Explore the vast range of titles available.

Convolutional Neural Networks (CNNs) are widely regarded as one of the most effective solutions for image classification. However, developing high-performing systems with these models typically requires a substantial number of labeled images, which can be difficult to acquire. In image classification tasks, insufficient data often leads to overfitting, a critical issue for deep learning models like CNNs. In this study, we introduce a novel approach to addressing data scarcity by leveraging semi-supervised classification models based on Generative Adversarial Networks (SGAN). Our approach demonstrates significant improvements in both efficiency and performance, as shown by variations in the evolution of decision boundaries and overall accuracy. The analysis of decision boundaries is crucial, as it provides insights into the model’s ability to generalize and effectively classify new data points. Using the MNIST dataset, we show that our approach (SGAN) outperform CNN methods, even with fewer labeled images. Specifically, we observe that the distance between the images and the decision boundary in our approach is larger than in CNN-based methods, which contributes to greater model stability. Our approach achieves an accuracy of 84%, while the CNN model struggles to exceed 72%.

The aim of the present study is the first to evaluate the ecotoxic state of the marine environment in Anza-Taghazout coasts (Morocco) after installation of two wastewater treatment plants using a natural population of marine bivalves Mytilus galloprovincialis . These coasts are exposed to many discharges generating, thus, different sources of pollutants. These pollutants can modulate the physiological responses of marine bivalves to environmental stress. In this context, a multibiomarker approach consisting of a battery of biomarker evaluation was used to assess the response of these species to stress. In the whole soft tissues of M. galloprovincialis , four biomarkers were evaluated as follows: acetylcholinesterase (AChE), glutathione S-transferase (GST), catalase (Cat), and malondialdehyde activity (MDA). In parallel, physico-chemical parameters were measured in the marine water of Anza-Taghazout within three selected sites: S 1 considered as “hotspot” located at Anza city; S 2 located near of Aourir city; and the third site, S 3 “reference” located in Imouran beach. Our results showed that activities of both glutathione S-transferase and catalase were higher in M. galloprovincialis collected from site S 1 , but high values of malondialdehyde and acetylcholinesterase activities were observed successively at S 3 and S 2 . Application of integrated biomarker response (IBR) index was suitable for classifying the stress response in the M. galloprovincialis but did not allow to evaluate the level of the xenobiotic exposure in the studied sites. The statistical results did not show any significant differences between the three studied sites, and therefore, S 1 has recently become clean due to the installation of two wastewater treatment plants.

The Bay of Agadir, located in Morocco, is of significant economic and ecological value, yet it has faced persistent pollution challenges due to industrial, port, and tourism activities. Despite recent improvements following the implementation of wastewater treatment plants, particularly in the Anza-Imouran sector, knowledge gaps remain regarding the interactions between marine environmental factors and pollution biomarkers in marine organisms. This study examines the influence of environmental factors on the biomarker responses of Mytilus galloprovincialis across three sites (Anza, Aourir, and Imouran) in Agadir Bay, covering the period from January 2017 to December 2018. Principal Component Analysis (PCA) was employed to explore the relationships between four key biomarkers (Catalase (CAT), Glutathione S-transferase (GST), Malondialdehyde (MDA), and Acetylcholinesterase (AChE)), and seven marine environmental factors (water temperature, air temperature, salinity, pH, dissolved oxygen, electrical conductivity, and precipitation). At Anza, Aourir, and Imouran, the first two principal components explained a significant portion of the total variance (80.19%, 78.63%, and 88.60%, respectively). Notable findings include a negative correlation between GST and water temperature ( r  = − 0.57) at Anza. In Aourir, CAT exhibited a positive correlation with rainfall and dissolved oxygen ( r  = 0.78 and r  = 0.41, respectively) but a negative correlation with pH and salinity ( r  = − 0.58 and r  = − 0.44, respectively). Additionally, GST was positively correlated with rainfall ( r  = 0.52), while showing a negative relationship with pH and water temperature ( r  = − 0.40 and r  = − 0.53, respectively). MDA was negatively correlated with salinity ( r  = − 0.59), and AChE was inversely associated with electrical conductivity ( r  = − 0.41). In Imouran, CAT was positively correlated with rainfall ( r  = 0.70), while exhibiting negative correlations with pH, salinity, and electrical conductivity ( r  = − 0.73, r  = − 0.60, and r  = − 0.61, respectively). GST showed a positive correlation with electrical conductivity and salinity ( r  = 0.55 and r  = 0.48), but a negative correlation with water temperature ( r  = − 0.47). MDA was positively correlated with rainfall ( r  = 0.66) and negatively with pH, electrical conductivity, and salinity ( r  = − 0.74, r  = − 0.58, and r  = − 0.67, respectively). These findings highlight the intricate relationship between marine environmental factors and biomarker variability in M. galloprovincialis , emphasizing the importance of further understanding their impact on marine organism health amid ongoing environmental changes. Graphical abstract

