{"title":"Deep Learning for Ligand-Based Virtual Screening in Drug Discovery","authors":"Meriem Bahi, M. Batouche","doi":"10.1109/PAIS.2018.8598488","DOIUrl":"https://doi.org/10.1109/PAIS.2018.8598488","url":null,"abstract":"Due to the time and cost problems with traditional drug discovery, new methods must be found to increase the declining efficiency of traditional approaches. Virtual Screening (VS) is one possible solution to solve this problem. VS of databases has become an attractive method for pharmaceutical research. It plays a crucial role in the early stage of the drug discovery and development process. It aims to reduce the enormous search space of chemical compounds. As the number of ligands in the databases is increasing rapidly, this step should be both fast and effective in order to distinguish between active and inactive ligands. Deep learning algorithms can be used for screening big databases of molecules and classifying the ligands as drug-like and non-druglike against a particular protein target and therefore speed up the VS process. In this paper, we propose a fast compound classification method based on a deep neural network for Virtual Screening called (DNN-VS) using the Spark-H2O platform in order to label small molecules from huge databases. Experimental results have shown that the proposed approach outperforms state-of-the-art machine learning techniques with an overall accuracy more than 99%.","PeriodicalId":197003,"journal":{"name":"2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS)","volume":"477 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123253940","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}
{"title":"Improving high-resolution satellite images retrieval using Linear SVM classifier and data augmentation","authors":"H. Sebai, Assia Kourgli","doi":"10.1109/PAIS.2018.8598536","DOIUrl":"https://doi.org/10.1109/PAIS.2018.8598536","url":null,"abstract":"The availability of huge remote sensing image dataset imposes recourse to powerful techniques of content-based image retrieval for archiving and mining. This paper propose descriptors based on the SIFT (Scale invariant features) combined with SVM linear classification. To build a powerful image classifier using very little training data, image augmentation is usually required to boost the performance of the classification. For this reason, an augmentation data is used to increase the training data for the SVM (Support vector Machine) classifier. The creation of the training data is done using several techniques of augmentation: anisotropic filter. We report a first evaluation of the CBIR (Content based image retrieval) and the second evaluation of the system aims to compare the deep learning with the boosted SVM classification.","PeriodicalId":197003,"journal":{"name":"2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123763200","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}
{"title":"Semi-automatic segmentation method of left for ventricle in cardiac cine MRI analysis of myocardial viability","authors":"Dali Youcef Sarra, Messadi Mohamed","doi":"10.1109/PAIS.2018.8598496","DOIUrl":"https://doi.org/10.1109/PAIS.2018.8598496","url":null,"abstract":"Cardiovascular disease is one of the major health problems in the world. The complexity of cardiac cine MR images and on the other hand, the diversity of cardiovascular disease require segmentation phase. This phase is an important step in the processing and interpretation of medical images. In this paper, a new approach for the segmentation of the left ventricle from short-axis cardiac cine MR images is presented. Our approach is based on three-steps: In the first one, we have effected a pretreatment using mathematical morphology to improve images quality. Thereafter, we proceed on the segmentation of the left ventricle, in this phase we combined between the region growing and the active contour methods to obtain the endocardial form exactly. Finally, the parameters were calculated for characterization, such as tele-diastolic volume (VTD), tele-systolic volume (VTS) and ejection fraction (FE) to predict cardiovascular diseases. The proposed method was tested on the Heart-database containing 18 patients. The results are satisfactory with excellent endocardial segmentation and a good correlation of 88% for VTD and 91% for VTS between our parameters and those of experts which shows the good performance of our approach which can be used to aid diagnosis.","PeriodicalId":197003,"journal":{"name":"2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS)","volume":"82 2-3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114032487","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}
Rabie Hamidane, L. Mouss, Abdelkader Bellarbi, Mehdaoui Rafik
