Explore the vast range of titles available.

Image quality assessment of 360-degree images is still in its early stages, especially when it comes to solutions that rely on machine learning. There are many challenges to be addressed related to training strategies and model architecture. In this paper, we propose a perceptually weighted multichannel convolutional neural network (CNN) using a weight-sharing strategy for 360-degree IQA (PW-360IQA). Our approach involves extracting visually important viewports based on several visual scan-path predictions, which are then fed to a multichannel CNN using DenseNet-121 as the backbone. In addition, we account for users’ exploration behavior and human visual system (HVS) properties by using information regarding visual trajectory and distortion probability maps. The inter-observer variability is integrated by leveraging different visual scan-paths to enrich the training data. PW-360IQA is designed to learn the local quality of each viewport and its contribution to the overall quality. We validate our model on two publicly available datasets, CVIQ and OIQA, and demonstrate that it performs robustly. Furthermore, the adopted strategy considerably decreases the complexity when compared to the state-of-the-art, enabling the model to attain comparable, if not better, results while requiring less computational complexity.

An attention-aware patch-based deep-learning model for a blind 360-degree image quality assessment (360-IQA) is introduced in this paper. It employs spatial attention mechanisms to focus on spatially significant features, in addition to short skip connections to align them. A long skip connection is adopted to allow features from the earliest layers to be used at the final level. Patches are properly sampled on the sphere to correspond to the viewports displayed to the user using head-mounted displays. The sampling incorporates the relevance of patches by considering (i) the exploration behavior and (ii) a latitude-based selection. An adaptive strategy is applied to improve the pooling of local patch qualities to global image quality. This includes an outlier score rejection step relying on the standard deviation of the obtained scores to consider the agreement, as well as a saliency to weigh them based on their visual significance. Experiments on available 360-IQA databases show that our model outperforms the state of the art in terms of accuracy and generalization ability. This is valid for general deep-learning-based models, multichannel models, and natural scene statistic-based models. Furthermore, when compared to multichannel models, the computational complexity is significantly reduced. Finally, an extensive ablation study gives insights into the efficacy of each component of the proposed model.

Located in a semi-arid to arid region, Morocco is confronting increasing water scarcity challenges. In the circular economy paradigm, the reuse of treated wastewater in agriculture is currently considered a possible solution to mitigate water shortage and pollution problems. In recent years, Morocco has made significative progress in urban wastewater treatment under the National Wastewater Program (PNA). However, rural sanitation has undergone significant delays. Therefore, an alternative technology for wastewater treatment and reuse in rural areas is investigated in this review, considering the region’s economic, social, and regulatory characteristics. Constructed wetlands (CWs) are a simple, sustainable, and cost-effective technology that has yet to be fully explored in Morocco. CWs, indeed, appear to be suitable for the treatment and reuse of wastewater in remote rural areas if they can produce effluent that meets the standards of agricultural irrigation. In this review, 29 studies covering 16 countries and different types of wastewater were collected and studied to assess the treatment efficiency of different types of CWs under different design and operational parameters, as well as their potential application in agricultural reuse. The results demonstrated that the removal efficiency of conventional contamination such as organic matter and suspended solids is generally high. CWs also demonstrated a remarkable capacity to remove heavy metals and emerging contaminants such as pharmaceuticals, care products, etc. The removal of microbial contamination, on the other hand, is challenging, and does not satisfy the standards all the time. However, it can be improved using hybrid constructed wetlands or by adding polishing treatment. In addition, several studies reported that CWs managed to produce effluent that met the requirements of wastewater reuse in agriculture of different countries or organisations including Morocco.

