Article
Chemistry, Inorganic & Nuclear
Yuanyuan Qin, Yuewei Wu, Shuchang Luo, Jing Xi, Yan Guo, Yi Ding, Jun Zhang, Xiangyu Liu
Summary: Four air-stable mononuclear Co(II) complexes have been synthesized and structurally characterized. Magnetic analysis and ab initio calculations reveal the magnetic anisotropies and energy barriers of these complexes, providing important insights into their magnetic behavior.
DALTON TRANSACTIONS
(2022)
Article
Computer Science, Theory & Methods
Stefano Marrone, Cristina Papa, Carlo Sansone
Summary: This study investigates reducing the size of CNN by removing some neurons only from the fully connected layers before network training, and further compressing the network through weight quantization. The results show that it is possible to reduce the network size without statistically affecting performance.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Computer Science, Information Systems
Yuao Zhang, Qingbiao Wu, Jueliang Hu
Summary: In this study, an adaptive regularized extreme learning machine (A-RELM) is proposed, which uses a function instead of a regularization factor to achieve better regularization. Experimental results show the advantages of the algorithm in some benchmark tests.
Article
Computer Science, Artificial Intelligence
Lei Chen, Fajie Yuan, Jiaxi Yang, Xiangnan He, Chengming Li, Min Yang
Summary: Making accurate recommendations for cold-start users is a challenge in recommender systems. Cross-domain recommendations offer a solution by transferring knowledge from a related domain. This paper proposes a novel User-specific Adaptive Fine-tuning (UAF) method, which selects fine-tuning layers based on each user's preferences, and experiments show its superior performance in user cold-start recommendation.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Junqi Luo, Liucun Zhu, Ning Wu, Mingyou Chen, Daopeng Liu, Zhenyu Zhang, Jiyuan Liu
Summary: This paper proposes a vision-guided robot for dynamic visual tracking of a manipulator. The hybrid adaptive control scheme combines an Extreme Learning Machine (ELM) and proportional-integral-derivative (PID) for accurate real-time tracking of moving objects. Experimental results demonstrate that the proposed method outperforms pure PID controllers in vision-tracking control.
Article
Chemistry, Analytical
Ahmad Alzahrani
Summary: This paper proposes a method for predicting non-stationary solar irradiance using an adaptive extreme learning machine. The method shows high accuracy in predicting solar irradiance.
Article
Computer Science, Artificial Intelligence
Jun Kong, Jin Wang, Xuejie Zhang
Summary: In this paper, a hierarchical BERT model called HAdaBERT is proposed to address the limitation of applying pretrained language models to document classification. The model utilizes a local encoder and a global encoder to encode the documents, and employs an adaptive fine-tuning strategy to improve performance.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Liye Xiao, Wei Shao, Fulong Jin, Zhuochun Wu
Summary: In order to improve the accuracy and efficiency of wind speed forecasting, a self-adaptive kernel extreme learning machine (KELM) is proposed in this paper. The KELM can simultaneously eliminate old data and learn from new data, achieving more accurate forecasting results at a faster calculation speed.
APPLIED SOFT COMPUTING
(2021)
Article
Engineering, Civil
S. M. A. Bin Al Islam, H. M. Abdul Aziz, Ali Hajbabaie
Summary: This paper proposes a stochastic gradient-based optimization model for traffic signal control with network-level vehicular energy consumption bounds. A mixed-integer linear mathematical program is used to formulate the signal control problem with inequality constraints on energy consumption. Empirical results demonstrate the effectiveness of the developed stochastic gradient approximation algorithm in achieving optimized signal settings without compromising delay.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Automation & Control Systems
Xiao-Zheng Jin, Miao-Miao Gao, Wei-Wei Che, Hai Wang
Summary: This article addresses the problem of event-triggered finite-time trajectory tracking control of perturbed Euler-Lagrange systems with nonlinear dynamics and disturbances. It employs the Extreme Learning Machine (ELM) framework and adaptive technique to tackle unknown nonlinearities and mitigate the effects of disturbances, nonlinearities, and errors. An adaptive ELM-based sliding mode control strategy is developed to ensure finite-time convergence of the system. Furthermore, an event-triggered control technique is proposed to regulate control outputs and reduce actuator actions and communication resources. The effectiveness of the strategies is demonstrated through simulations in a robotic manipulator system.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2023)
Article
Chemistry, Analytical
Murad Tukan, Alaa Maalouf, Matan Weksler, Dan Feldman
Summary: The study introduces an algorithm for compressing neural networks that utilizes modern techniques in computational geometry to approximate lp instead of k-rank l2 for effective compression. Experimental results confirm the practicality and theoretical advantage of this method in compressing networks such as BERT, DistilBERT, XLNet, and RoBERTa on the GLUE benchmark.
Article
Energy & Fuels
Congcong Li, Chaoqiang Fang, Yougen Huang, Hailong Zuo, Zhang Zhang, Shuoliang Wang
Summary: In mature waterflooding reservoirs, a significant amount of oil resources often remain untouched due to natural complexities and mismanagement. Infill drilling is a promising option to increase oil recovery, but determining the optimal well placements is critical and challenging. An integrated framework is constructed to achieve the best infill well locations and completions in multi-layer mature oil reservoirs.
