检索结果-内蒙古大学图书馆

21st International Conference on Computational Science, ICCS 2021

作者： Urbańczyk, Aleksandra Nowak, Bartosz Orzechowski, Patryk Moore, Jason H. Kisiel-Dorohinicki, Marek Byrski, Aleksander Institute of Computer Science AGH University of Science and Technology Kraków Poland Penn Institute for Biomedical Informatics University of Pennsylvania PhiladelphiaPA United States

ISBN: (纸本)9783030779634

Socio-cognitive computing is a paradigm developed for the last several years, it consists in introducing into metaheuristics mechanisms inspired by inter-individual learning and cognition. It was successfully applied in hybridizing ACO and PSO metaheuristics. In this paper we have followed our previous experiences in order to hybridize the acclaimed evolution strategies. The newly constructed hybrids were applied to popular benchmarks and compared with their referential versions. © 2021, Springer Nature Switzerland AG.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Dual-Band Planar Microstrip Monopole Antenna Design Using Multi-Objective Hybrid Optimization Algorithm

Dual-Band Planar Microstrip Monopole Antenna Design Using Mu...

引用

2023 Photonics and Electromagnetics Research Symposium, PIERS 2023

作者： Hosseini, V. Shapour, F. Pinho, P. Farhang, Y. Majidzadeh, K. Ghobadi, Ch. Nourinia, J. Barshandeh, S. Shokri, M. Amiri, Zh. Jalilirad, M. Kaboutari, K. Payame Noor University Department of Computer Engineering and Information Technology Tehran Iran Islamic Azad University Urmia Branch Computer Engineering Department Urmia Iran Instituto de Telecomunicações Aveiro Portugal University of Aveiro Department of Electronics Telecommunications and Informatics Aveiro Portugal Islamic Azad University Khoy Branch Department of Computer Engineering Khoy Iran Urmia University Department of Electrical Engineering Urmia Iran School of Engineering Department of Computer Science Afagh Higher Education Institute Urmia Iran

ISBN: (纸本)9798350312843

This research uses a new proposed multi-objective optimization algorithm that utilizes an untested combined chaotic map to integrate Customized Mutated PSO (CM-PSO) with a Modified Genetic Algorithm (MGA) to design an antenna with specific electromagnetic characteristics. The hybrid approach achieves preferred outcomes faster than PSO, CM-PSO, GA, and MGA by avoiding being trapped in local minimums. The proposed Metaheuristic Algorithm (MA) functionality has been authenticated successfully using Benchmark Functions (BFs) like Rastrigin Function (RaF), Ackley Function (AF), Rosenbrock Function (RoF), and Booth Function (BoF). Finally, the validity of the offered approach for electromagnetic applications is demonstrated by optimizing a dual-band planar microstrip monopole antenna with a simple structure, such that its optimized S11 be less than -10 dB at two frequency bands encompasses 2.4 to 2.484 and 5.15 to 5.825 GHz for Wireless Local Area Network (WLAN) with IEEE 802.11 standards. The proposed algorithm allows the optimization criteria to be customized. The optimization algorithm developed in MATLAB is used to determine the necessary parameter adjustments in order to achieve expected frequency bands using CM-PSO or an innovative MGA, while high-frequency and electromagnetic simulations are performed using computer Simulation technology (CST) Studio Suite. The dimensions of the proposed antenna's elements are critical input parameters of the algorithm, named decision variables. © 2023 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

Contactless Respiratory Rate Monitoring Using FMCW Radar

Contactless Respiratory Rate Monitoring Using FMCW Radar

引用

2022 International Symposium on Electronics and Smart Devices, ISESD 2022

作者： Widiyasari, Diyah Ahmadi, Nur Adiono, Trio Purwarianti, Ayu Purnomo, Ariana Tulus Lin, Ding-Bing Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung40132 Indonesia Bandung40132 Indonesia National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei Taiwan Sampoerna University Departement of Information System Jakarta Selatan12780 Indonesia

