检索结果-内蒙古大学图书馆

12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023

作者： Zheng, Chen Zhang, Huan Zhao, Yan Lai, Yuxuan The Open University of China Beijing China Engineering Research Center of Integration and Application of Digital Learning Technology Ministry of Education Beijing China

ISBN: (纸本)9783031446986

Coherence is a crucial aspect of evaluating text readability and can be assessed through two primary factors when evaluating an essay in a scoring scenario. The first factor is logical coherence, characterized by the appropriate use of discourse connectives and the establishment of logical relationships between sentences. The second factor is the appropriateness of punctuation, as inappropriate punctuation can lead to confused sentence structure. To address these concerns, we propose a coherence scoring model consisting of a regression model with two feature extractors: a local coherence discriminative model and a punctuation correction model. We employ gradient-boosting regression trees as the regression model and impose monotonicity constraints on the input features. The results show that our proposed model better generalizes unseen data. The model achieved third place in track 1 of NLPCC 2023 shared task 7. Additionally, we briefly introduce our solution for the remaining tracks, which achieves second place for track 2 and first place for both track 3 and track 4. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML

引用

Daimon 2024年 79卷 629-677页

作者： Weerts, Hilde Pfisterer, Florian Feurer, Matthias Eggensperger, Katharina Bergman, Edward Awad, Noor Vanschoren, Joaquin Pechenizkiy, Mykola Bischl, Bernd Hutter, Frank Eindhoven University of Technology Netherlands Ludwig-Maximilians-Universität München Munich Center for Machine Learning Germany Albert-Ludwigs-Universität Freiburg Germany University of Tübingen Germany

The field of automated machine learning (AutoML) introduces techniques that automate parts of the development of machine learning (ML) systems, accelerating the process and reducing barriers for novices. However, decisions derived from ML models can reproduce, amplify, or even introduce unfairness in our societies, causing harm to (groups of) individuals. In response, researchers have started to propose AutoML systems that jointly optimize fairness and predictive performance to mitigate fairness-related harm. However, fairness is a complex and inherently interdisciplinary subject, and solely posing it as an optimization problem can have adverse side effects. With this work, we aim to raise awareness among developers of AutoML systems about such limitations of fairness-aware AutoML, while also calling attention to the potential of AutoML as a tool for fairness research. We present a comprehensive overview of different ways in which fairness-related harm can arise and the ensuing implications for the design of fairness-aware AutoML. We conclude that while fairness cannot be automated, fairness-aware AutoML can play an important role in the toolbox of ML practitioners. We highlight several open technical challenges for future work in this direction. Additionally, we advocate for the creation of more user-centered assistive systems designed to tackle challenges encountered in fairness work. © 2024 The Authors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A self-driving solution for resource-constrained autonomous vehicles in parked areas

引用

High-Confidence Computing 2024年第1期4卷 32-42页

作者： Jin Qian Liang Zhang Qiwei Huang Xinyi Liu Xiaoshuang Xing Xuehan Li College of Information Engineering Taizhou UniversityTaizhou 225300China Engineering Research Center of Integration and Application of Digital Learning Technology Ministry of EducationBeijing 100039China School of Computer Science and Engineering Changshu Institute of TechnologyChangshu 215500China The School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China

Autonomous vehicles in industrial parks can provide intelligent,efficient,and environmentally friendly transportation services,making them crucial tools for solving internal transportation *** the characteristics of industrial park scenarios and limited resources,designing and implementing autonomous driving solutions for autonomous vehicles in these areas has become a research *** paper proposes an efficient autonomous driving solution based on path planning,target recognition,and driving decision-making as its core *** designs for path planning,lane positioning,driving decision-making,and anti-collision algorithms are *** analysis and experimental validation of the proposed solution demonstrate its effectiveness in meeting the autonomous driving needs within resource-constrained environments in industrial *** solution provides important references for enhancing the performance of autonomous vehicles in these areas.

