检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2023

作者： Jeong, Seunghun Park, Yejin Kim, Hong Kook Ai Graduate School Korea Republic of Gwangju Institute of Science and Technology School of Electrical Engineering and Computer Science Gwangju61005 Korea Republic of

ISBN: (纸本)9798350344318

This paper proposes an end-of-sentence (EOS) token modeling approach for streaming conformer-based Korean children's speech recognition applied to a social robot. The baseline system for speech recognition is a streaming conformer-based speech recognition model with the joint connectionist temporal classification attention-based encoder-decoder architecture, and it is trained with the AIHub Child•Infant Free-Talk dataset. However, it is difficult to determine sentence boundaries in children's speech because the speaking style of children is somewhat different from that of adults. Thus, the proposed approach is to insert EOS tokens into each sentence of a large children's dataset to detect sentence boundaries. Finally, we evaluated the performance of the proposed approach on a dataset collected under scenarios of a voice interaction between children and a social robot. Consequently, the proposed EOS token modeling decreased character error rate by 1.7%, compared to the baseline. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Automatic question generation for bahasa indonesia examination using copynet 9th

Automatic question generation for bahasa indonesia examinati...

引用

9th International Conference on computer science and Computational Intelligence, ICCSCI 2024

作者： Henry, Matthew Martianus Elwirehardja, Gregorius Natanael Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

In educational institutions, an educator is responsible for assessing the student's knowledge grasp through examination. Creating exam questions, even the low-level factoid questions, is time-consuming, especially for inexperienced educators. Therefore, this study aims to create a sequence-to-sequence model using CopyNet by exploiting its copying mechanism advantage to automatically generate Bahasa Indonesia factoid questions to ease the educator's burden. Indonesian records in the TyDi QA dataset are used as the model input. GRU and Bi-GRU are employed as the CopyNet encoder, while LSTM is used as the CopyNet decoder. The model that utilizes GRU as the encoder achieves BLEU1, BLEU2, BLEU3, BLEU4, and ROUGE-L scores of 0.28, 0.19, 0.14, 0.1, and 0.32, respectively. Bi-GRU utilization as the model encoder achieves BLEU1, BLEU2, BLEU3, BLEU4, and ROUGE-L scores of 0.26, 0.17, 0.12, 0.09, and 0.30, respectively. Models using either encoder still achieve low scores. However, compared with the previous work, the result is still on par regarding the BLEU score. Further examination found that the generated questions do not adhere to semantic and syntactical correctness. Adding more records to the dataset and utilizing a more advanced architecture like CopyBERT are encouraged to improve the model performance in future work. Despite the result, this study has shown that CopyNet, primarily designed for text summarization or single-turn dialogue, can be tailored for factoid question generation. © 2024 The Authors.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Constrained Two-Line Center Problems 35

Constrained Two-Line Center Problems

引用

35th International Symposium on Algorithms and Computation, ISAAC 2024

作者： Ahn, Taehoon Bae, Sang Won Graduate School of Artificial Intelligence Pohang University of Science and Technology Korea Republic of Division of Artificial Intelligence and Computer Science Kyonggi University Suwon Korea Republic of

ISBN: (纸本)9783959773546

Given a set P of n points in the plane, the two-line center problem asks to find two lines that minimize the maximum distance from each point in P to its closer one of the two resulting lines. The currently best algorithm for the problem takes O(n2 log2 n) time by Jaromczyk and Kowaluk in 1995. In this paper, we present faster algorithms for three variants of the two-line center problem in which the orientations of the resulting lines are constrained. Specifically, our algorithms solve the problem in O(n log n) time when the orientations of both lines are fixed;in O(n log3 n) time when the orientation of one line is fixed;and in O(n2α(n) log n) time when the angle between the two lines is fixed, where α(n) denotes the inverse Ackermann function. © Taehoon Ahn and Sang Won Bae.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Faster Algorithms for a Lexicographic Bi-Criteria Line Balancing Problem with Totally Ordered Precedence Constraints 13

Faster Algorithms for a Lexicographic Bi-Criteria Line Balan...

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Imahori, Shinji Karuno, Yoshiyuki Ueda, Yuma Chuo University Faculty of Science and Engineering Tokyo Japan Kyoto Institute of Technology Faculty of Mechanical Engineering Kyoto Japan Graduate School of Science and Technology Kyoto Institute of Technology Mechanodesign Program Kyoto Japan

