Showing papers in "International Journal of Computer Science and Information Technology in 2020"
TL;DR: In this paper, a framework capable of accurately forecasting future sales in the retail industry and classifying the product portfolio according to the expected level of forecasting reliability is presented, which is based on Facebook's Prophet algorithm and backtesting strategy.
Abstract: This paper presents a framework capable of accurately forecasting future sales in the retail industry and classifying the product portfolio according to the expected level of forecasting reliability. The proposed framework, that would be of great use for any company operating in the retail industry, is based on Facebook's Prophet algorithm and backtesting strategy. Real-world sales forecasting benchmark data obtained experimentally in a production environment in one of the biggest retail companies in Bosnia and Herzegovina is used to evaluate the framework and demonstrate its capabilities in a real-world use case scenario.
11 citations
TL;DR: Education systems and its actors are generally responding to quarantine and large-scale shutdown (partial) of cities with a sudden shift to Web-Based Learning.
Abstract: Education systems and its actors are generally responding to quarantine and large-scale shutdown (partial) of cities with a sudden shift to Web-Based Learning. However, given that a pandemic of this nature and scale is novel, there is a knowledge gap as to how teachers and learners should respond to the shift, and what the likely impact and the key considerations should be. This study aims to extrapolate and theorize from the existing knowledgebase about the use of Web-Based Learning, as well as from an expert and practitioner wisdom and experience, to offer high-level guidance for policymakers and education system actors that are forced to make decisions in fast-moving and very challenging circumstances with little guidance or relevant experience. It is an early attempt at theorizing the impact of the pandemic on two key actors (Learners and Teachers) and one interface (Content), all across eight dimensions of learning. The analysis is based on Khan’s (2001) dimension of Web-Based Learning and Anderson’s (2011) Model of Online Learning. Overall, we posit based on experience and practice, that the pandemic has delivered severe shocks to both the demand and supply side of Web-Based Learning, with Leaners, Teachers, and Content all significantly affected. While we hypothesize a general drop in the quality of teaching and learning in the short run, we expect the opposite to be the case in the long run, when the demand and supply side self-correct, albeit guided by strong government and market institutions.
8 citations
7 citations
TL;DR: In this paper, the authors proposed a smart parking management system (SPMS) that depends on Arduino parts, Android applications, and based on IoT, which gave the client the ability to check available parking spaces and reserve a parking spot.
Abstract: With growing, Car parking increases with the number of car users. With the increased use of smartphones and their applications, users prefer mobile phone-based solutions. This paper proposes the Smart Parking Management System (SPMS) that depends on Arduino parts, Android applications, and based on IoT. This gave the client the ability to check available parking spaces and reserve a parking spot. IR sensors are utilized to know if a car park space is allowed. Its area data are transmitted using the WI-FI module to the server and are recovered by the mobile application which offers many options attractively and with no cost to users and lets the user check reservation details. With IoT technology, the smart parking system can be connected wirelessly to easily track available locations.
6 citations
TL;DR: In this article, an Arabic grammar trainer (AGTrainer) which is an Intelligent CALL is used to train the students through different questions that deal with the different concepts of the Arabic language and have different difficulty levels.
Abstract: Computer-Assisted Language Learning (CALL) are computer-based tutoring systems that deal with linguistic skills. Adding intelligence in such systems is mainly based on using Natural Language Processing (NLP) tools to diagnose student errors, especially in language grammar. However, most such systems do not consider the modeling of student competence in linguistic skills, especially for the Arabic language. In this paper, we will deal with basic grammar concepts of the Arabic language taught for the fourth grade of the elementary school in Egypt. This is through Arabic Grammar Trainer (AGTrainer) which is an Intelligent CALL. The implemented system (AGTrainer) trains the students through different questions that deal with the different concepts and have different difficulty levels. Constraint-based student modeling (CBSM) technique is used as a short-term student model. CBSM is used to define in small grain level the different grammar skills through the defined skill structures. The main contribution of this paper is the hierarchal representation of the system's basic grammar skills as domain knowledge. That representation is used as a mechanism for efficiently checking constraints to model the student knowledge and diagnose the student errors and identify their cause. In addition, satisfying constraints and the number of trails the student takes for answering each question and fuzzy logic decision system are used to determine the student learning level for each lesson as a long-term model. The results of the evaluation showed the system's effectiveness in learning in addition to the satisfaction of students and teachers with its features and abilities.
3 citations
TL;DR: This study focuses on the vulnerabilities found on White-label Cloud-based IoT Camera on the market specifically on a Chinese brand sold by Shenzhen Gwelltimes Technology.