关键词： Autonomous vehicles Path planning Target recognition Driving decision-making Self-driving

来源：评论

学校读者我要写书评

暂无评论

OP-FedELM: One-Pass Privacy-Preserving Federated Classification via Evolving Clustering Method and Extreme learning Machine Hybrid 1

引用

23rd International Conference on Intelligent Systems Design and Applications, ISDA 2023

作者： Prasad, Polaki Durga Vivek, Yelleti Ravi, Vadlamani Center for Artificial Intelligence and Machine Learning Institute for Development and Research in Banking Technology Hyderabad500076 India School of Computer and Information Sciences University of Hyderabad Hyderabad500046 India

ISBN: (数字)9783031648366

ISBN: (纸本)9783031648359

The need to protect data privacy is critical in industries like healthcare, finance, and banking. Federated learning (FL) has attracted widespread attention due to its decentralized, distributed training and the potential to protect privacy. However, FL presents challenges like privacy concerns, network, and data heterogeneity. This motivated us to propose a two-phase, one-pass FL algorithm, where (I) In the first phase, the differentially private dataset is generated by incorporating the Laplacian mechanism, and (ii) during the second phase, we employed one-pass privacy-preserving federated extreme learning machine (OP-FedELM) for generating globally shared training dataset and build the global model. ELM generally tends to overfit training data at a client. Therefore, we employed a modified version of the Evolving clustering algorithm (ECM), an online one-pass clustering algorithm, to cluster training datasets at the clients. Further, it will reduce the computational training time of ELM and communication overhead. At the server, we employed a meta-clustering algorithm to cluster the updates from the clients. We also proposed another one-shot FL algorithm called privacy-preserving federated ELM based on minimum least square solution (FedELM-LS). The experimental analysis concludes that OP-FedELM is computationally less expensive yet achieves higher AUC in three of four datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancement of methanogenic activity by micronutrient control: Micronutrient availability in relation to sulfur transport

引用

Journal of Environmental Sciences 2023年第5期127卷 738-752页

作者： Krittiya Pornmai Sawwalak Itsadanont Monchupa Lertpattanapong Kessara Seneesrisakul Achiraya Jiraprasertwong Malinee Leethochawalit Hidetoshi Sekiguchi Sumaeth Chavadej The Petroleum and Petrochemical College Chulalongkorn UniversitySoi Chula 12Phyathai RoadPathumwanBangkok 10330Thailand Center of Excellence on Petrochemical and Materials Technology Chulalongkorn UniversityBangkok 10330Thailand School of Engineering and Technology Walailak UniversityNakhon Si Thammarat80160Thailand Center of Excellence on Wood and Biomaterials Walailak UniversityNakhon Si Thammarat80160Thailand Innovative Learning Center Srinakarinwirot UniversitySukhumvit RoadBangkokThailand Department of Chemical Engineering Tokyo Institute of Technology2-12-1 O-okayamaMeguro-kuTokyo 152-8552Japan

The main purpose of this research was to clarify the influence of the addition of iron(Fe)alone(0–100 mg/L)or 50 mg/L of Fe with 2 mg/L each of cobalt(Co),copper(Cu)and nickel(Ni)on the methanogenic activity of a mesophilic two-stage UASB system treating ethanol wastewater at a fixed chemical oxygen demand(COD)loading rate of 16 kg/m^(3)/day under a continuous mode of operation and steady state *** addition of Fe provided the dual benefits of a reduction in both the dissolved sulfide and the hydrogen sulfide(H_(2)S)content in produced gas,resulting inmarginally improved hydrogen(H_(2))and methane(CH_(4))*** the Fe dosage was increased beyond the optimum value of 50 mg/L,the process performance drastically declined,as a consequence of the high total volatile fatty acid(VFA)concentrations that inhibited both the acidogens and methanogens predominantly present in the 1st and 2nd reactors,*** chemical precipitation of iron sulfide was responsible for the reduction of produced H_(2)S in both the aqueous and gaseous phases as well as the minimization of added amounts of all other micronutrients to fulfil the sufficiency of all micronutrients for anaerobic digestion(AD).The addition of 2 mg/L each of Co,Cu and Ni together with 50 mg/L Fe resulted in the greatest enhancement in process performance,as indicated by the improved CH_(4) yield(mL/g COD applied)to about 42.3%,compared to that without micronutrient supplement.

关键词： Biogas Ethanol wastewater Ferric Micronutrients Sulfur transport

来源：评论

学校读者我要写书评

暂无评论

A Machine learning-Based Framework for Predicting E-Commerce Product Ratings

A Machine Learning-Based Framework for Predicting E-Commerce...

