A. Maghawry, Ahmed Al-qassed, Mohamed Awad, M. Kholief
{"title":"Automated Market Analysis by RFMx Encoding Based Customer Segmentation using Initial Centroid Selection Optimized K-means Clustering Algorithm","authors":"A. Maghawry, Ahmed Al-qassed, Mohamed Awad, M. Kholief","doi":"10.21608/ijci.2021.207737","DOIUrl":"https://doi.org/10.21608/ijci.2021.207737","url":null,"abstract":"Market analysis including customer segmentation is one of the most important approaches utilized by business owners to analyze customer behavior. Such analysis can provide significant insights and decision support for businesses. Multiple research effort was conducted for market analysis including the Recency, Frequency and Monetary analysis (RFM) in addition to many variations including RFD, RFE, RFM-I and RFMTC. In this research a methodology is proposed to utilize the intermediate vector representation of the introduced RFMx for machine learning toward high precision automatic customer segmentation. In this methodology there’s no need to calculate the actual final RFMx score. The RFMx technique introduces a multimonetary model where each monetary value is assigned different weight to suite the business targets of business owners. The proposed model allowed for finely tuned market analyses on product type or service type level. The results showed significant clustering results that lead to automatic customer segmentation without the need to calculate the final RFMx score.","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128055094","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":"Troubleshooting Payment Journey In Multilayer System Using Blockchain Technology","authors":"Ahmed Abd-Elwasaa, Eman M. Mohamed, A. Keshk","doi":"10.21608/ijci.2021.207745","DOIUrl":"https://doi.org/10.21608/ijci.2021.207745","url":null,"abstract":"Blockchain technology is the most promising field in the recent decade and future in many different industries. It is based on storing data in a decentralized distributed database with an encrypted way. Permission blockchains are the most of interest to companies, organizations, and other agencies to maintain their internal processes because of their trust, high privacy and control. Nowadays we are living in digital transformation age that everything should be maintained and operated by a system to ease our daily tasks. Electronic payment systems are one of many shapes for digital transformation, and they have many challenges in sending or receiving transactions as time latency, scalability, performance, and throughput rate also there is a need to maintain any failure through the payment process till it is completed. Tracing failed transactions may take more time and effort to discover what is the root cause of failure and which component has affected it. Therefore, the proposed framework is suggested using private blockchain to overcome the time delay of tracking failures and improve performance and throughput. Our results gained from the proposed framework enables us from tracing the failed transactions with little consumed time which provides more performance and efficiency. Also, by increasing the performance of finding trouble. Keywords—Blockchain, Electronic payment, Digital transformation, Fintech","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132758916","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":"Gamification in education: Serious Game Prototype for Children with Special Needs","authors":"Eman S. Shaltout, Khalid Amin, A. Afifi","doi":"10.21608/ijci.2021.207857","DOIUrl":"https://doi.org/10.21608/ijci.2021.207857","url":null,"abstract":"Gamification or integrating game elements within the non-game environment is widely used to improve systems, services, and the overall user experience. It is mainly intended for education purposes, not for mere entertainment. Gamification can provide many benefits like creating a stimulating environment for learning and engagement with content in an unconventional way. These benefits are vital for the education of children with special needs because they suffer from constant distraction and loss of motivation. Therefore, we introduce a serious game prototype for children with special needs. The main purpose of this serious game is to assess total reading and understanding the impact of augmented reality as a learning methodology. This game is a complementary approach to motivate students after using an AR learning environment. This assessment game was designed according to the systemic gamification principles and contains the elements of game formula like points, time, and player profile. It will be used to assess children after learning sessions using AR and flashcards. The card assessment game is an unconventional way to evaluate children. Each child is different from her/his peers in the academic level, so the number of words is chosen at the beginning of the game based on what the child has learned in the training sessions. The child profile result confirmed that the game can be used in assessment. Moreover, parents and specialists confirmed that children enjoyed the assessment session, and