2018 International Conference on Computing Sciences and Engineering (ICCSE)最新文献

Protein Subcellular and Secreted Localization Prediction Using Deep Learning 基于深度学习的蛋白质亚细胞和分泌定位预测

2018 International Conference on Computing Sciences and Engineering (ICCSE) Pub Date : 2018-06-05 DOI: 10.1109/ICCSE1.2018.8374220

H. Zidoum, M. Magdy

{"title":"Protein Subcellular and Secreted Localization Prediction Using Deep Learning","authors":"H. Zidoum, M. Magdy","doi":"10.1109/ICCSE1.2018.8374220","DOIUrl":"https://doi.org/10.1109/ICCSE1.2018.8374220","url":null,"abstract":"Predicting the protein structure and discovering its function according to its location in the cell is crucial for understanding the cellular translocation process and has direct applications in drug discovery. Computational prediction of protein localization is alternative to the time consuming experimental counterpart approach. We use deep learning approach to enhance the prediction accuracy while reducing the time in predicting uncharacterized protein sequence localization site. Our approach is based on general biological features of the protein sequence, and compartment specific features to which we added the physico-chemical sequence features. We collected the protein sequences from UniProt1/SWISS-PROT, then we collected the features for each protein. We consider five locations in the dataset, namely cytoplasm (CP), inner membrane (IM), outer membrane (OM), periplasm (PE) and secreted (SEC). We choose the protein sequences to be at least 100 amino-acid-length and a maximum length of 1000 amino acids. Each location contains 500 protein sequences. We propose a deep learning prediction method for bacteria taxonomy that combines a one-versus-one and one-versus all models along with feature selec-tion using linear svm ranking, and deep auto-encoders to initialize the weights. The method achieves overall accuracy of 97.81% using 10- fold cross-validation on our data. Our approach outperforms the current state of the art computational methods in protein subcellular localization on the selected dataset.","PeriodicalId":383579,"journal":{"name":"2018 International Conference on Computing Sciences and Engineering (ICCSE)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124668641","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

Hybrid Multistage Fuzzy Clustering System for Medical Data Classification 混合多级模糊聚类系统在医疗数据分类中的应用

2018 International Conference on Computing Sciences and Engineering (ICCSE) Pub Date : 2018-04-10 DOI: 10.29007/B9QT

Maryam Abdullah, Fawaz S. Al-Anzi, S. Al-Sharhan

{"title":"Hybrid Multistage Fuzzy Clustering System for Medical Data Classification","authors":"Maryam Abdullah, Fawaz S. Al-Anzi, S. Al-Sharhan","doi":"10.29007/B9QT","DOIUrl":"https://doi.org/10.29007/B9QT","url":null,"abstract":"Due to the rapid development in technology nowadays, massive amount of data are available. In medicine, decision making is entirely based on the hidden information in these massive data. For that reason, data mining and machine learning technologies provide powerful tools for knowledge discovery within data. Two main techniques are used interchangeably: clustering and classification. In machine learning, clustering is an unsupervised learning technique while classification is a supervised learning method. These techniques are capable of extracting useful patterns and information which aid the process of data analysis and clinical decisions. This research presents a recent study of these techniques in the medical field during the past five years. Moreover, this paper proposes a hybrid multistage fuzzy clustering system applied to medical data classification. In the proposed system, two fuzzy clustering algorithms specifically FCM and GK were initially employed to obtain the membership values. These weights are then used in the second stage of the system as additional informative features to improve the classification process completed by SVM algorithm. Wisconsin Breast Cancer dataset, real-world application, obtained from UCI were used in the experiments. The results of the experiments show that the additional weights further improve the classification accuracy with 99.06% and 100% sensitivity.","PeriodicalId":383579,"journal":{"name":"2018 International Conference on Computing Sciences and Engineering (ICCSE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124787014","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: 5

Comparison between Epsilon Normalized Least Means Square (ϵ-NLMS) and Recursive Least Squares (RLS) Adaptive Algorithms Epsilon归一化最小均方(ϵ-NLMS)与递归最小二乘(RLS)自适应算法的比较