{"title":"Implementation of a Preventive Maintenance System Based on Augmented Reality","authors":"Rabie Hamidane, L. Mouss, Abdelkader Bellarbi, Mehdaoui Rafik","doi":"10.1109/PAIS.2018.8598510","DOIUrl":"https://doi.org/10.1109/PAIS.2018.8598510","url":null,"abstract":"In this article, we present ARPM (Augmented Reality-based Preventive Maintenance) system, which aims at offering to the technician of a Cement Factory a virtual assistance in real time using various forms of 3D models, images or even texts, in order to help him to maintain and inspect his equipment. This system not only offers the possibility of reducing costs of the preventive maintenance, but also allows monitoring and even anticipating failures.In order to ensure a reliable maintenance operation, we adapted our system to be compatible with the CMMS system (Computerized Maintenance Management System) already exists in the Cement factory.","PeriodicalId":197003,"journal":{"name":"2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129627480","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}
A. Meraoumia, H. Bendjenna, M. Amroune, Yahia Dris
{"title":"Towards a Secure Online E-voting Protocol Based on Palmprint Features","authors":"A. Meraoumia, H. Bendjenna, M. Amroune, Yahia Dris","doi":"10.1109/PAIS.2018.8598520","DOIUrl":"https://doi.org/10.1109/PAIS.2018.8598520","url":null,"abstract":"Nowadays, internet becomes very vital for any kind of information exchange. One of application which can uses internet for information exchange is the electronic voting (e-voting). Indeed, e-voting has several advantages like the accessibility for the disabled and elderly; the ease of long-distance voting; the low costs and the greater voter turnout. Thus, the challenge that oppose e-voting process are the need of securing the transmitted information which include the voters data as well as the chosen candidates. In this paper, we propose a secure crypto-biometric scheme dedicated to online e-voting system. The fuzzy commitment concept associated with the palmprint (PLP) and palm-vein (PLV) is the core of our system. In this study, to enhance the discriminating capability of the PLP and/or PLV feature vectors, we use Gabor filter with thresholding method. After that, the information, which will be sent, is encrypted using a random key which is then embedded in a biometric feature vector using a fuzzy commitment scheme. Then, in the central election server, the embedded encryption key is extracted using a new retrieval scheme, which is then used to decrypt the transmitted information before be processed. The experimental results showed that online e-voting based crypto-biometric system has higher performances in terms of accuracies and key retrieval.","PeriodicalId":197003,"journal":{"name":"2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129706815","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}
Amel Boulemnadjel, Ferhat Kaabache, S. Kharfouchi, F. Hachouf
{"title":"Higher-Order Spatial Statistics: A Strong Alternative In Image Processing","authors":"Amel Boulemnadjel, Ferhat Kaabache, S. Kharfouchi, F. Hachouf","doi":"10.1109/PAIS.2018.8598513","DOIUrl":"https://doi.org/10.1109/PAIS.2018.8598513","url":null,"abstract":"The goal of the this work is twofold, namely: 1) to discuss a method for identification of linear 2-D nonminimum phase system using higher order cumulants alone, and to derive the almost-sure convergence properties of sample estimates of higher-order spatial statistics. The measure of almost sure convergence is obtained for the sample estimates of third and fourth order moments and cumulants. 2) The experimental cumulants are used as texture features, they are later, incorporated into classification schemes. Some applications using synthetic textures and aerial images are presented to illustrate great descriptive power of higher-order cumulants.","PeriodicalId":197003,"journal":{"name":"2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130609183","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}
{"title":"Using A Real-coded Genetic Algorithm to Predict Characterization Parameters for Petroleum Fraction","authors":"Chafik Belghit, Y. Lahiouel, T. A. Albahri","doi":"10.1109/PAIS.2018.8598528","DOIUrl":"https://doi.org/10.1109/PAIS.2018.8598528","url":null,"abstract":"In this paper, an efficient real-coded genetic algorithm (RCGA) for process optimization is developed to build new correlations to estimate properties of petroleum. This equation is a function of two input parameters that can be easily obtained. Moreover, an available data bank was used to develop the correlations using optimization. general experiment results reveal that the proposed RCGA is simple to use and provides a significantly faster convergence speed and much better search performance than comparative methods. The results of the proposed models are compared to others recommended in literature that have had large acceptance in the oil industry. The comparison results indicate that the proposed model is more precise than the most common models for characterizing petroleum fractions.","PeriodicalId":197003,"journal":{"name":"2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS)","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122054741","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}
