检索结果-内蒙古大学图书馆

DeepCNN:Spectro-temporal feature representation for speech emotion recognition

CAAI Transactions on intelligence Technology 2023年第2期8卷 401-417页

作者： Nasir Saleem Jiechao Gao Rizwana Irfan Ahmad Almadhor Hafiz Tayyab Rauf Yudong Zhang Seifedine Kadry Department of Electrical Engineering Faculty of Engineering and TechnologyGomal UniversityD.I.KhanPakistan Department of Computer Science University of VirginiaCharlottesvilleVirginiaUSA Department of Information Technology College of Computing and Information Technology at KhulaisUniversity of JeddahJeddahSaudi Arabia Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySkaka AljoufSaudi Arabia Centre for Smart Systems AI and CybersecurityStaffordshire UniversityStoke‐on‐TrentUK School of Computing and Mathematical Sciences University of LeicesterLeicesterUK Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) Ajman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon

Speech emotion recognition(SER)is an important research problem in human-computer interaction *** representation and extraction of features are significant challenges in SER *** the promising results of recent studies,they generally do not leverage progressive fusion techniques for effective feature representation and increasing receptive *** mitigate this problem,this article proposes DeepCNN,which is a fusion of spectral and temporal features of emotional speech by parallelising convolutional neural networks(CNNs)and a convolution layer-based *** parallel CNNs are applied to extract the spectral features(2D-CNN)and temporal features(1D-CNN)representations.A 2D-convolution layer-based transformer module extracts spectro-temporal features and concatenates them with features from parallel *** learnt low-level concatenated features are then applied to a deep framework of convolutional blocks,which retrieves high-level feature representation and subsequently categorises the emotional states using an attention gated recurrent unit and classification *** fusion technique results in a deeper hierarchical feature representation at a lower computational cost while simultaneously expanding the filter depth and reducing the feature *** Berlin Database of Emotional Speech(EMO-BD)and Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets are used in experiments to recognise distinct speech *** efficient spectral and temporal feature representation,the proposed SER model achieves 94.2%accuracy for different emotions on the EMO-BD and 81.1%accuracy on the IEMOCAP dataset *** proposed SER system,DeepCNN,outperforms the baseline SER systems in terms of emotion recognition accuracy on the EMO-BD and IEMOCAP datasets.

关键词： decision making deep learning

来源：评论

学校读者我要写书评

暂无评论

Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs 31

Idea23D: Collaborative LMM Agents Enable 3D Model Generation...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Chen, Junhao Li, Xiang Ye, Xiaojun Li, Chao Fan, Zhaoxin Zhao, Hao Tsinghua University China Tsinghua Shenzhen International Graduate School Tsinghua University China School of Software and Microelectronics Peking University China College of Computer Science Zhejiang University China College of Computer Science and Technology Harbin Engineering University China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing School of Artificial Intelligence Beihang University China

ISBN: (纸本)9798891761964

With the success of 2D diffusion models, 2D AIGC content has already transformed our lives. Recently, this success has been extended to 3D AIGC, with state-of-the-art methods generating textured 3D models from single images or text. However, we argue that current 3D AIGC methods still don't fully unleash human creativity. We often imagine 3D content made from multimodal inputs, such as what it would look like if my pet bunny were eating a doughnut on the table. In this paper, we explore a novel 3D AIGC approach: generating 3D content from IDEAs. An IDEA is a multimodal input composed of text, image, and 3D models. To our knowledge, this challenging and exciting 3D AIGC setting has not been studied before. We propose the new framework Idea23D, which combines three agents based on large multimodal models (LMMs) and existing algorithmic tools. These three LMM-based agents are tasked with prompt generation, model selection, and feedback reflection. They collaborate and critique each other in a fully automated loop, without human intervention. The framework then generates a text prompt to create 3D models that align closely with the input IDEAs. We demonstrate impressive 3D AIGC results that surpass previous methods. To comprehensively assess the 3D AIGC capabilities of Idea23D, we introduce the Eval3DAIGC-198 dataset, containing 198 multimodal inputs for 3D generation tasks. This dataset evaluates the alignment between generated 3D content and input IDEAs. Our user study and quantitative results show that Idea23D significantly improves the success rate and accuracy of 3D generation, with excellent compatibility across various LMM, Text-to-Image, and Image-to-3D models. Code and dataset are available at https://***/. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Joint Extraction of Interaction Features and Attention Mechanism Fused with Entity-Relations 36

Joint Extraction of Interaction Features and Attention Mecha...

