Search

Brain signals have recently been proposed as a strong biometric due to their characteristics such as, uniqueness, permanence, universality, and confidentiality. There are many factors that affect the stability of EEG signals as a biometric for example, using different recording devices, variation in participant emotional states, performing different mental tasks and recording in temporally spaced sessions. Due to the non-stationary nature of EEG signals, there are still speculations about the stability of using them for generating a unique and repeatable cryptographic key. The challenge that faces all biometric based crypto-systems is to overcome the variation in biometric itself over time and to generate multiple unique keys from the same observation. In this work, we investigate the stability of using EEG signals as a biometric for both personal authentication and cryptographic key generation. The authentication process was tested using three datasets AMIGOS, DEAP, and SEED. Achieving accuracy of 96.23%,98.85%, and 99.89% respectively. The key generation process generates a set of different keys with different lengths from the same observation. Each key is unique and repeatable. The generated keys were examined using NIST test suite, scale index test, and autocorrelation test. Time complexity analysis of the key generation process was performed.

Background: Phlebotomine sand flies are known as vectors of various pathogens such as Leishmania sp parasite and Toscana virus (TOSV). Leishmaniasis is endemic in Morocco, and TOSV is increasingly reported. Our objective is to analyze the specific composition of the natural population of sand flies in endemic and non endemic area of leishmaniasis in Morocco, thus evaluated their infection by Toscana virus. Methods: Sand flies were collected by CDC miniature light traps from seven different localities with an altitude range from 399 m to 1496 m. Synanthropic index was calculated for each sand fly species. The collected female sand flies were grouped in 73 pools, with a maximum of 50 specimens per pool, and submitted to real time PCR for TOSV detection. Results: 8 sand fly species were identified morphologically: 5 of the Phlebotomus genus and 3 of the Sergentomyia genus. Phlebotomus sergenti was the most abundant species comprising of 43,12% of identified sand flies, followed by P. papatasi (18,89%) and P. longicuspis (13,43%). Estimated synanthropic indices for these species were between + 1.1 and + 12.6 suggesting a high preference to anthropogenic environments. A total of 3558 sand fly females were grouped in 73 pools (up to 50 sand flies per pool) for TOSV detection. TOSV was detected in one pool (out of 6 tested) from Lalla Laaziza locality (Chichaoua Province) where P. sergenti was the most abundant sand fly species. Conclusion: We reported the TOSV for the first time in a central Morocco, where cutaneous leishmaniasis by L. tropica is endemic. This result has epidemiological importance for both researchers and health authorities to monitor circulation of TOSV and implement a surveillance plan of sand fly-borne phleboviruses in Morocco.

Emotion recognition plays an important role in human computer interaction systems as it helps the computer in understanding human behavior and their decision making process. Using Electroencephalographic (EEG) signals in emotion recognition offers a direct assessment on the inner state of human mind. This study aims to build a subject dependent emotion recognition system that differentiate between high and low levels of valance and arousal, using multidimensional EEG signals. Our system offers a transfer learning- minimum distance to Riemannian mean (TL-MDRM) framework. In this work, we perform two pre-processing stages. In the first stage, we analyze the EEG signals to investigate their non-Gaussianity and determine the most appropriate signal distribution. Using several statistical and goodness of fit tests, T-distribution was found to be the most appropriate distribution. Covariance matrix estimations plays a crucial step in manifold learning technique, based on the most suitable signal distribution the covariance matrix estimation technique is chosen. In the second stage, we perform transfer learning to deal with cross-session variability by generating a unique reference point for each participant and performing affine transformation for the covariance matrices on the symmetric positive definite (SPD) manifold around this point. The results show that, TL process improved the performance even when assuming Gaussian distribution, while assuming T-distribution with TL improved the performance further.

In the uncertainties within which the worldwide food security lies nowadays, the agricultural industry is raising a crucial need for being equipped with the state-of-the-art technologies for a more efficient, climate-resilient and sustainable production. The traditional production methods have to be revisited, and opportunities should be given for the innovative solutions henceforth brought by big data analytics, cloud computing and internet of things (IoT). In this context, we develop an optimized tinyML-oriented model for an active machine learning-based greenhouse microclimate management to be integrated in an on-field microcontroller. We design an experimental strawberry greenhouse from which we collect multivariate climate data through installed sensors. The obtained values' combinations are labeled according to a five-action multi-label control strategy, then used to prepare a machine learning-ready dataset. The dataset is used to train and five-fold cross-validate 90 Multi-Layer Perceptrons (MLPs) with varied hyperparameters to select the most performant –yet optimized– model instance for the addressed task. Our multi-label control approach enables designing highly scalable models with reduced computational complexity, comprising only n control neurons instead of (1 + ∑nk=1Cnk) neurons (usually generated from a classic single-label approach from n input variables). Our final selected model incorporates 2 hidden layers with 7 and 8 neurons respectively and 151 parameters; it scored a mean accuracy of 97% during the cross-validation phase, then 96% on our supplementary test set. The model enables an intelligent and autonomous greenhouse management with the less required computations. It can be efficiently deployed in microcontrollers within real world operating conditions.

