Proceedings of the 2020 5th International Conference on Intelligent Information Technology最新文献

筛选
英文 中文
Legal Protection of Copyright on Copyrighted Content Downloaded Through the Internet 通过互联网下载的版权内容的版权法律保护
Arvin Indrawan, G. Stevens, Gratianus Martin Brianto, F. Gaol, Tanty Oktavia
{"title":"Legal Protection of Copyright on Copyrighted Content Downloaded Through the Internet","authors":"Arvin Indrawan, G. Stevens, Gratianus Martin Brianto, F. Gaol, Tanty Oktavia","doi":"10.1145/3385209.3385228","DOIUrl":"https://doi.org/10.1145/3385209.3385228","url":null,"abstract":"The development of the internet made new problems within the scope of copyright. The internet is used to download copyrighted content and use it without permission from the creators. The legal protection of copyright the creators of content downloaded through the internet done in a way that the administration, through the instrument of criminal law and civil lawsuit. Legal efforts to protect the copyright of songwriters downloaded via the internet are carried out in several ways, namely the Ministry of Information and Technology to play an active role in blocking sites that provide free song download facilities and prepare human resources in the field of investigation such as from the National Police The Republic of Indonesia as well as Civil Servants and other Investigators such as prosecutors and judges who have the ability and knowledge in the field of IPR as well as the role of the Copyright Council to provide knowledge of the importance of IPR.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125906636","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
TargetNet Backdoor: Attack on Deep Neural Network with Use of Different Triggers TargetNet后门:使用不同触发器攻击深度神经网络
Hyun Kwon, Jungmin Roh, H. Yoon, Ki-Woong Park
{"title":"TargetNet Backdoor: Attack on Deep Neural Network with Use of Different Triggers","authors":"Hyun Kwon, Jungmin Roh, H. Yoon, Ki-Woong Park","doi":"10.1145/3385209.3385216","DOIUrl":"https://doi.org/10.1145/3385209.3385216","url":null,"abstract":"Deep neural networks (DNNs) provide good performance in image recognition, speech recognition, and pattern analysis. However, DNNs are vulnerable to backdoor attacks. Backdoor attacks allow attackers to proactively access DNN training data to train it on additional data that are malicious, including a specific trigger. Normally, DNNs correctly classify normal data, but malicious data with a specific trigger trained by attackers can cause misclassification by DNNs. For example, if an attacker sets up a road sign that includes a specific trigger, an autonomous vehicle equipped with a DNN may misidentify the road sign and cause an accident. Thus, an attacker can use a backdoor attack to threaten the DNN at any time. However, in certain cases, when an attacker wants to perform a targeted attack, it may be desirable for the data introduced through the backdoor to be misrecognized as a particular class chosen by the attacker according to the position of a trigger. For example, if a specific trigger is attached to the top right side of the road sign, it may be misunderstood as a left-turn sign; if a specific trigger is attached to the top left side of the road sign, it may be misunderstood as a right-turn sign; and if a specific trigger is attached to the bottom left side of the road sign, it may be misunderstood as a U-turn sign. In this paper, we propose the TargetNet backdoor, which is designed to be misidentified as a particular target class chosen by the attacker according to a specific trigger location. The proposed method additionally trains the target classifier on the TargetNet backdoor data so that data with a trigger at a specific location will be misidentified as the target class selected by the attacker. We used MNIST and Fashion-MNIST as experimental datasets and Tensor-flow as a machine learning library. Experimental results show that the proposed method applied to MNIST and Fashion-MNIST has a 100% attack success rate for the TargetNet backdoor and 99.17% and 91.4% accuracy rates on normal test data, respectively.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130005719","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
Low Resource Call of FFT Circuit Design FFT电路设计的低资源调用
Rongshan Wei, Zhiyun Zhu