引用

36th International Conference on Software engineering and Knowledge engineering, SEKE 2024

作者： Su, Lisha Yan, Rong College of Computer Science Inner Mongolia University Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot010021 China

ISBN: (纸本)1891706594

Joint extraction of entities and relations is an essential task in information extraction. Recently, tagging-based models have gained attention but with poor performance on overlapping triplets, which confronted the issues like cascading errors, information redundancy, and sensitivity to subject extraction. To solve the issue of overlapping triplets, we propose a model combined Gated Attention Unit (GAU) and Multi-head Attention Mechanism (MHA) in this paper. This model distinguishes features for entities and relations, and performs entity recognition for each head entity, different head entities are matched to the same or different tail entities. Then specific tail entity tagging is applied to determine all possible relations and corresponding tails. At the same time, in order to better solve the long-distance dependence and complex multiple relations between entities, GAU and MHA are used to enhance the semantic representation, effectively identify entities and relations, and enhance the learning ability and generalization ability of the model. Experiment results on the public datasets DuIE2.0 and CMeIE show that our model performs better than baselines. © 2024 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Modulation of photocatalytic activity of SrBi_(2)Ta_(2)O_(9)nanosheets in NO removal by tuning facets exposure

引用

Journal of Materials science & Technology 2022年第27期122卷 91-100页

作者： Nan Li Qiuhui Zhu Guimei Liu Qi Zhao Haiqin Lv Mingzhe Yuan Qingguo Meng Yingtang Zhou Jingkun Xu Chuanyi Wang School of Environmental Science and Engineering Shaanxi University of Science and TechnologyXi’an 710021China Guangzhou Institute of Industrial Intelligence(GIII) Guangzhou 511400China National Engineering Research Center for Marine Aquaculture Marine Science and Technology CollegeZhejiang Ocean UniversityZhoushan 316004China Flexible Electronics Innovation Institute(FEII) Jiangxi Science&Technology Normal UniversityNanchang 330006China

Photocatalysts with exposure of different crystal facets often show great differences in their photocatalytic activities due to differences in surface atomic arrangement and ***,the actual photoreaction mechanism of a specific crystal facet in photocatalysis deserves to be *** this paper,as a case study,Sr Bi_(2)Ta_(2)O_(9)photocatalyst with preferential facet exposure was explored for the photocatalytic removal of NO at a ppb *** efficiency of NO removal was remarkably improved by tuning the crystal exposure facet with high(200)facet exposure *** exposure of(200)crystal facet in Sr Bi_(2)Ta_(2)O_(9)(SBT)by thermal calcination at 800℃(SBT-800)leads to the highest NO removal activity of51%under a 300 W Xe lamp for 20 min;under visible light,SBT 800 achieves a 5-fold enhancement in NO removal efficiency compared to its counterpart,*** species capture experiments prove that the superoxide radical·O_(2)-is the main active species for the photocatalytic removal of NO,and surface selective deposition experiments conclude that(200)is the main electron-rich crystal plane,based on which the results of density functional theory(DFT)computation reveal the Bi O terminated nature of(001)crystal plane,where the models with both Bi O and Ta O terminated(001)planes were created and *** study reveals that Sr Bi_(2)Ta_(2)O_(9)with a larger exposure of(200)facet provides more active reduction sites,thereby reducing more O_(2)to·O_(2)-,which further oxidizes the adsorbed NO to NO_(2)-/NO_(3)-.The present work underlines the role of facet tuning in the photoactivity modulation for NO removal photocatalytically.

关键词： SrBi_(2)Ta_(2)O_(9) NO removal Facet exposure Photocatalysis DFT computation

来源：评论

学校读者我要写书评

暂无评论

Integrated Fuzzy Logic and Data Mining Approach for Assessing Groundwater Vulnerability to Sea-Water Intrusion 16th

Integrated Fuzzy Logic and Data Mining Approach for Assessin...

