- Все статьи 584
Статьи журнала - International Journal of Information Engineering and Electronic Business
Все статьи: 584
Bi-gram based Query Expansion Technique for Amharic Information Retrieval System
Статья научная
Information retrieval system has been using to connect users of the information and information repository corpora. Even though the task of information retrieval systems is to retrieve relevant information, it is very difficult to find a perfect information retrieval system which is capable of retrieving relevant and only relevant documents as per user's query. The aim of this research is to increase precision of an Amharic information retrieval system while preserving the original recall. In order to achieve this bi-gram technique has been adopted for the query expansion. The main reason for performing query expansion is to provide relevant documents as per users' query that can satisfy their information need. Because users are not fully knowledgeable about the information domain area, they mostly formulate weak queries to retrieve documents. Thus, they end up frustrated with the results found from an information retrieval system. Amharic language has many meaning for a single word and also the word can be found in different form. These are some of the challenges that made the information retrieval system performing at very low level. Query expansion methods outperform in differentiating the various meanings of a polysemous term and find synonymous terms for reformulating users' query. Bi-gram technique uses the underling theory of expanding a query; using terms that appear adjacent to a query term frequently. The proposed technique was integrated to an information retrieval system. Then the retrieval system is tested with and without using bi-gram technique query expansion. The test result showed that bi-gram based method outperformed the original query based retrieval, and scored 8% improvement in total F-measure. This is an encouraging result to design an applicable search engine, for Amharic language.
Бесплатно
Big data optimization techniques: a survey
Статья научная
As the world is getting digitized the speed in which the amount of data is over owing from different sources in different format, it is not possible for the traditional system to compute and analysis this kind of big data for which big data tool like Hadoop is used which is an open source software. It stores and computes data in a distributed environment. In the last few years developing Big Data Applications has become increasingly important. In fact many organizations are depending upon knowledge extracted from huge amount of data. However traditional data technique shows a reduced performance, accuracy, slow responsiveness and lack of scalability. To solve the complicated Big Data problem, lots of work has been carried out. As a result various types of technologies have been developed. As the world is getting digitized the speed in which the amount of data is over owing from different sources in different format, it is not possible for the traditional system to compute and analysis this kind of big data for which big data tool like Hadoop is used which is an open source software. This research work is a survey about the survey of recent optimization technologies and their applications developed for Big Data. It aims to help to choose the right collaboration of various Big Data technologies according to requirements.
Бесплатно
Статья научная
Sentiment analysis, the process of determining the emotional tone of a text, is essential for comprehending user opinions and preferences. Unfortunately, the majority of research on sentiment analysis has focused on reviews written in English, leaving a void in the study of reviews written in other languages. This research focuses on the understudied topic of sentiment analysis of Bangla-language product reviews. The objective of this study is to compare the performance of machine learning models for binary and multiclass sentiment classification in the Bangla language in order to gain a deeper understanding of user sentiments regarding e-commerce product reviews. Creating a dataset of approximately one thousand Bangla product reviews from the e-commerce website 'Daraz', we classified sentiments using a variety of machine learning algorithms and natural language processing (NLP) feature extraction techniques such as TF-IDF, Count Vectorizer with N-gram methods. The overall performance of machine learning models for multiclass sentiment classification was lower than binary class sentiment classification. In multiclass sentiment classification, Logistic Regression with bigram count vectorizer achieved the maximum accuracy of 82.64%, while Random Forest with unigram TF-IDF vectorizer achieved the highest accuracy of 94.44%. Our proposed system outperforms previous multiclass sentiment classification techniques by a fine margin.