The rapid growth of anthropogenic activities in recent decades has resulted in the appearance of numerous new chemical compounds in the environment, known as \"emerging pollutants\" (EPs) or \"contaminants of emerging concern\" (CECs). Although partially or not yet regulated or monitored, there is growing research interest in these EPs among the scientific community because of their bioaccumulation, persistence, and adverse effects. Among these, endocrine disruptors, pesticides, and pharmaceuticals can have harmful impacts on human health and the ecosystem. Conventional wastewater treatment technologies are not effective in removing these contaminants, allowing them to be released into the receiving environment. In order to improve the understanding of emerging pollutants, this review discusses the source, occurrence, and impacts of bisphenol A, atrazine, amoxicillin, and paracetamol as model molecules of emerging environmental pollutants, an issue that remains underrepresented in Morocco. en, treatment methods for EPs are reviewed, including adsorption, advanced oxidation processes, biodegradation, and hybrid treatment. It is proposed that adsorption and photocatalysis can be used as simple, effective, and environmentally friendly technologies for their removal. us, we summarize some of the adsorbent and photocatalyst materials applied in recent work to control these pollutants. Towards the end of this paper, the development of inexpensive and locally available (Morocco) materials to remove these compounds from wastewater is considered.

The harmonized procedures in terms of the sampling, sample treatment and identification of microplastics in different environmental samples are missing, which poses challenges to researchers to compare the results or to adopt ‘the most effective’ monitoring approach. Furthermore, in the related literature, the used procedures are rarely tested with spiked microplastics to predetermine their recovery rates. Without this knowledge, results should only be discussed as rough estimations of the real environmental concentrations of microplastics. In this study, six different methods previously used in microplastic studies of different media were tested with municipal wastewater and digested sludge samples, spiked with seven different types of plastic particles and fibres. Recovery rates, time consumption, advantages and disadvantages were assessed and most suitable treatment procedures (i.e. high recovery rates in short amount of time) were chosen for both wastewater and sludge. Suitability of staining with Rose Bengal was examined together with most efficient methods, but it did not improve the recovery of microplastics. In addition, the possible impacts of the treatments for identification with micro-Raman and FTIR microscope were assessed. Filtration with size fractioning was found to be the best method for both wastewater and sludge samples, with recovery rates of spiked microplastics around 91.4% and 92.9%, respectively.

In the present work, the adsorption of vitamin B12 (VB12) on sugarcane-derived activated carbon (AC) was investigated with the purpose of developing a hybrid material able to degrade highly toxic and recalcitrant chlordecone (CLD) for remediating the severe environmental issue of pesticide pollution of water and soil. The AC used is made from locally accessible sugarcane bagasse. The experimental kinetic and isothermic data of VB12 adsorption on AC were modeled using multiple models, including Pseudo-Order 1 (Lagergren), Pseudo-Order 2, Elovich, and Brouers–Sotolongo models for the kinetics. The isotherms models used were Langmuir, Freundlich, Hill–Sips, Brouers–Sotolongo (BS), Brouers-Gaspard (BG), General Brouers–Sotolongo (GBS), and Redlich–Peterson (RP) models. The results showed that the BG model is the most suitable to satisfactorily describe the adsorption of VB12 on the studied AC, involving a heterogeneous adsorption mechanism onto a heterogeneous surface and providing the maximum adsorption capacity, a convenient tool to estimate the saturation level of adsorbate (i.e., chlordecone (CLD)) onto the adsorbent (AC). Voltammetric studies confirm the interaction between VB12 and the AC. Finally, molecular modeling is used to provide atomic insights showing the entrapment of VB12 inside the porous system to form a new hybrid material. The calculations provide the conformations with the best binding energy in the GaudiMM environment.

