{"title":"Steganalysis System for Colour Images Based on Merging the Colour Gradient Cooccurrence Matrix and Histogram of Difference Image","authors":"Ahd Aljarf, Saad Amin","doi":"10.1109/NCG.2018.8593181","DOIUrl":"https://doi.org/10.1109/NCG.2018.8593181","url":null,"abstract":"Steganography is the science of hiding information in some other medium. These media can be text, images, audio or video files. Steganographic analysis (steganalysis), on the other hand, is the science of detecting the existence of hidden information.Many steganalysis methods have been introduced in the literature. These methods have been developed to combat specific steganography techniques and to detect data hidden in specific image formats. However, no single steganalysis method or tool can detect all types of steganography or support all available image formats.This paper presented an image steganalysis system that combines the colour gradient co-occurrence matrix (CGCM) features and number of histogram features. The proposed system is considered as blind image steganalysis, which rely on the extraction of selections of image features.The CGCM takes into account information of both colour correlations and gradients among the pixels in an image.In addition, the histogram features are extracted by exploiting the histogram of difference image, which is usually a generalised Gaussian distribution centered at 0.The tested CGCM features and histogram features were merged together to improve the performance of the system. Merging two different types of features allows taking advantages of the beneficial properties of each in order to increase the system ability in terms of detection.The proposed detection system was trained and tested to distinguish stego images from clean ones using the iscriminant Analysis (DA) classification method and Multilayer Perceptron neural network (MLP).The experimental results prove that the proposed system possesses reliable detection ability and accuracy. The proposed system is a more generalized detector than previous systems, covering a wider variety of types of stego images and image formats.","PeriodicalId":305464,"journal":{"name":"2018 21st Saudi Computer Society National Computer Conference (NCC)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128403430","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}
Mohammed Hussian, Magdi Osman Ali, Abdelzahir Abdelmaboud
{"title":"Rock Fall Trajectory Prediction System for Enhancing Traffic Safety","authors":"Mohammed Hussian, Magdi Osman Ali, Abdelzahir Abdelmaboud","doi":"10.1109/NCG.2018.8593194","DOIUrl":"https://doi.org/10.1109/NCG.2018.8593194","url":null,"abstract":"Recently, there is high rate of rock fall risk that affecting road, railways, people and forest. Studies with different methods have been developed to deal with risk analysis and early warning system. This paper proposed one of the modern emerge technology based on hybrid system of computer vision and control theory. The system works as a real-time monitoring and application that predict, tracks and analyses the rock movement, then automatically generates the early worming messages and supports for further necessary action. Model with required algorithm has been designed to represent this system. The primary obtained results prove success and applicability of the system.","PeriodicalId":305464,"journal":{"name":"2018 21st Saudi Computer Society National Computer Conference (NCC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132108764","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":"A Novel (K, X)-isomorphism Method for Protecting Privacy in Weighted social Network","authors":"Sarah Al-Kharji, Yuan Tian, Mznah Al-Rodhaan","doi":"10.1109/NCG.2018.8593107","DOIUrl":"https://doi.org/10.1109/NCG.2018.8593107","url":null,"abstract":"From the beginning of 21st century, most people, especially the young ones, used to share whatever they want from their stuff like photo, chats, opinion, interests, accomplishments, and so on, over the social network day after day. One of the quite popular debates is about that if the social network sites preserve the individual privacy or not. The anonymizing techniques are famous techniques which provide privacy preservation for the published structural data. The proposed method aims to preserve the individuals’ privacy in the weighted social network network. This research proposes a (K, X)-isomorphism method, which is an anonymizing technique that produces for every subgraph a K -1 candidate subgraph. A (K X)-isomorphism depends on a range of methods that will help to make for every subgraph a ${K-1}$ similar subgraphs, like weighted community detection, graph density, weighted maximum common subgraph and bi-clustering methods. This research improves an MPD_V method which is a maximum common subgraph, where this improvement makes MPD_V more fitting to find the similarly weighted subgraphs.","PeriodicalId":305464,"journal":{"name":"2018 21st Saudi Computer Society National Computer Conference (NCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125638188","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":"Maximizing Reliability of Heterogeneous Distributed System Using an Adapted Discrete Flower Pollination Algorithm for Task Allocation Problem","authors":"Farid Abbache, Hamoudi Kalla","doi":"10.1109/NCG.2018.8593117","DOIUrl":"https://doi.org/10.1109/NCG.2018.8593117","url":null,"abstract":"Finding task allocation that