Université Moulay Ismail de Meknes

Breast cancer is the most common invasive cancer in women, affecting more than 10% of women worldwide. Microscopic analysis of a biopsy remains one of the most important methods to diagnose the type of breast cancer. This requires specialized analysis by pathologists, in a task that i) is highly time- and cost-consuming and ii) often leads to nonconsensual results. The relevance and potential of automatic classification algorithms using hematoxylin-eosin stained histopathological images has already been demonstrated, but the reported results are still sub-optimal for clinical use. With the goal of advancing the state-of-the-art in automatic classification, the Grand Challenge on BreAst Cancer Histology images (BACH) was organized in conjunction with the 15th International Conference on Image Analysis and Recognition (ICIAR 2018). BACH aimed at the classification and localization of clinically relevant histopathological classes in microscopy and whole-slide images from a large annotated dataset, specifically compiled and made publicly available for the challenge. Following a positive response from the scientific community, a total of 64 submissions, out of 677 registrations, effectively entered the competition. The submitted algorithms improved the state-of-the-art in automatic classification of breast cancer with microscopy images to an accuracy of 87%. Convolutional neuronal networks were the most successful methodology in the BACH challenge. Detailed analysis of the collective results allowed the identification of remaining challenges in the field and recommendations for future developments. The BACH dataset remains publicly available as to promote further improvements to the field of automatic classification in digital pathology.

In this study, an improved crossover operator is suggested, for solving path planning problems using genetic algorithms (GA) in static environment. GA has been widely applied in path optimization problem which consists in finding a valid and feasible path between two positions while avoiding obstacles and optimizing some criteria such as distance (length of the path), safety (the path must be as far as possible from the obstacles) ...etc. Several researches have provided new approaches used GA to produce an optimal path. Crossover operators existing in the literature can generate infeasible paths, most of these methods dont take into account the variable length chromosomes. The proposed crossover operator avoids premature convergence and offers feasible paths with better fitness value than its parents, thus the algorithm converges more rapidly. A new fitness function which takes into account the distance, the safety and the energy, is also suggested. In order to prove the validity of the proposed method, it is applied to many different environments and compared with three studies in the literature. The simulation results show that using GA with the improved crossover operators and the fitness function helps to find optimal solutions compared to other methods.

The experimental adsorption equilibrium of Cd(II) onto chitosan (Cd(II)/CS) and methyl orange onto bentonite (MO/Bt) were studied in batch adsorption experiments at room temperature for an initial concentration of 236.5 mg/L for Cd (II) (pH = 5) and 33 mg/L for MO (pH = 3). The adsorption rate increases rapidly for t < 30 min, and the equilibrium is reached after this contact time for both systems. The values of the experimental maximum amount of Cd(II) and MO adsorbed are qe = 56.70 and 56.55 mg/g for Cd/CS and MO/Bt, respectively. The obtained experimental data were analysed using the linear and the nonlinear forms of pseudo-first and pseudo-second order kinetic models (LPFO, NLPFO, LPSO, NLPSO). The appropriate model to describe the adsorption kinetics of each system was determined based on the comparison of R2 and the standard deviation Δq (%). It was found that the adsorption process of Cd(II)/CS followed NLPFO and that of MO/Bt can be described by both of NLPSO and LPSO. The results show that the nonlinear forms (NLPSO and NLPFO) are suitable for describing the kinetics adsorption reactions in the liquid phase and the LPSO (qt = f(1/t) model can also be suitable for some systems, depending on the experimental conditions. Because of qt values, determined from these models correspond well to the experimental data as confirmed by the error analysis values of R2 and Δq (%), it is noticed that the determination of R2 alone is insufficient to decide among the kinetic models.

The work presented in this article constitutes a contribution to modeling and forecasting the demand in a food company, by using time series approach. Our work demonstrates how the historical demand data could be utilized to forecast future demand and how these forecasts affect the supply chain. The historical demand information was used to develop several autoregressive integrated moving average (ARIMA) models by using Box–Jenkins time series procedure and the adequate model was selected according to four performance criteria: Akaike criterion, Schwarz Bayesian criterion, maximum likelihood, and standard error. The selected model corresponded to the ARIMA (1, 0, 1) and it was validated by another historical demand information under the same conditions. The results obtained prove that the model could be utilized to model and forecast the future demand in this food manufacturing. These results will provide to managers of this manufacturing reliable guidelines in making decisions.

