EAI Endorsed Transactions on Scalable Information Systems

EcomFraudEX: An Explainable Machine Learning Framework for Victim-Centric and Dual-Sided Fraud Incident Classification in E-Commerce

Salman Farsi, Mahfuzulhoq Chowdhury — Mon, 20 Jan 2025 00:00:00 +0000

The popularity of e-commerce businesses and online shopping is experiencing rapid growth all around the world. Nowadays, people are more inclined to shop online than in the actual shops. Due to this advancement, fraudsters have set new traps to deceive consumers. Whether it is true that customers often become victims of fraud, it also happens that a fraud customer tries to deceive the seller and hassle the seller intentionally in several ways. To address these issues, an automated system is required so that fraud incidents can be classified. This will facilitate taking legal action and reporting to consumer rights authorities. Existing research on fraud detection and prevention didn't cover customer and seller-side fraud simultaneously. Besides, most of the work focused on fraud detection rather than post-fraud incident classification. To overcome these gaps, this research endeavor conducts a thorough online survey of customers and sellers to gather incident-specific victim data on fraud cases and it addresses the issue for both customer and seller. This paper proposes a machine learning (ML) based explainable fraud incident classification framework EcomFraudEX, that can efficiently classify these fraud incidents and analyze the reason behind each incident. This framework particularly focuses on proper feature selection techniques, hyper-parameter tuning of models, and exploring different ML and ensemble models. Ensemble majority voting schemes consisting of Random Forest (RF), XGBoost, and CatBoost achieved the highest F1-score of 96% with the Chi-Square feature selection technique in the customer complaint dataset and 98% with the RF feature selection technique in the seller complaint dataset. To explain the incident reasoning, Local Interpretable Model Agnostic Explanation (LIME) and Shapely Additive Explanation (SHAP) were further utilized. The proposed scheme achieved a 1.57% higher F1-score and 2.13% higher accuracy than previous works.

Efficient DNA-Based Logistic Mapping Algorithm for Color Image Encryption

Aya Goudjil, Aicha Benyoucef, M'Hamed Hamadouche, Mohamed Amine Riahla — Thu, 13 Feb 2025 00:00:00 +0000

INTRODUCTION: Color images hold significant information and are widely used in diverse domains. The protection of these images against unauthorized access over the internet is a necessity that relies on encryption techniques. However, traditional encryption methods face challenges with the increasing capability and efficiency of quantum computing to solve complex problems. DNA cryptography is a promising field in information security, utilizing DNA molecules with massive parallelism and vast storage capacity to encode and decode information. While chaotic systems have been widely used in encryption due to their sensitivity to initial conditions and parameter values, resulting in unpredictability and significant variation. Exploiting the characteristics of DNA cryptography and chaotic systems is a promising alternative for securing data. Nevertheless, current methodologies exhibit limitations such as a small key space and weak resistance to differential attacks.
OBJECTIVES: This paper addresses these gaps by proposing an RGB image encryption algorithm based on DNA cryptography and a 1D logistic map.
METHODS: The proposed method randomly generates a DNA encoding/decoding table to generate the row-column permutation of the image. After the permutation of the image, the logistic map is used to generate three keys for RGB channels and seven DNA encoding-decoding rules, three are used to encode the keys into DNA sequence, the second three to encode the image RGB channel, and the last to perform the DNA-XOR operation. Finally, decode the result into integers using the DNA encoding/decoding table and generate the encrypted image.
RESULTS: The analysis of the proposed technique demonstrates significant robustness against various attacks, as evidenced by metrics such as a key space exceeding 2100, an average NPCR of 99.613667%, an average UACI of 50.273742%, an entropy value approaching 8, and a strong key sensitivity.
CONCLUSION: These results validate its capacity to effectively resist differential, brute-force, and statistical attacks.

Virtual reality simulation research on the quality and strength of the riveting process for the top cover accessory of battery pack

Wang Yang-qing, Tang Wenke, Ning Shui-gen, Cao Bing-xin — Wed, 12 Feb 2025 00:00:00 +0000

INTRODUCTION: Based on the riveting theory, a 3D model of the riveting structure was established, and the riveting process of three kinds of plate thickness was simulated by Deform-3D virtual simulation, and the theoretical values of the key parameters of the riveting structure were obtained.

