Showing papers in "Journal of Computer Science in 2019"
TL;DR: A survey of major EEG-based ASD classification approaches from 2010 to 2018, which adopt machine learning is presented, exploring different techniques and tools used for pre-processing, feature extraction and feature selection techniques, classification models and measures for evaluating the model.
Abstract: Autism Spectrum Disorder is a lifelong neurodevelopmental condition which affects social interaction, communication and behaviour of an individual. The symptoms are diverse with different levels of severity. Recent studies have revealed that early intervention is highly effective for improving the condition. However, current ASD diagnostic criteria are subjective which makes early diagnosis challenging, due to the unavailability of well-defined medical tests to diagnose ASD. Over the years, several objective measures utilizing abnormalities found in EEG signals and statistical analysis have been proposed. Machine learning based approaches provide more flexibility and have produced better results in ASD classification. This paper presents a survey of major EEG-based ASD classification approaches from 2010 to 2018, which adopt machine learning. The methodology is divided into four phases: EEG data collection, pre-processing, feature extraction and classification. This study explores different techniques and tools used for pre-processing, feature extraction and feature selection techniques, classification models and measures for evaluating the model. We analyze the strengths and weaknesses of the techniques and tools. Further, this study summarizes the ASD classification approaches and discusses the existing challenges, limitations and future directions.
33 citations
TL;DR: A system's model for Augmented Reality Learning in which a traditional book is converted to an interactive book using Glyphs (TAGs) and multimedia is described, which can be used by a child, parent, or by a teacher to make learning an enjoyable experience.
Abstract: This paper describes a system's model for Augmented Reality Learning in which a traditional book is converted to an interactive book using Glyphs (TAGs) and multimedia. The interactive book can be used by a child, parent, or by a teacher to make learning an enjoyable experience. As the child goes through the contents of the book, illustrations and images come to live, thus enforcing the learning and comprehension of concepts in an interactive and fun way. To make a printed book interactive, special TAGs (Glyphs) are inserted in the required places within the book, ready to be read by the webcam and then converted to video, 2-D or 3-D images, audio and explanation text. An actual example (Sandy Starfish) is presented to illustrate the architecture and the implementation of the Augmented Reality learning system and to explain the steps and procedure used to transform a textbook to an interactive one.
22 citations
TL;DR: This study applied the SEMMA data mining methodology to select, explore and model the data set and three methods were selected: Decision trees (J48), Bayesian networks (Naive Bayes and Logistic Regression (Simple Logistic), obtaining the best results with J48 based on the metrics.
Abstract: Obesity has become a global epidemic that has doubled since 1980, with serious consequences for health in children, teenagers and adults. Obesity is a problem has been growing steadily and that is why every day appear new studies involving children obesity, especially those looking for influence factors and how to predict emergence of the condition under these factors. In this study, authors applied the SEMMA data mining methodology, to select, explore and model the data set and then three methods were selected: Decision trees (J48), Bayesian networks (Naive Bayes) and Logistic Regression (Simple Logistic), obtaining the best results with J48 based on the metrics: Precision, recall, TP Rate and FP Rate. Finally, a software was built to use and train the selected method, using the Weka library. The results confirmed the Decision Trees technique has the best precision rate (97.4%), improving results of previous studies with similar background.
21 citations
TL;DR: A comparative analysis has been done by applying Faster region based convolutional neural network on thermal images and visual spectrum images and results show that thermal camera images are better as compared to visible spectrum images.
Abstract: In recent years, object detection and classification has gained so much popularity in different application areas like face detection, self- driving cars, pedestrian detection, security surveillance systems etc. The traditional detection methods like background subtraction, Gaussian Mixture Model (GMM), Support Vector Machine (SVM) have certain drawbacks like overlapping of objects, distortion due to smoke, fog, lightening conditions etc. In this paper, thermal images are used as thermal cameras capture the image by using the heat generated by the objects. Thermal camera images are not influenced by smoke and bad weather conditions which makes them a built-up apparatus in inquiry and safeguards or fire-fighting applications. These days, deep learning techniques are extensively used for detection and classification. In this paper, a comparative analysis has been done by applying Faster region based convolutional neural network on thermal images and visual spectrum images. The experimental results show that thermal camera images are better as compared to visible spectrum images.
18 citations
TL;DR: A systematic literature review and analysis of the research literature reveals patterns, trends and gaps in the existing literature and discusses briefly the next generation research directions in this area.