the game is not limited to test only, as some children play it for language development. Keywords—Gamification, Mobile Based game, Serious games, children with special needs, Education, Augmented Reality.","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134629273","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":"Survey of Computation Integrity Methods For Big Data","authors":"Doaa abo aly, Walid Atwa, Hamdy M. Mousa","doi":"10.21608/ijci.2021.207757","DOIUrl":"https://doi.org/10.21608/ijci.2021.207757","url":null,"abstract":"Nowadays, big data becomes widespread. Big data has great value, but it faces many challenges. One of these challenges is security. Many classic security techniques exist, but these mechanisms are not appropriate for big data security. To secure big data, it is necessary to secure many aspects such as infrastructure, data privacy, data management, and integrity and reactive. Securing computations in distributed programming frameworks and protecting non-relational data stores are two requirements for infrastructure protection. This survey will highlight securing MapReduce as one of the most popular distributed programming frameworks. Security of MapReduce computation is an important consideration when a MapReduce computation is performed on a public or hybrid cloud. When a MapReduce job is executed on public cloud or hybrid cloud, an integrity check of its result is required. In this survey, a set of previous techniques that check the result integrity of MapReduce will be explained. In addition to discussion of the advantages and disadvantages of each technique. Keywords—Big data, MapReduce, security, distributed computing.","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114196765","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":"Variational 3D Mesh Generation of Man-Made Objects","authors":"G. Fahim, S. Zarif, Khalid Amin","doi":"10.21608/ijci.2021.207826","DOIUrl":"https://doi.org/10.21608/ijci.2021.207826","url":null,"abstract":"Data-driven 3D shape analysis, reconstruction, and generation is an active research topic that finds many useful applications in the fields of computer games, computer graphics, and augmented/virtual reality. Many of the previous mesh-based generative approaches work on natural shapes such as human faces and bodies and little work targets man-made objects. This work proposes a generative probabilistic framework for 3D man-made mesh shapes. Specifically, it proposes a Variational Autoencoder that works directly on mesh vertices and encodes meshes into a probabilistic, smooth, and traversable latent space that can be sampled after training and decoded to generate novel and plausible shapes. Extensive experiments show the representational power of the proposed framework and the underlying latent space. Operations such as random sample generation, linear interpolation, and shape arithmetic can be performed using the proposed method and produce plausible results. An additional advantage of the proposed framework is that it learns to produce a disentangled shape representation which gives finer control over the generated mesh and allows generating shapes with specific qualities without losing the reconstruction power of the autoencoder.","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114857703","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":"Editorial: Special issue for selected articles from the proceedings of the first international conference on computers and information, ICCI'2021.","authors":"","doi":"10.21608/ijci.2021.207726","DOIUrl":"https://doi.org/10.21608/ijci.2021.207726","url":null,"abstract":"","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128075611","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 Review for Recommender System Models and Deep Learning","authors":"F. Nagy, A. Haroun, Hatem Abdel-Kader, A. Keshk","doi":"10.21608/ijci.2021.207864","DOIUrl":"https://doi.org/10.21608/ijci.2021.207864","url":null,"abstract":"In the big data and data Science age, the advancement in technology accelerated the need to make a choice from a huge amount of various alternatives and this vast amount of online data is a time consuming and very tedious task. Recommendation systems (RS) are an enormous solution to solve information overload problem. Recommendation systems have caught the attention of researchers and companies recently. It can handle data with a huge amount and help the user to make a decision. In this paper we introduce an overview for the traditional recommendation systems models, the recommendation systems advantages and shortcoming, the recommendation systems challenges, common deep learning traditional technology, how deep learning-based recommendation systems works, deep learning for recommendations and open problems and the novel research trends on this field. Key words-recommender system, challenges, deep learning, RS open issues, future research directions.","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130956403","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":"Enhanced User Authentication Based on Dynamic Port Knocking