- Все статьи 611
Статьи журнала - International Journal of Information Engineering and Electronic Business
Все статьи: 611
Exploring Semantic Relatedness in Arabic Corpora using Paradigmatic and Syntagmatic Models
Статья научная
In this paper we explore two paradigms: firstly, paradigmatic representation via the native HAL model including a model enriched by adding word order information using the permutation technique of Sahlgren and al [21], and secondly the syntagmatic representation via a words-by-documents model constructed using the Random Indexing method. We demonstrate that these kinds of word space models which were initially dedicated to extract similarity can also been efficient for extracting relatedness from Arabic corpora. For a given word the proposed models search the related words to it. A result is qualified as a failure when the number of related words given by a model is less than or equal to 4, otherwise it is considered as a success. To decide if a word is related to other one, we get help from an expert of the economic domain and use a glossary1 of the domain. First we begin by a comparison between a native HAL model and term- document model. The simple HAL model records a better result with a success rate of 72.92%. In a second stage, we want to boost the HAL model results by adding word order information via the permutation technique of sahlgren and al [21]. The success rate of the enriched HAL model attempt 79.2 %.
Бесплатно
Статья научная
Businesses nowadays may save a significant amount of money by using technological solutions. It is impossible to deny this when considering the expenses of acquiring and training new personnel. When faced with such difficulties, technology is virtually always able to assist. Business Intelligence/Machine Learning (BI/ML) is an essential tool in today's decision-making process because of the many issues it has created for contemporary business decision-making. A comparative study of regression models, including linear regression, random forests, and gradient boosting, could unravel their effectiveness in predictive analytics within BI. Machine learning contribution in businesses is vital as it has a strong link with business intelligence, and it helps business decision-making in businesses. Without machine learning, business intelligence is not practical while making decisions, as business owners can't make decisions effectively. This paper will comprehensively review the noteworthy contributions of Machine Learning and its Impact on Business Intelligence. Further, it will discuss the challenges and opportunities of machine learning in business intelligence. Finally, the paper will discuss future correspondence about machine learning in businesses.
Бесплатно
Статья научная
This paper tackles a critical issue emerging when planning the deployment of a wireless network in rural regions: the cost estimation. Wireless Networks have usually been presented as a cost-effective solution to bridge the digital divide between rural and urban regions. But this assertion is too general and does not give an insight about the real estimation of the deployment cost of such an infrastructure. Providing such a cost estimation framework may help to avoid underestimation or overestimation of required resources since the budget is almost always limited in rural regions. This work extends the Probabilistic Cost Model (PCM) that has been proposed. This model does not take into account the difference in the costs of unexpected events. To extend the PCMfirst, a list of unexpected events that can occur when deploying Wireless Networks has been established. This list is based on data from past projects and a set of unexpected events that can occur. Afterwards, the standard deviation and the average have been computed for each unexpected event. The Poisson process has been therefore used to predict the number of unexpected events that may occur during the network deployment. This approach led to the proposal of a model that gives an estimation of the total cost of contingencies, which takes into account the probability that the total cost of unexpected events does not exceed a given contingency. The evaluation of the proposed model on a given dataset provided a good accuracy in the prediction of the cost induced by unexpected events.
Бесплатно
Extended Proxy Mobile IPv6 Scheme Using Global Local Mobility Anchor
Статья научная
The internet was basically designed for the static nodes, but with the development of mobile nodes such as smart phones, that have wireless capabilities, the first design was insufficient. MNs change their point of attachment while they are roaming (traveling) in the internet, to maintain the survival of ongoing sessions for these mobile nodes, the internet requires techniques for managing mobility.. Currently, there are two types of mobility management protocols, host-based protocols and network-based protocols, the involvement of MN in the mobility process is must in the first type, while is unnecessary in the second type. The IETF standardized the Proxy Mobile IPv6 (PMIPv6) protocol in 2004, to overcome the limitations experienced by the host-based protocol, Mobile IPv6 (MIPv6) such as sub-optimal routing, handover latency, packet loss and single point of failure, however, the biggest drawback of PMIPv6 is the lack of inter-domain handover. This paper provides an efficient scheme based on standard PMIPv6 called (E-PMIPv6) to support inter-domain handover by introducing a new entity called (GLMA) which enables MN to traverse different domains while keeping the ongoing sessions, additionally; we use buffering techniques to pre-emptively lighten packet losses. The ultimate goal for the suggested scheme is to solve the scalability problem for the PMIPv6 and it is extensions to encourage network operators to deploy E-PMIPv6 for large networks. Results of preliminary analysis of handover latencies and related packet losses favored (E-PMIPv6) over two of the leading contenders.