Abstract: The Internet is driving force on how we communicate with one another, from posting messages and images to Facebook or “tweeting” your activities from your vacation. Today it is being used everywhere, now imagine a device that connects to the internet sends out data based on its sensors, this is the Internet-ofThings, a connection of objects with a plethora of sensors. Smart devices as they are commonly called, are invading our homes. With the proliferation of cheap Cloud-based IoT Camera use as a surveillance system to monitor our homes and loved ones right from the palm of our hand using our smartphones. These cameras are mostly white-label product, a process in which the product comes from a single manufacturer and bought by a different company where they are re-branded and sold with their own product name, a method commonly practice in the retail and manufacturing industry. Each Cloud-based IoT cameras sold are not properly tested for security. The problem arises when a hacker, hacks into the Cloud-based IoT Camera sees everything we do, without us knowing about it. Invading our personal digital privacy. This study focuses on the vulnerabilities found on White-label Cloud-based IoT Camera on the market specifically on a Chinese brand sold by Shenzhen Gwelltimes Technology. How this IoT device can be compromised and how to protect our selves from such cyber-attacks.
3 citations
TL;DR: The paper focuses on researching and improving the EM algorithm to suit the LiDAR point cloud classification and using the scheduling parameter for step E to help the algorithm converge faster with a shorter run time.
Abstract: EM algorithm is a common algorithm in data mining techniques. With the idea of using two iterations of E and M, the algorithm creates a model that can assign class labels to data points. In addition, EM not only optimizes the parameters of the model but also can predict device data during the iteration. Therefore, the paper focuses on researching and improving the EM algorithm to suit the LiDAR point cloud classification. Based on the idea of breaking point cloud and using the scheduling parameter for step E to help the algorithm converge faster with a shorter run time. The proposed algorithm is tested with measurement data set in Nghe An province, Vietnam for more than 92% accuracy and has faster runtime than the original EM algorithm.
2 citations
TL;DR: Critical analysis was made on all of these techniques on the same computer system and excellent results were obtained.
Abstract: Creating 3D vehicle model is complex process that requires basic knowledge of polygonal modeling. In this research, environment map is used as lighting with HDRI image. The final process of converting 3D scene to 2D image is called rendering. Image data will be obtained in four ways with various toolsets used in 3ds Max. They are: Scaneline, V-Ray, Mental Ray and Corona Renderer. At final step was made critical analysis on all of these techniques on the same computer system and excellent results were obtained.
2 citations
TL;DR: This paper proposes to represent dialog turns by binary encoded bags of automatically selected keywords to be subsequently used in a machine learning classifier, and achieves a level of accuracy significantly higher than a statistical baseline for prediction of frustration intensity for a current turn.
Abstract: This paper examines emotion intensity prediction in dialogs between clients and customer support representatives occurring on Twitter. We focus on a single emotion type, namely, frustration, modelling the user's level of frustration while attempting to predict frustration intensity on the current and next turn, based on the text of turns coming from both dialog participants. A subset of the Kaggle Customer Support on Twitter dataset was used as the modelling data, annotated with per-turn frustration intensity ratings. We propose to represent dialog turns by binary encoded bags of automatically selected keywords to be subsequently used in a machine learning classifier. To assess the classification quality, we examined two different levels of accuracy imprecision tolerance. Our model achieved a level of accuracy significantly higher than a statistical baseline for prediction of frustration intensity for a current turn. However, we did not find the additional information from customer support turns to help predict frustration intensity of the next turn, and the reason for that is possibly the stability of user’s frustration level over the course of the conversation, in other words, the inability of support’s response to exert much influence to user’s initial frustration level.
2 citations
TL;DR: This work conducted comparative analysis of different supervised dimension reduction techniques by integrating a set of different data splitting algorithms and devised a model built on weighted average rank Weighted Mean Rank Risk Adjusted Model (WMRRAM) for consent ranking of learning classifier algorithms.
Abstract: We conducted comparative analysis of different supervised dimension reduction techniques by integrating a set of different data splitting algorithms and demonstrate the relative efficacy of learning algorithms dependence of sample complexity. The issue of sample complexity discussed in the dependence of data splitting algorithms. In line with the expectations, every supervised learning classifier demonstrated different capability for different data splitting algorithms and no way to calculate overall ranking of techniques was directly available. We specifically focused the classifier ranking dependence of data splitting algorithms and devised a model built on weighted average rank Weighted Mean Rank Risk Adjusted Model (WMRRAM) for consent ranking of learning classifier algorithms.
2 citations
TL;DR: This study demonstrates the future trends of Next Generation Sequencing data analysis in disease detection and sample datasets of each genetic detection method was included and the challenges facing genetic disease detection were elaborated.