Technique","authors":"Alaa Zidan, Khalid Amin, T. Ghanem","doi":"10.21608/ijci.2021.207854","DOIUrl":"https://doi.org/10.21608/ijci.2021.207854","url":null,"abstract":"Abstract—Port knocking is a passive authentication mechanism which aims to control firewall response using a sequence of connection attempts to its closed ports. Dynamic port knocking which varies in each session, faces many challenges which are knocking sequence synchronization between client and server, handling high load of normal requests, out of order knocks, lost knocks, knocking through NAT, and knocking attacks. In this paper, a proposed dynamic port knocking approach is provided. The proposed approach, with the help of intermediate IPS, enables client and target server to generate a unique dynamic knocking sequence based on a secured random seed. This process is executed only at first communication session. Next, client begins to authenticate himself by knocking the target service with different ports and different number of knocks each time a session is initiated. Client-Server knocking synchronization, lost knocks, and out of order knocks are considered for issuing a correct knocking. The proposed approach provides immunity against several network attacks such as DoS attack, replay attack, and brute forcing attack. Extensive simulation shows that the proposed work overcome other compared approaches in terms of response time, memory utilization, CPU utilization, and the number of provided features.","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127063869","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":"Parallel Fast Dynamic Algorithm for Sequence Alignment Using OpenMP and Partitioning Scheme","authors":"Sara Shehab","doi":"10.21608/ijci.2021.207743","DOIUrl":"https://doi.org/10.21608/ijci.2021.207743","url":null,"abstract":"Sequence alignment process considered one of the most important tasks in bioinformatic. There are two types of alignment pairwise and multiple sequence alignment. Many algorithms proposed to complete this task. The key parameter in these algorithms is alignment and its scoring value. If the proposed algorithm maximizes the score, so it will be optimal. The algorithms used to align sequences have two main drawbacks. The first is the sensitivity when the data used is very large, the output score is not optimal and has a bad sensitivity. The second is the execution time when the data is large. To overcome these two problems the parallel version of Fast Dynamic Algorithm for Pairwise sequence Alignment is proposed. The first problem solved by partitioning scheme and the second solved by using OpenMP to distribute tasks on available threads. The results indicated that the proposed parallel Algorithms achieve high level of accuracy and sensitivity and improve the execution time. Keywords—Sequence alignment, optimal score, Fast Dynamic Algorithm for Pairwise Sequence Alignment, OpenMP","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125967064","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":"Detecting and Predicting Crimes using Data Mining Techniques: Comparative Study","authors":"S. Zahran, Eman M. Mohamed, Hamdy M. Mousa","doi":"10.21608/ijci.2021.207749","DOIUrl":"https://doi.org/10.21608/ijci.2021.207749","url":null,"abstract":"Crime is a major problem in our society where the highest priority is concerned with individuals, society, and government. Thus, it seems important to study factors and relations between the occurrence of different crimes to avoid more upcoming crimes. Crime prediction is a method of trying to study the causes and motives of crime and predict the times and places of its occurrence to reduce the commission of crimes that are expected to occur in the future. Data mining is an important way to facilitate the solution of future crime problems by investigating hidden crime patterns and historical crime data. Therefore, this study aims to analyze and discuss the various factors affecting the commission of crimes and the methods that are applied to predict future crimes and analyze their results. In this study, the model of crime prediction is proposed which is based on some classification algorithms such as (NB, KNN, Decision Tree, random forest, Linear Regression, Logistic Regression, SVM), these classification algorithms are applied to four real data sets (Chicago dataset, Los Angeles dataset, Egypt dataset, United States dataset), Egypt data set was extracted primarily from the online website (Zabatak.com) and comparing between their scores. The experimental results showed that the Random Forest classifier achieves a high score on four data sets compared with other classifiers. Random Forest achieves %88 on the Los Angeles dataset, %92 on the Egypt dataset, %97 on the Chicago dataset, and 81.7% on the United States dataset. Keywords— Crime prediction, data mining, classification, clustering, KNN, NB, SVM","PeriodicalId":137729,"journal":{"name":"IJCI. International Journal of Computers and Information","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115069914","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}