引用

International Bhurban Conference on Applied Sciences & technology, IBCAST

作者： Muneeb Iqbal Faizan Hamayat Rana Fayyaz Ahmad Syed Khursheed Husnain Quality Management Department Artificial Intelligence Technology Center National Center for Physics Islamabad Pakistan Machine Learning and Deep Learning Lab Artificial Intelligence Technology Center National Center for Physics Islamabad Pakistan

ISBN: (数字)9798331516680

ISBN: (纸本)9798331516697

Big data has been the center of attention for industry due to the volume of data that is being generated and growing over time. Machine learning algorithms are being employed more and more to anticipate various features of products. Product ratings are one of the key metrics used by every firm to evaluate the performance of its products. The product rating methodology persuades customers to purchase any item. It also demonstrates a product's potential for success in the consumer market. In order to forecast a product's rating based on its category, listed price, reduced price, and number of ratings, this study used a machine learning model. The Amazon dataset, which is accessible on Kaggle, was used in this study. This study evaluates various machine learning models using a dataset of 61,950 electronics appliance entries from Amazon to predict product ratings based on category, listed price, reduced price, and number of ratings. The Random Forest model outperforms others, with a precision of 0.65 and recall of 0.6 for 1-star ratings, and demonstrates superior performance for 2-star, 4-star, and 5-star predictions.

关键词： Support vector machines Stars Training data Machine learning Predictive models Nearest neighbor methods Data models Random forests Consumer electronics Context modeling

来源：评论

学校读者我要写书评

暂无评论

Generation of male germ cells in vitro from the stem cells

引用

Asian Journal of Andrology 2023年第1期25卷 13-20页

作者： Ying-Hong Cui Wei Chen Si Wu Cai-Lin Wan Zuping He The Key Laboratory of Model Animals and Stem Cell Biology in Hunan Province Hunan Normal University School of MedicineThe Manufacture-Based Learning and Research Demonstration Center for Human Reproductive Health New Technology of Hunan Normal UniversityChangsha 410013China

Infertility has become a serious disease since it affects 10%–15%of couples worldwide,and male infertility contributes to about 50%of the ***,a significant decrease occurs in the newborn population by 7.82 million in 2020 compared to 2016 in *** such,it is essential to explore the effective methods of obtaining functional male gametes for restoring male *** cells,including embryonic stem cells(ESCs),induced pluripotent stem cells(iPSCs),spermatogonial stem cells(SSCs),and mesenchymal stem cells(MSCs),possess the abilities of both self-renewal and differentiation into germ ***,much progress has recently been achieved in the generation of male germ cells in vitro from various kinds of stem cells under the specified conditions,e.g.,the coculturing with Sertoli cells,three-dimensional culture system,the addition of growth factors and cytokines,and/or the overexpression of germ cell-related *** this review,we address the current advance in the derivation of male germ cells in vitro from stem cells based on the studies of the peers and us,and we highlight the perspectives and potential application of stem cell-derived male gametes in reproductive medicine.

关键词： application in vitro generation male germ cells stem cells

来源：评论

学校读者我要写书评

暂无评论

A comparative evaluation of augmented reality and virtual reality on chemistry experiment learning in higher level education

引用

Multimedia Tools and Applications 2024年 1-40页

作者： Lam, Meng Chun Majid, Nazatul Aini Abd Hassan, Nurul Izzaty Mobarak, Nadhratun Naiim Tan, Siok Yee Hashim, Harwati Liew, Sook Yee Soon, Daniel Abidin, Rimaniza Zainal Suwadi, Nur Asylah Mixed Reality and Pervasive Computing Lab Center for Artificial Intelligence Technology Faculty of Information Science & Technology Universiti Kebangsaan Malaysia Bangi43600 Malaysia Department of Chemical Sciences Faculty of Science and Technology Universiti Kebangsaan Malaysia Selangor Bangi43600 Malaysia Centre of Innovation in Teaching and Learning Faculty of Education Universiti Kebangsaan Malaysia Bangi43600 Malaysia Chemistry Division Centre for Foundation Studies in Science Universiti Malaya Kuala Lumpur50603 Malaysia Center for Software Technology and Management Faculty of Information Science & Technology Universiti Kebangsaan Malaysia Bangi43600 Malaysia