Abstract: In today’s world, most of the data (real world) is present in imbalanced form by nature. This is because of not having efficient algorithms to put this data (i.e., generated data by billion of internet- connected devices (IoTs)) in respective format. Imbalanced data poses a great challenge to (both) data mining and machine learning algorithms. The imbalanced dataset consists of a majority class and a minority class, where the majority class takes the lead over the minority class. Generally, several standard learning algorithms assume the balanced class distribution or equal misclassification costs. If prediction is performed by these learning algorithms on imbalanced data, the accuracy will be high for majority classes, i.e., resulting in poor performance. To overcome this problem (or improving accuracy of deision/prediction-making process), data mining and machine learning researchers have addressed the problem of imbalanced data using data-level, algorithmic level and ensemble or hybrid methods. This article presents a systematic literature review and analyze the results of more than 400 research papers published between 2002-2017 (till June 2017), resulting in a broader and elaborate investigation of the literature in this area of research. Note that extension of this article/work will contain till December 2018 research articles, which will be published in June 2019 (now these more papers/articles did not include due to no. of pages/space issues). The systematic analysis of the research literature has focus on the key role of Data Intrinsic Problems in classification, handling the imbalanced data and the techniques used to overcome the skewed distribution. Furthermore, this article reveals patterns, trends and gaps in the existing literature and discusses briefly the next generation research directions in this area.
16 citations
TL;DR: A disciplined Model-Driven approach for the e-business information system is proposed, which generates the IFML model automatically in the PIM level from business value model in the CIM level, using the ATL transformation language.
Abstract: Nowadays the software industry has known a significant growth, while the end-users have become very demanding. In this sense, the model transformation has become one of the essential solutions to ensure competitiveness in the field of the software industry domain. For that, the Object Management Group (OMG) proposes for the Model-Driven Architecture (MDA) approach three abstraction levels, namely Computation Independent Model (CIM), Platform Independent Model (PIM) and Platform Specific Model (PSM). Therefore, our contribution in this paper is to shed more light on the first MDA transformation, which is the transformation from CIM to PIM levels. We propose a disciplined Model-Driven approach for the e-business information system, which generates the IFML (Interaction Flow Modeling Language) model automatically in the PIM level from business value model in the CIM level, using the ATL transformation language. For this purpose, the business value model is illustrated by the E3value model, whereas, the IFML model exhibits the front-end applications content, interface composition, user interaction and control behavior for several kinds of applications, such as web applications, mobile applications and desktop applications.
14 citations
TL;DR: The simulation results showed that the optimal model order to estimate the given Facebook and Twitter time series are ARMA [5, 5] and ARMA[3, 3], respectively, since they correspond to the minimum acceptable prediction error values.
Abstract: In this study, an Auto-Regressive Moving Average (ARMA) Model with optimal order has been developed to estimate and forecast the short term future numbers of the monthly active Facebook and Twitter worldwide users. In order to pickup the optimal estimation order, we analyzed the model order vs. the corresponding model error in terms of final prediction error. The simulation results showed that the optimal model order to estimate the given Facebook and Twitter time series are ARMA[5, 5] and ARMA[3, 3], respectively, since they correspond to the minimum acceptable prediction error values. Besides, the optimal models recorded a high-level of estimation accuracy with fit percents of 98.8% and 96.5% for Facebook and Twitter time series, respectively. Eventually, the developed framework can be used accurately to estimate the spectrum for any linear time series.
13 citations
TL;DR: This study presents a Phrase-Based Statistical Machine Translation system between English and Bangla languages in both directions and provides useful insights that translating into morphologically richer language is harder than translating from them and this is mainly due to the difficulties of translating noun inflections.
Abstract: An efficient and publicly open machine translation system is in dire need to get the maximum benefits of Information and Communication Technology through removing the language barrier in this era of globalization. In this study, we present a Phrase-Based Statistical Machine Translation (PBMT) system between English and Bangla languages in both directions. To the best of our knowledge, the system is trained on the largest dataset of more than three million tokens each side in English↔Bangla translation task. In the system, we perform data preprocessing and use optimized parameters to produce efficient system output. We analyze our system output from several viewpoints: overall results, comparisons with the available systems, sentence type and length effect, and behaviour of two challenging linguistic properties– prepositional phrase and noun inflection. Our analysis provides useful insights that translating into morphologically richer language is harder than translating from them and this is mainly due to the difficulties of translating noun inflections. Comparisons with the available systems show that our system outperforms the other systems significantly and gain 10.84 BLEU, 2.18 NIST and 19.02 TER points over the next best system. The analysis of the sentence type and length effect shows that simple sentences are easier to translate and the sentences longer than 15 words are harder to translate for English↔Bangla translation task. To foster the English↔Bangla machine translation research, we have developed development and test datasets, which are representative in sentence length and balanced in genre to be used as a benchmark and are made publicly available.