For decades, researchers of different areas, ranging from artificial intelligence to computer vision, have intensively investigated human-centered data, i [...]

The assessment of the impacts of the expansion of the invasive species on taxonomic diversity, the abundance and dominance of groups of algae, the presence and/or absence of species of ecological interest that may or may not be indicative of water quality well mentioned, through the installation of a 20 × 20 cm quadrat representing the minimum area. The observation stations were visited monthly, during a repetitive three-year cycle, during the spring, summer and autumn seasons, periods of maximum growth and development of the algal flora and the results suggest the following facts. The invasive alga Caulerpa cylindracea Sonder, 1845 tends to colonise disturbed ecosystems reflecting a reduction in native algal diversity; in fact, we note a drastic impoverishment of the invaded algal community, represented by a limited number of Macrophyte algae accompanying the invasive taxon in phytosociological surveys and a Shannon-Weaver Diversity Index (H’) and Equitability reduced by 4.49 and 0.77 n the heavily affected station. The number of macroalgal species accompanying the invasive species has dropped by 52% in Salamandre. In addition, the multidimensional analysis, represented by the Hierarchical Ascendant Clustering applied to this case, confirms our results.

This study aims to highlight the natural risks induced by spatiotemporal interaction between the geomorphological features and the urban growth of Jeddah, the largest city in Makkah Province, Saudi Arabia. The methodology is based on remote sensing and Geographic Information System (GIS) techniques. A spatial analysis of the GIS layers extracted from multisource remotely sensed data from 1965 to 2020 was performed. The results show that the urban area has doubled more than 30 times and has increased from around 36 sq. km in 1965 to more than 1,130 sq. km in 2020. Consequently, the city expands to all morphological units, resulting in multihazard susceptibility and exposure. In order to identify and and prioritize the various risks associated to geomorphic processes, a map has been designed to classify the natural risk areas according to their intensity and their factors. Thus, geomorphological constraints have a significant impact on urban planning.

The number of newly described sandfly-borne phleboviruses has been steadily growing in recent years. Some phleboviruses are human pathogens, but their health relevance is largely uncharacterized. We aimed to investigate the circulation of these viruses in the Emilia-Romagna region where several have already been described. A total of 482 sandflies were collected in a site in Reggio Emilia in 2019 and 2020. Sandflies collected in 2020 were grouped in 21 pools with a maximum of 25 sandflies per pool, submitted to real time PCR, and isolated in Vero cell culture. Complete genome sequencing showed the isolation of a strain of a Ponticelli III virus. This virus, which belongs to the species Adana phlebovirus, differed in the M segment from the Ponticelli I and Ponticelli II viruses. Analysis performed on the genomic segments of the newly isolated virus compared with other phleboviruses highlighted a strong purifying selection in the L segments, and different substitution saturation, highest in the M segments. Future research should address the ecological processes driving the occurrence of these novel phleboviruses and their possible impact on public health.

Leishmaniasis is endemic in Morocco where both cutaneous and visceral forms coexist. To date, anthroponotic cutaneous leishmaniasis (ACL) determinants remain poorly investigated in Morocco. However, the disease risk factors identification is vital to determine the specific preventive process. In this aim, a case-control study was conducted in the main active ACL foci in central Morocco. Epidemiological data were extracted from bulletins, registers and annual reports of the regional direction of Health offices. The socioeconomic and environmental data were collected from epidemiological surveys, completed by a questionnaire intended for accessible positive population and control people selected from the cases’ entourage. The study included 258 cases and 395 controls. Our results showed that many socioeconomic factors were associated with ACL in Morocco such as the rural habitation (OR = 4.163; 95% CI: 2.91–5.96), movement to endemic area (OR = 4.53; 95% CI: 3.03–6.77), provenance from leishmaniasis foci (in Essaouira focus OR = 5.34; 95% CI: 1.19–24.03) and poverty. In addition, environmental factors like proximity of vegetation (OR = 2.45; 95% CI: 1.14–5.25), poor domestic hygiene, particularly the absence of sewage system/waste management (OR = 1.63; 95% CI: 1.35–1.96), and presence of animals (OR = 2.67; 95% CI: 1.14–5.25) increase the risk of ACL in Morocco. Except for Matrimonial status (married people, OR = 4.11; 95% CI: 1.80–9.41), there is however no significant association of the disease with the other socio-demographic factors in the study area (p>0.05). These several risk factors must be taken in consideration to prevent this disease through multidisciplinary collaboration and community participation.