引用

16th International Conference on Application of Fuzzy Systems, Soft Computing and Artificial intelligence Tools, ICAFS 2023

作者： Sadikoglu, Fahreddin Nourani, Vahid Najafi, Hessam Maleki, Sana Paknezhad, Nardin Jabbarian Department of Computer Engineering Near East University Nicosia Cyprus Department of IT Odlar Yurdu University Baku Azerbaijan Center of Excellence in Hydroinformatics Faculty of Civil Engineering University of Tabriz Tabriz Iran College of Environmental Science and Engineering Nankai University Tianjin China

ISBN: (纸本)9783031762826

The GALDIT model is used for the assessment of the aquifer vulnerability of Groundwater (GW), but it relies on expert judgment that contains uncertainty and is one of its weaknesses. To tackle the challenge of managing uncertainty and identifying specific vulnerabilities, this study employed a combination of Mamdani Fuzzy Logic (MFL) and data mining techniques. Then the obtained results were compared with the traditional GALDIT method. According to the Electrical Conductivity (EC) values, the Heidke Skill Score (HSS) and Total Accuracy (TA) criteria were applied to assess the outcomes of the applied methods. The surrounding aquifers of Urmia Lake was case study in this paper. The findings indicated that the GALDIT index varied from 2 to 8. The TA and HSS values in the MFL modeling were determined to be 0.59 and 0.48, respectively, therefore MFL led to more accurate and reliable results for evaluating GW vulnerability compared to the traditional GALDIT method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Salt water intrusion

来源：评论

学校读者我要写书评

暂无评论

Saving The Elf: Immersive VR Experience Utilizing Multiple Relaxing Approaches

Saving The Elf: Immersive VR Experience Utilizing Multiple R...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Nie, Cheng Ding, Ding Wu, Jinhao Yang, Xu Ou, Ronghuang Du, Wei College of Software Engineering Southeast University Nanjing China Southeast University Computer Experimental Teaching Center Nanjing China School of Computer Science and Engineering Southeast University Nanjing China School of Artificial Intelligence Southeast University Nanjing China School of Public Health Southeast University Nanjing China

ISBN: (纸本)9781665410205

The global prevalence of anxiety has seen a significant increase in the past few years. Anxiety, if left untreated, can lead to various detrimental effects, such as sleep disturbances, excessive fear, and even suicidal tendencies. Traditional face-to-face therapies have been employed to address this issue;however, their effectiveness is limited by time and space constraints, particularly during the COVID-19 pandemic. As a result, computer-based systems have emerged as a potential solution. However, most existing relaxation systems rely on a single method and have unnatural interactions, leading to a lack of variety and engagement. To overcome these limitations, this study proposes a virtual reality (VR) relaxation system that combines various relaxation techniques, a captivating storyline and natural interactions to enhance the user experience. To assess the effectiveness of the proposed system, a pilot study was conducted with 36 participants. The study utilized a between-subjects design, dividing the participants into three groups: a control group, a progressive muscular relaxation group, and a virtual reality relaxation group. The findings revealed that the virtual reality relaxation system significantly reduced anxiety levels among the participants. Importantly, this effect was observed to persist even after a period of time and was found to be more effective than using only one relaxation method in the long term. Moreover, the performance of our system is close to that of commercial systems. © 2024 IEEE.

关键词： Virtual environments

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

Mechanistic modeling of copper corrosions in data center environments

引用

Building Simulation 2024年第3期17卷 483-492页

作者： Rui Zhang Jianshun Zhang Roger Schmidt Jeremy L.Gilbert Department of Mechanical and Aerospace Engineering College of Engineering and Computer ScienceSyracuse UniversitySyracuseNY13244USA Buildings and Transportation Science Division Oak Ridge National LaboratoryOak RidgeTN37830USA SyracuseCoE-New York Center of Excellence in Environmental and Energy Systems Syracuse University727 E.Washington StreetSyracuseNY13244USA Department of Bioengineering Clemson UniversityClemson-Medical University of South Carolina Bioengineering ProgramCharlestonSC29425USA

Air-side economizers are increasingly used to take advantage of“free-cooling”in data centers with the intent of reducing the carbon footprint of ***,they can introduce outdoor pollutants to indoor environment of data centers and cause corrosion damage to the information technology *** evaluate the reliability of information technology equipment under various thermal and air-pollution conditions,a mechanistic model based on multi-ion transport and chemical reactions was *** model was used to predict Cu corrosion caused by Cl_(2)-containing pollutant *** also accounted for the effects of temperature(25℃and 28℃),relative humidity(50%,75%,and 95%),and *** also identified higher air temperature as a corrosion barrier and higher relative humidity as a corrosion accelerator,which agreed well with the experimental *** average root mean square error of the prediction was 13.7Å.The model can be used to evaluate the thermal guideline for data centers design and operation when Cl_(2)is present based on pre-established acceptable risk of corrosion in data centers’environment.

