- All articles 719
-
International Journal of Information Engineering and Electronic Business @ijieeb
Journal articles - International Journal of Information Engineering and Electronic Business
All articles: 719
Scientific article
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.
Free
Failures in Cloud Computing Data Centers in 3-tier Cloud Architecture
Scientific article
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.
Free
Scientific article
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.
Free
Feature Engineering based Approach for Prediction of Movie Ratings
Scientific article
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.
Free
Scientific article
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.
Free
Feature Selection for Fraud Detection: Improving Machine Learning Capabilities on Portable Wallet
Scientific article
The rapid growth of mobile wallet usage has led to a sharp increase in fraudulent transactions, making fraud detection in portable wallets a pressing concern. Accurately detecting fraud is difficult because transaction data is complicated and unbalanced. Conventional rule-based systems are less flexible and frequently provide large false positive rates along with poor accuracy. Effective feature selection is crucial to the performance of Machine Learning (ML) models, notwithstanding their increased detection rates. Redundancy and noise are introduced by high-dimensional data, which lowers model performance and raises computing costs. The advantages of hybrid feature selection are frequently overlooked in current research, particularly when it comes to portable wallet fraud detection. By combining Random Forest Importance, LASSO Regression, Recursive Feature Elimination (RFE), and Mutual Information (MI) with resampling to solve class imbalance, this study fills that gap. Our approach provides a more reliable and effective solution for safe portable wallet fraud detection by removing superfluous features, increasing accuracy, and reducing computing cost. The model becomes faster and more effective when superfluous characteristics are eliminated because this reduces the computational effort. By concentrating just on the most instructive data, it increases accuracy. By addressing class imbalance and combining several selection strategies, the hybrid approach guarantees robustness. All things considered, this leads to a scalable and safe fraud detection system for transactions using mobile wallets. Our results show that a successful feature selection approach improves fraud detection accuracy, which in turn improves operational effectiveness and financial security.
Free
Financial Forecasting with Deep Learning Models Based Ensemble Technique in Stock Market Analysis
Scientific article
In recent years, deep learning techniques have emerged as powerful tools for analyzing and predict- ing complex patterns in sequential data across various fields. This study employs an ensemble of advanced deep learning models: Long Short-Term Memory (LSTM), Bi-Directional LSTM, Gated Recurrent Unit (GRU), LSTM Convolutional Neural Network (CNN), and LSTM with Self-Attention, to enhance prediction accuracy in time series forecasting. These models are applied to three distinct financial datasets: Tata Motors, HDFC Bank, and INFY.NS, we conduct a thorough comparative analysis to assess their performance. Utilizing K-fold cross-validation, we convert loss (MSE) into RMSE and MAPE, which help estimate accuracy .we achieved train accuracies of 97.46% for Tata Motors, 75.93% for INFY.NS, and 56.60% for HDFC Bank. Our empirical results highlight the strengths and limitations of each model within the ensemble framework and pro- vide valuable insights into their effectiveness in capturing complex patterns in financial time series data. This research underscores the potential of deep learning-based ensemble techniques for improving stock price forecasting and offers significant implications for investors and the development of sophisticated trading and risk management systems.
Free
Finite State Machine Model in Jungle Adventure Game an Introduction to Survival Skills
Scientific article
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.
Free
Folding Bicycle Prospective Buyer Prediction Model
Scientific article
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.
Free
Forecasting of Indonesian Digital Economy based on Available New Start-up
Scientific article
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.
Free
Scientific article
Advanced Metering Infrastructure (AMI) connects smart meters, data concentrator units, and utility control centers through persistent two-way communication. This architecture improves demand response and distributed-energy management, but it also exposes resource-constrained meters to replay, false-data injection, physical extraction, and long-term key compromise. This article develops a formally verified and statistically evaluated lightweight AMI authentication and key agreement protocol for resource-constrained smart-grid deployments. We first reconstruct the AMI authentication workflow as a four-message lightweight authenticated key exchange and map each entity, message, and key dependency to a smart-grid deployment model guided by NISTIR 7628 and IEC 62351. We then identify replay-within-window exposure, insufficient responder freshness, weak identity-to-key binding, missing key-compromise impersonation protection, and retrospective session-key recovery. To address these weaknesses, we propose AMI-AKE, a transcript-bound protocol using ephemeral Curve25519 contributions, session identifiers, nonce and timestamp binding, binding signatures, and separate key-derivation function (KDF) outputs for encryption and integrity. ProVerif-style verification queries and an extended Canetti-Krawczyk (eCK)-oriented game proof are provided for mutual authentication, secrecy, forward secrecy, and key-compromise impersonation (KCI) resistance. A Contiki-OS and ARM Cortex-M4 benchmark with 1,000 repeated trials reports 18.4 +/- 1.2 ms authentication latency, 542 +/- 9.1 sessions/s throughput, and 99.2 +/- 0.4% false-data-injection detection under controlled prototype conditions. The proposed design replaces subjective security labels with objective metrics, confidence intervals, and a reproducible simulation plan for 1,000-10,000 smart meters.