Abstract: Multiple sclerosis disease is a main cause of non-traumatic disabilities and one of the most common neurological disorders in young adults over many countries. In this work, we introduce a survey study of the utilization of machine learning methods in Multiple Sclerosis early genetic disease detection methods incorporating Microarray data analysis and Single Nucleotide Polymorphism data analysis and explains in details the machine learning methods used in literature. In addition, this study demonstrates the future trends of Next Generation Sequencing data analysis in disease detection and sample datasets of each genetic detection method was included .in addition, the challenges facing genetic disease detection were elaborated.
TL;DR: This quantitative post positivist research used the information system (IS) success model to analyze how information quality and system quality influence information use in business intelligence systems and investigated the moderating effects of maturity constructs on the relationships between quality factors and information use.
Abstract: Business intelligence systems are highly complex systems that senior executives use to process vast amounts of information when making decisions. Business intelligence systems are rarely used to their full potential due to a poor understanding of the factors that contribute to system success. Organizations using business intelligence systems frequently find that it is not easy to evaluate the effectiveness of these systems, and researchers have noted that there is limited scholarly and practical understanding of how quality factors affect information use within these systems. This quantitative post positivist research used the information system (IS) success model to analyze how information quality and system quality influence information use in business intelligence systems. This study was also designed to investigate the moderating effects of maturity constructs (i.e., data sources and analytical capabilities) on the relationships between quality factors and information use.
TL;DR: Develop a mobile application and create a unique QR code label with equipment naming to facilitate each worker management of protection tools to achieve a common goal: Everyone Going Home Safe and Well Every day.
Abstract: In every night of non-traffic hours, different jobs are conducting maintenance works in “Railway” trackside area. This project will explain a specific section of track under the sole control an Engineer’s Person-in-Charge as procedures. And how to provide protection methods by which a person or persons on or near a track are safeguarded from potential train movements or a train is safeguarded from other train movements or obstructions, or persons or equipment are safeguarded from traction power.Consolidated past several investigation reports and according to related is rules, workflow or procedures etc. to summarize. There are protection tools left on trackside area incident caused by the workers are forgetting and poor management. Proposed are different project themes in the light of their expertise, experience and observation in their daily works. The proposed themes are compared, assessed and prioritized under the criteria - “Manageable”, “Measurable”, “Result of Benefit”, “Standardization” and “Priority” in the Decision Matrix. Establish some solve problem methods for comparing to find out which that lower-cost plan accordingly. I came up with a conclusion and the ideas as develop a mobile application and create a unique QR code label with equipment naming to facilitate each worker management of protection tools. This is also fulfilled in popular terms of Creativity and Innovations. Used the MIT App Inventor (Massachusetts Institute of technology) an intuitive and visual programming preform for mobile application are development. Stage 1: program for individual mobile user application. Stage 2: build-up Network centralized storage with supervising console operation. Stage 3: testing system under with 5G network compatibility, bandwidth and network speed is applicable people will be able to use more of the network dedicated to each mobile phone.Finally, successful to apply trial works a fruitful outcome after implementation of the project solution. There was no missing of protection tools on trackside area within the trial period. With the safety-first culture boosted by us, I believe we can achieve a common goal: Everyone Going Home Safe and Well Every day.
TL;DR: The aim of this study is to describe the clinical, demographic, and histopathologic findings of lichen planopilaris in the Iranian population.
Abstract: Introduction: Demographic studies of a disease can reveal the characteristics of that disease among a specific population and will help the physicians to achieve a more accurate perception about it.The demographic of Lichen PlanoPilaris (LPP) among the Iranian population is unknown. The aim of this study is to describe the clinical, demographic, and histopathologic findings of lichen planopilaris in the Iranian population. Materials and Methods: In this cross-sectional study, all the patients with Lichen planopilaris were referred to the dermatology clinic of Imam Khomeini hospital from 2013 to 2015. Lichen planopilaris can be diagnosed by collecting histological evidence, dermatological examination, and clinical diagnosis. Their demographic characteristics, drug histories, onset of disease, and family histories were obtained by written questionnaire. Additionally, this study employed SPSS v.20 as the statistical analysis software. Results: One hundred patients were enrolled in this study. With an average age of 47.11 years, 78% of the patients were female, and 50 of these were housewives. The patients included were often from Tehran with Fars ethnicity. Among these patients, 7 had alopecia areata skin disease, and 10 of them suffered from thyroid disease. Most of the histopathology samples collected from these biopsies revealed degeneration of the basal layer of the follicular structure, perifollicular fibrosis, inflammatory cells, and atrophy of the pilosebaceous structures. Conclusion: Both the age spectrum and the disease distribution of LPP among the Iranian population were very diverse when compared to previous studies. Moreover, this study helps the physicians to have a brighter vision about the main reason and cause of LPP spread among diverse Iranian Ethnicities.
TL;DR: The introduced 3D systems utilize recent findings in field-emission and nano applications to implement the function of the basic 3D lattice networks using nano controlled-switching, including ternary lattice computing via carbon nanotubes and carbon field- Emission techniques.