Constructed wetlands offer a sustainable, decentralized solution for wastewater treatment and reuse in Morocco. This study evaluated mesocosm-scale advanced vertical flow constructed wetlands (AVFCWs) incorporating locally sourced reactive media to assess phosphate mining residues as a novel substrate. Accordingly, four configurations were compared: a sand-based control (CW-A) and three amended systems combining pozzolan with phosphate mining residues (CW-B), clay (CW-C), and biochar (CW-D), operated in batch mode under hydraulic retention times (HRTs) of 24, 48, and 72 h. The incorporation of reactive media significantly improved treatment efficiency, with CW-D achieving high removal efficiencies across most parameters. COD and TSS removal reached 80% and 88%, respectively, while nitrogen removal exceeded 82% in optimal configurations. Phosphorus removal reached 76% in CW-B and 88% in CW-C. The removal of Cd and Cu exceeded 85% in all systems, with phosphate mining residues demonstrating strong potential for metal immobilization. However, despite these high removal efficiencies, the treated effluent did not meet Moroccan reuse standards for cadmium and fecal coliforms, indicating that single-stage AVFCWs are insufficient for safe agricultural reuse and require additional polishing steps. Extended HRT improved AVFCWs’ performance, but increased water loss, reaching up to 28% due to evapotranspiration. Hence, phosphate mining residues emerge as a promising substrate, pending further optimization, while supporting circular economy objectives.

This work deals with the thermal performance of a battery thermal management system in an electric vehicle composed of a heat pipe and cold plate. The experimental results demonstrate that the cooling system composed of a unique heat pipe and cold plate can disipate heat input power as high as 40 W with temperatures lower than the safety temperature of 60 °C. The heat transfer is analyzed using CFD simulations and IR measurements. It is demonstrated that the battery module's maximum temperature is well predicted by simulations, and IR temperature measurements are in good agreement with the simulated ones.

Integrating plasmonic nanoparticles into the photoactive metal-organic matrix is highly desirable due to the plasmonic near field enhancement, complementary light absorption, and accelerated separation of photogenerated charge carriers at the junction interface. The construction of a well-defined, intimate interface is vital for efficient charge carrier separation, however, it remains a challenge in synthesis. Here we synthesize a junction bearing intimate interface, composed of plasmonic Ag nanoparticles and matrix with silver node via a facile one-step approach. The plasmonic effect of Ag nanoparticles on the matrix is visualized through electron energy loss mapping. Moreover, charge carrier transfer from the plasmonic nanoparticles to the matrix is verified through ultrafast transient absorption spectroscopy and in-situ photoelectron spectroscopy. The system delivers highly efficient visible-light photocatalytic H 2 generation, surpassing most reported metal-organic framework-based photocatalytic systems. This work sheds light on effective electronic and energy bridging between plasmonic nanoparticles and organic semiconductors. The integration of plasmonic structures with photoactive matrices offers a promising means to enhance solar-to-fuel conversion. Here, the authors bridge plasmonic nanoparticles and metal-organic matrix through interface-engineering to boost photocatalytic hydrogen evolution.

In this paper, we propose a novel approach for face spoofing detection using a combination of color texture descriptors with a new convolutional neural network (CNN) architecture. The proposed approach is based on a new convolutional neural network architecture composed of two CNN parallel branches. The first branch is fed with complementary shallow local phase quantization (LPQ) invariant descriptors that result from joint color texture information from the hue, saturation, and value (HSV) color space to accurately capture the reflection properties of the face. Combining the HSV color space with LPQ is known to significantly improve performance. The second branch of the CNN takes an RGB image directly as input, effectively separating chromatic (color-related) information from achromatic (brightness-related) information in order to extract crucial facial color features. Each branch of the CNN produces a vector of deep features that are extracted. To effectively concatenate the deep features from the two output branches, we employ an attention mechanism based combination method. This method captures the complementarity of the two branches, improving the accuracy and robustness of the model. The combined feature vectors form an input vector for the next Dense layer, where the model can distinguish between live and spoofed faces. Our method detects 2D facial spoofing attacks involving printed photos and replayed videos. We showcase the effectiveness and superior performance of our approach through a series of experiments conducted on both the CASIA-FASD and Replay-Attack datasets. Our results are promising and surpassing those of other state-of-the-art methods on both used datasets in terms of 9 performance metrics.