Бесплатно
Extracting Feature Curves on Point Sets
Статья научная
We present an effective algorithm for detecting feature curves on point sets. Based on the local surface fitting method, our algorithm first compute the curvatures and principal directions of each point of point sets. The algorithm then extracts potential feature points according to the biggist principal curvature of the point, and evaluates the principal directions of the detected points. By projecting the points onto the principal axes of their neighborhoods, the potential feature points are smoothed. Using the principal directions with each optimized point, feature curves are generated by polyline growing along the principal directions of feature points. The results indicate that our algorithm is sensitive to both sharp and smooth feature curves of point set, and it supports multi-resolution extraction of features.
Бесплатно
Статья научная
Although remarkable success has been achieved by genome-wide association (GWA) studies over the past few years, genetic variants discovered in GWA studies can typically account for only a small fraction of heritability of most common diseases. As such, the identification of multiple rare variants that are associated with complex diseases has been receiving more and more attentions. However, most of the recently developed statistical approaches for detecting association of rare variants with diseases require the selection of functional variants before the successive analysis, making an effective bioinformatics method for filtering out non-relevant rare variants indispensible. In this paper, we focus on a specific type of genetic variants called single amino acid polymorphisms (SAAPs). We propose to prioritize candidate SAAPs for a specific disease according to their association scores that are calculated using a guilt-by-association model with a set of features derived from protein sequences. We validate the proposed approach in a systematic way and demonstrate that the proposed model is powerful in distinguishing disease-associated SAAPs for the specific disease of interest.
Бесплатно
Extractive based text summarization using k-means and TF-IDF
Статья научная
The quantity of information on the internet is massively increasing and gigantic volume of data with numerous compositions accessible openly online become more widespread. It is challenging nowadays for a user to extract the information efficiently and smoothly. As one of the methods to tackle this challenge, text summarization process diminishes the redundant information and retrieves the useful and relevant information from a text document to form a compressed and shorter version which is easy to understand and time-saving while reflecting the main idea of the discussed topic within the document. The approaches of automatic text summarization earn a keen interest within the Text Mining and NLP (Natural Language Processing) communities because it is a laborious job to manually summarize a text document. Mainly there are two types of text summarization, namely extractive based and abstractive based. This paper focuses on the extractive based summarization using K-Means Clustering with TF-IDF (Term Frequency-Inverse Document Frequency) for summarization. The paper also reflects the idea of true K and using that value of K divides the sentences of the input document to present the final summary. Furth more, we have combined the K-means, TF-IDF with the issue of K value and predict the resulting system summary which shows comparatively best results.
Бесплатно
Статья научная
The implementation of face recognition with TensorFlow deep learning uses the webcam as a surveillance camera on the Raspberry Pi, aiming to provide a sense of security to the requiring party. A frequent surveillance camera problem is that crimes are performed at certain hours, the absence of early warning features, and there is no application of facial recognition on surveillance cameras. The function of this system is to perform facial recognition on every face captured by the webcam. Use the Histogram of the Oriented Gradient (HOG) method for the extraction process of deep learning. The image that is input from the camera will undergo a gray scaling process, then it will be taken the extraction value and classified by deep learning framework with TensorFlow. The system will send notifications when faces are not recognized. Based on the analysis of the data is done, the conclusion that the implementation of face recognition is built on the Raspberry Pi using a Python programming language with the help of TensorFlow so that the training process of the sample is much faster and more accurate. It uses a Graphical User Interface (GUI) as the main display and is built using Python designer, using email as an initial warning delivery medium to the user as well as using the webcam as the main camera to capture image.
Бесплатно
Failures in Cloud Computing Data Centers in 3-tier Cloud Architecture
Статья научная
This paper presents an methodology for providing high availability to the demands of cloud's clients. To succeed this objective, failover approaches for cloud computing using combined checkpointing procedures with load balancing algorithms are purposed in this paper. Purposed methodology assimilate checkpointing feature with load balancing algorithms and also make multilevel barrier to diminution checkpointing overheads. For execution of purposed failover approaches, a cloud simulation environment is established, which the ability to provide high availability to clients in case of disaster/recovery of service nodes. Also in this paper comparison of developed simulator is made with existing approaches. The purposed failover strategy will work on application layer and provide highly availability for Platform as a Service (PaaS) feature of cloud computing.