Maintenance in manufacturing has been developed and researched in the last few decades at a very rapid rate. It’s a major step in process control to build a decision tool that detects defects in equipment or processes as quickly as possible to maintain high process efficiencies. However, the high complexity of machines, and the increase in data available in almost all areas, makes research on improving the accuracy of fault detection via data-mining more and more challenging issue in this field. In our paper we present a new predictive model of semiconductor failures, based on machine learning approach, for predictive maintenance in industry 4.0. The framework of our model includes: Dataset and data acquisition, data preprocessing in three phases (over-sampling, data cleaning, and attribute reduction with principal component analysis (PCA) technique and CfsSubsetEval technique), data modeling, evaluation model and implementation model. We used SECOM dataset to develop four different models based on four algorithms (Naive Bayesian, C4.5 Decision tree, Multilayer perceptron (MLP), Support vector machine), according to the five metrics (True Positive rate, False Positive rate, Precision, F-Mesure and Accuracy). We implemented our new predictive model with 91, 95% of accuracy, as a new efficient predictive model of semiconductor failures.

One of the most common medical imaging methods is a chest x-ray, as it contributes to the early detection of lung cancer compared to other methods. this work presents the use of a generative adversarial network to perform lung chest x-ray image segmentation. The network is two frameworks neural (generator and discriminator). In our work the generator is trained to generate a mask for the input of a given original image, the discriminator distinguishes between the original mask and the generated mask, the final objective is to generate masks for the input. The model is trained and evaluated, well generalized experimental results of the JSRT dataset reveal that the proposed model can a dice score of 0.9778, which is better than other reported state-of-the-art results.

Climate change is one of the most trend topics of the decade in the world. The recent years were the warmest in 139 years, however identifying deniers and believers of this subject still a very big issue. The challenge is to have an efficient tool to detect deniers in order to deploy the appropriate strategy facing this phenomenon. Moreover, Bidirectional Encoder Representations from Transformers (BERT) pre-trained model has taken Natural Language Processing tasks results so far. In this paper we presented an efficient technological tool based on deep learning model and BERT model for detecting people’s opinions on climate change on social media platforms. We used convolutional neural network targeting the public opinions on climate change on Twitter. The results showed that our model outperforms the machine learning approaches: Naive Bays, Support Vector Machine and Logistic Regression. This model is able to analyze people’s behavior and detect believers and deniers of this disaster with high accuracy results (98% for believers and 90% for deniers). Our model could be a powerful citizen sensing tool that can be used by governments for monitoring and governance, especially for smart cities.

Accurate segmentation of chest X-rays is essential for effective medical image analysis, but challenges arise due to inherent stability issues caused by factors such as poor image quality, anatomical variations, and disease-related abnormalities. While Generative Adversarial Networks (GANs) offer automated segmentation, their stability remains a significant limitation. In this paper, we introduce a novel approach to address segmentation stability by integrating GANs with wavelet transforms. Our proposed model features a two-network architecture (generator and discriminator). The discriminator differentiates between the original mask and the mask generated after the generator is trained to produce a mask from a given image. The model was implemented and evaluated on two X-ray datasets, utilizing both original images and perturbed images, the latter generated by adding noise via the Gaussian noise method. A comparative analysis with traditional GANs reveals that our proposed model, which combines GANs with wavelet transforms, outperforms in terms of stability, accuracy, and efficiency. The results highlight the efficacy of our model in overcoming stability limitations in chest X-ray segmentation, potentially advancing subsequent tasks in medical image analysis. This approach provides a valuable tool for clinicians and researchers in the field of medical image analysis.