Abstract With the advent of cloud computing, many new networking concepts have been introduced to simplify network management and bring innovation through network programmability. The emergence of the software‐defined networking (SDN) paradigm is one of these adopted concepts in the cloud model so as to eliminate the network infrastructure maintenance processes and guarantee easy management. In this fashion, SDN offers real‐time performance and responds to high availability requirements. However, this new emerging paradigm has been facing many technological hurdles; some of them are inherent, while others are inherited from existing adopted technologies. In this paper, our purpose is to shed light on SDN related issues and give insight into the challenges facing the future of this revolutionary network model, from both protocol and architecture perspectives. Additionally, we aim to present different existing solutions and mitigation techniques that address SDN scalability, elasticity, dependability, reliability, high availability, resiliency, security, and performance concerns. Copyright © 2017 John Wiley &amp; Sons, Ltd.

Coronavirus is still the leading cause of death worldwide. There are a set number of COVID-19 test units accessible in emergency clinics because of the expanding cases daily. Therefore, it is important to implement an automatic detection and classification system as a speedy elective finding choice to forestall COVID-19 spreading among individuals. Medical images analysis is one of the most promising research areas, it provides facilities for diagnosis and making decisions of a number of diseases such as Coronavirus. This paper conducts a comparative study of the use of the recent deep learning models (VGG16, VGG19, DenseNet201, Inception_ResNet_V2, Inception_V3, Resnet50, and MobileNet_V2) to deal with detection and classification of coronavirus pneumonia. The experiments were conducted using chest X-ray & CT dataset of 6087 images (2780 images of bacterial pneumonia, 1493 of coronavirus, 231 of Covid19, and 1583 normal) and confusion matrices are used to evaluate model performances. Results found out that the use of inception_Resnet_V2 and Densnet201 provide better results compared to other models used in this work (92.18% accuracy for Inception-ResNetV2 and 88.09% accuracy for Densnet201).Communicated by Ramaswamy H. Sarma.

activity against SARS-Cov-2 could be interesting.

Hybrid organic-inorganic perovskite solar cells (PSCs) are the novel fourth-generation solar cells, with impressive progress in the last few years. MAPbI3 is a cost-effective material used as an absorber layer in PSCs. Due to the different diffusion length of carriers, the electron transporting material (ETM) plays a vital role in PSCs' performance. ZnO ETM is a promising candidate for low-cost and high-efficiency photovoltaic technology. In this work, the normal n-i-p planar heterojunction structure has been simulated using SCAPS-1D. The influence of various parameters such as the defect density, the thickness of the MAPbI3 layer, the temperature on fill factor, the open-circuit voltage, the short circuit current density, and the power conversion efficiency are investigated and discussed in detail. We found that a 21.42% efficiency can be obtained under a thickness of around 0.5 μm, and a total defect of 1013 cm−3 at ambient temperature. These simulation results will help fabricate low-cost, high-efficiency, and low-temperature PSCs.

Forest fire disaster is currently the subject of intense research worldwide. The development of accurate strategies to prevent potential impacts and minimize the occurrence of disastrous events as much as possible requires modeling and forecasting severe conditions. In this study, we developed five new hybrid machine learning algorithms namely, Frequency Ratio-Multilayer Perceptron (FR-MLP), Frequency Ratio-Logistic Regression (FR-LR), Frequency Ratio-Classification and Regression Tree (FR-CART), Frequency Ratio-Support Vector Machine (FR-SVM), and Frequency Ratio-Random Forest (FR-RF), for mapping forest fire susceptibility in the north of Morocco. To this end, a total of 510 points of historic forest fires as the forest fire inventory map and 10 independent causal factors including elevation, slope, aspect, distance to roads, distance to residential areas, land use, normalized difference vegetation index (NDVI), rainfall, temperature, and wind speed were used. The area under the receiver operating characteristics (ROC) curves (AUC) was computed to assess the effectiveness of the models. The results of conducting proposed models indicated that RF-FR achieved the highest performance (AUC = 0.989), followed by SVM-FR (AUC = 0.959), MLP-FR (AUC = 0.858), CART-FR (AUC = 0.847), LR-FR (AUC = 0.809) in the forecasting of the forest fire. The outcome of this research as a prediction map of forest fire risk areas can provide crucial support for the management of Mediterranean forest ecosystems. Moreover, the results demonstrate that these novel developed hybrid models can increase the accuracy and performance of forest fire susceptibility studies and the approach can be applied to other areas.