Бесплатно
Статья научная
The key of fast identification algorithm of time-varying modal parameter based on subspace tracking is to find efficient and fast subspace-tracking algorithm. This paper presents a modified version of NIC(Novel Information Criterion) adopted in two-layer linear neural network learning for subspace tracking, which is applied in time-varying modal parameter identification algorithm based on subspace tracking and get a new time-varying modal parameter identification algorithm. Comparing with the original subspace-tracking algorithm, there is no need to set a key control parameter in advance. Simulation experiments show that new time-varying modal parameter identification algorithm has a faster convergence in the initial period and a real experiment under laboratory conditions confirms further its validity of the time-varying modal identification algorithm presented in this paper.
Бесплатно
Feature Engineering based Approach for Prediction of Movie Ratings
Статья научная
The buying behavior of the consumer is grown nowadays through recommender systems. Though it recommends, still there are limitations to give a recommendation to the users. In order to address data sparsity and scalability, a hybrid approach is developed for the effective recommendation in this paper. It combines the feature engineering attributes and collaborative filtering for prediction. The proposed system implemented using supervised learning algorithms. The results empirically proved that the mean absolute error of prediction was reduced. This approach shows very promising results.
Бесплатно
Статья научная
Dimensionality reduction is generally performed when high dimensional data like text are classified. This can be done either by using feature extraction techniques or by using feature selection techniques. This paper analyses which dimension reduction technique is better for classifying text data like emails. Email classification is difficult due to its high dimensional sparse features that affect the generalization performance of classifiers. In phishing email detection, dimensionality reduction techniques are used to keep the most instructive and discriminative features from a collection of emails, consists of both phishing and legitimate, for better detection. Two feature selection techniques - Chi-Square and Information Gain Ratio and two feature extraction techniques – Principal Component Analysis and Latent Semantic Analysis are used for the analysis. It is found that feature extraction techniques offer better performance for the classification, give stable classification results with the different number of features chosen, and robustly keep the performance over time.
Бесплатно
Finite State Machine Model in Jungle Adventure Game an Introduction to Survival Skills
Статья научная
Game is one of the big industries today and can be an alternative entertainment and fun for children and adults. Game can be used as an interactive and interesting learning media. One of the platform game development methods is the Finite State Machine (FSM). This method is used to adjust the behavior of the NPC (Non-Player Character) to guide the player through the game. This study developed an Android-based "Jungle Adventure" game with interesting gameplay to make the learning process very enjoyable so that the player is expected to be able to play while learning. Combination NPC with FSM will make that responses under certain conditions, and NPC will accompany player like a friend survival.
Бесплатно
Folding Bicycle Prospective Buyer Prediction Model
Статья научная
The trend of bicycle exercise during the pandemic has resulted in increased sales and even scarcity of bicycle stock in some shops. The phenomenon has raised attention from both the bicycle industry and government to provide necessary responses toward the trends. Even though it is a trend, many prospective buyers are still confused about their choices. The types of bicycles that sell the most on the market are folding bikes, mountain bikes, and racing bikes. The research data were collected from 242 bicycle users who came from various bicycle communities in major cities of Java Island, Indonesia. Some of the predictors used were age, gender, height, weight, and cycling speed. The target variable is the type of bicycle whose data is categorical. Predictor variables consist of nominal and ordinal variables, so preprocessing needs to be done using Python's Sklearn library. To test the accuracy of the model, the data was broken down into training data and test data with a test size of 20%. Several methods are used to form a classification model, including K-NN, Naive Bayes, Support Vector Machine, Decision Tree, and Random Forest. The results of the classification model evaluation show that the Support Vector Machine and Decision Tree have the highest accuracy of 90%, while Naive Bayes has the lowest accuracy of 73%. The model formed can be a predictive tool for potential bicycle buyers in order to be able to choose the right type of bicycle.
Бесплатно
Forecasting of Indonesian Digital Economy based on Available New Start-up
Статья научная
Since the last 5 years, digital economy is growing steadily in Indonesia. Right now, the digital economy faces some potential problems and Covid-19 pandemic. This paper presents current data of the national Gross Domestic Product (GDP) and other GDPs (billion IDR) and the number of start-up, and predicts near some categories of future GDP and numbers of available new start-up for the next few years. The forecast will use Markov chain analysis. The results indicate that, while there are problems faced by the digital economy industry, the GDP and numbers of start-up are significantly increasing.
