A New Centralized Detection-Based Process for Evaluating Anomalies and Analyzing the First Causes

Aug 5, 2026

Upload by Himbo

Many works focus on improving data performance in computing, especially techniques that use machine learning to evaluate big data and refine how results are measured across security, quality of service, data synchronization, scalability, and data structuring. This work strengthens prior big-data and safety processes by improving the analysis of causes behind frauds and intrusions that disrupt data traffic. The approach enhances machine learning with expert-set thresholds and integrates knowledge to interpret anomaly causes, aiming to raise anomaly detection rates while reducing human operational effort.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Anomalies Detection (AD)

Deep Causes Analysis (DCA)

Proposed anomaly detection workflow

Paper—ANew Centralized Detection-Based Process for Evaluating Anomalies and Analyzing the First… A New Centralized Detection-Based Process for Evaluating Anomalies and Analyzing the First Causes Using Machine Learning and Web Semantic [https://doi.org/10.3991/ijoe.v19i03.30079](https://doi.org/10.3991/ijoe.v19i03.30079) Abdellatif Lasbahani1(􀀍), Rachid Tahri2, Abdessamed Jarrar3, Youssef Balouki2 1Laboratory EMI, University Sultan Moulay Slimane, Beni Mellal, Morocco 2Faculty of Sciences and Techniques, Hassan First University, Settat, Morocco 3Faculty of Sciences, Mohammed First University, Oujda, Morocco [abbdellatif.lasbahani@gmail.com](abbdellatif.lasbahani@gmail.com) Abstract—In the last decades, many works have been done to enhance data performances in the computer field. Data performance consists to describe all improvements which can be added to data traffic. More precisely, we are talking about techniques allowing improving the evaluation of big data using machine learning. Data evaluation is composed of several variables such as security, quality of service, data synchronization, scalability, and data structuring. In this work, we complete our proceedings done to supervise the continuity of technological evolution in terms of big data and safety. In other words, we aim to add brick to our previous processes to take into consideration the enhancement of the analysis of the causes generating frauds and intrusions preventing data traffic. To achieve this end, we increase current machine learning techniques with prior knowledge based on data thresholds set by experts in the first place. We also aim to integrate knowledge facilitating the interpretation of the causes causing all kinds of anomalies in the second place. Finally, our process will be endowed with the requirements to improve the rate of detection of anomalies and reduce human involvement operation. Keywords—anomaly detection, semantic web, knowledge graphs, machine learning, frauds and intrusions, prior knowledge, data thresholds, deep cause’s analysis 1 Introduction Recently, we have assisted a technological growth in several topics. As an example, we focus on the field of the Internet of Things (IoT), which has seen an emergence and technological remarkable migration. These IoTs components constantly create and generate data which focuses on the description of the statue, the environment and the context of this data. For this purpose, there are a variety of components integrating the principle and logic of the Internet of Things such as sensors. Sensors monitoring systems have deployed into almost industries, a variety of research domain and applications as healthcare and logistics. Such technology can give useful information’s Paper—ANew Centralized Detection-Based Process for Evaluating Anomalies and Analyzing the First… into an institution’s physical objects and the connection and interaction between these objects. However, awareness in the industrial environment has become an obligation requiring placing and implementing more intelligent objects or sensors integrating data analysis. Data-driven investing provides a valuable position for companies that have this advantage. From a safety point of view, there are two more gifted methods; we find the Anomalies Detection (AD) and Deep Causes Analysis (DCA), which ensure theirregular investigation of the data. Indeed, these methods and tools are becoming more accessible and available in order to add more considerations to the data in the analysis phase and even implementation in the field of exploitation. Anomalies Detection is a step in data mining process which consists of identifying data points, events, and / or observations that deviate from a dataset’s normal behavior. In other words, this processus can indicate critical incidents distributed over several types such as a technical glitch, or potential opportunities, for instance a change in consumer behavior, also identifying behavior

FAQs

What problem does the proposed process address?

It addresses improving evaluation of anomalies in big data by analyzing the first causes behind frauds and intrusions that disrupt data traffic, while enhancing anomaly detection performance and reducing manual effort.

How does the work improve machine learning for anomaly evaluation?

It augments current machine learning techniques with prior knowledge, using expert-defined data thresholds as an initial guidance for evaluation.

What role do AD and DCA play in the approach?

AD identifies data points or events that deviate from normal behavior, while DCA guides correction by helping resolve the real causes behind the detected anomaly.

Aug 5, 2026

Upload by Himbo