Blockchain (e.g., Bitcoin and Ethereum) has drawn much attention and has been widely-deployed in recent years. However, blockchain scalability is emerging as a challenging issue. This paper outlines the existing solutions to blockchain scalability, which can be classified into two categories: first layer and second layer solutions. First layer solutions propose modifications to the blockchain (i.e., changing the blockchain structure, such as block size) while second layer solutions propose mechanisms that are implemented outside of the blockchain. In particular, we focus on sharding as a promising first layer solution to the scalability issue; the basic idea behind sharding is to divide the blockchain network into multiple committees, each processing a separate set of transactions. More specifically, (a) we propose a taxonomy based on committee formation and intra-committee consensus; and (b) we compare the main existing sharding-based blockchain protocols. We also present a performance-based comparative analysis (i.e., throughput and latency), of the advantages, and disadvantages in existing scalability solutions.

Recent spectacular progress in computational technologies has led to an unprecedented boom in the field of Artificial Intelligence (AI). AI is now used in a plethora of research areas and has demonstrated its capability to bring new approaches and solutions to various research problems. However, the extensive computation required to train AI algorithms comes with a cost. Driven by the need to reduce the energy consumption, the carbon footprint and the cost of computers running machine learning algorithms, TinyML is nowadays considered as a promising AI alternative focusing on technologies and applications for extremely low-profile devices. This paper presents the results of a literature survey of all TinyML applications and related research efforts. Our survey builds a taxonomy of TinyML techniques that have been used so far to bring new solutions to various domains, such as healthcare, smart farming, environment, and anomaly detection. Finally, this survey highlights the remaining challenges and points out possible future research directions. We anticipate that this survey will motivate further discussions on the various fields of applications of TinyML and the synergy of resource-constrained devices and edge intelligence.

Agriculture must overcome escalating problems in order to feed a growing population while preserving the environment and natural resources. Recently, it has become clear that sensors and the Internet of Things (IoT) are effective tools for boosting agricultural sustainability and food security. This study provides insights into the global market size for smart agriculture in future years from 2021 to 2030, In addition, this research offered four levels of the IoT architecture for smart agriculture: the perception or sensing and actuator layer, the network layer, the cloud layer, and the application layer. The state of the art in IoT and sensor technologies for agriculture is examined in this review paper, along with some of their potential uses, including 1) irrigation monitoring systems, 2) fertilizer administration, 3) crop disease detection, 4) monitoring (yield monitoring, quality monitoring, processing monitoring logistic monotoring), forecasting, and harvesting, 5) climate conditions monitoring, and 6) fire detection. Additionally, this review offers a number of sensors for agriculture that can detect parameters like soil NPK, moisture, nitrate, pH, electrical conductivity, CO2, temperature, humidity, light, weather station, water level, livestock, plant disease, smoke, flame, flexible wearable. Subsequently, this study highlights the advantages of IoT in smart agriculture, including superior efficiency, expansion, reduced resources, cleaner method, agility, and product quality improvement. However, there are still issues that need to be resolved in order for IoT technology to be used in agriculture where covered in this paper, and also provide insights into future research directions and opportunities. This study will contribute to helping future readers and researchers to better understand the state of academic achievement in this subject.

