Proceedings of the 3rd International Conference on Advances in Artificial Intelligence最新文献_第3页

Evaluation of the Impact of Noise on Biometric Authentication Systems 噪声对生物识别认证系统影响的评估

Proceedings of the 3rd International Conference on Advances in Artificial Intelligence Pub Date : 2019-10-26 DOI: 10.1145/3369114.3369118

M. Lafkih, M. Mikram, S. Ghouzali, M. Haziti

{"title":"Evaluation of the Impact of Noise on Biometric Authentication Systems","authors":"M. Lafkih, M. Mikram, S. Ghouzali, M. Haziti","doi":"10.1145/3369114.3369118","DOIUrl":"https://doi.org/10.1145/3369114.3369118","url":null,"abstract":"Intra-class and inter-class are considered as fundamental premise of biometric authentication systems. In order to have a good recognition rate, the biometric images must be captured from favorable conditions. Biometric trait acquisition and processing can be affected by external elements that influence the treatment and the functionality of biometric authentication systems. In effect, the performance can be degraded and the security of the biometric authentication system can be also affected. There are several factors that can affect the performance and the security of biometric systems. There are several factors that can affect the performance and the security of biometric systems. In this work the impact of noise on authentication biometric systems is evaluated. Face and fingerprint images are successively noised in order to measure the impact of the noise on the fingerprint and face biometric systems. Experiment results show that the noise degradation has an important impact on the security and the performance of different biometric authentication system; the system accepts very degraded request (that can be presented by an unknown person) and reject the real user.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129410435","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: 1

A Study of Cooperation with Privacy Loss Based on Asymmetric Constraint Optimization Problem Among Agents 基于非对称约束优化问题的代理间隐私损失合作研究

Proceedings of the 3rd International Conference on Advances in Artificial Intelligence Pub Date : 2019-10-26 DOI: 10.1145/3369114.3369145

T. Matsui

引用次数: 1

Filter-Based Information-Theoretic Feature Selection 基于滤波器的信息论特征选择

Proceedings of the 3rd International Conference on Advances in Artificial Intelligence Pub Date : 2019-10-26 DOI: 10.1145/3369114.3369119

F. Pisheh, R. Vilalta

引用次数: 1

A Hybrid Feature Selection Method for Classifying Metagenomic Data in Relation to Inflammatory Bowel Disease 炎症性肠病相关宏基因组数据分类的混合特征选择方法

Proceedings of the 3rd International Conference on Advances in Artificial Intelligence Pub Date : 2019-10-26 DOI: 10.1145/3369114.3371675

M. Alshawaqfeh, Ammar Gharaibeh, B. Wajid

引用次数: 2

New Sentiment Analysis Model Using LDA for Arabic Tweets 基于LDA的阿拉伯语推文情感分析新模型

Proceedings of the 3rd International Conference on Advances in Artificial Intelligence Pub Date : 2019-10-26 DOI: 10.1145/3369114.3369123

Majdi Beseiso

引用次数: 1

Toward a Deep Recommender System for MOOCs Platforms 面向mooc平台的深度推荐系统

Proceedings of the 3rd International Conference on Advances in Artificial Intelligence Pub Date : 2019-10-26 DOI: 10.1145/3369114.3369157

Khaoula Mrhar, Mounia Abik

引用次数: 5

Proceedings of the 3rd International Conference on Advances in Artificial Intelligence Pub Date : 2019-10-26 DOI: 10.1145/3369114.3369127

H. Murfi

引用次数: 2

Smart Assistant for Blind and Visually Impaired People 盲人和视障人士智能助手

Proceedings of the 3rd International Conference on Advances in Artificial Intelligence Pub Date : 2019-10-26 DOI: 10.1145/3369114.3369139

Nourhan Tahoun, Anwar Awad, Talal Bonny

{"title":"Smart Assistant for Blind and Visually Impaired People","authors":"Nourhan Tahoun, Anwar Awad, Talal Bonny","doi":"10.1145/3369114.3369139","DOIUrl":"https://doi.org/10.1145/3369114.3369139","url":null,"abstract":"Blind or visually impaired people feel miserable and helpless when people help them in their daily simple jobs. Many of them are afraid of going out unless it's necessary. Blind people usually memorize the location of objects so they can find them without struggling, but what if the location of any object has been changed for any reason? Or what if they want to go to an outside place? How they will recognize objects? Colors are also another challenge for them. Smart Assistant for blind people is a portable device. This device will make blind and visually impaired people's lives much easier, as it will help them in recognizing objects. Another aim is to identify texts on objects. An additional feature for the device is to make the device capable of recognizing different colors. This device is easy to use, and it can be used by users of different ages. There are two main parts for our project: software part and hardware part. Hardware part will contain camera, Ultrasonic sensor, Bluetooth headset, Raspberry Pi and power bank. While the software part will be OpenCV as the framework, that uses Python as the programming language. We also use a deep learning technique. This technique is a type of machine learning methods that uses neural network architectures to extract features from an image in order to recognize the object exists in the captured image.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117280473","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: 21

Time to Lane Crossing Estimation Using Deep Learning-Based Instance Segmentation Scheme 基于深度学习实例分割方案的车道交叉时间估计

Proceedings of the 3rd International Conference on Advances in Artificial Intelligence Pub Date : 2019-10-26 DOI: 10.1145/3369114.3369150

Shih-Ting Huang, Yu-Ching Chan, Yu‐Chen Lin, Chun‐Liang Lin

{"title":"Time to Lane Crossing Estimation Using Deep Learning-Based Instance Segmentation Scheme","authors":"Shih-Ting Huang, Yu-Ching Chan, Yu‐Chen Lin, Chun‐Liang Lin","doi":"10.1145/3369114.3369150","DOIUrl":"https://doi.org/10.1145/3369114.3369150","url":null,"abstract":"The main goal of this paper is to develop a deep-learning-based instance segmentation of lane detection for time to lane crossing (TLC) estimation. As is well known, the TLC strategy can build lane departure warning systems (LDWs) with enhanced predictive capabilities which play the role of security early warning in order to prevent dangerous driving situations. LDWs quite relies on the accurate detection of the road markings. Instance segmentation is a task to detect specific objects in an image and create a mask around the object. We use an evolved fully convolutional networks (FCNs) based instance segmentation to yield the high-quality segmentation maps with finer details. It is an effective approach to providing us the high accurate lane detection for LDWs. Time to lane crossing (TLC) is a kind of lane departure indicator in LDWs. For TLC computation, both straight and curved vehicle paths are considered. Thus, the road curvature is an important variable in computations. In this paper, a lane mark fitting algorithm based on inverse perspective mapping (IPM) and sliding window technologies are proposed to compute the road curvature. TLC is duration available for the driver before any lane boundary crossing. The experimental results demonstrate that the proposed deep learning-based instance segmentation can significantly detect the lane. The experiment results illustrate that the proposed TLC estimation strategy can significantly enhance the lane marks recognition accuracy and then provide drivers with timely warnings to avoid unintentional lane departure.","PeriodicalId":262468,"journal":{"name":"Proceedings of the 3rd International Conference on Advances in Artificial Intelligence","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125337832","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: 1

Generating Datasets for Classification Task and Predicting Best Classifiers with Conditional Generative Adversarial Networks 基于条件生成对抗网络的分类任务数据集生成与最佳分类器预测

Proceedings of the 3rd International Conference on Advances in Artificial Intelligence Pub Date : 2019-10-26 DOI: 10.1145/3369114.3369153

Ilya Kachalsky, Alexey Zabashta, A. Filchenkov, G. Korneev

引用次数: 2