ISBN: (数字)9798350396607

ISBN: (纸本)9798350396607

Vital sign monitoring plays a very important role in the early diagnosis and prognosis of a disease, as well as for patient health management. Among other vital signs, respiratory rate (RR) is rarely recorded and often forgotten despite the fact that it is an essential predictor of serious events such as cardiac arrest and deteriorating clinical condition. In this paper, we propose a frequency-modulated continuous-wave (FMCW) radar for contactless RR monitoring. We employ FFT to calculate RR in frequency-domain and combine it with Kalman filter to smooth out the estimated RR. We use a public dataset measuring RR from 50 children under 13 years of age recorded with 60 GHz FMCW radar. The experimental results show that the proposed method yields MAE and RMSE of 3.20 and 4.10, respectively, with respect to the reference device. Incorporating Kalman filter reduces the percentage of error by 14.83% and 13.36% compared to without it. The overall results suggest that radar-based technology can be potentially used for contactless RR monitoring which is suitable for those who cannot use contact-based monitoring devices. © 2022 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Automated graph representation learning: A survey

Automated graph representation learning: A survey

引用

2021 IEEE International Conference on Engineering, technology and Innovation, ICE/ITMC 2021

作者： Madurapperuma, Sanjula Welihindha, Sudharshana Computer Science and Engineering University of Westminster London United Kingdom School of Computing Informatics Institute of Technology Colombo 6 Sri Lanka

ISBN: (纸本)9781665449632

Research on Graph Representation Learning has seen many innovations in the recent years given the close resemblance of real-world data to graphs and its already wide usage. Graph data are considerably more difficult to analyse than traditional Euclidean data structures, which is the gap that Graph Representation Learning aims to cater to. However, automating Graph Representation Learning is a research area that is only starting to gain the focus it deserves. Most of the work that has been made available is not adequately documented or clear in their approach. It would be greatly beneficial for such work to be thoroughly analysed and evaluated under a common criterion. This paper introduces a novel automated Graph Representation Learning workflow that is utilized by an ongoing research project called AutoGRL which is built by the authors. It provides a standardized and modular production-ready platform for automated Graph Representation Learning with a level of autonomy and performance that has not been discovered. This paper also delivers an analysis of the existing work in the automated Graph Representation Learning domain, the benefits and limitations of the existing work, including comparisons of features along with new and unique research directions that are currently under-explored in the field. © 2021 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Martian Mineral Identification Using an Artificial Neural Network With Extracted Spectral Features In CRISM MTRDR Data

Enhancing Martian Mineral Identification Using an Artificial...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Priyanka Kumari Sampriti Soor Amba Shetty B. S. Daya Sagar Department of Water Resources and Ocean Engineering NIT Karnataka Surathkal India School of Computer Engineering Kalinga Institute of Industrial Technology Bhubaneswar India Systems Science and Informatics Unit Indian Statistical Institute Bangalore India

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Creating a supervised learning model for mineral identification is challenging due to the lack of ground-truth data. This study utilizes a method from existing literature that generates a training dataset by augmenting available spectra in the MICA spectral library. However, rather than using entire spectra for identification, this study extracts spectral features from each spectrum for model training. It employs the apparent continuum removal method, Segmented Curve Fitting, to identify the most informative or distinguishable parts in the spectral domain. Spectral features are then extracted based on band-centers and band-areas for each selected part. The model is evaluated against a Targeted Reduced Data Record (TRDR) dataset obtained using a hierarchical Bayesian model, demonstrating improved identification performance than the existing supervised models. Finally, using this model, dominant minerals are identified in MTRDR data from the Nilli Fossae region of Mars, and a corresponding mineral map is presented.