We have measured the permittivity of representative samples of natural seawater, synthetic seawater, and aqueous NaCl solutions over the frequency range 3–20 GHz, in 0.1‐GHz steps and over the temperature range −2°–30°C in 1° steps. Additional measurements have been made at spot frequencies (23.8, 36.5, and 89 GHz) and at selected temperatures between −2° and 3O°C. The data from these measurements have allowed us to deduce an interpolation function for ε( υ t, S ) in the ranges 2 ≤ υ ≤ 20 GHz, −2° ≤ t ≤ 30°C, and 20‰ ≤ S ≤ 40‰ with a precision of 1%. If the frequency range is extended up to 40 GHz, the precision of the interpolation function is about 3%.The data have also allowed us to compare the permittivities of natural seawater, synthetic seawater, and aqueous NaCl solution with the same salinities. Natural and synthetic seawater have the same permittivities within a 1% experimental error estimate. An aqueous NaCl solution has a significantly different permittivity (up to about 6% difference, depending upon the frequency and temperature).

The study of land use/land cover (LULC) has become an increasingly important stage in the development of forest ecosystems strategies. Hence, the main goal of this study was to describe the vegetation change of Azrou Forest in the Middle Atlas, Morocco, between 1987 and 2017. To achieve this, a set of Landsat images, including one Multispectral Scanner (MSS) scene from 1987; one Enhanced Thematic Mapper Plus (ETM+) scene from 2000; two Thematic Mapper (TM) scenes from 1995 and 2011; and one Landsat 8 Operational Land Imager (OLI) scene from 2017; were acquired and processed. Ground-based survey data and the normalized difference vegetation index (NDVI) were used to identify and to improve the discrimination between LULC categories. Then, the maximum likelihood (ML) classification method was applied was applied, in order to produce land cover maps for each year. Three classes were considered by the classification of NDVI value: low-density vegetation; moderate-density vegetation, and high-density vegetation. Our study achieved classification accuracies of 66.8% (1987), 99.9% (1995), 99.8% (2000), 99.9% (2011), and 99.9% (2017). The results from the Landsat-based image analysis show that the area of low-density vegetation was decreased from 27.4% to 2.1% over the past 30 years. While, in 2017, the class of high-density vegetation was increased to 64.6% of the total area of study area. The results of this study show that the total forest cover remained stable. The present study highlights the importance of the image classification algorithms combined with NDVI index for better understanding the changes that have occurred in this forest. Therefore, the findings of this study could assist planners and decision-makers to guide, in a good manner, the sustainable land development of areas with similar backgrounds.

Purpose This article presents a review of the existing state-of-the-art literature concerning Supply Chain Management 4.0 (SCM 4.0) and identifies and evaluates the relationship between digital technologies and Supply Chain Management. Design/methodology/approach A literature review of state-of-the-art publications in the subject field and a bibliometric analysis were conducted. Findings The paper identifies the impact of novel technologies on the different supply chain processes. Furthermore, the paper develops a roadmap framework for future research and practice. Practical implications The proposed work is useful for both academics and practitioners as it outlines the pillar components for every supply chain transformation. It also proposes a range of research questions that can be used as a base to guide the future research direction of the field. Originality/value This paper presents a novel and original literature review-based study on SCM4.0 as no comprehensive review is available where bibliometric analysis, motivations, barriers and technologies' impact on different SC processes have been considered.

Crop production stands as a pivotal pillar of global food security, but its sustainability faces complex challenges from plant diseases, which pose a substantial threat to agricultural productivity. Climate change significantly alters the dynamics of plant pathogens, primarily through changes in temperature, humidity, and precipitation patterns, which can enhance the virulence and spread of various plant diseases. Indeed, the increased frequency of extreme weather events, which is a direct consequence of climate change, creates favorable conditions for outbreaks of plant diseases. As global temperatures rise, the geographic range of many plant pathogens is expanding, exposing new regions and species to diseases previously limited to warmer climates. Climate change not only affects the prevalence and severity of plant diseases but also influences the effectiveness of disease management strategies, necessitating adaptive approaches in agricultural practices. This review presents a thorough examination of the relationship between climate change and plant pathogens and carefully provides an analysis of the interplay between climatic shifts and disease dynamics. In addition to insights into the development of effective strategies for countering the adverse impacts of climate change on plant diseases, these insights hold significant promise for bolstering global crop production resilience against mounting environmental challenges.