2018 International Conference on Computing Sciences and Engineering (ICCSE) Pub Date : 2018-04-02 DOI: 10.29007/H74F

A. Mahdi, L. Abdulameer, A. Morad

引用次数: 1

Watch Your Smartwatch 看好你的智能手表

2018 International Conference on Computing Sciences and Engineering (ICCSE) Pub Date : 2018-03-11 DOI: 10.1109/ICCSE1.2018.8374228

Manal Al-Sharrah, A. Salman, I. Ahmad

{"title":"Watch Your Smartwatch","authors":"Manal Al-Sharrah, A. Salman, I. Ahmad","doi":"10.1109/ICCSE1.2018.8374228","DOIUrl":"https://doi.org/10.1109/ICCSE1.2018.8374228","url":null,"abstract":"Smartwatches are trending devices that give its users the ability to be connected, send/receive emails and messages, keep track of health and fitness, and even make calls on the go. Despite these benefits, the disadvantages of smartwatches can be equally terrifying. Smartwatches contain sensitive data and useful information that could be misused if a smartwatch gets lost or stolen. This paper develops a framework to do forensics for smartwatches according to three analysis stages: physical, backup, and wireless communication. We followed the proposed framework using Apple Watch. We found that the watch stores a lot of personal information such as contacts details, text messages, calendar details, Emails, pictures, and wallet data including: stored payment cards, gate passes, and event tickets, if any. In addition, the logical acquisition of the backup files revealed to us that more sensitive information such as the user's secure ID, Wi-Fi, Bluetooth, and MAC addresses can be extracted directly from the backup. Therefore, users must encrypt their backup files to keep their personal data secured. Based on our experiment, we believe that a smartwatch can be used as a valuable evidence for forensic investigators and a more advanced framework must be further developed in this emerging field.","PeriodicalId":383579,"journal":{"name":"2018 International Conference on Computing Sciences and Engineering (ICCSE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134176638","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: 13

Anomaly Detection: Firewalls Capabilities and Limitations 异常检测:防火墙的能力和限制

2018 International Conference on Computing Sciences and Engineering (ICCSE) Pub Date : 2018-03-11 DOI: 10.1109/ICCSE1.2018.8374204

Sultan Alsehibani, Sultan Almuhammadi

引用次数: 3

Citizens' Perspective on the Impact of Social Media on Politics in Kuwait 科威特公民对社交媒体对政治影响的看法

2018 International Conference on Computing Sciences and Engineering (ICCSE) Pub Date : 2018-03-11 DOI: 10.1109/ICCSE1.2018.8374207

Bedour Sharar, M. Abd-El-Barr

{"title":"Citizens' Perspective on the Impact of Social Media on Politics in Kuwait","authors":"Bedour Sharar, M. Abd-El-Barr","doi":"10.1109/ICCSE1.2018.8374207","DOIUrl":"https://doi.org/10.1109/ICCSE1.2018.8374207","url":null,"abstract":"The use of social media in Kuwait has clearly grown in a noticeable way. This growth has affected Kuwaitis in a number of ways. One such effect is in the political arena. This study investigates one aspect of the relationship between social media and politics in Kuwait. The plan is to study the impact of social media on politics in Kuwait from citizens' perspective. In particular, the study focuses mainly on the level of engagement of Kuwaitis citizens' in political issues. For instance, we investigate the role of social media in Kuwaitis' awareness, their participation and political involvement. Towards this objective, a survey has been conducted in February 2016 through which a sample of 637 Kuwaitis were surveyed about their use of social media in dealing with political issues. The collected data were analyzed using the statistical tool SPSS. Analysis of the obtained results reveals that Kuwaitis use social media platforms, especially Twitter, to help them express their political views as well as, accept others' political views. The results also showed that there exists a statistically significant relationship between using social media and the increased political awareness, political participation and attitude of Kuwaitis towards politics. In light of the results, a series of recommendations are made for Kuwaiti citizens, government officials and parliament members. Some suggestions for future studies are also provided.","PeriodicalId":383579,"journal":{"name":"2018 International Conference on Computing Sciences and Engineering (ICCSE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123814530","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