13 citations
TL;DR: It is observed that neural machine translation with and without subword segmentation significantly outperform the phrase-based statistical machine translation system, thus establishing itself as the state-of-the-art technology for low-resource English-Bangla machine translation.
Abstract: Neural machine translation has recently been able to gain state-of-the-art translation quality for many language pairs. However, neural machine translation has been less tested for English-Bangla language pair, two linguistically distant and widely spoken languages. In this paper, we apply neural machine translation to the task of English-Bangla translation in both directions and compare it against a standard phrase-based statistical machine translation system. We obtain up to +0.30 and +4.95 BLEU improvement over phrase-based statistical machine translation for English-to-Bangla and Bangla-to-English respectively. Due to low-resource and morphological richness of Bangla, English-Bangla translation task produces a large number of rare words. We apply subword segmentation with byte pair encoding to handle this rare words issue. We obtain up to +0.69 and +0.30 BLEU improvement over baseline neural machine translation for English-to-Bangla and Bangla-to-English respectively. We further investigate our system output for several challenging linguistic properties like subject-verb agreement, noun inflection, long distance reordering and rare words translation. We observe that neural machine translation with and without subword segmentation significantly outperform the phrase-based statistical machine translation system, thus establishing itself as the state-of-the-art technology for low-resource English-Bangla machine translation.
12 citations
TL;DR: This study proposes a new centroid memory (A-ACOC) for data clustering that can retain the information of a previous clustering solution and shows that the accuracy of the proposed algorithm surpasses those of its counterparts.
Abstract: Ant Colony Optimization (ACO) is a generic algorithm, which has been widely used in different application domains due to its simplicity
and adaptiveness to different optimization problems. The key component that governs the search process in this algorithm is the management of its memory model. In contrast to other algorithms, ACO explicitly utilizes an
adaptive memory, which is important to its performance in terms of producing optimal results. The algorithm’s memory records previous search regions and is fully responsible for transferring the neighborhood of the current structures to the next iteration. Ant Colony Optimization for
Clustering (ACOC) is a swarm algorithm inspired from nature to solve clustering issues as optimization problems. However, ACOC defined
implicit memory (pheromone matrix) inability to retain previous information on an ant’s movements in the pheromone matrix. The problem arises because ACOC is a centroid-label clustering algorithm, in which the relationship between a centroid and instance is unstable. The label of the current centroid value changes from one iteration to another because of changes in centroid label. Thus the pheromone values are lost because they are associated with the label (position) of the centroid. ACOC cannot
transfer the current clustering solution to the next iterations due to the history of the search being lost during the algorithm run. This study
proposes a new centroid memory (A-ACOC) for data clustering that can retain the information of a previous clustering solution. This is possible
because the pheromone is associated with the adaptive instance and not with label of the centroid. Centroids will be identified based on the adaptive instance route. A comparison of the performance of several common clustering algorithms using real-world data sets shows that the accuracy of the proposed algorithm surpasses those of its counterparts.
11 citations
TL;DR: WSD algorithms were classified to three categories as Knowledge-based, supervised and unsupervised techniques, which will helps the researchers in the field of natural language processing to select the suitable algorithms to solve their particular problem in WSD.
Abstract: The process of identifying the correct sense of a given word in a particular sentence is called Word Sense Disambiguation (WSD). It is complex problem because it involves drawing knowledge from various sources. Significant amount of effort has been put into resolving this problem in machine learning since its inception but the toil is still ongoing. Many techniques were used in WSD and implemented on different corpora for almost all languages. In this paper, WSD algorithms were classified to three categories as Knowledge-based, supervised and unsupervised techniques. Each category will be studied in details with explanation of almost all the algorithms in each category. Hence work examples for each method were taken with the used language, the used corpora and other factors. The benefits and drawback of each method were recorded. Some of these techniques have limitations in some situations, therefore this work will helps the researchers in the field of natural language processing to select the suitable algorithms to solve their particular problem in WSD. The novelty of the work can be seen in the comparison of the used works and the used algorithms. From this work, it was concluded that (i) some methods give high accuracy for language but low for other, (ii) the size of the used data set affects the performance of the used algorithm, (iii) some of these approaches can be run fastly but with limitation of the accuracy and (iv) most of these approaches are implemented for many languages successfully.