OBJECTIVES: Through the tensile and shear tests of riveted samples, it was found that the simulation theory of key parameters of riveting was close to the experimental values, which showed the feasibility of the simulation.

METHODS: Through the experiment, it was further found that the shear strength and tensile strength were increased with the increase of plate thickness.

RESULTS: The shear strength and tensile strength of a 1.5mm thick plate were increased by 81.2% and 35.2%, respectively, compared with that of a 1.0mm thick plate. The shear resistance and tensile strength of the 2.0 mm thick plate were 111.4% and 54.5% higher than that of the 1.0 mm thick plate.

CONCLUSION: During the experiment, it was not found that the upper and lower plates were separated directly, but the neck of the riveted joint was directly broken.

Design and Simulation of Quasi-microstrip Yagi Antenna in Railway Mobile Communication

Junhua Shao, Qiang Li, Junmei Tan — Thu, 16 Jan 2025 00:00:00 +0000

PROBLEM STATEMENT: The performance and size constraints of the current railway mobile communication systems force the development of more effective communication methods.

OBJECTIVES: This study aims to build a quasi-microstrip Yagi antenna with a 900MHz centre frequency that minimizes the antenna's physical dimensions and improves communication capabilities between trains.

METHODS: HFSS simulation was used during the design phase to optimize the antenna's characteristics, which included bending the active oscillator to increase gain. Important performance indicators were assessed, including voltage standing wave ratio (VSWR), bandwidth, and return loss.

RESULTS: The optimized antenna produced a VSWR of less than 2, a maximum gain of 8.35dB, a bandwidth of 105MHz (spanning from 845MHz to 950MHz), and a return loss of -19.49dB at the centre frequency. According to these results, the antenna satisfies the operating criteria for railway mobile communication.

CONCLUSION: The quasi-microstrip Yagi antenna proves useful in engineering applications since it not only meets the communication requirements of railway systems but also shrinks considerably in size compared to conventional Yagi antennas.

Digital Innovation in Admission Processes based on an Architectural Model of Information Security using Blockchain Technology

Tue, 25 Feb 2025 00:00:00 +0000

INTRODUCTION:

The digital transformation in higher education, particularly in admission processes, has raised concerns about data integrity and security. In Peru, public universities face challenges in ensuring transparency and protecting sensitive information during admissions. This research proposes an innovative solution using BLOCKCHAIN technology to enhance data security and integrity.

OBJECTIVES:

The study aims to develop a digital innovation proposal based on an architectural model of information security, specifically to (1) ensure data integrity and confidentiality, (2) propose a secure online admission process, and (3) analyze current admission processes (AS-IS) while designing an improved model (TO-BE) with BLOCKCHAIN technology.

METHODS:

This study follows a quantitative approach, aiming to implement digital innovation through an architectural information security model to ensure data integrity in admission processes. To achieve this, BLOCKCHAIN technology is applied, known for its ability to securely record transactions and enhance data transparency and security. A proposed eight-phase process was then developed, focusing on an architectural model for secure information handling, incorporating BLOCKCHAIN for data transparency.

RESULTS:

The proposed model significantly improves data integrity and security, ensuring transparency and reducing fraud risks. The TO-BE process addresses vulnerabilities in the current system, offering a more efficient framework for managing sensitive data throughout the admission phases.

CONCLUSION:

Public universities in Peru must adopt BLOCKCHAIN technology to safeguard data integrity in admissions. The proposed model offers a robust solution for secure and reliable online processes, with potential for a transformative impact.

Exploring Social Media Research Trends in Malaysia using Bibliometric Analysis and Topic Modelling

Thu, 02 Jan 2025 00:00:00 +0000

This study explores the evolving dynamics of social media research in Malaysia. The main objective is to identify trends and patterns in research, specifically examining the volume and focus of scholarly articles over the last decade. Using bibliometric analysis and topic modelling, the study identifies major research clusters and key themes like digital marketing, political communication, and public health, and to map out collaborations among researchers. The findings show a significant increase in social media-related studies, highlighting a trend towards more varied and complex topics. This includes a greater emphasis on social media's role in political communication, consumer behaviour, and crisis management. Looking forward, this study suggests that future studies should explore the applications of emerging technologies such as artificial intelligence (AI) on social media practices, assess the spread and impact of negative information such as fake news and hate speech, and extend cross-disciplinary methodologies to fully understand the extensive effects of social media.