Journal of Software Engineering & Intelligent Systems

ISSN: 2518-8739 (Online)
August 2021 | VOLUME. 6  ISSUE. 2
Title:

WEKA VS. RAPID MINER: TOWARDS A COMPREHENSIVE COMPARISON FOR DIAGNOSIS OF AUTISM USING ENSEMBLES

Authors:

Razieh Asgarnezhad, Karrar Ali Mohsin Alhameedawi

Abstract:

Autism is the most well-known disorder that received high interest from researchers recently. This disorder may be in all ages of people. All exist datasets suffer from low quality for data analysis. Most of the related works focus on base classifiers. In this article, we suggested a comprehensive comparison to improve the diagnosis of autism disorder using effective pre-processing and ensemble methods. The pre-processing stage consists of resolving missing values and outliers. Also, the ensemble methods include voting, boosting, bagging, and stacking. For the evaluation of comparisons, two popular data mining tools are applied. The obtained results prove that our work promotes classification performance rather than the base methods in terms of precision, recall, accuracy, and F1. The highest values for these criteria are obtained 100%.

Keywords: data mining; autism mellitus; ensembles; weka; rapid miner;
Available: WEKA VS. RAPID MINER: TOWARDS A COMPREHENSIVE COMPARISON FOR DIAGNOSIS OF AUTISM USING ENSEMBLES by Razieh Asgarnezhad, Karrar Ali Mohsin Alhameedawi will be available under cc by-nc 4.0 License on 31st August 2021. Permissions beyond the scope of this license may be available at JSEIS.
Download PDF

Title:

THREATS AND SECURITY VULNERABILITY ESTIMATE FOR MOBILE CYBER CRIMINOLOGY PLATFORM

Authors:

Mohammad Dweikat, Mahmoud Jazzar

Abstract:

The use of mobile phones with multiple services and applications has increased the usability of bring your own device (BYOD) in education, business, and other walks of life. This increase in important features and services led to changing the concept of mobile phones to the new generation of phones called smartphones. One of the advantages of smart phones is that it provides a large number of applications for customers. Therefore, hackers can easily launch various attacks on smartphones that run exclusively on iOS and Android operating systems. Attention should be paid to the steady increase in the exacerbation of this problem through two-way screening, preventive, and detection techniques. This article examines smartphones as vulnerabilities and threats. Review current threats to rank them as most severe. Besides describing what app developers, app store companies, and ordinary users must do to defend against such cyber-attacks.

Keywords: mobile phishing; threats; social engineering; man-the-middle; jailbreak; broken cryptography; data leakage
Available: THREATS AND SECURITY VULNERABILITY ESTIMATE FOR MOBILE CYBER CRIMINOLOGY PLATFORM by Mohammad Dweikat, Mahmoud Jazzar will be available under cc by-nc 4.0 License on 31st August 2021. Permissions beyond the scope of this license may be available at JSEIS.
Download PDF

Title:

SURVEILLANCE ROBOT USING INTERNET OF THINGS

Authors:

D.Ragaleela, K. Manoj Kumar, D. Kavya, G. Sasi Kumar, A. Lakshman Sai

Abstract:

The method to monitor a situation, an area or an individual is video surveillance. This usually happens in a wartime scenario in which border monitoring and enemy land are important for the protection of a country. The deployment of near-sensitive individuals will accomplish human monitoring to monitor changes continually. However, personnel are limited and deployment is not always viable in remote areas. A robot that can be used for video monitoring & monitoring and controlled by a GUI has been created. A video transmission facility is provided for the control mechanism. A high-speed picture transfer is realistically accomplished for the video transmission. The robot first comes with a camera, where the scenes are captured and the photos are transferred to the server on which the user controls and watches the live streams.

