检索结果-内蒙古大学图书馆

7th International Conference on Information Management and Management Science, IMMS 2024

作者： Cheng, Xijie Feng, Weiqing Pang, Su Hu, Gang Cai, Shimin College of Management Science Chengdu University of Technology China Faculty of Computer Science & Information Technology Universiti Malaya Malaysia Sichuan Tobacco Company Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China China

ISBN: (纸本)9798400716997

Traditional methods for assessing tobacco leaf quality rely heavily on experience and subjective judgment, resulting in inefficiency, and a lack of accuracy and reproducibility. To address these challenges, there is an urgent need for a tobacco leaf quality assessment system capable of assessing various aspects of leaf quality in a systematic and quantitative manner. In this paper, we quantitatively analyze the tobacco leaf quality assessment system for Sichuan tobacco, specifically focusing on the Yunyan 87 variety. In further, we employ Grey Relational Analysis and Circle Ill-Condition Index Analysis for indicator selection and optimization. Through quantitative analysis, key indicators that significantly impact the assessment results and exhibit low information redundancy are retained, and weights are reallocated based on correlation analysis. The optimized system retains four core indicators: Oil Content, Delicacy, Total Nicotine, and Sugar-to-Nicotine Ratio, significantly enhancing the scientific rigor and practical utility of the assessment process. This optimized assessment tool provides a scientific basis for quality control in Sichuan tobacco production, ultimately enhancing production efficiency and product quality. © 2024 ACM.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

A Review on Heart Diseases Prediction Using Artificial Intelligence 1st

A Review on Heart Diseases Prediction Using Artificial Intel...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Hasnat, Rehnuma Al Mamun, Abdullah Musha, Ahmmad Tahabilder, Anik Department of Electrical and Electronic Engineering Pabna University of Science and Technology Pabna Bangladesh Faculty of Engineering and Technology Multimedia University Melaka Malaysia Department of Computer Science Wayne State University DetroitMI United States

ISBN: (纸本)9783031346217

Heart disease is one of the major concerns of this modern world. The insufficiency of the experts has made this issue a bigger concern. Diagnosing heart diseases at an early stage is possible with Artificial Intelligence (AI) techniques, which will lessen the needed number of experts. This paper has initially discussed different kinds of heart diseases and the importance of detecting them early. Two popular diagnosis systems for collecting data and their working function are then highlighted. Different types of Model architectures in the corresponding field are described. Firstly, the Support Vector Machine (SVM) machine learning algorithm is described, and secondly, popular deep learning model architecture such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), etc. are highlighted to detect heart disease. Finally, discussion, comparison, and future work are described. This article aims to clarify AI’s present and future state in medical technology to predict heart diseases. © 2023, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Development and analysis of whispering gallery mode model for refractive index sensing 6

Development and analysis of whispering gallery mode model fo...

引用

6th Photonics Meeting 2023, PM 2023

作者： Batumalay, M. Zain, H.A. Rahim, H.R.A. Harun, S.W. Department of Electrical Engineering University of Malaya Kuala Lumpur50603 Malaysia Faculty of Data Science and Information Technology INTI International University Nilai Negeri Sembilan71800 Malaysia Faculty of Electronic and Computer Engineering Universiti Teknikal Malaysia Melaka Melaka Malaysia

A refractive index sensor based on a whispering gallery mode resonator is numerically investigated in this paper. Whispering gallery mode resonators confine light and can be used in sensing applications, and this work presents the model built using COMSOL software to analyze their sensing performance. This work has investigated the WGM resonators' response to refractive index changes numerically using 2D models in the refractive index ranges 1.000 and 1.333. The resonator showed a sensitivity of 167 nm/RIU in the refractive index range of 1.3331.4 and a sensitivity of 95 nm/RIU in the refractive index range of 1.000-1.010. The sensing resonator has potential applications for biological and chemical analytes. © Published under licence by IOP Publishing Ltd.

关键词： Refractive index

来源：评论

学校读者我要写书评

暂无评论

Novel Size-Reduced Coaxial Cavity Filters For 5G Networks 12

Novel Size-Reduced Coaxial Cavity Filters For 5G Networks

引用

12th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2024

作者： Huong, Tran Thi Thu Bao, An Tri Le, Trong-Hieu Yem, Vu Van University of Economics - Technology for Industries Faculty of Electronics and Computer Engineering Hanoi Viet Nam Hanoi - Amsterdam High School for The Gifted Hanoi Viet Nam Electric Power University Faculty of Electronics and Telecommunications Hanoi Viet Nam Hanoi University of Science and Technology School of Electrical and Electronic Engineering Hanoi Viet Nam

ISBN: (纸本)9798350351019

This paper presents a novel coaxial cavity filter using in 5G NR Base Stations. The resonant cylinder utilizes stepped impedance technology combined with folding edge bending and rectangular zigzag arm structure on the top to improve the electrical coupling mainline. Therefore, dimensions of cavity filter are reduced while maintaining the filter performance parameters. This proposed resonator is verified in the design of one filter integrated in C-Band 5G station with ten orders and four zero points. The dimensions of the filter are only 56.81 mm x 15.56 mm x 9.5 mm (length x width x height). The simulation results show the passband of 304MHz, the return loss of 15.6dB, the insertion loss of 0.1dB. These specifications are suitable for applying in Band C 5G network. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Hysteresis Current Control of Buck-Boost Non-Isolated Onboard Charger for Electric Vehicles 49

Hysteresis Current Control of Buck-Boost Non-Isolated Onboar...