Бесплатно
Bioinformatics Analysis and Characteristics of the giant panda Interferon-alpha
Статья научная
In this report, the amino acid sequence of giant panda interferon-α (gpIFN-α) was determined and compared with 15 corresponding IFN-α sequences. Phylogenetic analysis showed that the 15 interferons fell into two large groups. The giant panda and ferret branched and were most closely related to fox and dog and evolved into a distinct phylogenetic lineage from that of eukaryotic mammalians which evolved into another lineage. After analyzing the encoded amino acid sequence of the gpIFN-α using bioinformatics, the results revealed that in the full amino acid sequence, there were no transmembrane domain, one N-glycosylation sites, eight O-glycosylation sites and nine antigenic determinants. Secondary structure analyzed showed that the Alpha helix, Extended strand, Beta turn and Random coil each occupied 60.37%(99aa), 4.88%(8aa), 9.76%, 25%(41aa) respectively. In conclusion, our results will give the opportunity to investigate more in detail function study in giant panda and add to studies on the evolution of the IFN system in vertebrates and avian more generally.
Бесплатно
Blockchain and IFPS based Secure System for Managing e-FIR
Статья научная
In recent times, various forms of crime have been happening worldwide. The law-and-order department of any country officially records a crime in electronic forms or on paper when the crime is reported by a victim or someone on behalf of the victim. The document that is prepared to file any perceptible committed crimes including dowry, kidnap, murder, rape, theft, and others is called First Information Report(FIR). Nowadays, online FIR also known as e-FIR has been used worldwide. Every day a number of e-FIR are filed, and they are maintained in a centralized database with the aid of third-party trust. Consequently, malicious entities including insiders and outsiders’ dishonest personnel, and third-party authorities may tamper with e-FIR that questions the transparency and integrity of FIR reports. To address this exposure, in this paper, we propose a blockchain based FIR system to store all kinds of offense-related records to assure security, fidelity and privacy of FIR records. In this proposed system, the blockchain technology that refers to a decentralized and distributed ledger across peer-to-peer networks continually updates the shared ledger and strictly maintains synchronization among all network nodes. Though blockchain technology guarantees tamper-proof of the data, it cannot store a large amount of data due to the replication of ledger among all network nodes. To solve this issue, we adopt the Inter-Planetary File system (IPFS) protocol to store data in the blockchain. IPFS is a distributed file-sharing system that can be leveraged to store and share large files. The blockchain based FIR system has been tested on an Ethereum environment using blockchain and IPFS technology.
Бесплатно
Body and Face Animation Based on Motion Capture
Статья научная
This paper introduces the motion capture technology and its use in computer animation. Motion capture is a powerful aid in computer animation and a supplement to the traditional key-frame animation. We use professional cameras to record the body motion and facial expression of the actor and then manipulate the data in software to eliminate some occlusion and confusion errors. As to data that is still not satisfying, we use data filter to smooth the motion by cutting some awry frames. Then we import the captured data into Motionbuilder to adjust the motion and preview the real-time animation. At last in Maya we combine the motion data and character model, let the captured data drive the character and add the scene model and music to export the whole animation. In the course of computer animation, we use this method to design the animation of military boxing, basketball playing, folk dancing and facial expression.
Бесплатно
Boosting Afaan Oromo Named Entity Recognition with Multiple Methods
Статья научная
Named Entity Recognizer (NER) is a widely used method of Information extraction (IE) in Natural language processing (NLP) and Information Retrieval (IR) aimed at predicting and categorizing words of a given text into predefined classes of Named Entities like a person, date/time, organization, location, etc. This paper adopts boosting NER for Afaan Oromo by using multiple methods. Combinations of approaches such as machine learning, the stored rules, and pattern matching make a system more efficient and accurate to recognize candidates name entities (NEs). It takes the strongest points from each method to boost the system performance by voting a candidate NE which is detected in more than 1 entity category or out of context because of word ambiguity, it penalized by Word senses disambiguation. Subsequent NEs tagged with identical tags merged as a single tag before the final output. The evaluation shows the system is outperformed. Finally, the future direction is forwarded a hybrid approach of rule-based with unsupervised zero-resource cross-lingual to enhance more.
