检索结果-内蒙古大学图书馆

Practical model with strong interpretability and predictability: An explanatory model for individuals' destination prediction considering personal and crowd travel behavior

Practical model with strong interpretability and predictabil...

引用

作者： Zhao, Juanjuan Ye, Jiexia Xu, Minxian Xu, Chengzhong Shenzhen Institutes of Advanced Technology China Academic of Science Shenzhen China State Key Lab of IOTSC Department of Computer Science University of Macau SAR China

Real-time individuals' destination prediction is of great significance for real-time user tracking, service recommendation and other related applications. Traditional technology mainly used statistical methods based on the travel patterns mined from personal history travel data. However, it is not clear how to predict the destinations of individuals with only limited personal historical data. In this paper, taking the public transportation metro systems as example, we design a practical method called practical model with strong interpretability and predictability to predict each passenger's destination. Our main novelties are two aspects: (1) We propose to predict individuals' destination by combining personal and crowd behavior under certain context. (2) An explanatory model combining discrete choice model and neural network model is proposed to predict individuals' stochastic trip's destination, which can be applied to other transportation analysis scenarios about individuals' choice behavior such as travel mode choice or route choice. We validate our method based on extensive experiments, using smart card data collected by automatic fare collection system and weather data in Shenzhen, China. The experimental results demonstrate that our approach can achieve better performance than other baselines in terms of prediction accuracy. © 2020 John Wiley & Sons, Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Online crowdsourced truck delivery using historical information

引用

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2022年第2期301卷 486-501页

作者： Zhang, Huili Luo, Kelin Xu, Yao Xu, Yinfeng Tong, Weitian [a]School of Management Xi’an Jiaotong University and State Key Lab for Manufacturing Systems Engineering Xi’an 710049 China [b]Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven the Netherlands [c]Department of Computer Science Georgia Southern University Statesboro GA 30458 USA

Various crowdsourced logistics platforms are forming rapidly along with the booming mobile Internet. Motivated by modern crowdsourced truck logistics platforms, we introduce the online crowdsourced truck delivery (OCTD) problem and reformulate it as the online bipartite hyper-matching problem. We then explore the possibility of accommodating historical information to design efficient online algorithms to serve online orders. To the best of our knowledge, it is the first work on incorporating historical information to solve the online bipartite hyper-matching problem. Depending on whether orders can be partially served, we investigate two practical situations, i.e. separable and inseparable cases. For the inseparable case, we propose a randomized online algorithm, named HYPER-MATCHING , whose competitive ratio is a non-decreasing function of the amount of historical information. For the separable case, we modify HYPER-MATCHING to present another randomized online algorithm, named SEPARABLE-HYPER-MATCHING . It is worth noting that the competitive ratios of HYPER-MATCHING and SEPARABLE-HYPER-MATCHING either beat or match the current best online algorithms when no historical information is considered. We then present four computationally efficient heuristic algorithms, including a greedy variant and a batch processing variant for each of the inseparable and separable cases. We perform a sequence of experiments using synthetic and real-world datasets, with an emphasis on the influence that historical information has on algorithm performance. The experiment results demonstrate the effectiveness of our algorithms and particularly the positive influence of historical information on our algorithms.(c) 2021 Elsevier B.V. All rights reserved.

关键词： Transportation Online crowdsourced truck delivery Online bipartite hyper-matching Random order model Historical information

来源：评论

学校读者我要写书评

暂无评论

Improving the Interpretability through Maximizing Mutual Information for EEG Emotion Recognition

引用

IEEE Transactions on Affective Computing 2024年第02期16卷 744-757页

作者： Yang, Hua Philip Chen, C.L. Chen, Bianna Zhang, Tong North Carolina State University Department of Computer Science United States South China University of Technology Guangdong Provincial Key Laboratory of AI Large Model and Intelligent Cognition The School of Computer Science and Engineering Guangzhou510006 China Pazhou Lab Guangzhou510335 China Engineering Research Center The Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou China