Keywords: raspberry pi; motor driver; surveillance robot; internet of things
Available: SURVEILLANCE ROBOT USING INTERNET OF THINGS by D.Ragaleela, K. Manoj Kumar, D. Kavya, G. Sasi Kumar, A. Lakshman Sai will be available under cc by-nc 4.0 License on 31st August 2021. Permissions beyond the scope of this license may be available at JSEIS.
Download PDF

Title:

SEMANTIC MODELING FOR LEARNING MATERIALS IN E-TUTOR SYSTEMS

Authors:

Jawad Alshboul, Ghanim Hussein Ali Ahmed, Erika Baksa-Varga

Abstract:

E-learning platforms are becoming increasingly popular in the academic community due to various learning benefits achieved through learning without place or time limitations. Nowadays, the use of technology to enhance education and learning is rapidly expanding. By applying learning technologies like Intelligent Tutoring Systems, we can enhance the learning process. Intelligent Tutoring System is a technique that represents a form of computer-based training using artificial intelligence methods in which the system uses a knowledge base to give feedback to the learner as the student interacts with the system. Several techniques of knowledge representation are found in the literature. The most commonly used are Rule-based, Case-Based, Logic-based, Frame-based, Bayesian network, and Semantic-based. For the sake of learning personalization, ontologies have been used recently in learning systems as methods for knowledge representation. Ontology offers a shared vocabulary for domain modeling in which it shows the concepts present in the domain and their properties and relationships. The semantic modelling is typically based on an ontology that specifies classes and properties, i.e., the ontology determines the vocabulary to be used for the semantic description. Based on the overview of these techniques a semantic model for learning materials has been implemented using ontology. The constructed ontology can be applied in the future to support adaptive intelligent e-learning frameworks.

Keywords: semantic modeling; knowledge representation; ontology; learning materials; e-tutor
Available: SEMANTIC MODELING FOR LEARNING MATERIALS IN E-TUTOR SYSTEMS by Jawad Alshboul, Ghanim Hussein Ali Ahmed, Erika Baksa-Varga will be available under cc by-nc 4.0 License on 31st August 2021. Permissions beyond the scope of this license may be available at JSEIS.
Download PDF

Title:

CUSTOMER CHURN PREDICTION IN THE BANKING INDUSTRY USING CRISP-DM UTILIZING MACHINE LEARNING TECHNIQUES

Authors:

Bimo Adiparwa Dwijaya, Setia Wirawan

Abstract:

Customer churn is a big issue in the banking industry. This can result in losses for the banking industry in terms of earnings, costs, and even reputation. The banking industry needs to determine a strategy to reduce the churn rate, in order to optimize revenue. Therefore, this study was made in order to find the factors that influence customer churn and predict customers who will churn. This study uses the CRISP-DM methodology by utilizing machine learning techniques, including Random Forest, XGBoost, and K-Nearest Neighbor (KNN) with 10000 customer bank churn datasets which are separated into 80:20 train sets and test sets. The results of research conducted, it can be concluded that there are eight variables that affect customer churn as a result of feature selection, namely Age, EstimatedSalary, CreditScore, Balance, NumOfProducts, Tenure, IsActiveMember, and Geography variables. The final results of testing accuracy from performance measurements are calculated using a confusion matrix, including the accuracy of Random Forest model is 87.05%, XGboost is having 90.75%, and accuracy of KNN is 100%. While the final results of the ROC analysis testing, the Random Forest model got a score 0.882, XGboost got a value 0.948, and KNN got a score of 1. The KNN technique outperforms all models with an accuracy that reaches 100% and an AUC score of 1. KNN can be applied, and the banking industry can determine a strategy to reduce the churn rate, to optimize the revenue.

Keywords: CRISP-DM; customer churn; k-nearest neighbor; random forest; xgboost
Available: CUSTOMER CHURN PREDICTION IN THE BANKING INDUSTRY USING CRISP-DM UTILIZING MACHINE LEARNING TECHNIQUES by Bimo Adiparwa Dwijaya, Setia Wirawan will be available under cc by-nc 4.0 License on 31st August 2021. Permissions beyond the scope of this license may be available at JSEIS.
Download PDF

Title:

SOCIAL ENGINEERING ATTACKS: A SURVEY

Authors:

Mahmoud Jazzar

Abstract:

Our modern era is witnessing an amazing and rapid development in the field of technology, its use has become necessary in various areas of life, it has contributed to facilitating communication between people, and making their sensitive information available through social media platforms, which may not have adequate protection for such information and thus facilitate the occurrence of violations and threats through the social engineering attacks. Social engineering is the easiest and fastest way to gather information about individuals or organizations and gain their trust by exploiting human weaknesses, targeting the psychological state of individuals or workers in institutions. This paper provides a survey about the social engineering attacks, their classifications, and prevention procedures.

