Due to the complicated structure of the script, variety of writing styles used, and the inherent challenges associated with unbalanced data, handwritten digit recognition poses an additional category of challenges.Selecting the optimal method for precise and effective recognition is essential given the growing need for automated recognition systems across a range of industries, including document analysis, postal services, and historical document preservation.This research aims to present an ensemble learning approach on neural networks, such Artificial Neural Network (ANN), , MobileNet-V2 and proposed optimized hyper-tuned sequential Convolutional Neural Network (SDM-CNN), to judge the performance of handwritten digit recognition.A vote procedure of bagging is then used to choose the final result.Authors used MNIST dataset to evaluate the performances of chosen neural networks.After implementing the models, the predictions from each of these five models were combined to create an ensemble of the outcomes.The results after final voting demonstrate that our proposed model achieved better accuracy of 99.28% with reduced computational time and less parameters.The experiment makes use of the Keras and Tensorflow learning modules of Python, which are used to implement each experiment on Google Collaboratory.

The concept of automatization of Quality 5.0 management differs from the concept of automatization of Quality 4.0 management because it aims not only at the quality of products and services, which allows retaining or raising competitiveness, but also the goals of balanced sustainable social, environmental, and economic development.Automatization of Quality 5.0 management, similar to other components of the Fifth Industrial Revolution, involves the creation of products and services with value-added, which includes consumer advantages and the level of social corporate responsibility of the manufacturing company.In this paper, we systematised and described the features of sustainable innovations for automatization of Quality 5.0 management, based on the effective use and combination of intellectual technologies (including machine learning and the Internet of Things). We distinguished the specifics of the architecture of sustainable innovations based on an analysis of the examples of competitive innovative solutions with a big life cycle.The objective of this paper was to identify the types of sustainable innovations in the sphere of the Internet of Things and machine learning, which influence the effectiveness of the automatization of Quality 5.0 management.For this, we used the system approach, comparative analysis, and content analysis.Thus, we determined the features of the integration of intellectual digital technologies (machine learning and the Internet of Things) within the creation of sustainable innovations connected with the automatization of Quality 5.0 management.

Since the advent of results-based management through the Organic Law No. 130-13 on the Finance Law, management control has been increasingly developing in the Moroccan public sector.With varying degrees of integration across different public institutions, management control has introduced several innovations within these organizations, the primary one being the introduction of a new management philosophy focused on the pursuit of performance and surpassing the logic of available resources.This article aims to study the impact of management control tools especially resultsbased budgeting to enhance the performance of a social public sector as higher education in the Moroccan context. At first, we will review the basic concepts related to our issue thru a literature review marking the interrelationships and overlaps of these concepts. Then, by conducting a critical analysis of various indicators issued from multiple annual reports of the higher education and scientific research and innovation ministry, to conclude by a discuss explaining the probable factors that have hindered the favorable development of the indicators in relation to the allocated budgets per program.This work serves to improve the conditions for implementing and operationalizing management control by rethinking the choice of the right tools adapted to the public context and the social character of the sector.

The concept of managing Quality 5.0 at smart farms is based on the provisions of the paradigm of the Fifth Industrial Revolution. Its course involves the creation of favourable conditions to ensure social well-being in rural territories, the development of the processes of agricultural production based on man-machine interaction, the achievement of environmental goals (protection of ecosystems from the negative influence of farms), and an increase in the economic sustainability of farms. In this paper, we determine the types of models for managing Quality 5.0 in the activities of smart farms based on innovative solutions in the sphere of AI. We prove that the effectiveness of implementing each model depends on the impact of factors that may have positive and negative manifestations. The goal of this paper is to establish the list and features of managing Quality 5.0 at the smart farm using sustainable innovations based on artificial intelligence tools. The scientific novelty of this paper lies in determining the list of factors of influence on the effectiveness of models of managing Quality 5.0 at smart farms, the analysis of which allows raising the effectiveness of agriculture’s intellectualisation.

Advancements and challenges in automatic smart street lamp systems for energy efficiency, economic feasibility, fault detection, energy reporting, and enhanced surveillance.These systems consist of multiple integrated advanced sensor technology based systems, algorithms and object detection mechanisms that includes use of cameras to adjust lighting intensity as determined by objects detected.In particular, the system enhances light to enable safety and visibility under human activity without wasting energy by turning down lights to give range to animal passing or incidental locomotion.Such an adaptive approach greatly reduces unnecessary energy consumptions, steering in the right direction for sustainability goals.Furthermore, the deployment of remote surveillance systems facilitates real time and secured video access to remote and under monitored areas.With these systems, smart grid integration allows for real time monitoring, knowledge of best practices for proactive maintenance and adaptive design of lighting strategies to improve performance and minimize system downtime.These systems use state of the art technologies including IoT, machine learning and data analytics to establish a complete and reliable fault detection and predictive maintenance with accurate and cost effective energy consumption reporting.A detailed review of current technologies, strategic frameworks as foundations for future innovation in urban lighting systems.What these advancements represent is a step forward in the current efforts towards a smart city, which has the promise of improving the urban infrastructure, reducing energy consumption, building safer and more sustainable communities.