Бесплатно
Building Consumers' Trust Based on Pick-up Goods Behavior in the Convenience Stores in Taiwan
Статья научная
With the adoption of Internet, online shopping has provided a convenience way to purchase goods or services from anywhere at any time in recent years globally. Especially, convenience stores are available for consumers to pick up goods ordered from Internet shops in Taiwan. Therefore, convenience stores have become an important success factor for increasing a lot of profit in online shopping in Taiwan. In the past, researches have indicated that consumers dare not or are not willing to purchase goods in online shopping. The reasons include the problem of security and the lack of consumers’ trust. Thus, these problems constitute a key barrier to the use of online shopping as well as long-term commitment to the relationship building. Therefore, there is a need to build up consumers’ trust in order to overcome the influential factors in online shopping. In this paper, we use statistic analysis method by questionnaires to discuss the characteristics of pick-up goods in the convenience stores and illustrate the relationship between consumers’ trust in online shopping and pick-up goods behavior in convenience stores. In our experiment, questionnaire items are measured by Likert scale. In 227 valid questionnaires, 90% participants deeply believe that pick-up goods in the convenience stores can promote consumers’ trust in online shopping.
Бесплатно
Business Process Re-Engineering in Public Administration of Kingdom of Saudi Arabia
Статья научная
The government of Saudi Arabia is in the phase of transformation. Business process reengineering (BPR) can play a vital role in assessing this conversion. BPR methodologies provide ways to optimize the use of resources while maintaining high-quality services. The aim of this paper is to investigate the introduction of BPR in Saudi Arabia public sector. A framework is proposed to transform change using a knowledge based. The proposed solution is validated through survey. The results of the survey show that Saudi Governmental Agencies acquire the power to implement the BPR successfully especially if it is implemented with knowledge management and the BPR movement started at small scale.
Бесплатно
Business decision support system based on sentiment analysis
Статья научная
Since organizational decisions are vital to organizational development, customers’ views and feedback are equally important to inform good decisions. Given this relevance, this paper seeks to automate a sentiment analysis system - SentDesk- that can aid tracking sentiments in customers’ reviews and feedback. The study was contextualised in some business organisations in Ghana. Three business organizational marketers were made to annotate emotions and as well tag sentiments to each instance in the corpora. Kappa and Krippendoff coefficients were computed to obtain the annotation agreement in the corpora. The SentDesk system was evaluated in the environment alongside comparing the output to that of the average sentiments tagged by the marketers. Also, the SentDesk system was evaluated in the environment by the selected marketers after they had tested the platform. By finding the average kappa value from the corpora (CFR + ISEAR), the average kappa coefficient was found to be 0.40 (40%). The results of evaluating the SentDesk system with humans shows that the system performed as better as humans. The study also revealed that, while annotating emotions and sentiments in the datasets, counsellor’s own emotions influences their perception of emotions.
Бесплатно
CSRFDtool: Automated Detection and Prevention of a Reflected Cross-Site Request Forgery
Статья научная
The number of Internet users is dramatically increased every year. Most of these users are exposed to the dangers of attackers in one way or another. The reason for this lies in the presence of many weaknesses that are not known for ordinary users. In addition, the lack of user awareness is considered as the main reason for falling into the attackers' snares. Cross Site Request Forgery (CSRF) has placed in the list of the most dangerous threats to security in OWASP Top Ten for 2013. CSRF is an attack that forces the user's browser to send or perform unwanted request or action without user awareness by exploiting a valid session between the browser and the server. When CSRF attack success, it leads to many bad consequences. An attacker may reach private and personal information and modify it. This paper aims to detect and prevent a specific type of CSRF, called reflected CSRF. In a reflected CSRF, a malicious code could be injected by the attackers. This paper explores how CSRF Detection Extension prevents the reflected CSRF by checking browser specific information. Our evaluation shows that the proposed solution is successful in preventing this type of attack.