ISBN: (纸本)9798350373332

The line balancing has been an important production strategy which aims at redressing the balance of workloads on machines in an assembly type of production system. In this paper, a lexicographic bi-criteria optimization model of the line balancing is revisited for a mass-production of one homogeneous product. A sequence of machines and a totally ordered set of tasks are given. The machines are considered to be situated along with a production line, according to their sequence. Precedence relations between tasks are specified by the total order of tasks. The task set also consists of a given number of disjoint subsets, namely categories such that tasks in a category are considered to constitute a certain kind of family of technical skills. Each task has a positive processing time and a category index. A solution to the problem is expressed by an assignment of tasks to machines, and for the feasibility of a solution, the assignment must obey the totally ordered precedence constraint on tasks. The sum of processing times of tasks assigned to a machine in a feasible solution is the load of the machine, and the number of category indexes of tasks assigned to a machine is referred to as the degree of diverseness of the task subset. The primary objective of the problem is to minimize the maximum machine load, and the second objective is to minimize the maximum degree of diverseness of tasks assigned to a machine. The lexicographic bi-criteria line balancing problem with totally ordered precedence constraints has been known to admit a polynomial time exact algorithm, whose time complexity is linear in the number of machines and squared in the number of tasks. In this paper, a faster polynomial time exact algorithm is proposed, which improves the time complexity to be squared in the number of tasks. © 2024 IEEE.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models

MamMIL: Multiple Instance Learning for Whole Slide Images wi...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Fang, Zijie Wang, Yifeng Zhang, Ye Wang, Zhi Zhang, Jian Ji, Xiangyang Zhang, Yongbing Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen China Shenzhen China School of Computer Science and Technology Shenzhen China Peking University School of Electronic and Computer Engineering Shenzhen Graduate School Shenzhen China Tsinghua University Department of Automation Beijing China

ISBN: (纸本)9798350386226

Recently, pathological diagnosis has achieved superior performance by combining deep learning models with the multiple instance learning (MIL) framework using whole slide images (WSIs). However, the giga-pixeled nature of WSIs poses a great challenge for efficient MIL. Existing studies either do not consider global dependencies among instances, or use approximations such as linear attentions to model the pair-to-pair instance interactions, which inevitably brings performance bottlenecks. To tackle this challenge, we propose a framework named MamMIL for WSI analysis by cooperating the selective structured state space model (i.e., Mamba) with MIL, enabling the modeling of global instance dependencies while maintaining linear complexity. Specifically, considering the irregularity of the tissue regions in WSIs, we represent each WSI as an undirected graph. To address the problem that Mamba can only process 1D sequences, we further propose a topology-aware scanning mechanism to serialize the WSI graphs while preserving the topological relationships among the instances. Finally, in order to further perceive the topological structures among the instances and incorporate short-range feature interactions, we propose an instance aggregation block based on graph neural networks. Experiments show that MamMIL can achieve advanced performance than the state-of-the-art frameworks. The code can be accessed at https://***/Vison307/MamMIL. © 2024 IEEE.

关键词： Undirected graphs

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Helmet Wearing Detecting Algorithms Based on YOLO 5

A Systematic Review of Helmet Wearing Detecting Algorithms B...

引用

5th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2024

作者： Wang, Tianshun Ren, Fei Fu, Lifang Doma, Bonifacio T. School of Information Technology Mapua University Makati Philippines School of Graduate Studies Mapua University Makati Philippines Zhengzhou Shengda University Department of Computer Science and Technology Zhengzhou China

ISBN: (纸本)9798350385557

In industrial production and social transportation, there are often various potential risks that threaten the life safety of participants. In all workers' lives in the most serious, generally likely to happen are falling objects, collapses, and traffic accidents, etc. These serious lessons let all workers live on the helmet wearing and supervision more and more attention, effective supervision will reduce accidents. Therefore, we collected literature and provided an overview of deep learning algorithms related to helmet detection. After comparing features of popular object detection algorithms, YOLO algorithm was chosen as the research object in this field. First, the development history of the YOLO algorithm (YOLOvl∼YOLOv8) is described, and then the literature on YOLO-based helmet wearing detection is reviewed. Second, we analyze selected literature to identify current knowledge, key gaps, and improvements in YOLO for specific helmet wearing detection tasks. Finally, future improvement ideas and research trends are analyzed and prospected. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Random Forest Based QSAR Model Analysis for Predicting Drug Effectiveness Against Mycobacterium Tuberculosis Bacteria 11

Random Forest Based QSAR Model Analysis for Predicting Drug ...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Ekosputri, Alicia Josephine Ardianti, Amanda Anggreainy, Maria Susan Artanto, Brychan Fitriawati, Nora Valentina, Fanny Angelia Santoso, Vincent Kartamulya School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11530 Indonesia Bina Nusantara University Binus Online Learning Information Systems Department Jakarta11530 Indonesia

ISBN: (纸本)9798350389654

This research focuses on the use of machine learning methods, especially Random Forest, in designing tuberculosis drugs more effectively and efficiently. The research process begins with the creation of a QSAR (Quantitative Structure-Activity Relationship) model using a dataset from ChEMBL that includes compounds with activity against Mycobacterium tuberculosis. This model aims to predict the pIC50 value, which is an indicator of a compound's biological activity as a tuberculosis drug. The results of the Random Forest model showed high accuracy, which is 92%. This accuracy indicates that the model has a good ability in predicting the effectiveness of compounds against Mycobacterium tuberculosis. With this result, the developed model can be used as an auxiliary tool in the discovery of tuberculosis drugs and can be further developed to increase the effectiveness in drug research. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Analysis of Extreme Diurnal Temperature Range: Based on Generalized Extreme Value Model 21

Analysis of Extreme Diurnal Temperature Range: Based on Gene...