关键词： Training Absorption Supervised learning Artificial neural networks Feature extraction Data models Libraries

来源：评论

学校读者我要写书评

暂无评论

Relationship prompt learning is enough for open-vocabulary semantic segmentation 24

Relationship prompt learning is enough for open-vocabulary s...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jiahao Li Yang Lu Yuan Xie Yanyun Qu School of Informatics Xiamen University School of Informatics Xiamen University and Institute of Artificial Intelligence Xiamen University and Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University School of Computer Science and Technology East China Normal University and Chongqing Institute of East China Normal University

ISBN: (纸本)9798331314385

Open-vocabulary semantic segmentation (OVSS) aims to segment unseen classes without corresponding labels. Existing Vision-Language Model (VLM)-based methods leverage VLM's rich knowledge to enhance additional explicit segmentation-specific networks, yielding competitive results, but at the cost of extensive training cost. To reduce the cost, we attempt to enable VLM to directly produce the segmentation results without any segmentation-specific networks. Prompt learning offers a direct and parameter-efficient approach, yet it falls short in guiding VLM for pixel-level visual classification. Therefore, we propose the Relationship Prompt Module (RPM), which generates the relationship prompt that directs VLM to extract pixel-level semantic embeddings suitable for OVSS. More-over, RPM integrates with VLM to construct the Relationship Prompt Network (RPN), achieving OVSS without any segmentation-specific networks. RPN attains state-of-the-art performance with merely about 3M trainable parameters (2% of total parameters).

关键词：

来源：评论

学校读者我要写书评

暂无评论

WEIGHTED SUM OF SEGMENTED CORRELATION: AN EFFICIENT METHOD FOR SPECTRA MATCHING IN HYPERSPECTRAL IMAGES

arXiv

引用

arXiv 2024年

作者： Soor, Sampriti Kumari, Priyanka Sagar, B.S. Daya Shetty, Amba School of Computer Engineering Kalinga Institute of Industrial Technology Bhubaneswar India Department of Water Resources and Ocean Engineering NIT Karnataka Surathkal India Systems Science and Informatics Unit Indian Statistical Institute Bangalore India

Matching a target spectrum with known spectra in a spectral library is a common method for material identification in hyperspectral imaging research. Hyperspectral spectra exhibit precise absorption features across different wavelength segments, and the unique shapes and positions of these absorptions create distinct spectral signatures for each material, aiding in their identification. Therefore, only the specific positions can be considered for material identification. This study introduces the Weighted Sum of Segmented Correlation method, which calculates correlation indices between various segments of a library and a test spectrum, and derives a matching index, favoring positive correlations and penalizing negative correlations using assigned weights. The effectiveness of this approach is evaluated for mineral identification in hyperspectral images from both Earth and Martian surfaces. © 2024, CC BY-NC-ND.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Big data-driven target identification by machine learning: DRD2 as a therapeutic target for psoriasis

引用

Journal of Dermatological Science 2025年第1期119卷 9-17页

作者： Sakai, Takashi Sawada, Ryusuke Ichinose, Otoha Terabayashi, Takeshi Hatano, Yutaka Yamanishi, Yoshihiro Ishizaki, Toshimasa Department of Dermatology Faculty of Medicine Oita University Oita Japan Department of Pharmacology Okayama University Graduate School of Medicine Dentistry and Pharmaceutical Sciences Okayama Japan Department of Bioscience and Bioinformatics Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka Japan Department of Pharmacology Faculty of Medicine Oita University Oita Japan Department of Complex Systems Science Graduate School of Informatics Nagoya University Aichi Japan

