2021 International Conference on Cyber-Physical Social Intelligence (ICCSI)最新文献_第8页

Optimizing Bike Rebalancing via Spatial Crowdsourcing: A Matching Approach 通过空间众包优化自行车再平衡:一种匹配方法

2021 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2021-12-18 DOI: 10.1109/ICCSI53130.2021.9736162

Cameron Thatcher, Ning Wang

{"title":"Optimizing Bike Rebalancing via Spatial Crowdsourcing: A Matching Approach","authors":"Cameron Thatcher, Ning Wang","doi":"10.1109/ICCSI53130.2021.9736162","DOIUrl":"https://doi.org/10.1109/ICCSI53130.2021.9736162","url":null,"abstract":"Bike sharing systems are a new form of public transportation where users are allowed to take out and return bicycles using various stations throughout the city. While such a system is innovative, and has solidified its prevalence to the public, it is still in its infancy with many improvements yet to come. One of the largest issues present is the imbalance of the Bike Sharing System (BSS), or more broadly ridesharing systems, the unavailability of bikes or empty parking spaces in areas with a high density of users. In this paper, we propose a spatial crowdsourcing approach where users receive monetary incentives to rebalance bikes by returning bikes to stations that need it rather than users' intended locations to improve the system's overall bike utilization. However, how to determine the best incentive mechanism is challenging. We formulate this problem into an optimal matching problem and convert it into a minimum-cost flow problem to find the best way to choose which stations to rebalance and the optimal rebalancing amount. To demonstrate the effectiveness of the proposed method, we validate our approach using D.C. Capital BikeShare data and extensive simulation shows that our approach on average can improve the efficiency and cost of simple greedy algorithms by 32.1%.","PeriodicalId":175851,"journal":{"name":"2021 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126665471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cross-Modality Domain Adaptation for hand-vein recognition 手部静脉识别的跨模态域自适应

2021 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2021-12-18 DOI: 10.1109/ICCSI53130.2021.9736171

Shuqiang Yang, Huafeng Qin, M. El-Yacoubi, Chongwen Liu

{"title":"Cross-Modality Domain Adaptation for hand-vein recognition","authors":"Shuqiang Yang, Huafeng Qin, M. El-Yacoubi, Chongwen Liu","doi":"10.1109/ICCSI53130.2021.9736171","DOIUrl":"https://doi.org/10.1109/ICCSI53130.2021.9736171","url":null,"abstract":"Palm-vein recognition has attracted increasing attention over the last years. Although deep learning-based approaches, such as Convolutional Neural Networks (CNN), have been shown to be effective for feature representation, thereby achieving good performance in vein verification tasks, they typically are trained on large labeled datasets. In general, labeling vein images is expensive and time cost, and typical hand-tuned approaches for data augmentation can not collect the complex variations in such images. To address this problem, a novel unsupervised domain adaptation approach, named CycleGAN-based domain adaptation (CGAN-DA), is proposed to automatically extract discriminant from the palm-vein network, without the need of any image annotation. Our proposed CGAN-DA allows a learning scheme that ensures a synergistic fusion of adaptations image-wise and feature-wise. Concretely, we transform the image appearance across two domains (palm-vein image domain and retinal image domain), in order to enhance the domain-invariance of the extracted features for the palm-vein segmentation task. Without using any annotation from the target domain (palm-vein images), our model learning is guided by several adversarial losses, a cycle consistence loss and a segmentation loss. Our experimental on the public CASIA palm-vein dataset show that our approach is capable of achieving state-of-the art verification accuracy.","PeriodicalId":175851,"journal":{"name":"2021 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116810219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Process Mining Model to Predict Mortality in Paralytic Ileus Patients 过程挖掘模型预测麻痹性肠梗阻患者死亡率

2021 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2021-08-03 DOI: 10.1109/ICCSI53130.2021.9736217

M. Pishgar, M. Razo, Julian Theis, H. Darabi

引用次数: 7

Masking Neural Networks Using Reachability Graphs to Predict Process Events 利用可达性图屏蔽神经网络来预测过程事件

2021 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2021-08-01 DOI: 10.1109/ICCSI53130.2021.9736237

Julian Theis, H. Darabi

引用次数: 1

Data-driven Predictive Analysis for Smart Manufacturing Processes Based on a Decomposition Approach 基于分解方法的智能制造过程数据驱动预测分析

2021 International Conference on Cyber-Physical Social Intelligence (ICCSI) Pub Date : 2021-07-28 DOI: 10.36227/techrxiv.15045426.v1

Mohammadhossein Ghahramani, Mengchu Zhou

引用次数: 0