maximizes reliability of a heterogeneous distributed system is an NP-hard problem. For that, meta-heuristic is used to get a sub optimal solution in reasonable time. The Flower Pollination algorithm is new meta-heuristic used successfully for solving different problems in different fields. The original Flower Pollination algorithm is designed to deal with continuous problem. Thus, applying this algorithm to discrete problems in its original form seems to be very hard or useless. In this paper, we propose an adapted discrete version of the Flower Pollination algorithm to deal with the problem of maximizing reliability of a heterogeneous distributed system under task allocation problem. This algorithm is called Adapted Discrete Flower Pollination algorithm (ADFP). To confirm the effectiveness of our algorithm, we have tested and compared its results with that of Hybrid Particle Swarm optimization (HPSO). The Experiments results show the effectiveness and superiority of ADFP over HPSO in all tested cases.","PeriodicalId":305464,"journal":{"name":"2018 21st Saudi Computer Society National Computer Conference (NCC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131166321","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":"Ensuring Privacy Protection of the Users of E-commerce Systems","authors":"Shahad Almuzairai, Sara Alaradi, Nisreen Innab","doi":"10.1109/NCG.2018.8592937","DOIUrl":"https://doi.org/10.1109/NCG.2018.8592937","url":null,"abstract":"In the light of the development that are daily done in the internet and wireless networks, E-commerce systems received a lot of attention, where it can makes our life easily. In such systems, the customer is forced to send his/her order based on his real location. After the performing the order, the customer pays using his/her own Visa card. However, the information contained in the Visa card and those included in the sent order may reveal sensitive information about the customer. Therefore, the privacy of the customer must be protected when dealing with the Ecommerce systems. In this paper, we introduce a system that ensures the privacy of the E-commerce systems’ users. Specifically, we introduce a novel fragmentation based technique (FBT) to protect the privacy of the information included in the Visa cards. In regards to the information included in the sent order, we propose two approaches: Adopted k-Anonymity Approach (AkA), which protects the Identity of the customer and Smart Location Transformation (SLT) to protect the location privacy of the customer. Our proposed approaches showed a higher privacy protection and better performance in relative to the previous approaches.","PeriodicalId":305464,"journal":{"name":"2018 21st Saudi Computer Society National Computer Conference (NCC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134437819","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":"An Enhanced Sociopsychological-based Trust Model for Boosting Security in Wireless Sensors Networks","authors":"M. Alqhatani, Mostafa G. M. Mostafa","doi":"10.1109/NCG.2018.8593002","DOIUrl":"https://doi.org/10.1109/NCG.2018.8593002","url":null,"abstract":"Wireless sensor network (WSN) is growing exponentially, as well as WSN attacks. Trust between nodes in WSNs is emerging as a crucial factor in WSN security, since nodes cooperation is vital besides their capability of sensing, processing and communicating data. Research on security in WSNs has explored cryptography mechanisms, intrusion detection systems. Using these traditional techniques to eliminate insider attacks is possible but is inefficient in WSNs due to computational limitations. In this paper, we propose an enhanced sociopsychological-based trust model that utilizes fuzzy logic for realistically relate the Ability, Benevolence and Integrity components to get better and smooth trust rating, which in turn enhances the WSN stability. Preliminary results of our model show good improvement in trust rating computation over the original model.","PeriodicalId":305464,"journal":{"name":"2018 21st Saudi Computer Society National Computer Conference (NCC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121185986","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}
Tarek Abudawood, Heelah A. Alraqibah, Waleed Alsanie
{"title":"Towards Language-independent Sentiment Analysis","authors":"Tarek Abudawood, Heelah A. Alraqibah, Waleed Alsanie","doi":"10.1109/NCG.2018.8593042","DOIUrl":"https://doi.org/10.1109/NCG.2018.8593042","url":null,"abstract":"In this work, we systematically develop a Language-independent Sentiment Analysis (LISA) approach. We argue that it is generic enough to be applied across different languages/domains. Our argument is supported by an empirical evaluation showing that the proposed approach produces a competitive predictive performance if compared to others sentiment analysis approaches where there is a heavy reliance on language resources and absence of systematic pre-processing methodologies. Furthermore, when LISA is encapsulated into a multi-lingual and multi-domain version, (MLISA), we can have an accurate and compact model that can be applied to multiple languages/domains simultaneously and, hence, it suitable for online sentiment classification.","PeriodicalId":305464,"journal":{"name":"2018 21st Saudi Computer Society National Computer Conference (NCC)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116423462","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}
