2017 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)最新文献_第5页

Simultaneous clustering of multiple heterogeneous gene expression datasets 同时聚类多个异质基因表达数据集

2017 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT) Pub Date : 2017-10-01 DOI: 10.1109/AEECT.2017.8257763

Basel Abu-Jamous, S. Kelly

引用次数: 0

Secure model for distributed data structures on distributed hash tables 分布式哈希表上分布式数据结构的安全模型

2017 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT) Pub Date : 2017-10-01 DOI: 10.1109/AEECT.2017.8257771

Read Al-Aaridhi, Ahmet Yüksektepe, Kalman Graffi

{"title":"Secure model for distributed data structures on distributed hash tables","authors":"Read Al-Aaridhi, Ahmet Yüksektepe, Kalman Graffi","doi":"10.1109/AEECT.2017.8257771","DOIUrl":"https://doi.org/10.1109/AEECT.2017.8257771","url":null,"abstract":"Distributed Hash Tables and unstructured Peer-to-Peer networks present an alternative basis for global software applications. Compared to the Client-Server applications, P2P applications have significant advantages. By eliminating the idea of Servers as the single point of failures and single point of control out of the picture. P2P networks are suitable for many applications like Distributed Online Social Networks the modern society needs today. Distributed Applications built on top of a P2P network are much more resistant to complete system breakdowns, power misuse by authorities (e.g. censorship) and limitless surveillance. In previous work, we presented Distributed Data Structure (DDS) offers a middle-ware for distributed applications. This software has been implemented in a simulation framework for P2P networks called PeerFactSim.KOM. The DDS middle-ware works on top of a Distributed Hash Table (DHT) overlay as a structured P2P network and offers an object-oriented, distributed storage layer. The security of data is an essential topic in such environments. Therefore, without proper security mechanisms, the idea of storing private and sensitive data on unknown network peers become useless, as the stored data can be read or manipulated. In this paper, we present and evaluate a concept of a secure model working completely without trusted nodes for such distributed data structures in peer-to-peer networks. In the evaluation, we show that the time and storage overhead introduced through the security architecture for DDS comes with acceptable proportions for large P2P applications.","PeriodicalId":286127,"journal":{"name":"2017 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133651931","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

Investigating hybrid approaches for Arabic text diacritization with recurrent neural networks 用递归神经网络研究阿拉伯文本变音符化的混合方法

2017 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT) Pub Date : 2017-10-01 DOI: 10.1109/AEECT.2017.8257765

Saba' Alqudah, Gheith A. Abandah, Alaa Arabiyat

{"title":"Investigating hybrid approaches for Arabic text diacritization with recurrent neural networks","authors":"Saba' Alqudah, Gheith A. Abandah, Alaa Arabiyat","doi":"10.1109/AEECT.2017.8257765","DOIUrl":"https://doi.org/10.1109/AEECT.2017.8257765","url":null,"abstract":"Deep neural networks are efficiently used today to solve many complex problems including the automatic diacritization of Arabic text. This paper investigates a hybrid approach for this problem based on a recurrent neural network (RNN). We use the MADAMIRA full morphological and syntactical analyzer to assist the RNN. Only the high confidence diacritics and word segmentation output of this analyzer is fed to the RNN that generates the fully diacritized output. On the LDC ATB3 benchmark, the suggested hybrid approach performs better than the statistical approach. It achieves diacritic and word error rates of 2.39 and 8.40%, respectively, which are 34 and 26% improvements, respectively, over the best previous hybrid results. We implemented the RNN using parallel software and hardware. We use the CURRENNT library to run the RNN on a GPU with 16 streaming multiprocessors. Compared with the previous RNN-based system, our solution is 326 times faster to train and takes an average 0.003 seconds to diacritize a word. This speed makes training on very large data sets feasible to build larger and more accurate deep neural networks.","PeriodicalId":286127,"journal":{"name":"2017 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115488578","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: 20

Traffic light detection for colorblind individuals 色盲个体的交通灯检测

2017 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT) Pub Date : 2017-10-01 DOI: 10.1109/AEECT.2017.8257737

Jamal Al-Nabulsi, A. Mesleh, A. Yunis

引用次数: 6