Бесплатно
Статья научная
This paper presents the calculation of the classic-curvature and the intensity-curvature term before interpolation of a bivariate polynomial model function. The classic-curvature is termed as yc (x, y) and the intensity-curvature term before interpolation is termed as E0. The classic-curvature is defined as the sum of the four second order partial derivatives of the bivariate polynomial. The intensity-curvature term before interpolation is defined as the integral of the product between the pixel intensity value termed as f(0, 0) and the classic-curvature calculated at the origin of the coordinate system of the pixel. This paper presents an application of the calculation of classic-curvature and the intensity-curvature term before interpolation using two-dimensional Magnetic Resonance Imaging (MRI) data and reports for the first time in the literature on the behavior of the intensity-curvature term before interpolation.
Бесплатно
Class Complexity Metric to Predict Understandability
Статья научная
This paper presents a new class complexity metric of an Object-Oriented (OO) program which is used to predict the understandability of classes. The propose complexity metric is evaluated theoretically against Weyuker's properties to analyze the nature of metric and empirically evaluated against three small projects developed by Post Graduate (PG)/Under Graduate (UG) teams. Least Square Regression Analysis technique is performed to arrive at the result and find correlation coefficient of propose metric with the Degree of Understandability. The result indicates that the propose metric is a good predictor of understandability of classes. JHAWK TOOL (Java Code Metrics Tool) were used to evaluate the parameters values involved in propose metric and for analyzing the results of projects, Matlab6.1 and IBM SPSS software were used.
Бесплатно
Статья научная
The aim of this paper is to investigate the performance of time delay neural networks (TDNNs) and the probabilistic neural networks (PNNs) trained with nonlinear features (Lyapunov exponents and Entropy) on electroencephalogram signals (EEG) in a specific pathological state. For this purpose, two types of EEG signals (normal and partial epilepsy) are analyzed. To evaluate the performance of the classifiers, mean square error (MSE) and elapsed time of each classifier are examined. The results show that TDNN with 12 neurons in hidden layer result in a lower MSE with the training time of about 19.69 second. According to the results, when the sigma values are lower than 0.56, the best performance in the proposed probabilistic neural network structure is achieved. The results of present study show that applying the nonlinear features to train these networks can serve as useful tool in classifying of the EEG signals.
Бесплатно
Classification of the User's Intent Detection in E-commerce systems – Survey and Recommendations
Статья научная
The personalized experience gets more and more attention these days. Many e-commerce businesses are looking for methods to deliver personalized service. Consumers are expecting, if not demanding, highly personalized experiences. Moreover, customers are typically willing to spend more when they receive such a custom-tailored service. A prerequisite to provide a genuinely personalized experience is to understand the customer. Intent detection is a new and challenging approach in modern e-commerce to understand the customer. We find that various aspects of customer intent detection can be tackled by leveraging tremendous recent recommendation systems' progress. In this work, we review existing works from different domains that can be re-used for customer intent detection in the e-commerce. Even though many methods are used, there is no comparison of available approaches. Based on a review of nearly 100 articles from 2015 until 2019, we propose a categorization of types of intent detection, personalization context, building a customer profile, and dynamic changes in user interests handling. We also summarize existing methods from applicability in the e-commerce domain, including the aspect of the General Data Protection Regulation requirements. The paper aims at the classification of applied techniques and highlights their advantages and disadvantages.
Бесплатно
Classifying Similarity and Defect Fabric Textures based on GLCM and Binary Pattern Schemes
Статья научная
Textures are one of the basic features in visual searching,computational vision and also a general property of any surface having ambiguity. This paper presents a texture classification system which has high tolerance against illumination variation. A Gray Level Co-occurrence Matrix (GLCM) and binary pattern based automated similarity identification and defect detection model is presented. Different features are calculated from both GLCM and binary patterns (LBP, LLBP, and SLBP). Then a new rotation-invariant, scale invariant steerable decomposition filter is applied to filter the four orientation sub bands of the image. The experimental results are evaluated and a comparative analysis has been performed for the four different feature types. Finally the texture is classified by different classifiers (PNN, K-NN and SVM) and the classification performance of each classifier is compared. The experimental results have shown that the proposed method produces more accuracy and better classification accuracy over other methods.