关键词： chloride pollutant mixture copper corrosion model data center temperature relative humidity synergistic effect

来源：评论

学校读者我要写书评

暂无评论

Polymerization-Amplified Photoacoustic Signal by Enhancing Near-Infrared Light-Harvesting Capacity and Thermal-to-Acoustic Conversion

引用

Chinese Journal of Polymer science 2022年第9期40卷 1090-1100页

作者： He-Qi Gao Jing-Tian Zhang Xin-Wen Qi Di Jiao Yu-Ning Hong Ke Shan Xiang-Long Kong Dan Ding Key Laboratory of Bioactive Materials Ministry of Educationand College of Life SciencesNankai UniversityTianjin 300071China Center for AIE Research Shenzhen Key Laboratory of Polymer Science and TechnologyGuangdong Research Center for Interfacial Engineering of Functional MaterialsCollege of Materials Science and EngineeringCollege of Physics and Optoelectronic EngineeringShenzhen UniversityShenzhen 518060China Department of Chemistry and Physics La Trobe Institute for Molecular ScienceLa Trobe UniversityMelbourneVictoria3086Australia Shandong Artificial intelligence Institute and Shandong Computer Science Center Qilu University of TechnologyJinan 250353China

As a frontier imaging technique for biomedical applications,photoacoustic(PA)imaging has been developed *** development of new design strategies and excellent PA imaging reagents to boost PA conversion is eagerly desirable for high quality PA imaging but complicated to ***,we develop a new strategy in which PA imaging reagents with better properties can be easily optimized by polymerization.A series of new PA imaging reagents were designed and *** polymerization strategy can effectively promote the PA signal by specifically increasing the thermal-to-acoustic conversion *** these materials shared the same building units,the optimized effectiveness of polymerization strategy in terms of near-infrared light-harvesting capacity and thermal-to-acoustic conversion efficiency are discussed,*** polymers with intense intramolecular motion exhibit an amplified PA signal by elevating thermal-to-acoustic conversion and its higher light-harvesting capability at redshifted *** simultaneously strong PA signal and photothermal conversion efficiency of p-TTmB NPs enable precise PA imaging and effective photothermal *** work highlights a simple and available design guideline of polymerization for amplifying the PA effect and optimizing existing materials.

关键词： Intramolecular motion Thermal-to-acoustic conversion Photoacoustic imaging Photothermal conversion efficiency Polymerization

来源：评论

学校读者我要写书评

暂无评论

Stable Learning via Triplex Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial intelligence 2024年第10期5卷 5267-5276页

作者： Yang, Shuai Jiang, Tingting Dang, Qianlong Gu, Lichuan Wu, Xindong Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing Hefei230036 China Northwest A & F University College of Science Yangling712100 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

Stable learning aims to learn a model that generalizes well to arbitrary unseen target domain by leveraging a single source domain. Recent advances in stable learning have focused on balancing the distribution of confounders for each feature to eliminate spurious correlations. However, previous studies treat all features equally without considering the difficulties of confounder balancing associated with different features, and regard irrelevant features as confounders, deteriorating generalization performance. To tackle these issues, this article proposes a novel triplex learning (TriL) based stable learning algorithm, which performs sample reweighting, causal feature selection, and representation learning to remove spurious correlations. Specifically, first, TriL adaptively assigns weights to the confounder balancing term of each feature in accordance with the difficulties of confounder balancing, and aligns the confounder distribution of each feature by learning a group of sample weights. Second, TriL integrates the sample weights into a weighted cross-entropy model to compute causal effects of features for excluding irrelevant features from the confounder set. Finally, TriL relearns a set of sample weights and uses them to guide a new supervised dual-autoencoder containing two classifiers to learn feature representations. TriL forces the results of two classifiers to remain consistent for removing spurious correlations by using a cross-classifier consistency regularization. Extensive experiments on synthetic and two real-world datasets show the superiority of TriL compared with seven methods. © 2024 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：