引用

49th Annual Conference of the IEEE Industrial electronics Society, IECON 2023

作者： Komurcugil, Hasan Guler, Naki Bayhan, Sertac Gulbudak, Ozan Eastern Mediterranean University Department of Computer Engineering Famagusta Turkey Gazi University Technology Faculty Department of Electrical-Electronic Engineering Ankara Turkey Qatar Environment and Energy Research Institute Doha Qatar Karabuk University Department of Electrical & Electronics Engineering Turkey

ISBN: (纸本)9798350331820

This paper proposes a hysteresis current control (HCC) method for a single-inductor buck-boost non-isolated onboard charger for electric vehicles. The charger is capable of working both in the boost and buck modes. The proposed HCC relies on the buck-boost inductor current and its reference which is generated using a proportional-resonant (PR) controller using grid current error. The reference current generated by PR controller is modified to suppress the oscillations in the inductor currents. An active damping by using a virtual resistor connected in series to filter inductor is used which does not require an additional sensor. A proportional-integral (PI) controller is used to generate the amplitude of grid current reference, which is utilized in constant current (CC) and constant voltage (CV) modes. The effectiveness of the proposed control strategy as well as the control method, is investigated by simulation studies by considering two different battery voltage levels (48V and 350V). The results show that the proposed method is able to charge the battery in CV and CC modes. Moreover, the grid current is maintained in unity power factor at a reasonably low total harmonic distortion (THD) which is smaller than the limits recognized by international standards. © 2023 IEEE.

关键词： Charging (batteries)

来源：评论

学校读者我要写书评

暂无评论

Exploiting Partial Observability and Optimized Simple State Representations in Deep Q-Learning 20

Exploiting Partial Observability and Optimized Simple State ...

引用

20th International Conference on Frontiers of Information Technology, FIT 2023

作者： Mahmood, Danyaal Arshad, Usama Ali, Raja Hashim Ul Abideen, Zain Shah, Muhammad Huzaifa Khan, Talha Ali Ijaz, Ali Zeeshan Ali, Nisar Siddique, Abu Bakar Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany Applications & Nanostructure BCMaterials Basque Center for Materials Spain University of Regina Faculty of Electronic Systems Engineering Regina Canada

ISBN: (纸本)9798350395785

The advent of deep Q-learning has opened up new possibilities in training autonomous agents to perform intelligently in intricate settings. This research work examines the potential of deep Q-learning in the paradigmatic Snake game, which requires an agent to navigate a grid, ingest food items, and avoid collisions. We incorporated a partially observable game state, introducing a novel level of difficulty to the task. Our proposed approach utilizes a straightforward feed-forward neural network to estimate Q-values of potential actions, given the current state. The agent progressively learns to balance between exploration and exploitation, allowing it to navigate optimally in the game scenario. Most existing studies in deep Q-learning for the Snake game overlook the complexities posed by partial observability, focusing mainly on fully observable state representations. Furthermore, the majority of the investigations delve into the efficacy of complex neural network architectures, leaving a gap in the understanding of the performance of more simplistic feed-forward networks. Our study fills this gap by offering an in-depth exploration and analysis of deep Q-learning strategies, especially when applied to partially observable game states and simple neural networks. Simulations and results reveal that adopting simpler state representations can significantly boost the agent's performance in the Snake game. A more detailed and intricate reward function is also observed to enhance the agent's decision-making skills and overall proficiency in the game. These observations underscore the significance of optimizing state representations and reward functions for maximizing the performance of deep Q-learning agents in the Snake game. © 2023 IEEE.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Wire grounding electrode placed near cylindrical multi-layered ground non-homogeneity 22

Wire grounding electrode placed near cylindrical multi-layer...

引用

22nd International Symposium on Electrical Apparatus and Technologies, SIELA 2022

作者： Jovanovic, Dejan Cvetkovic, Nenad Jovanovic, Dragana Vuckovic, Dragan Hederic, Zeljko University of Nis Faculty of Electronic Engineering Nis Serbia Josip J. Strossmayer University Faculty of El. Engineering Computer Science and Information Technology Osijek Croatia

ISBN: (数字)9781665411394

ISBN: (纸本)9781665411394

Analysis and realization of grounding system fulfilling technical requirements, very often require analysis of the influence of soil non-homogeneity on grounding characteristics. In some cases, non-homogeneity can be approximated as vertical homogeneous cylindrical domain. Such non-homogeneities are various tubes, wells or pillar foundation. In this paper, the procedure for modeling of soil non-homogeneity as multilayered cylindrical domain is presented. The approach is based on using the Method of Moments and Green's function, applicable for analysis of grounding electrodes placed in the surrounding soil. Within that, particular procedure for grounding electrode formed of finite number of wires is described. It has been applied on problem of vertical electrode in the vicinity of well having concrete cylindrical shell. © 2022 IEEE.