Background: The development of medical treatments has traditionally relied on researchers leveraging scientific knowledge to hypothesize disease mechanisms and identify therapeutic agents. However, the depletion of novel therapeutic targets has become a significant challenge, resulting in stagnation within pharmaceutical research. Objective: To address the scarcity of therapeutic targets, we developed a machine learning (ML)-based system capable of predicting therapeutic target molecules for diseases. To validate its utility, we applied this system to psoriasis, aiming to identify novel treatment strategies. Methods: Our approach utilized a large clinical database to calculate reporting odds ratios for all drugs associated with the prevention of diseases of interest. We identified target proteins by analyzing large chemical structure databases to discover proteins commonly associated with preventive drug candidates. Experimental validation was conducted by administering a predicted therapeutic candidate in an imiquimod-induced psoriasis mouse model. Results: The ML-based predictions identified drugs for Parkinson's disease as potential preventive candidates for psoriasis. Further analysis highlighted dopamine receptor D2 (DRD2) as a therapeutic target. Administration of a DRD2 agonist alleviated psoriasis symptoms in mice, evidenced by the downregulation of mRNA expression in the IL-17 pathway and reduced serum tumor necrosis factor-α levels. Conclusion: This study demonstrates the utility of a novel ML-based system for identifying therapeutic targets, as shown by its successful application in uncovering the role of DRD2 in psoriasis. Beyond psoriasis, this system offers significant potential for exploring pathological mechanisms and discovering therapeutic targets across various diseases. © 2025 The Authors

关键词： artificial intelligence big data dopamine receptor D2 machine learning psoriasis

来源：评论

学校读者我要写书评

暂无评论

Digital twin assisted workpiece referencing for compensating the stock deviation of casted parts

引用

Procedia CIRP 2023年 118卷 288-293页

作者： Tamás Cserteg Gábor Erdős Gergely Horváth András Kovács EPIC Centre of Excellence in Production Informatics and Control Institute for Computer Science and Control (SZTAKI) Budapest H-1111 Hungary Faculty of Informatics Eötvös Loránd University Budapest H-1117 Hungary Department of Manufacturing Science and Technology Budapest University of Technology and Economics Budapest H-1111 Hungary

Stock deviation of casted parts needs to be handled by adapting the CNC machining code to every new batch. Usually, human experts deal with this workpiece referencing task, but the demand for automation is expressed by the industry. This paper introduces a Digital Twin (DT) supported workpiece referencing method, implemented in the following steps: building the DT of the CNC machining cell, loading measurements of the casted part into the DT, solving the workpiece referencing problem as a convex optimization problem, and generating the compensated CNC code. The proposed approach is illustrated in a case study from the automotive industry.

关键词： Machining Workpiece referencing Digital Twin Convex optimization

来源：评论

学校读者我要写书评

暂无评论

A Heterogeneous Network-based Contrastive Learning Approach for Predicting Drug-Target Interaction

A Heterogeneous Network-based Contrastive Learning Approach ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Hu, Junwei Bewong, Michael Kwashie, Selasi Zhang, Wen Nofong, Vincent M. Wu, Guangsheng Feng, Zaiwen Huazhong Agricultural University College of Informatics Hubei Wuhan China Charles Sturt University School of Computing Mathematics & Engineering Wagga WaggaNSW Australia Charles Sturt University Artificial Intelligence & Cyber Futures Institute BathurstNSW Australia University of Mines and Technology Faculty of Engineering Tarkwa Ghana Xinyu University School of Mathematics and Computer Science China

ISBN: (纸本)9798350386226

Drug-target interaction (DTI) prediction is crucial for drug development and repositioning. Methods using heterogeneous graph neural networks (HGNNs) for DTI prediction have become a promising approach, with attention-based models often achieving excellent performance. However, these methods typically overlook edge features when dealing with heterogeneous biomedical networks. We propose a heterogeneous network-based contrastive learning method called HNCL-DTI, which designs a heterogeneous graph attention network to predict potential/novel DTIs. Specifically, our HNCL-DTI utilizes contrastive learning to collaboratively learn node representations from the perspective of both node-based and edge-based attention within the heterogeneous structure of biomedical networks. Experimental results show that HNCL-DTI outperforms existing advanced baseline methods on benchmark datasets, demonstrating strong predictive ability and practical effectiveness. The data and source code are available at https://***/Zaiwen/HNCL-DTI. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：