Abstract: New implementations for concurrent computing applications of 3D networks using corresponding nano and field-emission controlled-switching components are introduced. The developed implementations are performed within 3D lattice-based systems to perform the required concurrent computing. The introduced 3D systems utilize recent findings in field-emission and nano applications to implement the function of the basic 3D lattice networks using nano controlled-switching. This includes ternary lattice computing via carbon nanotubes and carbon field-emission techniques. The presented realization of lattice networks can be important for several reasons including the reduction of power consumption, which is an important specification for the system design in several future and emerging technologies, and in achieving high performance and reliability realizations. The introduced implementations for 3D lattice computations, with 2D lattice networks as a special case, are also important for the design within modern technologies that require optimal design specifications of high speed, high regularity and ease-of-manufacturability, such as in highly-reliable error-correcting signal processing applications.
TL;DR: A new ranking approach for shadowed fuzzy numbers is developed using value, ambiguity and fuzziness for shadowing fuzzy numbers to solve a hybrid multi-attribute decision making problem in which the evaluations of alternatives are expressed with different types of uncertain numbers.
Abstract: In many decision situations, decision-makers face a kind of complex problems. In these decision-making problems, different types of fuzzy numbers are defined and, have multiple types of membership functions. So, we need a standard form to formulate uncertain numbers in the problem. Shadowed fuzzy numbers are considered granule numbers which approximate different types and different forms of fuzzy numbers. In this paper, a new ranking approach for shadowed fuzzy numbers is developed using value, ambiguity and fuzziness for shadowed fuzzy numbers. The new ranking method has been compared with other existing approaches through numerical examples. Also, the new method is applied to a hybrid multi-attribute decision making problem in which the evaluations of alternatives are expressed with different types of uncertain numbers. The comparative study for the results of different examples illustrates the reliability of the new method.
TL;DR: Maximum flow algorithm including superposition theorem is applied to solve the traffic flow of radio network and using the total flow per subcarrier, a new traffic model is also developed in the paper.
Abstract: In this paper, we propose a new traffic flow model of the Long Term Evaluation (LTE) network for the Evolved Universal Terrestrial Radio Access Network (E-UTRAN). Here only one Evolve Node B (eNB) nearest to the Mobility Management Entity (MME) and Serving Gateway (S-GW) will use the S1 link to bridge the E-UTRAN and Evolved Packet Core (EPC). All the eNBs of a tracking area will be connected to each other by the X2 link. Determination of capacity of a links of such a network is a challenging job since each node offers its own traffic and at the same time conveys traffic of other nodes. In this paper, we apply maximum flow algorithm including superposition theorem to solve the traffic flow of radio network. Using the total flow per subcarrier, a new traffic model is also developed in the paper. The relation among the traffic parameters: ‘blocking probability’, ‘offered traffic’, ‘instantaneous capacity’, ‘average holding time’, and ‘number of users’ are shown graphically under both QPSK and 16-QAM. The concept of the network will be helpful to improve the SINR of the received signal ofeNBslocated long distance relative to MME/S-GW.
TL;DR: The authors analysed and proposed a solution for the problem of cost optimization for packages delivery for long-distance deliveries using a combination of paths delivered by supplier fleets, worldwide, local carriers and drop-ship networks.
Abstract: A variety of goods and services in the contemporary world requires evolutionary improvement of services e-commerce platform performance and optimization of costs. Contemporary society is deeply integrated with delivery services, purchasing of goods and services online, that makes competition between service and good providers a key selection factor for end-user.. As long as logistic, timely, and cost-effective delivery plays important part authors decided to analyse possible ways of improvements in the current field, especially for regions distantly located from popular distribution canters and drop-ship delivery networks. Considering both: fast and lazy delivery the factor of costs is playing an important role for each end-user. The work proposes a simulation that analyses the current cost of delivery for e-commerce orders in the context of delivery by the Supplier Fleet, World-Wide delivery service fleet, and possible vendor drop-ship and checks of the alternative ways can be used to minimize the costs. Special attention is given to Drop-Ship networks as the factor of possible costs decrease. The main object of investigation is focused around mid and small companies living far from big distribution canters, in the rural areas but actively using e-commerce solutions for their daily activities. The authors analysed and proposed a solution for the problem of cost optimization for packages delivery for long-distance deliveries using a combination of paths delivered by supplier fleets, worldwide, local carriers and drop-ship networks. Data models and Add-ons of contemporary Enterprise Resource Planning systems have been used, and additional development is proposed in the perspective of the flow selection change for combination of carriers. The experiment is based on data sources of the United States companies using a wide range of carriers for delivery services and uses the data sources of the real companies; however, it applies repetitive simulations to analyse variances in obtained solutions for different combinations of carriers.