This research offers a comprehensive comparative analysis of efficient deep learning models for predicting diseases in orange fruits, with a particular emphasis on the impact of meteorological factors on disease prevalence. Citrus diseases such as Blackspot, Canker, and Greening are significantly influenced by environmental conditions. Recognizing the crucial role of weather conditions in the development and spread of these diseases, we concentrate on enhancing prediction accuracy by integrating Convolutional Neural Networks (CNNs) with various classification algorithms to develop hybrid models that account for meteorological impacts. Specifically, we assess the performance of a CNN combined with Gradient Boosting (CNN-GB) and compare it against other hybrid models such as CNN integrated with Long Short-Term Memory networks (CNN-LSTM), Support Vector Machines (CNN-SVM), and Random Forest classifiers (CNN-Random Forest). These models are evaluated using different optimization algorithms to determine the most effective approach for disease prediction under varying meteorological conditions. A meticulously curated dataset comprising 1,600 training images and 300 testing images of orange fruits exhibiting a variety of disease symptoms was utilized for evaluation. The dataset reflects diverse environmental conditions to capture the meteorological impact on disease manifestation. All the models tested, the CNN-GB hybrid model with NDAM optimizer exhibited superior performance (Accuracy 98.03) in comparison of other models like CNN (Accuracy 96.03), CNN+LSTM (Accuracy 96.16), CNN + SVM (Accuracy 97.13) and CNN + Random Forest (Accuracy 97.79). The exceptional performance of the CNN-GB model suggests that integrating CNNs with powerful classification algorithms like Gradient Boosting, along with considerations of meteorological data, can significantly enhance disease detection in crops. This advancement contributes to more proactive and effective disease management strategies, ultimately reducing economic losses and increasing productivity in the agricultural sector.

Recent studies have shown that the losses generated in the production, due to the maintenance system, have been a limiting factor in the search for the improvement of the productivity of the processes and the quality of the products. Such objectives are directly associated with the company’s capacity to reduce their production costs and offer products and services that meet the client´s needs. The company is seen today as a value chain, where manufacturing, maintenance, and logistics, among other sectors, influence the organization's results. In this context, a study was developed to analyze the performance of the maintenance sector of an automotive company and its influence on the company's results. The work aimed at analyzing the results obtained with the implementation of Total Productive Maintenance (TPM), a methodology for optimizing the performance of production processes, in the body sector of an automobile industry in Brazil. For this, a follow-up and evaluation of indicators were carried out, showing the performance of the company's maintenance system and the results with the production. In this way, the gains in competitiveness obtained were made evident, including the achievement of the Organization's goals for the production line of the bodywork of one of its popular vehicles.

This study assesses the potential of offshore wind as an energy source in Libya and develops a comprehensive database of wind resources.Meteorological data from the RETScreen Clean Energy Management Software program was used to analyze wind energy characteristics and generate wind energy at selected locations with a height of 10 m and a depth of 50 m.The study found that Derna had the highest wind speed, while the Ajdabiya and Benghazi sites consistently had the lowest average wind speeds.The study found that the collective energy potential in shallow waters along the Libyan shore constitutes about 13% and 45% of the existing renewable and wind energy capacity, with an estimated technical capacity of 339 GW/h.The results indicate the shallow seas of Derna, Tobruk, and Misrata are ideal for offshore wind energy development due to their abundant wind resources and low energy costs, with average costs ranging from $100 to 400 $/MWh.

In this article, we investigate the resilience of Moroccan hotels to health crises, focusing on the impact of crisis management on the hotel sector in the city of Marrakech.Although the literature on crisis management is abundant, studies on resilience specific to health crises in the hotel industry are limited.We adopted a quantitative approach, using binary logistic regression to analyze data from a representative sample of Marrakech hotels.Key variables include organizational culture, internal communication, external stakeholder relations, and institutional support.Results indicate that organizational culture and internal communication are essential for resilience in times of health crisis, with external relations and institutional support playing a prominent role.Our findings show that strategic crisis management integrating internal and external factors is important for surviving health crises.The main limitation of this study stems from its quantitative approach, which may not fully capture the subtleties of individual experiences.Future research could examine other regions or use qualitative methodologies.Our results suggest avenues for future studies on the implementation and impact of crisis management strategies in the hospitality industry.