TL;DR: Evaluating and comparing these two libraries for Deep Neural Network: TensorFlow and PyTorch shows thatPyTorch library presented a better performance, even though the Tensor Flow libraryPresented a greater GPU utilization rate.
Abstract: Through the increase in deep learning study and use, in the last years there was a development of specific libraries for Deep Neural Network (DNN). Each one of these libraries has different performance results and applies different techniques to optimize the implementation of algorithms. Therefore, even though implementing the same algorithm and using different libraries, the performance of their executions may have a considerable variation. For this reason, developers and scientists that work with deep learning need scientific experimental studies that examine the performance of those libraries. Therefore, this paper has the aim of evaluating and comparing these two libraries: TensorFlow and PyTorch. We have used three parameters: Hardware utilization, hardware temperature and execution time in a context of heterogeneous platforms with CPU and GPU. We used the MNIST database for training and testing the LeNet Convolutional Neural Network (CNN). We performed a scientific experiment following the Goal Question Metrics (GQM) methodology, data were validated through statistical tests. After data analysis, we show that PyTorch library presented a better performance, even though the TensorFlow library presented a greater GPU utilization rate.
TL;DR: This research aimed at improving the Decision Tree C4.5 algorithm by adding a grid search function in order to improve prediction accuracy in classifying and predicting the students’ performance.
Abstract: Students’ information in higher education institutions increases yearly. It is hard for them to extract meaningful information from the huge amount of data manually. Such information can support academic staff to stop students from dropping out at the end of courses. This can be done by evaluating the students’ performance for the course and also by predicting their performance in the final exam early by using classification algorithms. Four classification algorithms, which are Decision Tree C4.5, Random Forest, Support Vector Machine (SVM) and Naive Bayes, were used in this research in order to classify and predict the students' performance. Furthermore, this research aimed at improving the Decision Tree C4.5 algorithm by adding a grid search function in order to improve prediction accuracy in classifying and predicting the students’ performance. Also, the features of this evaluation have been extracted through the interviews with academic staff of three universities (University of Zakho, Duhok Polytechnic University and University of Duhok), in Duhok province, Kurdistan Region, Iraq and through the review of the literature. A new prototype has been proposed as a tool to classify and predict the students’ performance by using Accrod.Net library. Three datasets were utilized in this research in order to test the improved Decision Tree C4.5 with the traditional C4.5 and three other selected algorithms. The results showed that the improved Decision Tree C4.5 outperformed the traditional C4.5 and also performed better when compared to C4.5 (J48) in Weka tool and other algorithms used in this research.
TL;DR: This paper surveyed a total of 1575 research papers published in the refereed conferences and journals in the area of short-texts mining from 2006 until 2017, from which 187 primary studies were included and analyzed to constitute the source of the present paper.
Abstract: With the growing number of connected online users producing a tremendous amount of unstructured short-texts daily, understanding and mining these data becomes very useful for individuals, governments and companies for identifying the public users’ attitudes towards different entities, such as products, services, events, places, organizations and topics. However, analyzing these short-texts using traditional methods becomes a significant challenge due to the shortness and sparsity nature of short-texts. To address such challenges, the literature introduced a broad spectrum of short-texts mining approaches and applications. Hence, this paper provides a comprehensive survey of this spectrum based on a criterion-based research strategy. The different mining techniques and approaches utilized in short-texts were highlighted along with their related issues and challenges. This paper surveyed a total of 1575 research papers published in the refereed conferences and journals in the area of short-texts mining were sur-veyed from 2006 until 2017, from which 187 primary studies were included and analyzed to constitute the source of the present paper. After a careful review of these articles, it is obvious that there are research gaps in other languages than English and Chinese, multi-languages, and in specific domain studies.
TL;DR: New and powerful features extracted by skeletonization of the lesion are presented to improve the classification accuracy and give a good classification accuracy compared to recent approaches from the literature.
Abstract: This paper presents a new approach to detect and classify skin lesions for melanoma diagnosis with high accuracy. Skin lesion detection is based on an image decomposition into two components using the Partial Differential Equation (PDE). The first component that sufficiently preserves the contour is thus exploited to have an adequate segmentation of image lesion while the second component provides a good characterization of the texture. Moreover, to improve the classification accuracy, new and powerful features extracted by skeletonization of the lesion are presented. These features are compared and combined with well-known features from the literature. Features engineering was applied to select the most relevant features to be retained for the classification phase. The proposed approach was implemented and tested on a large database and gave a good classification accuracy compared to recent approaches from the literature.