A Smart SCADA System for Oil Refineries 用于炼油厂的智能SCADA系统

2018 International Conference on Computing Sciences and Engineering (ICCSE) Pub Date : 2018-03-11 DOI: 10.1109/ICCSE1.2018.8373996

Mahdi Al-Fadhli, A. Zaher

{"title":"A Smart SCADA System for Oil Refineries","authors":"Mahdi Al-Fadhli, A. Zaher","doi":"10.1109/ICCSE1.2018.8373996","DOIUrl":"https://doi.org/10.1109/ICCSE1.2018.8373996","url":null,"abstract":"This paper proposes a smart automated scheme to monitor and control various processes in oil refineries. The proposal aims to continuously collect data from oil tanks and pipelines, trigger alarm systems for any malfunction, apply effective solutions to the corresponding faults, in addition to other smart features that are integrated into the system to optimize its performance. The proposed design is implemented using LabVIEW, while the wireless data acquisition is made using LabJack. The results demonstrate a successful integration between control and monitoring for providing real-time, continuous and accurate in-formation about the status of the oil tanks and pipelines in the field. The proposed design proves to be a smart version of the well-known Supervisory Control and Data Acquisition systems. Extensions to other industrial processes that include pressure, heat, flow, oil level, and gas leakage, via installing dedicated sensors, are also investigated. A friendly graphical user interface and a mobile application are introduced to save the log files for the history of data and to provide means of remotely monitoring and controlling the sensors and actuators.","PeriodicalId":383579,"journal":{"name":"2018 International Conference on Computing Sciences and Engineering (ICCSE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116656340","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: 6

Signature Analysis as a Medium for Faults Detection in Induction Motors 特征分析作为感应电动机故障检测的一种手段

2018 International Conference on Computing Sciences and Engineering (ICCSE) Pub Date : 2018-03-01 DOI: 10.1109/ICCSE1.2018.8374224

Kareem Noor Al-Deen, Detlef Hummes, B. Fruth, C. Caironi, A. M. Abdel Ghaffar, Marina Karas

{"title":"Signature Analysis as a Medium for Faults Detection in Induction Motors","authors":"Kareem Noor Al-Deen, Detlef Hummes, B. Fruth, C. Caironi, A. M. Abdel Ghaffar, Marina Karas","doi":"10.1109/ICCSE1.2018.8374224","DOIUrl":"https://doi.org/10.1109/ICCSE1.2018.8374224","url":null,"abstract":"An induction motor (IM) is an essential component in process industries and power plants. Therefore, for most applications requiring IMs, the reliability, efficiency and performance are the key factors. Since the costs of break down and unforeseen shut downs in these industries are extremely high, the need for high reliability is always demanded. Most of the failures in IMs are caused by incipient faults progressed over a certain period. If such faults are detected in a reasonable time, it will save progression towards catastrophic damage. Therefore, condition monitoring of IM became increasingly significant. This paper proposes electrical method for online monitoring of IM such as Motor Current Signature Analysis (MCSA) and it proposes elimination of any other sensors. The MCSA technique makes use of the stator current signature for detecting fault frequencies and spectrum. When there is a fault in a motor, the harmonic frequency contents of the line current differ than that of a healthy motor. So, in this work, unbalance and misalignment faults detection methods are implemented using MCSA in LabVIEW with the help of fast fourier transform (FFT) and artificial neural network (ANN).","PeriodicalId":383579,"journal":{"name":"2018 International Conference on Computing Sciences and Engineering (ICCSE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125783605","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: 9

A Hybrid Ant Colony Optimization Algorithm for Topology Optimization of Local Area Networks 局部网络拓扑优化的混合蚁群算法

2018 International Conference on Computing Sciences and Engineering (ICCSE) Pub Date : 2018-03-01 DOI: 10.1109/ICCSE1.2018.8373993

S. Khan, M. Abd-El-Barr

引用次数: 2

Anger Detection in Arabic Speech Dialogs 阿拉伯语语音对话中的愤怒检测

2018 International Conference on Computing Sciences and Engineering (ICCSE) Pub Date : 2018-03-01 DOI: 10.1109/ICCSE1.2018.8374203

Ashraf Khalil, W. Al-Khatib, El-Sayed M. El-Alfy, L. Cheded

引用次数: 13