Бесплатно
Framework for an E-Voting System Applicable in Developing Economies
Статья научная
Information technology has pervaded virtually every facet of human life. Even in the delivery of governance, information technology has gradually found a place. One of its applications is the use of electronic voting, also known as e-voting, as opposed to the traditional manual method of voting. This form of voting, however, is not immune to challenges generally associated with voting. Two of these include guaranteeing voting access to all eligible voters, and providing necessary voting security. The challenge of accessibility is especially peculiar to developing countries where IT adoption is still relatively low. This paper proposes a framework for an e-voting system that would most benefit developing economies. It ensures availability of the system to only eligible voters and integrity of the voting process through its capacity to identify and prevent ineligible voters and multiple voting. To guarantee accessibility to all eligible voters, it supports both online and offline voting capabilities. Adopting electronic form of voting would provide a more robust, easier to use, and reliable system of voting, which, consequently, would contribute towards enhancing the delivery of democratic dividends.
Бесплатно
Fuzzy Stability and Synchronization of New 3D Chaotic Systems
Статья научная
This paper presents fuzzy model-based designs for control and synchronization of new chaotic system. The T–S fuzzy models for new chaotic systems are exactly derived. Then the asymptotic stability and synchronization are achieved by generalized backstepping method. On the other hand, this paper presents fuzzy model-based designs for synchronization of another chaotic system. Based on the T–S fuzzy new chaotic models, the fuzzy controllers for two different chaotic synchronization are designed via the active control technique. Numerical simulation results are presented to show the effectiveness of the proposed method.
Бесплатно
Fuzzy entropy based MOORA model for selecting material for mushroom in viet nam
Статья научная
The role of materials in the proper design and operation of products has been acknowledged. An incorrectly selected material for a certain product may cause premature failure of the final product. The right choice of available materials is very important to the success and competitiveness of manufacturing organizations. In Vietnam, tropical monsoon climate conditions greatly affect mushroom cultivation. The raw materials, additives and the ratio between them will also affect the quality and yield of mushrooms. Therefore, selecting the options for growing mushrooms or choosing good materials to grow mushrooms effectively is also a matter of concern. This is a problem of many decision-making problems. In this paper we multi-objective optimization on the basis of ratio analysis (MOORA) method to evaluate mushroom cultivation options in Vietnam.
Бесплатно
Статья научная
Congetive method is used in this research to create portfilo of movement robot manipulator. Gradient descent (GD) artificial intelligence based switching feedback linearization controller was used and robot's postures and trajectory were expected in MATLAB/SIMULINK environment. Feedback linearization controller (CTC) is an influential nonlinear controller to certain systems which it is based on feedback linearization and computes the required torques using the nonlinear feedback control law in certain systems. Practically a large amount of systems have uncertainties accordingly this method has a challenge. Switching feedback linearization controller is a significant combination nonlinear stable-robust controller under condition of partly uncertain dynamic parameters of system. This technique is used to control of highly nonlinear systems especially in nonlinear time varient nonlinear dynamic system. To increase the stability and robustness with regards to improve the robustness switching methodology is applied to feedback linearization controller. Lyapunov stability is proved in proposed controller based on switching function. To compensate for the dependence on switching parameters baseline methodology is used.The nonlinear model dynamic formulation problem in uncertain system can be solved by using artificial intelligence theorem. Fuzzy logic theory is used to estimate the system dynamic. Forward kinematics implemented the manipulator's movements. Results validated the robot's range of possible postures and trajectories
Бесплатно
Статья научная
Game-theoretic resource allocation algorithms are essential to managing the interference that Device-to-Device (D2D) and cellular transmissions could generate to each other in cellular networks since game-theoretic solutions are naturally autonomous and robust. In this paper, we present a survey on D2D communication in cellular networks with respect to the performance of the existing and accessible game-theoretic resource allocation algorithms published in 2013-2019. Each of the game-theoretic resource allocation algorithms with its properties such as utility, complexity, fairness, overhead cost, and convergence rate are reviewed and compared. The survey proved that game-theoretic solutions could be a viable strategy for practical implementation in 5G networks as each of the reviewed scheme attempts to optimize one or various essential performance metrics in the system. Finally, the paper recommends that serious efforts should be made by standardization bodies in incorporating game-theoretic strategy in D2D-enabled 5G networks while considering it as a road map for reliable and resource-efficient solutions in future cellular networks.
Бесплатно