TL;DR: The research will be a starter for futuristic research on automatic prediction of heart disease in human beings with various other parameters on electrocardiogram values.
Abstract: Human heart is the major organ of human being which could fail the other systems in the body at the same time. Hence predicting heart disease is one of the challenging researches that requires meticulous analysis of heart rhythms properly. The irregular heart rhythms or beat is referred to as the Arrhythmia where heart rhythms with low or high rates comparing to the normal heart beat rate which ranges from 60 to 100 beats per minute. The heartbeat can be monitored and identified with the electrical disorder disease called Arrhythmia. This is very deadly when untreated for a long time as mortality rate is extremely high. Hence a prediction system is required to identify the irregular nature of heart and predict the heart problem in the future. The major objective of this research paper is to predict the presence of arrhythmia which is caused as a result of electrical imbalance and irregular heart beat in human being. The prediction is formulated with the help of essential parameters from electrocardiogram like age, gender, height, weight, BMI, QRS duration, P-R interval, Q-T interval, T interval, P interval, QRS, T, P, QRST, J values which will help the prediction of Arrhythmia in human to the best. The dataset sample is collected from UCI Repository based on electrocardiogram report values and pre-processed using Mat lab. The data is converted into test data and prediction is expected to be completed using Machine Deep learning Algorithms as they could be the best models for disease or syndrome predictions. Finally, the Analytics is carried out using Rapid Miner Studio where machine learning algorithms is applied and results obtained. The research will be a starter for futuristic research on automatic prediction of heart disease in human beings with various other parameters.
TL;DR: Results show that the proposed extended trigger terms outperform the baseline by achieving 88% and 69% of F1-scores for the first and second datasets, respectively, implying the effectiveness of the proposed extension of trigger terms in terms of detecting new ADRs.
Abstract: Adverse Drug Reaction (ADR) is a disorder caused by taking medications. Studies have addressed extracting ADRs from social networks where users express their opinion regarding a specific medication. Extracting entities mainly depends on specific terms called trigger terms that may occur before or after ADRs. However, these terms should be extended, especially when examining multiple representation of N-gram. This study aims to propose an extension of trigger terms based on the multiple representation of N-gram. Two benchmark datasets are used in the experiments and three classifiers, namely, support vector machine, Naive Bayes and linear regression, are trained on the proposed extension. Furthermore, two document representations have been utilized including Term Frequency Inverse Document Frequency (TFIDF) and Count Vector (CV). Results show that the proposed extended trigger terms outperform the baseline by achieving 88% and 69% of F1-scores for the first and second datasets, respectively. This finding implies the effectiveness of the proposed extended trigger terms in terms of detecting new ADRs.
TL;DR: Using associate rule to recommend actions based on data to reduce electricity consumption in different houses in Egypt based on each inhabitant’s interest to solve the main research problem of the large power crisis in Egypt due to the high electricity consumption.
Abstract: Smart homes with smart technologies can provide better insights into saving energy and improving the quality of our life. All connected appliances are Internet of Things (IoT) devices that support applications inside a smart home which produce an amount of data that shows what households are doing during their daily life. IoT and Big Data Analytics (BDA) became the most popular technologies in our smart life that are rapidly affecting all areas of technologies and businesses to increase the benefits for organizations and individuals. This research paper contains a review study for recent papers with different techniques that discusses BDA challenges and benefits of a smart home and its relationship with IoT. Moreover, the research paper also contains a proposed approach with its technique (clustering algorithm) for analysing data to solve the main research problem of the large power crisis in Egypt due to the high electricity consumption. Thus, using associate rule to recommend actions based on these data to reduce electricity consumption in different houses in Egypt based on each inhabitant’s interest.
TL;DR: A new model has been proposed to be used for big data set sentiment classification in the Cloudera parallel network environment and is able to process millions of Vietnamese documents, in addition to data in other languages, to shorten the execution time in the distributed environment.