Бесплатно
Client Server iOS in Player versus Player (PVP) of “Borneo Snap”
Статья научная
Borneo Snap is a Kalimantan’s animals snap card game. Play proceeds with the players taking it in turns to remove a card from the top of their deck and place it face-up on a central pile. If two cards placed consecutively on the pile are identical (same picture) then the first player to shout "Snap!"will get all of it. This game is built for the iOS platform. Game Player Versus Player (PVP) Borneo Snap using peer-to-peer API from Game Kit (XCode Framework) and Wi-Fi or Bluetooth, but actually, Borneo Snap uses client-server architecture model, each player in a player versus player game session only can communicate with server intermediaries. If the player sends data updates when playing cards to other players, this data update will first be through the server, then forwarded to all other players. The result of this research, with client-server framework Borneo Snap can be played by more than 1 player and more iOS gadget too
Бесплатно
Статья научная
In this paper, we present the design and development of a collaborative knowledge-sharing platform with Blockchain based smart contracts (CodeBlockS) to help increase the trust and efficiency of how developers find the solution to their problems or try to learn new things. The popularity of Question-and-Answer websites such as StackOverflow, Ask, and Yahoo, as well as online course websites like as Udemy, is gradually expanding. Given this increased popularity, the quality and efficiency of user interaction must be improved such that users can try to connect with each other, ask questions about technical problems they are experiencing, or if they want to learn a topic in exchange for a fee and potentially collaborate on a project, or simply share their thoughts on a topic and improve their knowledge and network at the same time. Because these contracts will contain money, CodeBlockS has employed Ethereum Blockchain-based smart contracts to manage the data and money, as blockchain-based smart contracts are immutable and handle payments very securely. In general, social networking websites there are very few people sharing valuable knowledge and many people sharing worthless, time-consuming content that creates distraction. With the CodeBlockS system, developers find the solution to their problems or try to learn new things, and users can share their thoughts and learning on the platform. The platform also provides inbuilt smart contracts functionality using which two users can create a contract where one user will teach or solve doubt of the other user and receive fees towards service rendered.
Бесплатно
Coffee Leaf Disease Recognition Using Gist Feature
Статья научная
Coffee leaf disease recognition is important as its quality can be affected by the disease like –rust. This paper presents a coffee leaf disease recognition system with the help of gist feature. This research can help coffee producers in diagnosis of coffee plants in initial stage. Rocole coffee leaf dataset is considered in this study. Input image is pre-processed first. Resize and filtering is used as pre-processing work. Gist feature is extracted from pre-processed image. Extracted features are trained with machine learning algorithm. In testing phase, features are extracted and tested with trained ML model. Simulation is done with 10 fold cross validation. Different ML models are used and selected the best among them based on performance. SVM achieved overall 99.8% accuracy in recognizing coffee leaf disease.
Бесплатно
Color Histogram and DBC Co-Occurrence Matrix for Content Based Image Retrieval
Статья научная
This paper presents the integration of color histogram and DBC co-occurrence matrix for content based image retrieval. The exit DBC collect the directional edges which are calculated by applying the first-order derivatives in 0º, 45º, 90º and 135º directions. The feature vector length of DBC for a particular direction is 512 which are more for image retrieval. To avoid this problem, we collect the directional edges by excluding the center pixel and further applied the rotation invariant property. Further, we calculated the co-occurrence matrix to form the feature vector. Finally, the HSV color histogram and the DBC co-occurrence matrix are integrated to form the feature database. The retrieval results of the proposed method have been tested by conducting three experiments on Brodatz, MIT VisTex texture databases and Corel-1000 natural database. The results after being investigated show a significant improvement in terms of their evaluation measures as compared to LBP, DBC and other transform domain features.
Бесплатно
2024 ©