Ahmed Zouinkhi

Prof. Dr. Ahmed Zouinkhi

National school of engineering of gabes, Gabès, Tunisia
orcid

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 October 2016 in Concurrent Engineering
Verified
Journal Article
Closed access
STSourour TRAB Trab
Sourour TRAB Trab
EBEddy Bajic
Eddy Bajic
AZAhmed Zouinkhi
Ahmed Zouinkhi
ATAndré Thomas
André Thomas
MAMohamed Naceur Abdelkrim
Mohamed Naceur Abdelkrim
RLRadhouane Hadj Ltaief
Radhouane Hadj Ltaief
A communicating object, or connected object, is a key element of the Internet of Things to shift a perceptible real world into a wide digital virtual world known as the cyber-physical system. Knowing that sustainability, safety, and logistic issues are among the significant goals and challenges of modern industrial enterprises, the communicating object can be a relevant concept to guarantee safety performance in logistics and warehouse management. This article presents the impacts and advantages of the communicating object in smart logistics and the design of a communicating object model inspired from Internet of Things European research projects, which controls and monitors safety risks in a hazardous and chemical industrial context. Generic safety-based scenarios are presented, which rely on a set of negotiated interaction mechanisms for storage and picking. The relevant deployment of intelligence in a warehouse management system leads to propose a new concept called “IoT-controlled Safe Area.” Our contribution is to bring informational, communicational, and decisional capabilities close to the warehousing physical world thanks to the communicating object. This enables achieving safety assurance with a decrease in the decision-making delay and an increase in the solving efficiency of local and dynamic disruptions, while avoiding inherent shortcomings of the warehouse management system centralization. For this, an industrial implementation is presented.

1 January 2015 in Procedia Computer Science
Verified
Journal Article
Open access
STSourour Trab
Sourour Trab
EBEddy Bajic
Eddy Bajic
AZAhmed Zouinkhi
Ahmed Zouinkhi
MAMohamed Naceur Abdelkrim
Mohamed Naceur Abdelkrim
HCHassen Chekir
Hassen Chekir
RLRadhouane Hadj Ltaief
Radhouane Hadj Ltaief
One of the most relevant topics in warehouse management system (WMS) is the security issue and concerns the optimal placement allocation of products with respect of product and human safety in a sustainable system. Knowing that differences often exist between virtual view of products placements in centralized WMS and the real situation in the facility due to unplanned movements resulting from human errors or products’ misplacements, we propose a reactive and compatibility constraint approach for product storage allocation. Our aim is to reduce the size of floating locations largely used in WMS and to avoid the inherent risks of hazardous accidents which can be generated by incompatibility between products and then to minimize the total logistic costs and to guarantee higher warehousing service levels in a safety monitored environment. This work proposes a multi-agent architecture for product allocation planning with compatibility constraints (PAP/CC), which uses a decision mechanism for product's placement, based on negotiations between agents associated to compatibility tests. This approach represents an improvement key for decentralized management of warehouses in a dynamic and reactive environment. Negotiations mechanisms relying on an Internet of Things (IoT) infrastructure and multi agent systems are defined in order to solve security problem of product allocation operations. Industrial deployment of IoT platform represents an ideal solution for decentralized management and to support collaboration between products and shelves. A simulation case of the proposed interactions mechanisms is provided with the use of NetLogo environment which offers many advantages to control agents and to describe their interactions in a graphical environment

1 January 2018 in International Journal of Embedded Systems
Verified
Journal Article
Closed access
STSourour Trab
Sourour Trab
EBEddy Bajic
Eddy Bajic
AZAhmed Zouinkhi
Ahmed Zouinkhi
MAMohamed Naceur Abdelkrim
Mohamed Naceur Abdelkrim
HCHassen Chekir
Hassen Chekir
Security and risk management in warehouses and logistics is a key factor to achieve a sustainable and safe supply chain. The paper aims at proposing RFID-IoT-enabled warehouse management focused on safety assurance for goods and people leveraging product class-based storage (pCBS), communicating object, RFID and IoT components. Security issues between products, storage locations, transportation equipment, environment and people are handled with the use of potential fields methods associated with smart product management in RFID-IoT warehouse architecture. A dynamic calculation of suitable storage locations is proposed, founded on negotiation mechanisms between products and shelves and their availability and compatibility constraints according to pCBS method. A safe and secure product storage path discovery method is presented using attractive/repulsive potential fields for path minimisation while maximising security level along the way. A multi-agent-based simulation with NetLogo demonstrates the effectiveness of the proposal allowing to achieve safe warehouse management by using smart product reactivity against critical risks.

27 August 2019 in International Journal of Communication Systems
Verified
Journal Article
Closed access
PDF file
AZAhmed Zouinkhi
Ahmed Zouinkhi
HAHayfa Ayadi
Hayfa Ayadi
TVThierry Val
Thierry Val
BBBoumedyen Boussaid
Boumedyen Boussaid
MAMohamed Naceur Abdelkrim
Mohamed Naceur Abdelkrim

1 December 2015
Verified
Conference Paper
Closed access
HAHayfa Ayadi
Hayfa Ayadi
AZAhmed Zouinkhi
Ahmed Zouinkhi
BBBoumedyen Boussaid
Boumedyen Boussaid
MAM Naceur Abdelkrim
M Naceur Abdelkrim
Wireless sensor networks are gaining more and more attention these days. They gave us the chance of collecting data from noisy environment. So it becomes possible to obtain precise and continuous monitoring of different phenomenons. However wireless Sensor Network (WSN) is affected by many anomalies that occur due to software or hardware problems. So various protocols are developed in order to detect and localize faults then distinguish the faulty node from the right one. In this paper we are concentrated on a specific type of faults in WSN which is the outlier. We are focus on the classification of data (outlier and normal) using three different methods of machine learning then we compare between them. These methods are validated using real data obtained from motes deployed in an actual living lab.

20 December 2020
Verified
Conference Paper
Closed access
IAImen Azzouz
Imen Azzouz
BBBoumedyen Boussaid
Boumedyen Boussaid
AZAhmed Zouinkhi
Ahmed Zouinkhi
MAM. Naceur Abdelkrim
M. Naceur Abdelkrim
Wireless Sensor Networks are deployed in harsh environments. Their key advantage is there flexibility and low cost. But they can face many failures which created the need to improve data accuracy. Many artificial intelligence techniques has demonstrated impressive results in fault detection and faults diagnosis. Lately, machine learning emerged as a powerfull artificial intelligence based technique to solve the problem of failures in WSN. In this paper, a multi-fault classification is evaluated using deep learning technique based on LSTM classifier and then compared with different machine learning techniques such as Support Vector Machine (SVM), Random Forest (RF), Multilayer Perceptron (MLP)and Probabilistic Neural Network (PNN). The performance of this mentioned techniques used for fault detection in WSNs were compared based on four metrics: Detection Accuracy (DA), True Positive Rate (TPR), Matthews Correlation Coefficients (MCC)and False Alarm (FA).