Abstract: Solutions to process big data are imperative and beneficial for numerous fields of research and commercial applications. Thus, a new model has been proposed in this paper to be used for big data set sentiment classification in the Cloudera parallel network environment. Clustering Using Representatives (CURE), combined with Hadoop MAP (M) / REDUCE (R) in Cloudera – a parallel network system, was used for 20,000 documents in a Vietnamese testing data set. The testing data set included 10,000 positive Vietnamese documents and 10,000 negative ones. After testing our new model on the data set, a 62.92% accuracy rate of sentiment classification was achieved. Although our data set is small, this proposed model is able to process millions of Vietnamese documents, in addition to data in other languages, to shorten the execution time in the distributed environment
TL;DR: The results show that it takes on average 2 seconds for the proposed system to detect an intruder and that the system can successfully detect the intruder with accuracy of 90%.
Abstract: This research aims to design and implement a home security system with human detection capability. Traditional home security systems, i.e., Closed-Circuit Television (CCTV) can only capture and record videos without the ability of giving warning feedback if there is any suspicious object. Therefore, an additional object detection and warning method is required. The proposed design is implemented using Raspberry Pi 3 and Arduino, that is connected by USB cable. The PIR sensor is installed on Arduino and webcam is mounted on Raspberry Pi 3. The Raspberry Pi 3 is used to process inputs from sensors and process images for human detection. PIR sensor detects the movement around the sensor to activate the webcam to capture a picture. Then, the object recognition is performed using Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) to detect the suspicious object. If the suspicious object is detected, then the alarm is activated and sends an email to warn the house owner about the existence of the intruder. The results show that it takes on average 2 seconds for the proposed system to detect an intruder and that the system can successfully detect the intruder with accuracy of 90%.
TL;DR: The utilization of the Blockchain Technology Coupled with Public Key Cryptography as a security mechanism for Vehicle Identification and Transaction Authentication in IoV scenario is directed and the associated network model for a Blockchain based security processes is laid down.
Abstract: Internet of Vehicle (IoV) is now changing the landscape of Transportation System-paving the way of the so called Intelligent Transport System as it is being powered by the plethora of converging smart sensors and technologies. However, beyond its potential, this technology is still in a ground zero level considering the many facets of issues and concerns that needs to be addressed prior to its full implementation. One of the never ending and unresolved issues is on the area of Security and Privacy. In fact, security and privacy is always the prevailing concern not only of that of IoV but also in other areas of Communication and Network dependent systems. On this note, this paper directs the utilization of the Blockchain Technology Coupled with Public Key Cryptography as a security mechanism for Vehicle Identification and Transaction Authentication in IoV scenario. It lays down also the associated network model for a Blockchain based security processes. It also defines and describes the IoV Block and Blockchain requirements and conditions as the block are being propagated in the network.
TL;DR: The performance of the back-propagation neural network in training and testing cases is actually better than the radial base function, so it can be recommended as a useful tool in the software effort and cost estimation.
Abstract: Software development effort estimation becomes a very important and vital tool for many researchers in different fields. Software estimation used in controlling, organizing and achieving projects in the required time and cost to avoid the financial punishments due to the time delay and other different circumstances that may happen. Good project cost estimation will lead to project success and reduce the risk of project failure. In this paper, two neural network models are used, the Back-propagation algorithm versus the redial base algorithm. A comparison is done between the suggested models to find the best model that can reduce the project risks related to time and increase the profit by achieving the demands of the required project in time. The two models are implemented on a 60 of NASA public dataset, divided into 45 data samples for training and 15 data samples for testing. From the result obtained we can clearly say that the performance of the back-propagation neural network in training and testing cases is actually better than the radial base function, so the back-propagation algorithm can be recommended as a useful tool in the software effort and cost estimation.
TL;DR: This research seek to study and use vulnerability assessment as a tool to improve security by identifying vulnerabilities and proposing solutions to solve the security issues.
Abstract: Nowadays information has become anasset to many institutions and as a result these institutions have become targets for people with malicious intents to attack these institutions. The web is now an important means of transacting business and without security, websites cannot thrive in today’s complex computer ecosystem as there are new threats emerging as old ones are being tackled. Vulnerability assessment of websites is one of the means by which security can be improved on websites. This research seek to study and use vulnerability assessment as a tool to improve security by identifying vulnerabilities and proposing solutions to solve the security issues. Assessment was done on 5 web hosts belonging to different institutions in Ghana. Nmap, Nikto and Nessus were the tools used for the assessment, the assessment was carried out in four stages, and the first stage in the assessment was planning which involved activities and configurations performed before the actual assessment. The second stage was information gathering which involved obtaining information about the targets necessary to help identify vulnerabilities. This was followed by vulnerability scanning to identify vulnerabilities on the target hosts. The results indicated all the five hosts had security flaws which needed to be addressed. In all 16 vulnerabilities were identified on host 1, 8 vulnerabilities were identified on host 2, 15 vulnerabilities on host 3, 4 vulnerabilities on host 4 and 10 vulnerabilities on host 5. After the vulnerabilities were identified, a solution was proposed to mitigate the security flaws identified.