Keywords: social engineering attacks; phishing; pretexting; tailgating; scareware; ransomware; pop-up windows; Robocalls and Quid Pro Quo
Available: SOCIAL ENGINEERING ATTACKS: A SURVEY by Mahmoud Jazzar will be available under cc by-nc 4.0 License on 31st August 2021. Permissions beyond the scope of this license may be available at JSEIS.
Download PDF

Title:

QUALITY ANALYSIS ON COSMETIC E-COMMERCE WEBSITE USING ISO 25010

Authors:

Cut Cherryl Aulia, Widya Silfianti

Abstract:

The existence of social distancing restrictions during the Covid 19 pandemic made people spend longer at home so that they can be used to treat skin, body, and hair. In Indonesia, there are many e-commerce sites in the growing cosmetic category. Sociolla is one of the e-commerce websites that are in the first position in the cosmetic website category. One of the advantages of the Sociolla website is the presentation of good and complete features, but with the more complete activities that can be done on the website, more complaints can occur when using the website. Competition between e-commerce to be the most superior is unavoidable, given a large number of e-commerce websites in Indonesia. Website quality is one of the most important things in the competition between e-commerce. Quality testing on the website can be done to maintain the quality of the website. The method used in testing the quality of the Sociolla website is Software Quality Assurance (SQA) with the ISO 25010 model. The test will focus on the user's perspective. The results of the tests that have been carried out are that the Sociolla website scores 4,3501 on the 8 characteristics and 27 sub-characteristics used. This value means that the quality of the Sociolla website is good.

Keywords: ISO 25010; sociolla website; software quality; software quality assurance; e-commerce
Available: QUALITY ANALYSIS ON COSMETIC E-COMMERCE WEBSITE USING ISO 25010 by Cut Cherryl Aulia, Widya Silfianti will be available under cc by-nc 4.0 License on 31st August 2021. Permissions beyond the scope of this license may be available at JSEIS.
Download PDF

Title:

SURVEY ON INDOOR NAVIGATION SOLUTIONS

Authors:

Mohd Aaqib Lone, Owais Mujtaba Khanday, Aadil Gani Ganie, Gowher Rashid Bhat

Abstract:

Indoor navigation is a significant subject in today's world since almost eighty percent of the work is carried out in the indoor environment. Navigation systems are incredibly relevant in numerous fields, such as transport, health monitoring and marketing, tourism and for military purposes. To locate an item or individual at a given location, navigation systems rely on positioning services. The location of objects or individuals may be determined in various ways in the indoor environment, such as the floor, several rooms or coordinates. The influence of indoor navigation helps to perform routine operations in many areas of fire response situations, retail store sales, and building safety acts. A significant number of specifications are required to design a suitable indoor navigation technology, such as accuracy, reliability, robustness, cost, and scalability.

Keywords: indoor navigation; indoorGML; OntoNav; LOC8; ONALIN; ILONA
Available: SURVEY ON INDOOR NAVIGATION SOLUTIONS by Mohd Aaqib Lone, Owais Mujtaba Khanday, Aadil Gani Ganie, Gowher Rashid Bhat will be available under cc by-nc 4.0 License on 31st August 2021. Permissions beyond the scope of this license may be available at JSEIS.
Download PDF

Title:

MULTI-MODAL BIOMETRIC SYSTEM FOR ACCESS CONTROL

Authors:

M.H.Saad, M.Sayed, H.I.Saleh

Abstract:

This paper proposes a multimodal biometric identity method for human authentication based on the combination of face, fingerprint and speech recognition. To derive features of speech recognition, cepstral coefficients and statistical coefficients are used, and the two coefficients are compared. This paper proposes an efficient face recognition algorithm using a Local Binary Pattern (LBP) for features extraction and a Canonical Correlation Analysis (CCA) for features fusion and classification. LBP is used to extract the facial features. Then, the extracted features are transformed to different transform domains. In the proposed algorithm, two-Dimensional Principal Component Analysis (2DPCA) technique is used for dimensionality reduction to produce more compact, robust and discriminative features, which are then fused using the CCA, classifier. Fingerprint implemented based on a minutiae based matching technique. This approach has been intensively studied, also is the backbone of the current available fingerprint recognition products. The fusion of biometric systems, such as voice and face recognition, into a single multimodal biometric system is accomplished by the use of features fusion and scores fusion. The computer simulation studies show that using cepstral coefficients and predictive coefficients for speech recognition yields better results, while LPB and CCA experiments yield better results for face recognition and fingerprint based on a minutiae based matching technique yield better results for fingerprint recognition. Furthermore, the proposed multimodal biometrics method outperforms other scenarios in terms of score fusion.

Keywords: authentication; face recognition; fingerprint; voice recognition; canonical correlation analysis
Available: MULTI-MODAL BIOMETRIC SYSTEM FOR ACCESS CONTROL by M.H.Saad, M.Sayed, H.I.Saleh will be available under cc by-nc 4.0 License on 31st August 2021. Permissions beyond the scope of this license may be available at JSEIS.
Download PDF

Title:

CONTROL ALARMS BY USING NRF 24101 RADIO MODULE

Authors:

Mohamed Ali Hadi, Razieh Asgarnezhad, Mustafa Saleh Rahim, Nabaa Basim Aziz, Mais Adil Zagier

Abstract:

Due to the development of microelectronics technology and high-speed digital signal processing technologies, wireless communication is undoubtedly a convenient, fast and effective method. It has been used widely in industrial production and people's life; especially it has enabled new advanced methods of data acquisition and transmission for complicated terrain conditions, hostile environmental conditions and other places that are inconvenient to reach for humans. Here, we design a scheme of wireless communication system that has small size, low cost and can collect environmental factors such as temperature data remotely and in real time. The core of the system control module ATMEGA328 microcontroller is a high-performance single chip microcomputer with a wide voltage, low power consumption, high integration, strong anti-interference and strong portability characteristics. The core of Arduino UNO processor is ATmega328. It has 14 pins for digital input/output (six pins can be used as a PWM output), 6 analog input pins, 32 KB Flash Memory and 1 KB EEPROM. The sensor has anti-interference ability, high integration, high precision, low power consumption, small size and low price. Software is based on the Arduino exploitation environment. Arduino has its own exploitation environment which is based on Eclipse IDE development environment, similar to the JAVA and C/C ++, the UI is user friendly and program compilation and flashing of software with Arduino IDE is simple. NRF24L0l through configuration registers, define all the configuration characteristics. The configuration register can be set-up through SPI. SPI (Serial Peripheral interface) is a synchronous serial communication interface. It has10 Mbps maximum transmission rate and Twelve instructions are associated with SPI.

Keywords: IoT; sensors; signal processing; power consumption; wireless communication;
Available: CONTROL ALARMS BY USING NRF 24101 RADIO MODULE by Mohamed Ali Hadi, Razieh Asgarnezhad, Mustafa Saleh Rahim, Nabaa Basim Aziz,Mais Adil Zagier will be available under cc by-nc 4.0 License on 31st August 2021. Permissions beyond the scope of this license may be available at JSEIS.
Download PDF

Archive

Volume 6
Issue 2   New
Issue 1
Volume 5
Issue 3
Issue 2
Issue 1
Volume 4
Issue 3
Issue 2
Issue 1
Volume 3
Issue 3
Issue 2
Issue 1
Volume 2
Issue 3
Issue 2
Issue 1
Volume 1
Issue 2
Issue 1
Journal PicsCaomei Publishers © 2016-2021
f t