The aim of the present study was to develop an electronic nose for the quality control of red meat. Electronic nose and bacteriological measurements are performed to analyse samples of beef and sheep meat stored at 4°C for up to 15 days. Principal component analysis (PCA) and support vector machine (SVM) based classification techniques are used to investigate the performance of the electronic nose system in the spoilage classification of red meats. The bacteriological method was selected as the reference method to consistently train the electronic nose system. The SVM models built classified meat samples based on the total microbial population into "unspoiled" (microbial counts < 6 log10 cfu/g) and "spoiled" (microbial counts ≥ 6 log10 cfu/g). The preliminary results obtained by the bacteria total viable counts (TVC) show that the shelf-life of beef and sheep meats stored at 4 °C are 7 and 5 days, respectively. The electronic nose system coupled to SVM could discriminate between unspoiled/ spoiled beef or sheep meats with a success rate of 98.81 or 96.43 %, respectively. To investigate whether the results of the electronic nose correlated well with the results of the bacteriological analysis, partial least squares (PLS) calibration models were built and validated. Good correlation coefficients between the electronic nose signals and bacteriological data were obtained, a clear indication that the electronic nose system can become a simple and rapid technique for the quality control of red meats.

In tropical agroecosystems, limited N availability remains a major impediment to increasing yield. A 15 N‐recovery experiment was conducted in 13 diverse tropical agroecosystems. The objectives were to determine the total recovery of one single 15 N application of inorganic or organic N during three to six growing seasons and to establish whether the losses of N are governed by universal principles. Between 7 and 58% (average of 21%) of crop N uptake during the first growing season was derived from fertilizer. On average, 79% of crop N was derived from the soil. When 15 N‐labeled residues were applied, in the first growing season 4% of crop N was derived from the residues. Average recoveries of 15 N‐labeled fertilizer and residue in crops after the first growing season were 33 and 7%, respectively. Corresponding recoveries in the soil were 38 and 71%. An additional 6% of the fertilizer and 9.1% of the residue was recovered by crops during subsequent growing seasons. There were no significant differences in total 15 N recovery (average 54%) between N from fertilizer and N from residue. After five growing seasons, more residue N (40%) than fertilizer N (18%) was recovered in the soil, better sustaining the soil organic matter N content. Long‐term total recoveries of 15 N‐labeled fertilizer or residue in the crop and soil were similar. Soil N remained the primary source of N for crops. As higher rainfall and temperature tend to cause higher 15 N losses, management practices to improve N use efficiency and reduce losses in wet tropical regions will remain a challenge.

Electrical and dielectric properties for bulk ethylcarbazole‐terphenyl (PEcbz‐Ter) have been studied over frequency range 1 kHz–2 MHz and temperature range (R.T –120°C). The copolymer PEcbz‐Ter was characterised by using X‐ray diffraction. The frequency dependence of the dielectric constant () and dielectric loss () has been investigated using the complex permittivity. of the copolymer decreases with increasing frequency and increases with temperature. AC conductivity ( σ ac ) data were analysed by the universal power law. The behaviour of σ ac increases with increasing temperature and frequency. The change of the frequency exponent ( s ) with temperature was analysed in terms of different conduction mechanisms, and it was found that the correlated barrier‐hopping model is the predominant conduction mechanism. The electric modulus was used to analyze the relaxation phenomenon in the material.

This paper presents a hybrid state-of-charge (SOC) and state-of-health (SOH) estimation technique for lithium-ion batteries according to surface temperature variation (STV). The hybrid approach uses an adaptive observer to estimate the SOH while an extended Kalman filter (EKF) is used to predict the SOC. Unlike other estimation methods, the closed-loop estimation strategy takes into account the STV and its stability is guaranteed by Lyapunov direct method. In order to validate the proposed method, experiments have been carried out under different operating temperature conditions and various discharge currents. Results highlight the effectiveness of the approach in estimating SOC and SOH for different aging conditions.