关键词： Method of moments

来源：评论

学校读者我要写书评

暂无评论

Profit-based uncertainty estimation with application to credit scoring

引用

European Journal of Operational Research 2025年第2期325卷 303-316页

作者： Xu, Yong Kou, Gang Ergu, Daji College of Computer Science and Artificial Intelligence Southwest Minzu University Chengdu610225 China College of Electronic and Information Southwest Minzu University Chengdu610225 China Key Laboratory of Electronic Information Engineering Southwest Minzu University Chengdu610225 China School of Business Administration Faculty of Business Administration Southwestern University of Finance and Economics Chengdu611130 China Xiangjiang Laboratory Changsha410205 China

Credit scoring is pivotal in financial risk management and has attracted significant research interest. While existing studies primarily concentrate on enhancing model predictive power and economic value, they often overlook the crucial aspect of predictive uncertainty, especially in the context of deep neural networks applied to credit scoring. This study addresses uncertainty estimation in credit scoring and evaluates three widely used uncertainty methods across various credit datasets. Additionally, guided by the maximum profit criterion, we propose two profit-based uncertainty metrics to assess profit uncertainties stemming from predictive uncertainty, specifically targeting class-dependent and instance-dependent cost scenarios. Subsequently, we develop a classification system with a rejection mechanism based on these metrics. Our approach aims to improve model profitability and reduce predictive uncertainty, specifically regarding model profit. Empirical results across several benchmark credit datasets indicate that our proposed framework outperforms existing methods in terms of increasing model profit in different credit-scoring scenarios. Furthermore, sensitivity analyses of varying cost parameter settings highlight the robustness of our framework. © 2025 The Authors

关键词： Decision support systems Uncertainty estimation Performance measurement Deep learning Credit scoring

来源：评论

学校读者我要写书评

暂无评论

EV Scheduling Optimization by Utilizing Excess Photovoltaic Energy with Forward Dynamic Programming

EV Scheduling Optimization by Utilizing Excess Photovoltaic ...

引用

International Conference on Green Energy and Applications (ICGEA)

作者： Cuong Le-The Nhat Hoang Tuyen Nguyen-Duc Hirotaka Takano School of Electronic and Electrical Engineering Hanoi University of Science and Technology Hanoi Vietnam Dept. of Electrical Electronic and Computer Engineering Faculty of Engineering Gifu University Japan

ISBN: (数字)9798350349009

ISBN: (纸本)9798350349016

As the global trend toward sustainable transportation gains momentum, electric vehicles (EVs) have become increasingly popular due to their ecological advantages. However, as the EV population expands, issues pertaining to power quality, such as voltage stability and load profiles, have emerged. Various solutions have been proposed to mitigate the adverse effects of EV charging. One such approach involves the amalgamation of renewable energy sources (RES) within charging infrastructure, coupled with Vehicle-to-Grid (V2G) technology. In this article, a new method is presented that utilizes RES in conjunction with the Forward Dynamic Programming Algorithm to lower the cost of charging all EVs. This approach also works to even out the demand curve by considering EV owners' travel schedules.

关键词： Degradation Vehicle-to-grid Schedules Costs Heuristic algorithms Electricity Trajectory

来源：评论

学校读者我要写书评

暂无评论

Prediction of Polycystic Ovary Syndrome Using Genetic Algorithm-driven Feature Selection

Prediction of Polycystic Ovary Syndrome Using Genetic Algori...

引用

2023 International Conference on IT and Industrial Technologies, ICIT 2023

作者： Faridoon, Fatima Ali, Raja Hashim Ul Abideen, Zain Shahzadi, Nazia Ijaz, Ali Zeeshan Arshad, Usama Ali, Nisar Imad, Muhammad Nabi, Said Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Spain University of Regina Faculty of Electronic Systems Engineering Regina Canada

ISBN: (纸本)9798350315974

PolyCystic Ovary Syndrome (PCOS) is a hormonal disorder frequently found in women of reproductive age having a significant impact on the cause of infertility. It is an endocrine condition characterized by abnormalities in female hormone levels and aberrant synthesis of male hormones. This syndrome causes ovarian malfunction, increasing the risk of miscarriage and infertility. PCOS has a wide range of symptoms, making a diagnosis difficult. In this study, we proposed a feature selection method based on genetic algorithm with logistic regression to increase the accuracy of early diagnosis. A dataset containing the clinical and biochemical characteristics of 109 patients, including 36 with PCOS, is used. The genetic algorithm is used to extract the most important features from the dataset. Then, a logistic regression model is used for classification. The proposed model outperformed the baseline model that used all features, which had an accuracy of 86.2%, and produced a markedly improved accuracy of 95.4%. These results show that the proposed model effectively locates key characteristics for PCOS diagnosis. © 2023 IEEE.

关键词： Feature Selection

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：