{"title":"Low Resource Call of FFT Circuit Design","authors":"Rongshan Wei, Zhiyun Zhu","doi":"10.1145/3385209.3385218","DOIUrl":"https://doi.org/10.1145/3385209.3385218","url":null,"abstract":"Existing studies mainly focus on parallel structures and FFT circuit designs with a large sample sizes, and circuits will consume a lot of resources. To compensate for the abovementioned deficiencies, this paper proposed a new FFT circuit design method to reach the low-resource call goal of the FFT circuit. Under the framework of decimation-in-time (DIT) butterfly plot of 8,192 sampling points, the block operation scheme of recursive structure was adopted, and Euler's formula was used to optimize rotation factors in the butterfly plot. Results show that the proposed FFT design method in this paper can save register (REG) quantity by about 96.87% and look-up-table (LUT) quantity by an average of about 98.75% under the same quantity of sampling points, thus, resource call is reduced by a large margin. The study scheme can provide a reference for low resource call design of the FFT circuit.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122409661","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
Estimation of the Line of Sight from Eye Images with Eyelashes 带睫毛的人眼图像的视线估计
K. Hoshino, Satoshi Shimanoe, Yuya Nakai, Yuki Noguchi, Maki Nakamura
{"title":"Estimation of the Line of Sight from Eye Images with Eyelashes","authors":"K. Hoshino, Satoshi Shimanoe, Yuya Nakai, Yuki Noguchi, Maki Nakamura","doi":"10.1145/3385209.3385233","DOIUrl":"https://doi.org/10.1145/3385209.3385233","url":null,"abstract":"There are two methods for tracking the line of sight: the corneal reflection method and the pupil method. The former allows highly accurate measurement because the focus point is detected, however, its weakness is that deviations can occur in the positional relations between the eye and the camera. The latter has a strong positional relation between the eye and the camera because the pupil is shot by the camera, but because elliptical approximation is used, its weakness is masking of the pupil by eyelashes and the eyelid. When using an HMD or headgear in sports such as Japanese fencing, in either method, trying to estimate the user's line of sight is easier if the small cameras are facing down at an angle from the forehead at the eyes because the user's field of vision is not obstructed. Therefore, in this study, the authors proposed a line of sight estimating method that uses eye images that include eyelashes. Specifically, we proposed using inexpensive small cameras to take images of the eyes from slightly above. We also proposed processing to separate the eyelashes and pupils in the images to allow estimating the line of sight, and an eyeglasses-type device. Additionally, in order to achieve a stable line of sight estimation, we also made proposals for adjusting the various parameters to suit the sizes of the heads and distances between the eyes of individual users, such as the positioning and facing of the small cameras and the optical axes and intensity of supplementary light sources.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114213870","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: 4
Hardware-assisted High-performance DNA Alignment System 硬件辅助的高性能DNA比对系统
Binh Kieu-Do-Nguyen, C. Pham-Quoc, C. Pham
{"title":"Hardware-assisted High-performance DNA Alignment System","authors":"Binh Kieu-Do-Nguyen, C. Pham-Quoc, C. Pham","doi":"10.1145/3385209.3385223","DOIUrl":"https://doi.org/10.1145/3385209.3385223","url":null,"abstract":"The investigations of DNA become more and more important in this era. A plethora of new algorithms that were published over the last decade are apparent evidences for this fact. In the DNA's researches, alignment is one of the most important steps that is especially taken care and continuously developed. Despite they already have a lot of algorithms for this problem, and some of them provide impressive enhancements. But it is still far more to state that DNA alignment has already achieved the ideal performance. Therefore, in this work, we promote an efficient architecture which is based on our improved BWA-MEM algorithm that we have already published in [14]. Beside that, we also propose a communication protocol as well as as its API in order to ensure the accuracy and stability of the system. The system offers a speed-up by 18.14x when compared with modern computing platforms.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128766578","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
Toponym Extraction in Thai Tweets Using a Hybrid Approach 使用混合方法提取泰语推文中的地名
Manassanan Boonnavasin, Prapaporn Rattanatamrong