In the constantly evolving landscape of higher education, integrating cutting-edge technologies has become crucial for enhancing learning experiences. As advancements in Augmented Reality (AR) and Virtual Reality (VR) continue to redefine educational paradigms, it is essential to understand their unique contributions to Chemistry education. The objective of this study is to assess the impact of AR and VR technology on knowledge acquisition, performance, user acceptance, and motivation. This was achieved through a comparative analysis of AR and VR mobile applications in a learning environment for chemistry experiments. The evaluation involved three main phases: pre-test, post-test and exchange phase. A total of 32 participants were recruited for the between-subject evaluation. Each group completed demographic forms and knowledge tests to ensure balanced representation. Afterwards, the participants were required to complete the knowledge test and questionnaire in the post-test. While in the exchange phase, it was held to acquire participants’ preferences on the best application to conduct chemistry experiments. The results reveal significant findings for both groups, indicating that AR and VR applications offer enhanced learning experiences. The results showed significant improvements in knowledge acquisition for both AR and VR groups, with both AR and VR groups demonstrating a substantial increase in knowledge scores in the post-test phase. Notably, the AR score was 44% better than the VR group in the post-test phase. In addition, the participants expressed significantly greater satisfaction with AR than with VR, implying a higher level of comfort and contentment with AR technology for conducting chemistry experiments. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

RPRB-Net: A Sign Language Recognition Based on Multi-dimension Attentions

RPRB-Net: A Sign Language Recognition Based on Multi-dimensi...

引用

2023 International Conference on Machine Vision, Image Processing and Imaging technology, MVIPIT 2023

作者： Yang, Tian Shen, Cong Wang, Xinyue Ma, Xiaoyu Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education School of Computer Science and Engineering Tianjin China

ISBN: (纸本)9798350306545

Sign Language Recognition (SLR) is the process of translating sign language into text or speech, which can also be viewed as a communication and expression tool between deaf individuals and hearing people. SLR using deep neural network has undergone significant development over the last decade. In this study, we design a feature-enhanced SLR technique based on serval spaces. To aid the network learning features from channel and spatial dimensions, we inject various attention mechanisms into the feature extractor backbone. As a result, we named our approach ResNet + Pyramid-Split-Attention + Recurrent-Criss-Cross-Attention + BiLSTM Network (RPRB-Net). Besides, we employ the BiLSTM architecture to encode high-level representations in temporal sequence. The network is ultimately trained using an end-to-end CTC alignment strategy. Extensive trials show that RPRB-Net achieves WERs of 3.5% and 23.6% on the USTC and RWTH-2014 datasets, respectively. Besides, it implies that RPRB-Net significantly surpasses the cutting-edge SLR approaches. Additionally, numerous ablation experiments have confirmed the efficiency of configuration. © 2023 IEEE.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Remora Optimization Algorithm with Variable Neighborhood Search for the Flexible Job Shop Scheduling Problem 7

A Hybrid Remora Optimization Algorithm with Variable Neighbo...

引用

7th International Conference on Advanced Algorithms and Control Engineering, ICAACE 2024

作者： Yang, Zheng Liang, Xiaodan Li, Yajing Wang, Haoyue School Of Computer Science And Technology Tiangong University Tianjin China Engineering Research Center Of Integration And Application Of Digital Learning Technology Ministry Of Education The Open University Of China Beijing China College Of Artificial Intelligence Tianjin University Of Science And Technology Beijing China

ISBN: (纸本)9798350361445

Reducing the production makespan of modern small-batch, multi-variety jobs can be abstracted into a flexible job shop scheduling problem (FJSP). The organization can greatly improve production efficiency by scheduling according to the optimal solution of FJSP. However, due to the high computational complexity of FJSP, it is often difficult to achieve higher performance in actual production. To optimize the makespan of the FJSP, a hybrid remora optimization algorithm with variable neighborhood search (HROA-VNS) is proposed in this work. A hybrid initialization method based on machine load balancing is utilized to improve the quality of the initial population. To solve discrete FJSP, a conversion method for individual positions and scheduling solutions is proposed, and a host switching mechanism (HSM) is designed to enhance the development and exploration capabilities of the algorithm. Furthermore, for enhancing the accuracy and effectiveness of the optimal solution, a variable neighborhood search (VNS) strategy which contains multiple structures is designed for local search. According to the experimental data, compared with the basic algorithm, the HROA-VNS reduced the makespan by an average of 33.02% and 14.40% on the two benchmark test sets respectively, and it shows better performance than related algorithms. © 2024 IEEE.

关键词： Evolutionary algorithms

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：