Proceedings of the 3rd International Conference on Vision, Image and Signal Processing最新文献_第4页

Integrated Retrieval System Based on Medical Big Data 基于医疗大数据的综合检索系统

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387220

Song Yu

引用次数: 0

Analysis on Affected Factors of Employment in Wuhan City Based on Vector-Auto-Regression 基于向量自回归的武汉市就业影响因素分析

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3389114

Liu Yang, Shengchun Yu, Yongmei Ding

引用次数: 0

Crowd R-CNN: An Object Detection Model Utilizing Crowdsourced Labels Crowd R-CNN:一个利用众包标签的对象检测模型

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387180

Yucheng Hu, Meina Song

{"title":"Crowd R-CNN: An Object Detection Model Utilizing Crowdsourced Labels","authors":"Yucheng Hu, Meina Song","doi":"10.1145/3387168.3387180","DOIUrl":"https://doi.org/10.1145/3387168.3387180","url":null,"abstract":"Accuracy of object detection has increased significantly in recent years because of the rapid development of deep learning techniques. Nevertheless, its applications in many fields are still limited, mainly due to the lack of large datasets, especially datasets with accurate annotations. Crowdsourcing provides a promising approach to tackle the problem mentioned above because of their \"divide and conquer\" nature. Nonetheless, existing crowdsourced techniques, e.g., Amazon Mechanical Turk (MTurk), often fail to guarantee the quality of the annotations. In this paper, we propose a novel probabilistic scheme based on crowdsourcing for ground truth inference. As a representative of object detection, we choose Faster R-CNN as the base framework. We name our scheme Crowd R-CNN. We propose an aggregation approach to aggregate annotations from multiple annotators, which allows to convert anchor labels and annotated labels with each other and train the network end-to-end using backpropagation. To improve accuracy, Crowd R-CNN takes into consideration the multi-dimensional measure of the annotatore' ability and updates these parameters during training. Experimental results demonstrate that Crowd R-CNN can deal with noisy crowdsourced data effectively. Crowd R-CNN is able to achieve comparable results to the baseline with ground truth annotations and is the first algorithm to solve the problem of how to train deep object detection model utilizing crowdsourced labels.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126055286","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: 3

Customer Churn Prediction In Telecommunication Industry Using Machine Learning Classifiers 基于机器学习分类器的电信行业客户流失预测

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387219

Nurul Izzati Mohammad, Saiful Adli Ismail, M. Kama, O. Yusop, Azri Azmi

引用次数: 7

Twin-Delayed DDPG: A Deep Reinforcement Learning Technique to Model a Continuous Movement of an Intelligent Robot Agent 双延迟DDPG:一种模拟智能机器人连续运动的深度强化学习技术

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387199

Stephen Dankwa, Wenfeng Zheng

{"title":"Twin-Delayed DDPG: A Deep Reinforcement Learning Technique to Model a Continuous Movement of an Intelligent Robot Agent","authors":"Stephen Dankwa, Wenfeng Zheng","doi":"10.1145/3387168.3387199","DOIUrl":"https://doi.org/10.1145/3387168.3387199","url":null,"abstract":"In this current research, Twin-Delayed DDPG (TD3) algorithm has been used to solve the most challenging virtual Artificial Intelligence application by training a 4-ant-legged robot as an Intelligent Agent to run across a field. Twin-Delayed DDPG (TD3) is an incredibly smart AI model of a Deep Reinforcement Learning which combines the state-of-the-art methods in Artificial Intelligence. These includes Policy gradient, Actor-Critics, and continuous Double Deep Q-Learning. These Deep Reinforcement Learning approaches trained an Intelligent agent to interact with an environment with automatic feature engineering, that is, necessitating minimal domain knowledge. For the implementation of the TD3, we used a two-layer feedforward neural network of 400 and 300 hidden nodes respectively, with Rectified Linear Units (ReLU) as an activation function between each layer for both the Actor and Critics. We, then added a final tanh unit after the output of the Actor. The Critic receives both the state and action as input to the first layer. Both the network parameters were updated using Adam optimizer. The idea behind the Twin-Delayed DDPG (TD3) is to reduce overestimation bias in Deep Q-Learning with discrete actions which are ineffective in an Actor-Critic domain setting. Based on the Maximum Average Reward over the evaluation time-step, our model achieved an approximate maximum of 2364. Therefore, we can truly say that, TD3 has obviously improved on both the learning speed and performance of the Deep Deterministic Policy Gradient (DDPG) in a challenging environment in a continuous control domain.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124935434","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: 74

Towards a Smart Museum using BIM, IoT, Blockchain and Advanced Digital Technologies 利用BIM、物联网、区块链和先进数字技术建设智能博物馆

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387196

K. Siountri, Emmanouil Skondras, D. Vergados

{"title":"Towards a Smart Museum using BIM, IoT, Blockchain and Advanced Digital Technologies","authors":"K. Siountri, Emmanouil Skondras, D. Vergados","doi":"10.1145/3387168.3387196","DOIUrl":"https://doi.org/10.1145/3387168.3387196","url":null,"abstract":"Nowadays, the Architecture, Engineering and Construction (AEC) industry moves to the digital era, improving the collaboration among its partners using Information and Communications Technologies (ICT) tools. In this context, Building Information Modeling (BIM) provides to smart buildings novel mechanisms to embed Internet of Things (IoT) architectures, as well as to perform end-to-end communication, data exchange and information sharing between project actors. However, this openness and high decentralization of BIM and IoT services of smart buildings leads to several security issues that the use of Blockchain has been proved to provide an effective layer of data protection. This paper examines the interconnection and interoperability of BIM, IoT, Blockchain and advanced digital technologies in the demanding environment of a museum, where efficient and secure monitoring and management are critical factors that should be satisfied. It focuses on the application of the aforementioned technologies in the context of a building that has to deal with multiple administrative requirements, the management and protection of the exhibition areas and the objects exposed in them, the security and the convenience of the visitors, the financial management of the tickets and the profits from museum shops, the workshops, the laboratories and the storage areas, which usually contain numerous invaluable artifacts.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121891753","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: 18

Optimum Design on In-wheel Motor of New Energy Vehicles based on Improved Artificial Bee Colony Algorithm 基于改进人工蜂群算法的新能源汽车轮毂电机优化设计

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387207

Jie Luo, Heshan Zhang, Chun Yuan

引用次数: 1

Real-time Small Object Detection Model in the Bird-view UAV Imagery 鸟瞰无人机图像中的实时小目标检测模型

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387179

Seongkyun Han, J. Kwon, Soon-chul Kwon

引用次数: 1

Improved NMS Filter of Similar Categories for Road Damage Detection 基于相似类别的道路损伤检测改进NMS过滤器

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387241

Sixiong Yang, Bin Wu, Wenzhe Wang

引用次数: 0

GK2 Propulsion System GK2推进系统

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387226

A. Steinbeck, J. Chae, M. Abele

引用次数: 0