Otolith shape recognition is one of the relevant tool to ensure the sustainability of maritime resources. It is used to study taxonomy, age estimation and discrimination of stocks of fish species. The most performant otolith image classification models are based on convolutional neural network approaches. To build an efficient system, these models require a large number of labeled images, which is hard to obtain. The lack of data became a big challenge, and a real problem of otolith images classification models, it causes the over-fitting issue, which is the main trouble of deep convolutional neural network based models. In this paper, we present a relevant solution for the insufficiency of data. We propose a new semi-supervised classification model based on generative adversarial network. Our results showed that the model is more efficient and also perform better than convolutional neural network system even with a small training dataset. With this efficiency and performance, we found in addition that the accuracy of the model reached 80% on training set of say, 75 images compared to other models such as a convolutional neural network model which accuracy is limited to 60%.

Primary adenocarcinoma of the base of the tongue is an exceptionally rare malignancy, accounting for only a small proportion of oropharyngeal tumors. Diagnosis is challenging due to nonspecific symptoms and overlap with more common squamous cell carcinomas and salivary-type neoplasms. We report the case of a 59-year-old Moroccan woman presenting with progressive dysphagia and referred otalgia. Nasofibroscopy revealed a right-sided base of the tongue mass extending to the vallecula. Magnetic resonance imaging confirmed a 28 × 19 mm lesion with ipsilateral cervical lymphadenopathy. Biopsy demonstrated an undifferentiated invasive adenocarcinoma. Immunohistochemistry was positive for CK7 and CK20 and negative for p16. The patient underwent transmandibular resection with bilateral neck dissection, followed by adjuvant radiotherapy. At 6-month follow-up, she remained disease-free with good functional outcomes. A narrative systematic review was conducted in PubMed, Scopus, and Google Scholar using predefined keywords. Studies reporting primary base of the tongue adenocarcinoma were included. A total of 12 publications describing comparable cases were identified. Most patients presented with dysphagia and cervical lymphadenopathy. Surgery followed by radiotherapy was the most commonly reported management strategy. Prognosis appeared favorable in low-grade salivary-type tumors and more variable in high-grade or nonsalivary primaries. Primary base of the tongue adenocarcinoma is rare and requires a high index of suspicion and appropriate immunohistochemical evaluation. Multimodal management offers good oncologic control. Long-term follow-up is necessary due to uncertain metastatic potential.

since the Ministry of National Education introduced contractual recruitment in 2016, Morocco has faced significant challenges related to the well-being of its contractual teachers. This study investigates the impact of job precarity on the mental health of these teachers, specifically focusing on fatigue and psychological distress. we collected responses from 245 contractual teachers across Morocco's 12 regions, utilizing the Individual Strength Checklist (CIS) to assess fatigue and the General Health Questionnaire (GHQ) for psychological distress. Our findings reveal that teachers' average scores on the CIS (51.7 ± 19.7) and GHQ (12.3 ± 4.6) were notably high, indicating significant job-related stress and emotional suffering. our study indicates that teachers had very high average scores on the CIS (51.7 ± 19.7) and GHQ (12.3 ± 4.6), suggesting that they experienced considerable job-related stress and emotional distress. Our research revealed that 31% of teachers reported experiencing weariness, while 26% reported experiencing psychological distress. Additionally, out of the individuals who reported experiencing chronic exhaustion, 39% specifically experienced fatigue alone, while 61% experienced both fatigue and psychological discomfort. This suggests a significant association between these two conditions. the research emphasizes that Moroccan contractual teachers have a shared experience of exhaustion and mental anguish, which is worsened by the uncertainty of their job. Specific interventions are required to address and alleviate these unique effects on teachers' well-being, thereby enhancing the entire educational atmosphere.