Article
Engineering, Electrical & Electronic
Amir Ghaedi, Reza Sedaghati, Mehrdad Mahmoudian, Shahriyar Bazyari
Summary: This paper focuses on the reliability modeling of pelamis, a commercial-scale wave generator. A multi-state reliability model is proposed to address failures of components and changes in power production. The fuzzy c-means clustering methodology is applied to reduce the number of power states in the model. Numerical results demonstrate that wave converters can improve the reliability performance of electric systems, but wave period and height have an impact on the reliability indices of the power system. The effectiveness of the proposed method is validated by comparing with the outcomes obtained by analytical and Sequential Monte Carlo Simulation methods.
ELECTRIC POWER SYSTEMS RESEARCH
(2024)
Article
Computer Science, Artificial Intelligence
Mohammed Jameel, Mohamed Abouhawwash
Summary: This paper introduces a novel version of Karush-Kuhn-Tucker Proximity Metrics (KKTPM) applicable to single-, multi-, and many-objective optimization problems, along with an approximate approach to reduce computational burden. Extensive computational experiments demonstrate that the proposed metric has lower computational costs compared to other metrics, and it is independent of knowledge of the true Pareto-optimal front and applicable as a termination criterion for evolutionary algorithms.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Zhiqiang Li, Jie Jiang, Xi Chen, Min Zhang, Yong Wang, Qingli Li, Honggang Qi, Min Liu, Robert Laganiere
Summary: This paper proposes a scale-pyramid dynamic atrous convolution method (SDAConv), which dynamically arranges filters at dense scales in different semantic areas to improve the performance of deep convolutional neural networks.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Shuai Lu, Zongze Li, Xinyu Zhang, Jingyao Li
Summary: This paper focuses on the scenario of source-free domain adaptation (SFDA) and proposes a consistency regularization-based mutual alignment (CRMA) method. It randomly augments each target sample to increase sample diversity. It leverages the information maximization loss to improve the performance of mutual alignment. It aligns original samples and augmented samples to enhance the model's ability.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Iljeok Kim, Sung Wook Kim, Jeongsan Kim, Hyunsuk Huh, Iljoo Jeong, Taegyu Choi, Jeongchan Kim, Seungchul Lee
Summary: State-of-the-art deep learning methods have shown impressive performance in intelligent fault diagnosis of rolling element bearings. However, previous studies have faced challenges such as domain discrepancy and lack of interpretability. This study proposes a single domain generalizable and physically interpretable framework that embeds prior knowledge into the neural network, enabling domain generalization and interpretation.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Syed Hammad Hussain Shah, Anniken Susanne T. Karlsen, Mads Solberg, Ibrahim A. Hameed
Summary: Aging poses challenges to elderly individuals' social lives due to declining physical abilities, but group exercise in long-term care facilities is crucial for maintaining their physical and social well-being. However, accommodating these needs can be difficult due to staff shortages and lacking resources. To address this, a robotic exercise coach could be helpful. However, accurate and efficient human activity recognition is necessary for intelligent human-robot interaction in this context.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Huanqing Zhang, Jun Xie, Yi Xiao, Guiling Cui, Xinyu Zhu, Guanghua Xu, Qing Tao, Yuzhe Yang, Zhiyuan Ren, Min Li
Summary: This study analyzed the effects of steady-state auditory-visual motion stimuli on EEG and found that synchronous and asynchronous stimuli can enhance brain responses and activate areas involved in auditory and visual integration. Moreover, asynchronous stimuli activated the Anterior Cingulate region, indicating its involvement in conflicting processing of steady-state auditory-visual motion information.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Leilei Meng, Peng Duan, Kaizhou Gao, Biao Zhang, Wenqiang Zou, Yuyan Han, Chaoyong Zhang
Summary: This study developed thirteen mixed integer programming models to solve four different energy-conscious scheduling problems. The models were designed using different modeling ideas and linearization techniques. Experimental results showed the effectiveness and differences of the proposed MIP models.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Atiye Yousefi, Mir Saman Pishvaee, Babak Amiri
Summary: Designing a system that links pricing and advertising to improve supply chain performance can bring significant benefits. This study validates the importance of accurately selecting influencers for social media advertisements and suggests that choosing influencers based solely on their influence network may not yield the expected results.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Chao Zhu, Benshun Yi, Laigan Luo