Free
Formation of Innovativeness for the Business Processes of Enterprise Using Data Processing
Scientific article
The article discusses the issues of development and analysis of diagnostic procedures for business processes during enterprise management. The digitalization has become a priority at the state level of every country, influencing the daily lives of citizens and the enterprises activity. As a result, the ability to gather, analyze, process, and use the data has taken center place to support effective decision-making and sustain competitive market positions. The article considers the factors influencing the choice of data processing tools, analyses the difficulties faced during the data processing methods implementation, and outlines the essential features of such systems for effective management of enterprise activity. The main attention was paid to the development of a data processing method during the state diagnosis of business processes in case of assessing their compliance. The method involves calculating the probability density function for the costs of restoring the normal functioning of business processes and statistical characteristics of the probability of correct decision-making. Additionally, the article includes numerical examples demonstrating the use of this method to the business processes of an aviation enterprise engaged in providing and performing technological procedures for the operation of aircraft. The proposed data processing model can be used to analyze the efficiency of enterprises’ business processes and make decisions on organizational structure optimization to minimize the costs spent by enterprise.
Free
Framework for Evaluating Business Processes Modeling Techniques under Neutrosophic Environment
Scientific article
In today's, dynamic business environment and complexity of its operations make the need for modeling Business Processes (BP) is a very critical. Modeling BP is a very important task for improving BP and achieving business needs and goals. BP modeling techniques are necessary for making BP more understandable and easily maintainable which lead to successful Business Process Management (BPM). There many types of modeling techniques for expressing and modeling business process. However, each one has its own characteristics and not all modeling techniques are suitable to all parts of the process. Therefore, it is critical to determine the right and suitable modeling technique. The problem of evaluating BP modeling techniques has been addressed by many researches. However, there is need to handle uncertainty and take into account costs and benefits of BP modeling techniques during the evaluation process. This work aims to introduce different types of BP modeling techniques and present different views of characteristics, features and quality criteria of BPmodeling techniques that can help the modeler during the evaluation process. Also, this work aims to adapt and introduce neutrosophic framework to handle uncertainty and remove confusion during evaluating and determining the BP modeling suitable technique. Moreover, the proposed framework utilizes the neutrosophic benefits and costs method with simple way to improve its use and to balance between benefits and costs during the evaluation process. The proposed framework is applied to a real world case study and the results concluded that the proposed framework can be adopted by business organizations and institutes that need for determining the suitable BP modeling technique to improve their business processes. Also, the results concluded that the utilization of proposed framework can be helpful for handling uncertainty during the evaluation process.
Free
Framework for an E-Voting System Applicable in Developing Economies
Scientific article
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.
Free
Scientific article
The rise of FinTech lending in India has transformed credit access, yet studies examining customer experiences with artificial intelligence (AI)-enabled FinTech lending platforms remain limited. This study investigates the key drivers of user experience and the evolving sentiment toward AI-enabled lending platforms by analysing online reviews from 2017 to 2024 using LDA topic modelling and lexicon-based longitudinal sentiment analysis. Twelve key topics emerged, revealing significant negative sentiment around customer support, eligibility checks, documentation, repayment, and app trustworthiness. In contrast, app usability and interface design maintained strong positivity, while loan approval and disbursement processes saw declining sentiment. Despite these pain points, overall user experience remained positive, indicating that the perceived benefits such as speed, efficiency, and convenience provided by these platforms outweighed concerns like high interest rates, privacy risks, and poor customer service. The findings highlight a nuanced balance between technological advantages and operational shortcomings, offering insights for improving AI-enabled lending platforms.
Free
Fuzzy Stability and Synchronization of New 3D Chaotic Systems
Scientific article
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.
Free
Fuzzy entropy based MOORA model for selecting material for mushroom in viet nam
Scientific article
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.
Free
Scientific article
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
Free
Scientific article
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.
Free
GenAI-Driven Interview Performance Assessment: Revolutionizing Recruitment with AI Insights
Scientific article
This paper proposes IPAMS (Interview Performance Assessment using Gen AI), which is an AI-driven platform that automates interview evaluations using advanced technologies like Convolutional Neural Networks (CNN) to gain insights on facial emotions and expressions, Large Language Models (LLM) to generate and process interview questions, YOLO (You Only Look Once) for real-time object detection, and APIs for speech-to-text transcription and behavioral analysis. The system captures video responses and analyzes key elements such as sentiment, speech patterns, body posture, and facial expressions, generating a detailed report. This report highlights a candidate’s strengths and areas of improvement and is sent directly to their email with actionable insights. IPAMS modernizes recruitment by providing unbiased assessments, saving time and resources for recruiters. For candidates, it offers a valuable mock interview tool, delivering feedback on technical skills, confidence, stress levels, and nonverbal communication. By combining cutting-edge AI and analytics, IPAMS delivers an efficient, objective, and insightful solution for recruitment and self-assessment, benefiting all stakeholders in the interview process.
Free