The Sebkha of Oran, given its large size, is considered to be a remarkable feature of the west Algeria. The study of its evolution proved to be essential, following many interrogations specifically concerning its extension and its role in the ecological balance of the region. We aim to study the changes of the Sebkha over the last 20 years. To conduct the study, we used the Synthetic Aperture Radar (SAR) imagery, which offers spatial and temporal, regular, and precise tracking of surfaces. The diachronic analysis, based on amplitude images captured between 1992 and 2011, demonstrated the possibility of mapping the sebkha at different dates in order to apprehend its evolution over this period. The results obtained reveal a southwesterly extension caused by the phenomenon of saline crystallization gradually and steadily gaining ground, which corresponds to the inclination of the basin and the main wind direction of the region.

Falls are one of the most critical health care risks for elderly people, being, in some adverse circumstances, an indirect cause of death. Furthermore, demographic forecasts for the future show a growing elderly population worldwide. In this context, models for automatic fall detection and prediction are of paramount relevance, especially AI applications that use ambient, sensors or computer vision. In this paper, we present an approach for fall detection using computer vision techniques. Video sequences of a person in a closed environment are used as inputs to our algorithm. In our approach, we first apply the V2V-PoseNet model to detect 2D body skeleton in every frame. Specifically, our approach involves four steps: (1) the body skeleton is detected by V2V-PoseNet in each frame; (2) joints of skeleton are first mapped into the Riemannian manifold of positive semidefinite matrices of fixed-rank 2 to build time-parameterized trajectories; (3) a temporal warping is performed on the trajectories, providing a (dis-)similarity measure between them; (4) finally, a pairwise proximity function SVM is used to classify them into fall or non-fall, incorporating the (dis-)similarity measure into the kernel function. We evaluated our approach on two publicly available datasets URFD and Charfi. The results of the proposed approach are competitive with respect to state-of-the-art methods, while only involving 2D body skeletons.

Les fractures du quart distal de la jambe, sont des fractures dont le trait est situé au niveau du quart inférieur du tibia. Elles sont réputées graves et posent à la fois des problèmes de consolidation, de contention et de stabilité. Nous présentons l'expérience du service de traumatologie orthopédie de l'Hôpital militaire Avicenne de Marrakech, concernant 30 fractures fermées du quart inférieur de la jambe, sur une période de 10 ans (de Janvier 2001 à Décembre 2010) ayant reçu un enclouage centromédullaire. Le montage était verrouillé à 80% des cas et simple dans les autres cas. La moyenne d'âge de nos patients était de 36 ans. Il existait une nette prédominance masculine avec 27 hommes pour 3 femmes. La consolidation a été obtenue dans un délai normal de 17 semaines en moyenne et les résultats fonctionnels était satisfaisants. Un seul cas d'infection est survenu à 6 mois du geste chirurgical soit 3,3% et aucune autre complication n'a été mentionnée. Un cal vicieux a été retrouvé chez 30% de nos patients. Nos données épidémiologiques et nos résultats sont presque identiques à ceux de la littérature. Quant aux résultats angulaires, ils sont nettement inférieurs aux séries de plaques, à l'opposé, leurs résultats infectieux portent à la prudence et certains séries de clous rapportent d'excellents résultats angulaires à condition d'avoir un montage stable. A la lumière de ces résultats, nous sommes en droit de conclure au grand intérêt d'élargir les indications classiques de l'enclouage centromédullaire verrouillé à la prise en charge des fractures du quart distal de la jambe, à condition d'avoir un montage stable par un double verrouillage distal et une ostéosynthèse primaire des fractures distales de la fibula.

