2017 5th International Symposium on Computational and Business Intelligence (ISCBI)最新文献_第2页

A multi-key compressed sensing and machine learning privacy preserving computing scheme 一种多密钥压缩感知和机器学习隐私保护计算方案

2017 5th International Symposium on Computational and Business Intelligence (ISCBI) Pub Date : 2017-08-01 DOI: 10.1109/ISCBI.2017.8053548

M. Fakhr

{"title":"A multi-key compressed sensing and machine learning privacy preserving computing scheme","authors":"M. Fakhr","doi":"10.1109/ISCBI.2017.8053548","DOIUrl":"https://doi.org/10.1109/ISCBI.2017.8053548","url":null,"abstract":"Recently there has been a huge interest in secure and private cloud computing. In particular; to perform signal processing and machine learning tasks in the encrypted domain. Homomorphic encryption offers provably secure, asymmetric encryption solution to this problem, however, it comes with a high storage and computation cost. Compressed sensing (CS) and random projection (RP) approaches are much lighter; however, they lack privacy since the encryption uses a symmetric key which is the random projection matrix. A multi-key, compressed sensing encryption approach is proposed in this paper for performing basic generic computations. The computing architecture consists of a User, a Cloud (which stores encrypted data from an Owner), and a Trusted Third Party (TTP) which is responsible for distributing the random CS keys. The TTP also trains two machine learning modules; ML1 and ML2. ML1, used at the cloud, takes as input the multi-key encrypted data and produces an intermediate encrypted result. ML2, available at the user side, decrypts the results. This novel approach is much cheaper than homomorphic encryption in terms of data expansion, storage as well as encryption time. Also, it offers the privacy of the multi-keys. The proposed approach is applied on 2 generic computing tasks; namely, squared Euclidean distance and dot product. The developed approach is tested on the COREL image classification task using the squared Euclidean distance and on an autoregressive (AR) stock prediction task using the dot product.","PeriodicalId":128441,"journal":{"name":"2017 5th International Symposium on Computational and Business Intelligence (ISCBI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121572900","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

Keystroke recognition using neural network 使用神经网络进行击键识别

2017 5th International Symposium on Computational and Business Intelligence (ISCBI) Pub Date : 2017-08-01 DOI: 10.1109/ISCBI.2017.8053550

Purvashi Baynath, K. Soyjaudah, Maleika Heenaye-Mamode Khan

引用次数: 7

TPC: An automatically generated comprehensive English-Persian parallel corpus 自动生成的综合英语-波斯语平行语料库

2017 5th International Symposium on Computational and Business Intelligence (ISCBI) Pub Date : 2017-08-01 DOI: 10.1109/ISCBI.2017.8053551

Saeed Farzi, Heshaam Faili

{"title":"TPC: An automatically generated comprehensive English-Persian parallel corpus","authors":"Saeed Farzi, Heshaam Faili","doi":"10.1109/ISCBI.2017.8053551","DOIUrl":"https://doi.org/10.1109/ISCBI.2017.8053551","url":null,"abstract":"Nowadays; Parallel corpus is one of the most important resources which can be employed in different researches such as machine translation, bilingual lexicography, and linguistics. This paper describes the process of building a large-scale (about 400, 000 sentence pairs) English-Persian parallel corpus called Tehran Parallel Corpus (TPC). The aim of study is to introduce the structure and explain the materials utilized for constructing TPC. In addition, some useful tools developed within the project have been introduced and three sorts of the statistical machine translation systems trained by TPC have been considered. In order to develop a high quality parallel corpus, unsure alignments recognized via a MaxEnt classifier have been eliminated from the corpus. As an intrinsic evaluation, 1,600 sentence pairs are elicited randomly and compared manually with a gold standard test set. As an extrinsic evaluation, three Phrase-based SMT systems, which is trained by TPC are incorporated. The results demonstrate the superiority of our translator systems over English to Persian Google translator system in term of BLEU and TER metrics.","PeriodicalId":128441,"journal":{"name":"2017 5th International Symposium on Computational and Business Intelligence (ISCBI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129177937","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

Maximum-minimum temperature prediction using fuzzy random auto-regression time series model 利用模糊随机自回归时间序列模型预测最高最低温度