Trustworthy Graph Neural Networks (GNNs) for EEG emotion recognition should identify emotions accurately and elucidate corresponding rationales. Current GNNs have achieved notable performance by dynamically modeling emotional connections between EEG channels. However, these GNNs lack interpretability due to the absence of explicit rationale behind their predictions. This paper conducts a comprehensive identification of important EEG channels to enhance the interpretability of EEG emotion recognition from the perspective of mutual information. Specifically, an Adjacency-Explainable Graph Neural Network (AEG) for ante-hoc interpretability is proposed to capture genuine EEG emotional connections, which gives a theoretical guarantee to remove spurious connections. Moreover, a Channel-wise Adaptive Class Activation Mapping Explainer (CACA) for post-hoc interpretability is developed to locate the EEG channels that contribute most to predictions. Experimental results on three datasets, i.e., SEED, SEED-IV, and DREAMER, prove that imbuing training processes with enhanced interpretability ensures significant performance improvements in emotion recognition. Quantitative comparisons of post-hoc interpretability also demonstrate the superiority of CACA. Furthermore, this paper illustrates two potential applications of the proposed methodologies, showing their broader utility and significance. © 2010-2012 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning 48

I-Tuning: Tuning Frozen Language Models with Image for Light...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Luo, Ziyang Hu, Zhipeng Xi, Yadong Zhang, Rongsheng Ma, Jing Hong Kong Baptist University Department of Computer Science Hong Kong Zhejiang University College of Computer Science and Technology Hangzhou China NetEase Inc. Fuxi AI Lab Hangzhou China

ISBN: (纸本)9781728163277

Image Captioning is a traditional vision-and-language task that aims to generate the language description of an image. Recent studies focus on scaling up the model size and the number of training data, which significantly increase the cost of model training. Different to these heavy-cost models, we introduce a lightweight image captioning framework (I-Tuning), which contains a small number of trainable parameters. We design a novel I-Tuning cross-attention module to connect the non-trainable pre-trained language decoder GPT2 and vision encoder CLIP-ViT. Since most parameters are not required to be updated during training, our framework is lightweight and fast. Experimental results conducted on three image captioning benchmarks reveal that our frame-work achieves comparable or better performance than the large-scale baseline systems. But our models contain up to 10 times fewer trainable parameters and require much fewer data for training compared with state-of-the-art baselines. © 2023 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model 41

Evolution of Heuristics: Towards Efficient Automatic Algorit...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Fei Tong, Xialiang Yuan, Mingxuan Lin, Xi Luo, Fu Wang, Zhenkun Lu, Zhichao Zhang, Qingfu Department of Computer Science City University of Hong Kong Hong Kong Huawei Noah's Ark Lab Canada School of System Design and Intelligent Manufacturing Southern University of Science and Technology China

Heuristics are widely used for dealing with complex search and optimization problems. However, manual design of heuristics can be often very labour extensive and requires rich working experience and knowledge. This paper proposes Evolution of Heuristic (EoH), a novel evolutionary paradigm that leverages both Large Language Models (LLMs) and Evolutionary Computation (EC) methods for Automatic Heuristic Design (AHD). EoH represents the ideas of heuristics in natural language, termed thoughts. They are then translated into executable codes by LLMs. The evolution of both thoughts and codes in an evolutionary search framework makes it very effective and efficient for generating high-performance heuristics. Experiments on three widely studied combinatorial optimization benchmark problems demonstrate that EoH outperforms commonly used handcrafted heuristics and other recent AHD methods including FunSearch. Particularly, the heuristic produced by EoH with a low computational budget (in terms of the number of queries to LLMs) significantly outperforms widely-used human hand-crafted baseline algorithms for the online bin packing problem. Copyright 2024 by the author(s)

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

PPDMIT: a lightweight architecture for privacy-preserving data aggregation in the Internet of Things