引用

21st International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2024

作者： Yinqi, Luo Liyin, Liu Guoyi, Xie Sui, Luo Suhang, Li Graduate School University of Electronic Science and Technology of China Chengdu611731 China University of Electronic Science and Technology of China Logistics Support Department Chengdu611731 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu Sichuan611731 China

ISBN: (纸本)9798331519254

Cengong County is a traditional agricultural county in Guizhou province. Extreme temperature difference between day and night has a significant impact on the development of local agriculture. In order to analyze the distribution characteristics of extreme day-night temperature difference in the local area, a Generalized Extreme Value(GEV) model was constructed. Firstly, according to the relevant theory of GEV modeling, this paper extracts the daily temperature difference between day and night in Cengong County from 1960 to 2022, takes one year as the grouping unit, and calculates the maximum value in each group, so as to obtain the sample data needed for modeling. Then, the Maximum Likelihood Estimation(MLE) and Profile Likelihood Estimation(PLE) are used to solve the model parameter estimates. Secondly, the grouping length has a significant impact on the accuracy of the model, so the stability of the model under different grouping intervals is analyzed. The last, the return level is calculated under the different return period. The results showed that the maximum temperature difference between day and night in Cengong County obeyed Weibull distribution with an upper limit, and the theoretical upper limit was 26.819C°. The model had good extrapolation ability. © 2024 IEEE.

关键词： Weibull distribution

来源：评论

学校读者我要写书评

暂无评论

Energy Optimization of Distributed Video Processing System in Dynamic Environment 21

Energy Optimization of Distributed Video Processing System i...

引用

21st IEEE Consumer Communications and Networking Conference, CCNC 2024

作者： Lou, Yang Shimonishi, Hideyuki Murata, Masayuki Techasarntikul, Nattaon Graduate School of Information Science and Technology Osaka University Osaka Japan National Yang Ming Chiao Tung University Department of Computer Science Hsinchu Taiwan

ISBN: (纸本)9798350304572

To create a future society based on cyber-physical systems, we need real-time digital twins made with cameras and sensors. The challenge is making this energy-efficient. A model in [1] suggests dividing video analysis tasks among terminals, edge servers, and cloud servers to minimize power consumption. This paper addresses energy optimization in dynamic environments with a two-level approach: detecting and categorizing environmental changes (LEC and SEC) and using a two-level adaptive evolutionary algorithm (TAEA) to make corresponding adjustments. A case study with a differential evolution algorithm demonstrates its effectiveness in minimizing energy costs and improving processing accuracy and latency violations. © 2024 IEEE.

关键词： differential evolution dynamic system energy efficiency genetic algorithm optimization Video analysis

来源：评论

学校读者我要写书评

暂无评论

Recyclability and Self-Healing of Dynamic Cross-Linked Polyimide with Mechanical/Electrical Damage

引用

Energy & Environmental Materials 2023年第1期6卷 401-407页

作者： Baoquan Wan Ming-Sheng Zheng Xing Yang Xiaodi Dong Yuchao Li Yiu-Wing Mai George Chen Jun-Wei Zha School of Chemistry and Biological Engineering University of Science and Technology BeijingBeijing 100083China Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing 100083China Shunde Graduate School of University of Science and Technology Beijing Foshan 528300China School of Materials Science and Engineering Liaocheng UniversityLiaocheng 252059China Centre for Advanced Materials Technology(CAMT) School of AerospaceMechanical and Mechatronic EngineeringThe University of SydneySydney New South Wales 2006Australia Department of Electronics and Computer Science University of SouthamptonSouthampton SO171BJUK

Recyclability and self-healing are two most critical factors in developing sustainable polymers to deal with environmental pollution and resource *** this work,a dynamic cross-linked polyimide insulation film with full closed-loop recyclability is successfully prepared,which also possesses good self-healing ability after being mechanical/electrical damaged depending on the Schiff base dynamic covalent *** recycled and self-healed polyimide film still maintain its good tensile strength(r t)>60 MPa with Young’s modulus(E)>4 GPa,high thermal stability with glass transition temperature(T g)>220℃,and outstanding insulation property with breakdown strength(E 0)>358 kV mm^(-1),making it a very promising low energy consumption and high temperature resistant insulation *** strategy of using Schiff base dynamic covalent bonds for reversible repairing the structure of high T g polyimides promotes the wider application of such sustainable and recyclable material in the field of electrical power and micro-electronics.

关键词： electrical damage polyimide recyclability self-healing

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：