2017 5th International Symposium on Computational and Business Intelligence (ISCBI) Pub Date : 2017-08-01 DOI: 10.1109/ISCBI.2017.8053544

R. Efendi, N. Samsudin, N. Arbaiy, M. M. Deris

引用次数: 5

Reduction method of zigzag type-2 uncertain variable and its application in two stage STP 之字形2型不确定变量的约简方法及其在两阶段STP中的应用

2017 5th International Symposium on Computational and Business Intelligence (ISCBI) Pub Date : 2017-08-01 DOI: 10.1109/ISCBI.2017.8053561

D. Sengupta, U. Bera, Anirban Datta, Amrit Das

引用次数: 5

Defuzzication method of type-2 gamma fuzzy variables and its application to transportation problem 二类模糊变量的解模糊方法及其在交通问题中的应用

2017 5th International Symposium on Computational and Business Intelligence (ISCBI) Pub Date : 2017-08-01 DOI: 10.1109/ISCBI.2017.8053562

Akash Singh, U. Bera, D. Sengupta, Anirban Datta, Amrit Das

引用次数: 1

The nexus between R&D, innovation and profitability of indigenous oil firms: A structural equilibrium model approach 本土石油企业研发、创新与盈利能力的关系:一个结构均衡模型方法

2017 5th International Symposium on Computational and Business Intelligence (ISCBI) Pub Date : 2017-08-01 DOI: 10.1109/ISCBI.2017.8053554

Y. Akinwale

引用次数: 5

Facial feature detection: A facial symmetry approach 面部特征检测:一种面部对称方法

2017 5th International Symposium on Computational and Business Intelligence (ISCBI) Pub Date : 2017-08-01 DOI: 10.1109/ISCBI.2017.8053538

Gulbadan Sikander, S. Anwar, Y. Djawad

引用次数: 8

A novel backup path planning approach with ACO 一种新的基于蚁群算法的备份路径规划方法

2017 5th International Symposium on Computational and Business Intelligence (ISCBI) Pub Date : 2017-08-01 DOI: 10.1109/ISCBI.2017.8053543

Danny Meier, Ilir Tullumi, Yannick Stauffer, Rolf Dornberger, T. Hanne

引用次数: 5

Critical success factors of enterprise resource planning implementation in construction: Case of Taiwan 建筑业企业资源规划实施的关键成功因素:以台湾为例

2017 5th International Symposium on Computational and Business Intelligence (ISCBI) Pub Date : 2017-08-01 DOI: 10.1109/ISCBI.2017.8053556

Chi-Kao Chang, Min-Yuan Fang

{"title":"Critical success factors of enterprise resource planning implementation in construction: Case of Taiwan","authors":"Chi-Kao Chang, Min-Yuan Fang","doi":"10.1109/ISCBI.2017.8053556","DOIUrl":"https://doi.org/10.1109/ISCBI.2017.8053556","url":null,"abstract":"Over the past years, firms around the world have implemented enterprise resource planning (ERP) systems to have a standardized information system in their respective organizations and to re-engineer their business processes. Based on the business pressures force to take more powerful reactions, like as cost down the supply chain, slash stock, shorten manufacturing time, increase product category, promise the lead-time, provide better customer service, continue improving product quality, and coordinate globalize service efficiently. Hence, how to integrate EPR systems inner business has become the essential tool for business to face the variable world. Enterprise resource planning (ERP) systems have been used in integrating information and accelerating its distribution across functions and departments with the aim to increase organizations operational performance. Based on the view of BSC (Balanced Scorecard), this study mainly attempts to build and to construct the electronic performance management system(finance, customer, company internal process, and learn-growth) to make “performance indicators” evaluation by doing questionnaire analysis against company vision, blueprint, and mission. The case study is based on implementation of an ERP system on the steel industry in Taiwan. By the case, investigate into the key successful factors and the performances to implement the ERP system, the conclusion that discuss to gain according to the case, with provide the reference to the domestic enterprise in implementation of ERP system, hope it will make the enterprise more competitive and to create the biggest value for the customers.","PeriodicalId":128441,"journal":{"name":"2017 5th International Symposium on Computational and Business Intelligence (ISCBI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114073535","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