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第5期14卷 5211-5223页

作者： Gheisari, Mehdi Javadpour, Amir Gao, Jiechao Abbasi, Aaqif Afzaal Pham, Quoc-Viet Liu, Yang Department of Computer Science and Technology Harbin Institute of Technology Shenzhen China Department of Computer Science University of Virginia VA United States Department of Software Engineering Foundation University Islamabad44000 Pakistan Korean Southeast Center for the 4Th Industrial Revolution Leader Education Pusan National University Busan46241 Korea Republic of ADiT-Lab Electrotechnics and Telecommunications Department Instituto Politécnico de Viana do Castelo Porto4900-347 Portugal

Data is generated over time by each device in the Internet of Things (IoT) ecosphere. Recent years have seen a resurgence in interest in the IoT due to its positive impact on society. However, due to the automatic management of IoT devices, the possibility of disclosing sensitive information without user consent is high. A situation in which information should not be unintentionally disclosed to outside parties we do not trust, i.e., privacy-preservation. Additionally, IoT devices should share their data with others to perform data aggregation and provide high-level services. There is a trade-off between the amount of data utility and the amount of disclosure of data. This trade-off has been causing a big challenge in this field. To improve the efficiency of this trade-off rather than current studies, in this study, we propose a Privacy-Preserving Data Aggregation architecture, PPDMIT, that leverages Homomorphic Paillier Encryption (HPE), K-means, a One-way hash chain, and the Chinese Remainder Theorem (CRT). We have found that the proposed privacy-preserving architecture achieves more efficient data aggregation than current studies and improves privacy preservation by utilizing extensive simulations. Moreover, we found that our proposed architecture is highly applicable to IoT environments while preventing unauthorized data disclosure. Specifically, our solution depicted an 8.096% improvement over LPDA and 6.508% over PPIOT. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

VisioSLR: A Vision Data-Driven Framework for Sign Language Video Recognition and Performance Evaluation on Fine-Tuned YOLO Models 16

VisioSLR: A Vision Data-Driven Framework for Sign Language V...

引用

16th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2025 / 8th International Conference on Emerging Data and Industry 4.0, EDI40 2025

作者： Ismail, Leila Shahin, Nada Tesfaye, Henok Hennebelle, Alain Lab Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates

With the emergence of AI for good, there has been an increasing interest in building computer vision data-driven deep learning inclusive AI solutions. Sign language Recognition (SLR) has gained attention recently. It is an essential component of a sign-to-text translation system to support the deaf and hard-of-hearing population. This paper presents a computer VISIOn data-driven deep learning framework for Sign Language video Recognition (VisoSLR). VisioSLR provides a precise measurement of translating signs for developing an end-to-end computational translation system. Considering the scarcity of sign language datasets, which hinders the development of an accurate recognition model, we evaluate the performance of our framework by fine-tuning the very well-known YOLO models, which are built from a signs-unrelated collection of images and videos, using a small-sized sign language dataset. Gathering a sign language dataset for signs training would involve an enormous amount of time to collect and annotate videos in different environmental setups and multiple signers, in addition to the training time of a model. Numerical evaluations of VisioSLR show that our framework recognizes signs with a mean average precision of 97.4%, 97.1%, and 95.5% and 11, 12, and 12 milliseconds of recognition time on YOLOv8m, YOLOv9m, and YOLOv11m, respectively. © 2025 Elsevier B.V.. All rights reserved.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Multistage guidance on the diffusion model inspired by human artists’ creative thinking

引用

Frontiers of Information technology & Electronic Engineering 2024年第1期25卷 170-178页

作者： Wang QI Huanghuang DENG Taihao LI AI Research Institute Zhejiang LabHangzhou 311121China Department of Computer Science and Technology Zhejiang UniversityHangzhou 310027China

Current research on text-conditional image generation shows parallel performance with ordinary painters but still has much room for improvement when compared to that of artist-ability paintings,which usually represent multilevel semantics by gathering features ofmultiple objects into one *** a preliminary experiment,we confirm this and then seek the opinions of three groups of individuals with varying levels of art appreciation ability to determine the distinctions that exist between painters and *** then use these opinions to improve an artificial intelligence(AI)painting system from painter-level image generation toward artistic-level image generation.