{"title":"Toponym Extraction in Thai Tweets Using a Hybrid Approach","authors":"Manassanan Boonnavasin, Prapaporn Rattanatamrong","doi":"10.1145/3385209.3385225","DOIUrl":"https://doi.org/10.1145/3385209.3385225","url":null,"abstract":"Crowdsourcing has become an important tool in areas such as business and marketing. It can help organizations solve large-scale problems in areas including traffic management and political campaigning. Toponym extraction is necessary when analyzing crowdsourced data for traffic tracking or event reporting. Dictionaries and rule-based analysis are commonly used for matching and extracting entities from text. However, the creation of an effective dictionary is not an easy task, especially when the goal is to name a large number of locations. Named Entity Recognition (NER) can help address this, but the approach has certain limitations. In this paper, we describe an improved approach to toponym extraction from Twitter messages that combines a dictionary and NER. As tweets are limited to 280 characters, any locations mentioned are usually referred to using abbreviations. The variety of forms that location names take, and the unstructured language of tweets, are challenging both to the dictionary and NER methods. We divided tweets into four categories to investigate the effect of analyzing messages from different domains. The average accuracy was 49.18% when using only the dictionary, 59.30% when using only NER, and 75.43% when using the hybrid method.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116120861","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
The Emerging AI Policy for e-commerce Industry 新兴的电子商务行业人工智能政策
Zehra Ozge Yildiz, N. Beloff
{"title":"The Emerging AI Policy for e-commerce Industry","authors":"Zehra Ozge Yildiz, N. Beloff","doi":"10.1145/3385209.3385210","DOIUrl":"https://doi.org/10.1145/3385209.3385210","url":null,"abstract":"For the fast-growing e-Commerce industry, the AI is the game-changer but is it really utilised in a most effective way or is it just a risky 'artificial balloon'? Is it gambling to rely on AI technologies without forming a dedicated policy? To answer these questions and propose a cautious approach towards the emerging technologies, in this explanatory research, the risks related to the fast adaptation of AI technologies addressed with recommended actions. Within the scope of the research, eCommerce industry is analysed to reveal the issues related to AI implementations. Accordingly, the challenges of AI technologies have been questioned so that necessary precaution, preparation, and considerations can be pointed out. Accordingly, an AI policy for e-Commerce industry is formed for the businesses to benefit from the most recent technologies without risking the possible issues. Three main policy subjects have been determined as transparency of the technologies, accountability for the purpose, process and performance of them, and lastly, emerging user privacy and security related issues. For each policy subject, a review of the AI implementations, recent critics and forecasted expectations are investigated to list the recommendations for the candidate AI implementer. The research aims to provide an AI policy guideline for e-Commerce industry with a detailed overview of the outstanding issues, best practices and recommendations from scholars.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131611870","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
Seismic Data Analysis Regression Model on Reactor Pressure Vessel using Fast Fourier Transform and Machine Learning 基于快速傅里叶变换和机器学习的反应堆压力容器地震数据分析回归模型
Youjeong Park, Sung-Ho Yoon, Jun Hyeok Choi, M. Kim, Jae boong Choi
{"title":"Seismic Data Analysis Regression Model on Reactor Pressure Vessel using Fast Fourier Transform and Machine Learning","authors":"Youjeong Park, Sung-Ho Yoon, Jun Hyeok Choi, M. Kim, Jae boong Choi","doi":"10.1145/3385209.3385211","DOIUrl":"https://doi.org/10.1145/3385209.3385211","url":null,"abstract":"The paper presents a way for data analysis of seismic data in order to predict stress intensity data on reactor pressure vessel because it is important to investigate the integrity of the reactor pressure vessel. As the seismic waveform data are time-series data, fast Fourier Transform is implemented for data processing. After feature extraction using fast Fourier Transform, machine learning algorithms were used to analyze and predict the stress intensity data for regression. We applied Support Vector Regression, Random Forest Regression, K-nearest Neighbor Regression and Gradient Boosting Regressor and compared these algorithms in order to improve good accuracy on the regression. This research shows that it is possible to make the correlation between the seismic waveform data and the stress intensity for reliability on the reactor pressure vessel.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"263 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123394215","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