la synovite villonodulaire pigmentée (SVNP) est une prolifération bénigne rare de la synoviale des articulations, des bourses séreuses et des gaines tendineuses, d'étiopathogénie inconnue. Notre travail porte sur 20 cas de SVN du genou colligés à l'hôpital militaire Avicenne de Marrakech sur une période de 9 ans allant de janvier 2000 au décembre 2009 Il vise à identifier les spécificités de cette lésion, et à étudier ses principaux aspects anatomocliniques et pronostiques. L'incidence annuelle était de 2,2 cas par an, Ils étaient 15 hommes et 5 femmes, d'âge moyen de 32,5 ans, atteints du coté droit dans 55%des cas sous un mode mono articulaire chez 18 patients et bi articulaire chez un seul. La douleur et la tuméfaction étaient présentes dans 80% des cas, une masse palpable dans un cas, un syndrome méniscal a été retenu dans un cas, une mono arthrite septique dans 3 circonstances de même qu'un kyste poplité dans 2 autres. L'atteinte était diffuse dans 14 cas (70%), localisée dans 6 cas. L'imagerie par résonnance magnétique(IRM) pratiquée chez 5 patients était évocatrice chez 3, l'arthroscopie diagnostique a été utilisée chez 2 malades. La confirmation s'est faite à chaque fois à l'examen anatomopathlogique. Le traitement a consisté en une synovectomie subtotale dans 15 cas et en l'exérèse de la tumeur dans les autres formes localisées, 2 cas présentant une destruction ostéocartilagineuse ont nécessité une arthroplastie. L'évolution a été marquée par la survenue de 2 récidives sous la forme diffuse avec un recul de 3, 7 ans. On a noté une raideur avec atrophie quadricipitale chez 3 patients et une arthrolyse a été réalisée. Un cas de SVN confirmé par l'histologie s'est révélé être 5 mois après la synovectomie totale un Synovialosarcome monophasique envahissant l'os d'où l'indication de l'amputation.

Le débat principal autour des fractures de l'humérus se centre sur les indications thérapeutiques car tout type de stabilisation orthopédique ou chirurgicale trouve des défenseurs parfois inconditionnels et véhéments. A travers cette étude rétrospective, nous avons revu 80 patients traités initialement par embrochage fasciculé centromédullaire selon Hackethal au service de traumatologie orthopédie de l'hôpital militaire Avicenne entre janvier 2000 et janvier 2012. Les fractures ont été classées selon la classification AO et selon la classification de Hackethal modifiée par De La Caffinière. L'évaluation fonctionnelle a utilisé la classification de Stewart et Hundley modifiée. Nous avons obtenu 60 très bons résultats, 6 bons résultats, 2 assez bons résultats et 2 mauvais résultats. Les deux mauvais résultats étaient des cas de pseudarthrose. Nous n'avons pas noté de paralysie radiale iatrogène, ni d'infection, ni de migration de broches. Le délai moyen de consolidation a été de 9semaines et 6 jours. C'est une méthode fiable, de réalisation facile et à faible cout économique, qui fournit une bonne stabilisation du foyer de fracture permettant ainsi la mobilisation précoce avec des résultats fonctionnels excellents.

The Wadi Isser watershed is a continental basin that is currently under severe water erosion. The Mediterranean climatic conditions and associated alterations have prevailed since the Early Quaternary and deposited clay-rich sediments. This study aims to determine clay minerals that accelerate gully erosion in Wadi Isser, northern Algeria. Mineralogical analysis by X-ray diffraction (XRD) was carried out for thirteen samples, which are representatives of different stratigraphic units of the Wadi Isser watershed that are subject to erosion. The results distinguish three behaviors of clay minerals, significant to gully erosion. Kaolinite, chlorite and illite are stable minerals and have no influence on erosive potential. Interstratified chlorite-vermiculite, vermiculite, interstratified illite-vermiculite and illite-smectite are water acceptors and smectite is swelling clay mineral. The water acceptors and swelling clay minerals accelerate the gully erosion.

This work is aimed at the detection of adult images that appear in Internet. Skin detection is of the paramount importance in the detection of adult images. We build a maximum entropy model for this task. This model, called the First Order Model in this paper, is subject to constraints on the color gradients of neighboring pixels. Parameter estimation as well as optimization cannot be tackled without approximations. With Bethe tree approximation, parameter estimation is eradicated and the Belief Propagation algorithm permits to obtain exact and fast solution for skin probabilities at pixel locations. We show by the Receiver Operating Characteristics (ROC) curves that our skin detection improves the performance in the previous work in the context of skin pixel detecton rate and false positive rate. The output of skin detection is a grayscale skin map with the gray level indicating the belief of skin. We then calculate 9 simple features from this map which form a feature vector. We use the fit ellipses to catch the characteristics of skin distribution. Two fit ellipses are used for each skin map---the fit ellipse of all skin regions and the fit ellipse of the largest skin region. They are called respectively Global Fit Ellipse and Local Fit Ellipse in this paper. A multi-layer perceptron classifier is trained for these features. Plenty of experimental results are presented including photographs and a ROC curve calculated over a test set of 5,084 photographs, which show stimulating performance for such simple features.