S. Bayoumi, Khulood Alghamdi, Dalal Alqusair, Abeer Alfutamani
{"title":"Visualization of Fire Accidents in Saudi Arabia","authors":"S. Bayoumi, Khulood Alghamdi, Dalal Alqusair, Abeer Alfutamani","doi":"10.1109/NCG.2018.8593045","DOIUrl":"https://doi.org/10.1109/NCG.2018.8593045","url":null,"abstract":"Fire incidents are one of mortality and morbidity causes in the Kingdom of Saudi Arabia. These incidents are not only claiming the lives of many people in Saudi Arabia, but it also drains national resources that could utilise for the betterment of the country. General Directorate of Civil Defence (GDCD) is designing and implementing strategies to protect civilians as well as public and private properties from the danger of fires. In this paper, we have discussed the importance of data visualisation and how it can help in presenting vast and complex data in a way that is useful in the interpretation of information which can be helpful in the decision-making process. We used Tableau software to visualise the fire incidents data from year 1432–1434H to see the reasons for the often fire breakouts in the Kingdom of Saudi Arabia and rate of injuries and financial losses. Also, identifying regions where the highest percentage of fires occurs. The finding of this research along with other information and strategies encourage policy-makers and planners to allocate their efforts to make Saudi emergency management program a better model to follow.","PeriodicalId":305464,"journal":{"name":"2018 21st Saudi Computer Society National Computer Conference (NCC)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121099256","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}
Reem A. Alassaf, Khawla A. Alsulaim, Noura Y. Alroomi, N. Alsharif, Mishael F. Aljubeir, S. Olatunji, Alaa Y. Alahmadi, Mohammed Imran, Rahmah Alzahrani, Nora S. Alturayeif
{"title":"Preemptive Diagnosis of Diabetes Mellitus Using Machine Learning","authors":"Reem A. Alassaf, Khawla A. Alsulaim, Noura Y. Alroomi, N. Alsharif, Mishael F. Aljubeir, S. Olatunji, Alaa Y. Alahmadi, Mohammed Imran, Rahmah Alzahrani, Nora S. Alturayeif","doi":"10.1109/NCG.2018.8593201","DOIUrl":"https://doi.org/10.1109/NCG.2018.8593201","url":null,"abstract":"Diabetes Mellitus (DM) is one of the most prevalent chronic diseases in the world with around 150 million patients. Patients with chronic diseases are highly susceptible to deterioration in their physical and mental health; consequently, hindering their independence, restricting their daily activities imposing a large financial burden on them and the government. If not discovered early, chronic diseases may lead to serious health complications or in extreme cases, death. Diagnostic solutions have been explored using intelligent methods, however, different ethnic groups have variant factors leading to the development of a disease. Therefore, the proposed system aims to preemptively diagnose DM in a region never explored before. Data are retrieved from King Fahd University Hospital (KFUH) in Khobar, Saudi Arabia. Data undergoes preprocessing to identify relevant features and prepare for identification/classification process. Experimental results show that ANN outperformed SVM, Naïve Bayes, and K-Nearest Neighbor with the testing accuracy of 77.5%.","PeriodicalId":305464,"journal":{"name":"2018 21st Saudi Computer Society National Computer Conference (NCC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125225522","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":"A Comprehensively Secure Smart card access controls","authors":"Sulaiman Alazmi, Dr. Ahmad Raza Khan, Dr. Qian Yu","doi":"10.1109/NCG.2018.8592961","DOIUrl":"https://doi.org/10.1109/NCG.2018.8592961","url":null,"abstract":"The smart card has been used in many applications for access controls, such as banking, identification, transportation, telecommunication, health care and electronic payments. Smart cards contain an embedded chip used as either a microprocessor or memory, which create some complications in implementing smart cards for network access. Centralization and distribution access control models are most appropriate for smart cards. Smart cards can be used for PC access control, provided that changes to smart card infrastructure are completed. This research comprehensively integrates all the functionalities of the smart card to get one base application which a web service which can provide access to may functionalities of the smart card based on it usage. We integrate access to services such as payment at petrol pump, online shopping and others under a single umbrella such that the card reacts to the changes in which it is required also the information visibility on the card will change when the card is being used for different purposes and will popup required information on the card screen when a commodity is purchased securing all information on the web services which is directly integrated with the smart cards. Securing information residing on the card is very important as this card is a digital card it will be blank when no purchases are to be done so any one losing the card can login to the web service and clear all information residing on the digital card without worrying about its access by the intruders.","PeriodicalId":305464,"journal":{"name":"2018 21st Saudi Computer Society National Computer Conference (NCC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114160639","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}