The Design of Smart Cashless Transaction 智能无现金交易的设计
Anthony Bryan Fernando, Shreevasta, Ferry Desprianto, F. Gaol, Tanty Oktavia
{"title":"The Design of Smart Cashless Transaction","authors":"Anthony Bryan Fernando, Shreevasta, Ferry Desprianto, F. Gaol, Tanty Oktavia","doi":"10.1145/3385209.3385227","DOIUrl":"https://doi.org/10.1145/3385209.3385227","url":null,"abstract":"Cashless Transaction describes as a state where financial transactions are not bound by physical form such as banknotes or coins, but rather trough transfer of digital information (electronic representation of money). Cashless Transaction exists because of fast majorities of human transaction evolved towards digital environment, this creates an opportunity where legal money exists, recorded, and exchanged in digital form. Thus cashless transaction will make less effort in currency operation cost, keep on track with expenses, connected anytime everywhere as long as connected with internet, and eliminates the needs of banknotes or receipt. Cashless Transaction have done over the past few years making life easier by reducing a number of objects to merge into 1 functional object that could make payments faster and simpler starting with check the first mark of cashless transaction that's still being used nowadays, but cashless transaction doesn't stop evolving in this modern era where money is demonetized, cashless transaction is moving into the digital grid resulting a breakthrough mobile wallets and online transfer that offers people flexibility because its technology advancement makes it possible to make payments anytime and anywhere since it's only depend on a secure network(internet) and a platform, therefore cashless transaction could be done as fast as possible saving precious time. Cashless transaction has some of key components such as security, UX, Functionality, Performance and Data Integrity. Five key components could make cashless transaction become reality but also poses a different threat to cashless transaction. Hacking is one of them. Hacking could be done by anyone that have the ability to compromise the transmission, the transmission needs to have more data protection thus the cashless transaction could be done safely and free of risk.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127873597","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: 2
Analysis of Atmospheric Quality based on Cellular Automata Simulation 基于元胞自动机模拟的大气质量分析
H. Huynh, Phuoc Thanh Luu, H. H. Luong, Nghia Duong-Trung, Thai-Minh Truong, Nga Quynh Thi Tang, Tu Cam Thi Tran
{"title":"Analysis of Atmospheric Quality based on Cellular Automata Simulation","authors":"H. Huynh, Phuoc Thanh Luu, H. H. Luong, Nghia Duong-Trung, Thai-Minh Truong, Nga Quynh Thi Tang, Tu Cam Thi Tran","doi":"10.1145/3385209.3385213","DOIUrl":"https://doi.org/10.1145/3385209.3385213","url":null,"abstract":"Urban environmental problems are contributed by numerous factors, such as greenhouse gas emissions and air quality. Material combustion from vehicles, manufacturing plants, fossil fuel consumption, and many other industrial activities are the primary sources of atmospheric pollution. These noxious implications cause thousands of premature deaths, million years of life lost, and a contributor to climate change, primarily in developing countries. Therefore, pollution forecast and simulation before happening are the main focus of this paper. It helps address pollution levels, infrastructure installation of cities and underpins a range of environmental policies. Awareness of the characteristics of the atmospheric quality, including the mathematical basis for assessing pollution, allows building the pollution assessment models required to understand air quality and controls. In this paper, an effective model for simulating and analyzing atmospheric quality using cellular automata is proposed. Our model employs three novel underlying rules, e.g. rules of gravity, diffusion, and wind. Four experimental scenarios have been conducted to demonstrate the applicability of update rules necessitated to apprehend air pollution.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115190698","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书