TL;DR: The final result shows that sub-factors improve customer service and overall responsiveness is a key sub-factor in benefit factors, whereas the lack of financial and human support becomes a keySub-Factor in barriers.
Abstract: This study aims to identify and analyze the key sub-factors of benefits and barriers as critical success factors for the implementation of IT Governance. The hope of the research is that the results of this identification and analysis can provide a high value of benefits in order to stakeholders in implementing IT Governance. In addition, it is expected to also give a real contribution to the development of theory or concept in the field of IT Governance especially related to critical success factor. The method used in this research is the interpretive structural model, where this method is very suitable to find the key sub-factor with a well-structured hierarchy structure. The first step of this research begins with a literature review, survey and interviews by involving three experts in the field of IT Governance and then the information is processed according to the rules. The final result shows that sub-factors improve customer service and overall responsiveness is a key sub-factor in benefit factors, whereas the lack of financial and human support becomes a key sub-factor in barriers. These results are empirical because depending on the data obtained through expert interviews involved, therefore the quality and capacity of experts greatly affect the results obtained. This study demonstrates how benefits and constraints as a critical success factor in the application of IT Governance are interrelated. The interpretive structural model provides an understanding of how various benefits and barriers interact with each other. This is important because policymakers typically focus on one or two sub-factors only.
TL;DR: Survey and analysis of the patterns practiced by users when generating passwords at a small-sized university found that the use of numbers and uppercase letters is prevalent among users and the existence of such trends makes it easier for attackers to generate more effective dictionaries.
Abstract: No matter how sophisticated an organization’s security system is, it remains vulnerable due to the human factor. In this study, we surveyed and analyzed the patterns practiced by users when generating passwords at a small-sized university. We found that users are not as aware of security requirements and practices as they think. Moreover, the vast majority of users’ passwords are breakable within days or shorter. Interestingly, we found that the use of numbers and uppercase letters is prevalent among users. However, numbers are mostly used at the end of the passwords and uppercase letters are mostly used at the beginning of passwords. The existence of such trends makes it easier for attackers to generate more effective dictionaries. Based on the analysis in this study, we make recommendations to the IT department to improve the password policy. Additionally, we provide recommendations to the faculty, staff, and students on how to strengthen their passwords.
TL;DR: The simulation results show that STRWP provides a good performance with the three routing protocols in terms of packet delivery ratio, throughput and end to end delay.
Abstract: Vehicular Ad-hoc Networks (VANET) is an advanced wireless network that came to increase traffic safety, efficiency and to improve driving experience. The high mobility of nodes is the major characteristic in these networks. The aim of this paper is to figure out the impact of various mobility models on the performance of Ad-hoc On-demand Distance Vector (AODV), Cluster-Based Directional Routing (CBDR) and Greedy Perimeter Stateless Routing (GPSR) protocols. In this study, we analyze the performance of these routing protocols in different mobility models namely: Street Random Waypoint (STRWP), Gauss Markov and Freeway having varying speed. The simulation results show that STRWP provides a good performance with the three routing protocols in terms of packet delivery ratio, throughput and end to end delay.
TL;DR: This paper aim to provide the right method to follow in data collect phase within different domain according to client needs and requirements based on a prior literature review on different existing methods.
Abstract: Several organizations from different sectors depend increasingly on knowledge extracted from huge volumes of data generated by different sources, such as IoT, sensors and databases. At the core of data lifecycle, data reliability, analytics, security, scalability and use are important concerns. Coping with these issues in handling data requires understanding the challenges associated with it. Analysis process and storage devices have been widely studied. However, very few studies have explored the collect data phase. In this study we aim to analyse more the collect phase of data lifecycle to provide an optimized and smart approach. This paper aim to provide the right method to follow in data collect phase within different domain according to client needs and requirements. It provides not only a detailed view of the main steps, but also based on a prior literature review on different existing methods. This allowed us subsequently to establish a correspondence with the SLR method on which we based our method. We use an explicit example to illustrate the steps of our method.