{"title":"Fault Tolerance in Distributed Systems: A Survey","authors":"Abdeldjalil Ledmi, H. Bendjenna, S. Hemam","doi":"10.1109/PAIS.2018.8598484","DOIUrl":"https://doi.org/10.1109/PAIS.2018.8598484","url":null,"abstract":"Distributed systems can be homogeneous (cluster), or heterogeneous such as Grid, Cloud and P2P. Several problems can occur in these types of systems, such as quality of service (QoS), resource selection, load balancing and fault tolerance.Fault tolerance is a main subject regarding the design of distributed systems. When a hardware or software failure occurs in the system, it causes a failure and we call it, in this case, a fault. Moreover, in order to allow the system to continue its functionalities, even in the presence of these faults, they must find techniques, which tolerate failure; the goal of these techniques is to detect and to correct these errors.In this paper, we introduce at first an overview of the basic concepts of distributed systems and their failures types, then we present, in a detailed manner, the different techniques that tolerate fault, used to identify and to correct faults in different kinds of systems such as: cluster, grid computing, Cloud and P2P systems.","PeriodicalId":197003,"journal":{"name":"2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129433727","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}
{"title":"LMDS-SEA: Upgrading the Shape Exchange Algorithm (SEA) to handle general time series classification by local matching and distance selection","authors":"A. Lahreche, Bachir Boucheham","doi":"10.1109/PAIS.2018.8598504","DOIUrl":"https://doi.org/10.1109/PAIS.2018.8598504","url":null,"abstract":"In this paper, we propose an enhanced version of the Shape Exchange Algorithm (SEA) for the purpose of general Time Series Classification (TSC). Indeed, the SEA method is very effective in quasi-periodic time series matching. However, for general time series, it has been found that this method needs some kind of enhancement to meet state-of-the-art TSC techniques. The proposed LMDS-SEA method (Local Matching with Distance Selection Shape Exchange Algorithm) is based on two ideas: a) Distance Selection as an adaptation paradigm for classification method and b) Local Matching. The distance selection contribution consists in dynamically selecting the best distance to apply as a function of the data to classify from a pool of Euclidian Distance (ED), SEA and LM-SEA (Local Matching SEA). The Local Matching (SEA) contribution consists in matching equal and corresponding sub-sequences in the two time series to match, X and Y, using the SEA method locally. The newly proposed LMDS-SEA method was applied to classification of the public UCR benchmark (UCR: General Time Series Classification/Clustering dataset of the University of California at Riverside) based on 1NN classifier. Results show significant enhancements in the classification accuracy of the proposed 1NN LMDS-SEA classifier over the 1NN SEA classifier (1NN LMDS-SEA: 64 WINs, 1NN SEA: 00 WINs and 21 Ties). Results show also that the proposed 1NN LMDS-SEA classifier is more effective than the very effective 1NN DTW classifier (1NN LMDS-SEA: 50 WINs, 1NN DTW: 28 WINs and 7 Ties). Note that a win is credited to a classifier A over a classifier B if A is more accurate than classifier B, class-wise, over the 85 classes of the UCR benchmark.","PeriodicalId":197003,"journal":{"name":"2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125090326","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}
M. Soltane, Yudith Cardinale, Rafael Angarita, Philippe Rosse, M. Rukoz, Derdour Makhlouf, O. Kazar
{"title":"A Self-adaptive Agent-based System for Cloud Platforms","authors":"M. Soltane, Yudith Cardinale, Rafael Angarita, Philippe Rosse, M. Rukoz, Derdour Makhlouf, O. Kazar","doi":"10.1109/PAIS.2018.8598507","DOIUrl":"https://doi.org/10.1109/PAIS.2018.8598507","url":null,"abstract":"Cloud computing is a model for enabling on-demand network access to a shared pool of computing resources, that can be dynamically allocated and released with minimal effort. However, this task can be complex in highly dynamic environments with various resources to allocate for an increasing number of different users requirements. In this work, we propose a Cloud architecture based on a multi-agent system exhibiting a self-adaptive behavior to address the dynamic resource allocation. This self-adaptive system follows a MAPE-K approach to reason and act, according to QoS, Cloud service information, and propagated run-time information, to detect QoS degradation and make better resource allocation decisions. We validate our proposed Cloud architecture by simulation. Results show that it can properly allocate resources to reduce energy consumption, while satisfying the users demanded QoS.","PeriodicalId":197003,"journal":{"name":"2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127008105","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}