Summary: Sentiment analysis, especially aspect-level sentiment classification, has become a prominent research area in natural language processing. Existing methods mainly rely on keyword extraction from sentence contexts, but they neglect the crucial information contained within key phrases. To address this limitation, a novel deformable convolutional network model is proposed to leverage the power of phrases for aspect-level sentiment analysis. The model effectively extracts phrase representations at various contextual distances and incorporates a cross-correlation attention mechanism to capture interdependencies between phrases and words.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
O. Pandithurai, C. Venkataiah, Shrikant Tiwari, N. Ramanjaneyulu
Summary: Cloud computing provides users with on-demand services through the Internet, but it also faces security problems, especially the threat of Distributed Denial of Service (DDoS) attacks. To address this issue, this study proposes a method based on feature selection and Bi-LSTM classifier using a honey badger optimization algorithm to predict DDoS attacks in a cloud environment. The experimental results show that the proposed method achieves significant performance in predicting DDoS attacks.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Zeng Wang, Shi-jie Hu, Wei-dong Liu
Summary: This paper proposes a method of product feature sentiment analysis based on neural networks and feature extraction models, which can accurately extract product features and identify sentiment polarity from online review texts.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Yuxin Shen, Chen Tang, Zirui Fan, Tianbo Wu, Zhenkun Lei
Summary: This paper presents a novel blind watermarking scheme based on the QZ algorithm, which solves the non-blind problem in existing watermarking schemes by using the watermark and host image as inputs for the QZ algorithm. The experimental results show that our scheme is robust against various attacks and forgeries, and out-performs the existing addition-based schemes in terms of invisibility.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
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
Computer Science, Artificial Intelligence
Lijie Zhang, Dominik Janosik
Summary: This study aims to enhance short-term load forecasting for electric power by exploring and evaluating hybrid models using CatBoost and XGBoost algorithms. The CatBoost-Arithmetic Optimization Algorithm hybrid model performs best on the training dataset, while the XGBoost-Arithmetic Optimization Algorithm hybrid model demonstrates superior performance on the testing dataset. Temperature is identified as the most influential variable affecting load forecasting, and the month variable also has a notable impact. Employing hybrid models optimized with appropriate algorithms and incorporating temperature data can significantly improve the accuracy of short-term load forecasting.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Xiuli Chai, Shiping Song, Zhihua Gan, Guoqiang Long, Ye Tian, Xin He
Summary: The rapid development of wireless communication technology has provided great convenience for information transmission. Color images, as an important medium for data dissemination and sharing, face security and efficiency issues. Therefore, a deep image compressed sensing encryption network is proposed using multi-color space and texture features. This network achieves high visual performance by utilizing multiple color spaces and extracting texture details, and it has a higher scrambling degree and the ability to extract texture features.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Ying-Yi Hong, Christian Lian Paulo P. Rioflorido, Weina Zhang
Summary: This work proposes a hybrid deep learning technique that incorporates a quantum-inspired neural network to predict wind speeds 24 h in advance. The proposed method outperforms other methods for 24 h-ahead wind speed forecasting.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Xinyu Wang, Jianzhou Wang, Xinsong Niu, Chunying Wu
Summary: The new wind-speed point-interval prediction system proposed in this study adopts the fuzzy information granulation technology and multi-objective dragonfly algorithm to improve the accuracy and reliability of wind-speed prediction. By combining sub-models and using a multi-nonlinear weight strategy, this system addresses the issue of conventional models' inability to accurately fit nonlinear data characteristics.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Woyeong Kwon, Junho Lee, Sikgyeong Choi, Namsu Kim
Summary: In this study, faults in permanent magnet synchronous motors (PMSMs) were diagnosed and analyzed by monitoring the Hilbert spectrum of the stator current. Experimental results showed that fault detection can be improved by monitoring the overall instantaneous energy.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Yandan Tan, Hongbin Zhu, Jie Wu, Hongfeng Chai
Summary: The article introduces a method using a data-driven prior-based tabular variational autoencoder (DPTVAE) to synthesize credit data. The DPTVAE effectively addresses the challenges in credit data synthesis and demonstrates exceptional synthesis performance, particularly in identifying real default users based on synthetic data.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)