TL;DR: Once this smart technology is adopted, the labour-intensive task of monitoring will reduce while stakeholders shall be provided with a near real-time insight into the FAW situation in the field therefore enabling pro-activeness in their management of such a devastating pest.
Abstract: Maize is the main food crop that meets the nutritional needs of both humans and livestock in the sub-Saharan African region. Maize crop has in the recent past been threatened by the fall armyworm (Spodoptera frugiperda, J.E Smith) which has caused considerable maize yield losses in the region. Controlling this pest requires knowledge on the time, location and extent of infestation. In addition, the insect pest’s abundance and environmental conditions should be predicted as early as possible for integrated pest management to be effective. Consequently, a fall armyworm pheromone trap was deployed as a monitoring tool in the present study. The trap inspection is currently carried out manually every week. The purpose of this paper is to bring automation to the trap. We modify the trap and integrate Internet of Things technologies which include a Raspberry Pi 3 Model B+ micro-computer, Atmel 8-bit AVR microcontroller, 3G cellular modem and various sensors powered with an off-grid solar photovoltaic system to capture real-time fall armyworm moth images, environmental conditions and provide real-time indications of the pest occurrences. The environmental conditions include Geographical Positioning System coordinates, temperature, humidity, wind speed and direction. The captured images together with environmental conditions are uploaded to the cloud server where the image is classified instantly using Google’s pre-trained InceptionV3 Machine Learning model. Intended users view captured data including prediction accuracy via a web application. Once this smart technology is adopted, the labour-intensive task of monitoring will reduce while stakeholders shall be provided with a near real-time insight into the FAW situation in the field therefore enabling pro-activeness in their management of such a devastating pest.
TL;DR: The different application areas were data curation concept plays a critical role among Business, Retails, Culture, Arts, Health, Medicine, Social Media, Wireless Sensor Networks, Natural Language Processing (NLP) and Automated Feature Engineering are shown.
Abstract: Data Curation on data streams is effective in operating and reducing costs of BIG DATA analytic. Basically, analytic preparation requires data curation of available heterogeneous data sets available in big data clusters and such analytic process becomes harder when it comes to the concept of conducting the curation process on Data-on-Motion, in order to come at actionable insights and valuable analytic on a real-time basis including the Machine Learning further analytic and processing. In our paper, we identified and surveyed the different issues and challenges among different areas that are related to the big data. In addition to investigate, the most common techniques and methods followed through the implementations including Streams Curation, the Machine Learning Different Algorithms used in such implementations and the Feature Engineering different techniques that can be considered as curation pre-processing paradigm for data streams analytic. Furthermore, our paper shows the different application areas were data curation concept plays a critical role. Finally, we draw the map between the techniques and methods that are related to the data curation field to emphasize on its main critical role among Business, Retails, Culture, Arts, Health, Medicine, Social Media, Wireless Sensor Networks, Natural Language Processing (NLP) and Automated Feature Engineering (FE). On other hand, we identified the different issues and challenges among different areas including the IoT and Media Streams Curation to help the scholars in this region accordingly.
TL;DR: The novel approach on dental extraction forceps KM portal can support all the dental related personnel to improve the knowledge and helpful in learning practices and the next step is to model the ontology for the whole extraction process.
Abstract: Tooth extraction is one of the most usual surgical procedure in the field of dental. Not having proper knowledge of tooth and extraction instruments may cause too much complexity in extraction procedure or even some damages to patients’ jaws. Mainly when using extraction forceps, the proper forceps should be used according to the teeth and the situation. So, it is very much important to have a sound knowledge of the instruments to be used, especially on extraction forceps. So, the knowledge of extraction forceps should be disseminated properly. After identifying this need, as a first stage, we gathered the information regarding the dental extraction forceps from the experts in the field. Then we started developing ontology as a second stage. Finally, the Knowledge Management (KM) Portal, which helps to share the knowledge of dental extraction, was developed. Since the quality and the accuracy of the ontology is the key in this research, it was evaluated and validated by using inbuilt FaCT++ 1.6.5 reasoner, online validator OOPS! and ontology experts as an iterative approach. It was also evaluated by using ontology non-experts in the final stage as an application-based (field test) evaluation. A questionnaire survey was conducted to the users to evaluate the KM portal (i.e., ontology). The results show that 85% of them are agreed and strongly agreed on the usefulness of the system. We confidently believe that our novel approach on dental extraction forceps KM portal can support all the dental related personnel to improve the knowledge and helpful in learning practices. Our next step is to model the ontology for the whole extraction process.