关键词： gathering ordinary artist

来源：评论

学校读者我要写书评

暂无评论

Real-time road occupancy and traffic measurements using unmanned aerial vehicle and fundamental traffic flow diagrams

引用

Personal and Ubiquitous Computing 2023年第5期27卷 1669-1680页

作者： Ahmed, Afzal Outay, Fatima Farooq, Muhammad Umer Saeed, Sehrish Adnan, Muhammad Ismail, Muhammad Ali Qadir, Adnan Department of Urban & Infrastructure Engineering NED University of Engineering & Technology Karachi Pakistan Zayed University Dubai United Arab Emirates Department of Computer Science and Information Technology NED University of Engineering & Technology Karachi Pakistan Exascale Open Data Analytics Lab NED University of Engineering & Technology Karachi Pakistan Hasselt University Diepenbeek Belgium

The technologies and sensors developed for standard traffic streams often fail to accurately measure the heterogeneous traffic with no lane discipline. This research proposes an efficient framework to measure traffic flow parameters in real-time using an unmanned aerial vehicle (UAV). The proposed framework in this research estimates road area occupancy from the images extracted from the video recorded using a UAV by applying the image segmentation technique. The road area occupancy is converted into traffic density using an occupancy-density model developed for the local heterogeneous traffic. A speed-density fundamental diagram is developed, which estimates the average speed corresponding to the measured traffic density. The fundamental relation between flow rate, average speed, and density is applied to compute traffic flow rate using the estimated average speed and density. The proposed framework is computationally less demanding in comparison with other computer vision and artificial intelligence–based techniques. The proposed framework accurately measured road area occupancy with an average accuracy of 97.6%. Traffic density was measured with an average accuracy of 88.8%. Similarly, the average speed and flow rate were measured with an average accuracy of 85.4% and 84.2%, respectively. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

SoftPatch+: Fully unsupervised anomaly classification and segmentation

引用

Pattern Recognition 2025年 161卷

作者： Wang, Chengjie Jiang, Xi Gao, Bin-Bin Gan, Zhenye Liu, Yong Zheng, Feng Ma, Lizhuang Department of Computer Science and Engineering Shanghai Jiao Tong University China YouTu Lab Tencent China Department of Computer Science and Engineering Southern University of Science and Technology China

Although mainstream unsupervised anomaly detection (AD) (including image-level classification and pixel-level segmentation) algorithms perform well in academic datasets, their performance is limited in practical application due to the ideal experimental setting of clean training data. Training with noisy data is an inevitable problem in real-world anomaly detection but is seldom discussed. This paper is the first to consider fully unsupervised industrial anomaly detection (i.e., unsupervised AD with noisy data). To solve this problem, we proposed memory-based unsupervised AD methods, SoftPatch and SoftPatch+, which efficiently denoise the data at the patch level. Noise discriminators are utilized to generate outlier scores for patch-level noise elimination before coreset construction. The scores are then stored in the memory bank to soften the anomaly detection boundary. Compared with existing methods, SoftPatch maintains a strong modeling ability of normal data and alleviates the overconfidence problem in coreset, and SoftPatch+ has more robust performance which is particularly useful in real-world industrial inspection scenarios with high levels of noise (from 10% to 40%). Comprehensive experiments conducted in diverse noise scenarios demonstrate that both SoftPatch and SoftPatch+ outperform the state-of-the-art AD methods on the MVTecAD, ViSA, and BTAD benchmarks. Furthermore, the performance of SoftPatch and SoftPatch+ is comparable to that of the noise-free methods in conventional unsupervised AD setting. The code of the proposed methods can be found at https://***/TencentYoutuResearch/AnomalyDetection-SoftPatch. © 2024 Elsevier Ltd

关键词： Adversarial machine 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：