Claim Missing Document
Check
Articles

Found 3 Documents
Search

Performance evaluation of machine learning algorithms for meat freshness assessment Arsalane, Assia; Klilou, Abdessamad; Barbri, Noureddine El
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 5: October 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i5.pp5858-5865

Abstract

In meat industry, a non-destructive evaluation and prediction of meat quality attributes is highly required. Artificial vision technology is a powerful and widely used tool for meat quality evaluation because of reliability, reproducibility, non-invasiveness, and non-destructiveness. Machine learning methods are a fundamental and crucial part of artificial vision technology. Their choice is critical in determining successfully the quality of meat. The goal of this paper was to compare the performance of three artificial intelligence-based methods to evaluate the beef meat freshness. In this research, a dataset of beef meat samples images was used to extract the color and texture features. Different methods including the support vector machines (SVM), k-nearest neighbor (KNN), and naïve Bayes (NB) algorithms were applied to determine the freshness of samples. The accuracy rates of KNN, SVM and NB algorithms were obtained about 92.59%, 90.12% and 87.65%, respectively. The results show that the KNN provides the highest classification rates against SVM and NB algorithms.
Traffic signs detection and prohibitor signs recognition in Morocco road scene Taouqi, Imane; Klilou, Abdessamad; Chaji, Kebir; Arsalane, Assia
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 6: December 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i6.pp6313-6321

Abstract

Traffic sign detection is a crucial aspect of advanced driver assistance systems (ADAS) for academic research and the automotive industry. seeing that accurate and timely detection of traffic signs (TS) is essential for ensuring the safety of driving. However, TS detection methods encounter challenges like slow detection speed and a lack of robustness in complex environments. This paper suggests addressing these limitations by proposing the use of the you only look one version 7 (YOLOv7) network to detect and recognize TS in road scenes. Furthermore, the k-means++ algorithm is used to acquire anchor boxes. Additionally, a tiny version of YOLOv7 is used to take advantage of its real-time and low model size, which are required for real-time hardware implementation. So, we conducted an experiment using our proprietary Morocco dataset. According to the experimental results, YOLOv7 achieves 85% in terms of mean average precision (mAP) at 0.5 for all classes. And YOLOv7-tiny obtains 90% in the same term. Afterward, a recognition system for the prohibitive class using the convolutional neural network (CNN) is trained and integrated inside the YOLOv7 algorithm; its model achieves an accuracy of 99%, which leads to a good specification of the prohibitive sign meaning.
Improved automated parallel implementation of GMM background subtraction on a multicore digital signal processor Bariko, Smail; Klilou, Abdessamad; Abounada, Abdelouahed; Arsalane, Assia
International Journal of Reconfigurable and Embedded Systems (IJRES) Vol 13, No 3: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijres.v13.i3.pp552-559

Abstract

Scene segmentation is an essential step in a wide range of video processing applications, for instance, object recognition and tracking. The Gaussian mixture model (GMM) for background subtraction (BS) has gained widespread usage in scene segmentation, despite its known computational intensity. To tackle this challenge, we propose a practical solution to accelerate processing through a parallel implementation on an embedded multicore platform. In this paper, we present an improved automated parallel implementation of the GMM algorithm using the Orphan directive provided by open multiprocessing (OpenMP). Experimental assessments conducted on the eight cores of the C6678 digital signal processor (DSP) demonstrate significant advancements in parallel efficiency, particularly when handling high-resolution frames, including high-definition (HD) and full-HD resolutions. The achieved parallel efficiency surpasses the results obtained with classical OpenMP scheduling modes, encompassing dynamic, static, and guided approaches. Specifically, the parallel efficiency reaches approximately 82% for full-HD resolution frames and, 99.3% for low-resolution frames, respectively.