FRONTIERS IN ENERGY RESEARCH
(2022)
Article
Engineering, Civil
Mun Chon Ho, Joanne Mun-Yee Lim, Chun Yong Chong, Kah Keong Chua, Alvin Kuok Lim Siah
Summary: This paper proposes an improved algorithm called MSPSA for the offline calibration of high-dimensional OD parameters in a simulation-based traffic model. The MSPSA algorithm combines the gradient of SPSA with the gradient of a differentiable metamodel function to improve calibration efficiency. Testing on a synthetic toy network and a complex road network in KL, Malaysia, the MSPSA algorithm shows at least 50% improvement compared to SPSA and WSPSA in both synthetic and real-world scenarios.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Masataka Ohira, Kohei Takano, Zhewang Ma
Summary: This study proposes a new approach of using DQN for fine-tuning microstrip bandpass filters, introducing two neural-network-based surrogate models to handle cross couplings in planar BPFs, and successfully demonstrating the effectiveness of the method through numerical validation.
IEEE MICROWAVE AND WIRELESS COMPONENTS LETTERS
(2021)
Article
Chemistry, Multidisciplinary
Xin Zhang, Jing Fan, Mengzhe Hei
Summary: This article introduces a method for compressing and optimizing BERT models, identifying winning tickets for binary text classification tasks through simple, fast computations. Experiments show that the method performs well on different datasets.
APPLIED SCIENCES-BASEL
(2022)
Article
Economics
Anastasios Kouvelas, Mohammadreza Saeedmanesh, Nikolas Geroliminis
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL
(2017)
Editorial Material
Engineering, Civil
Anastasios Kouvelas, Andy Chow, Eric Gonzales, Mehmet Yildirimoglu, Rodrigo Castelan Carlson
JOURNAL OF ADVANCED TRANSPORTATION
(2018)
Article
Transportation Science & Technology
A. Tympakianaki, A. Spiliopoulou, A. Kouvelas, I. Papamichail, M. Papageorgiou, Y. Wang
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2014)
Article
Engineering, Civil
Anastasios Kouvelas, Jennie Lions, S. Alireza Fayazi, Pravin Varaiya
TRANSPORTATION RESEARCH RECORD
(2014)
Article
Computer Science, Information Systems
Kimia Chavoshi, Alexander Genser, Anastasios Kouvelas
Summary: This study investigates how to plan conflict-free and efficient crossings of antagonistic vehicles' movements at lightless intersections, focusing on vehicle communication and pairing control in an automated infrastructure environment.
Article
Chemistry, Analytical
Alexander Genser, Noel Hautle, Michail Makridis, Anastasios Kouvelas
Summary: Reliably estimating traffic state in a network is crucial for effective traffic management strategies. Combining data from different sensors presents challenges due to variability in sensor specifications, noise levels, and data heterogeneity. This study proposes a fusion methodology using video measurements, thermal imaging cameras, and Google Distance Matrix to assess sensor accuracy and estimate traffic conditions. The results demonstrate the efficiency and robustness of the proposed assessment and estimation methodology.
Proceedings Paper
Automation & Control Systems
Anastasios Kouvelas, Mohammadreza Saeedmanesh, Nikolas Geroliminis
2019 IEEE 58TH CONFERENCE ON DECISION AND CONTROL (CDC)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Georgios Sarlas, Anastasios Kouvelas
MT-ITS 2019: 2019 6TH INTERNATIONAL CONFERENCE ON MODELS AND TECHNOLOGIES FOR INTELLIGENT TRANSPORTATION SYSTEMS (MT-ITS)
(2019)
Proceedings Paper
Transportation Science & Technology
Alexander Genser, Philippe Nitsche, Anastasios Kouvelas
2019 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC)
(2019)
Proceedings Paper
Automation & Control Systems
Anastasios Kouvelas, Dimitris Triantafyllos, Nikolas Geroliminis
2018 EUROPEAN CONTROL CONFERENCE (ECC)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Anastasios Kouvelas, Mohammadreza Saeedmanesh, Nikolas Geroliminis
2017 IEEE 20TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Anastasios Kouvelas, Jean-Patrick Perrin, Saad Fokri, Nikolas Geroliminis
2017 5TH IEEE INTERNATIONAL CONFERENCE ON MODELS AND TECHNOLOGIES FOR INTELLIGENT TRANSPORTATION SYSTEMS (MT-ITS)
(2017)
Proceedings Paper
Automation & Control Systems
Anastasios Kouvelas, Mohammadreza Saeedmanesh, Nikolas Geroliminis
Proceedings Paper
Transportation Science & Technology
Anastasios Kouvelas, Mohammadreza Saeedmanesh, Nikolas Geroliminis
2015 IEEE 18TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS
(2015)
Proceedings Paper
Automation & Control Systems
Konstantinos Ampountolas, Anastasios Kouvelas
2015 AMERICAN CONTROL CONFERENCE (ACC)
(2015)