilled water and condenser water. Additionally, July is identified as the month with the highest potential for performance improvement. This study introduces a novel approach that balances feature selection, model accuracy, and optimal tuning of hyperparameters, highlighting the significance of a generic and simplified chiller system model in evaluating energy management opportunities for sustainable operation. The findings from this research can guide future efforts towards more energy-efficient and sustainable operations in commercial buildings.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Xiaoyan Chen, Yilin Sun, Qiuju Zhang, Xuesong Dai, Shen Tian, Yongxin Guo
Summary: In this study, a method for dynamically non-destructive grasping of thin-skinned fruits is proposed. It utilizes a multi-modal depth fusion convolutional neural network for image processing and segmentation, and combines the evaluation mechanism of optimal grasping stability and the forward-looking non-destructive grasp control algorithm. The proposed method greatly improves the comprehensive performance of grasping delicate fruits using flexible hands.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Yuxuan Yang, Siyuan Zhou, He Weng, Dongjing Wang, Xin Zhang, Dongjin Yu, Shuiguang Deng
Summary: The study proposes a novel model, POIGDE, which addresses the challenges of data sparsity and elusive motives by solving graph differential equations to capture continuous variation of users' interests. The model learns interest transference dynamics using a time-serial graph and an interval-aware attention mechanism, and applies Siamese learning to directly learn from label representations for predicting future POI visits. The model outperforms state-of-the-art models on real-world datasets, showing potential in the POI recommendation domain.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
S. Karthika, P. Rathika
Summary: The widespread development of monitoring devices in the power system has generated a large amount of power consumption data. Storing and transmitting this data has become a significant challenge. This paper proposes an adaptive data compression algorithm based on the discrete wavelet transform (DWT) for power system applications. It utilizes multi-objective particle swarm optimization (MO-PSO) to select the optimal threshold. The algorithm has been tested and outperforms other existing algorithms.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Jiaqi Guo, Haiyan Wu, Xiaolei Chen, Weiguo Lin
Summary: In this study, an adaptive SV-Borderline SMOTE-SVM algorithm is proposed to address the challenge of imbalanced data classification. The algorithm maps the data into kernel space using SVM and identifies support vectors, then generates new samples based on the neighbors of these support vectors. Extensive experiments show that this method is more effective than other approaches in imbalanced data classification.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Qiumei Zheng, Linkang Xu, Fenghua Wang, Yongqi Xu, Chao Lin, Guoqiang Zhang
Summary: This paper proposes a new semantic segmentation network model called HilbertSCNet, which combines the Hilbert curve traversal and the dual pathway idea to design a new spatial computation module to address the problem of loss of information for small targets in high-resolution images. The experiments show that the proposed network performs well in the segmentation of small targets in high-resolution maps such as drone aerial photography.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Mojtaba Ashour, Amir Mahdiyar
Summary: Analytic Hierarchy Process (AHP) is a widely applied technique in multi-criteria decision-making problems, but the sheer number of AHP methods presents challenges for scholars and practitioners in selecting the most suitable method. This paper reviews articles published between 2010 and 2023 proposing hybrid, improved, or modified AHP methods, classifies them based on their contributions, and provides a comprehensive summary table and roadmap to guide the method selection process.
APPLIED SOFT COMPUTING
(2024)
Review
Computer Science, Artificial Intelligence
Gerardo Humberto Valencia-Rivera, Maria Torcoroma Benavides-Robles, Alonso Vela Morales, Ivan Amaya, Jorge M. Cruz-Duarte, Jose Carlos Ortiz-Bayliss, Juan Gabriel Avina-Cervantes
Summary: Electric power system applications are complex optimization problems. Most literature reviews focus on studying electrical paradigms using different optimization techniques, but there is a lack of review on Metaheuristics (MHs) in these applications. Our work provides an overview of the paradigms underlying such applications and analyzes the most commonly used MHs and their search operators. We also discover a strong synergy between the Renewable Energies paradigm and other paradigms, and a significant interest in Load-Forecasting optimization problems. Based on our findings, we provide helpful recommendations for current challenges and potential research paths to support further development in this field.
APPLIED SOFT COMPUTING
(2024)