Emotion Recognition from Occluded Facial Images Using Deep EnsembleModel

Facial expression recognition has been a hot topic for decades, but high intraclass variation makes it challenging. To overcome intraclass variation for visual recognition, we introduce a novel fusion methodology, in which the proposed model first extract features followed by feature fusion. Specifically, RestNet-50, VGG-19, and Inception-V3 is used to ensure feature learning followed by feature fusion. Finally, the three feature extraction models are utilized using Ensemble Learning techniques for final expression classification. The representation learnt by the proposed methodology is robust to occlusions and pose variations and offers promising accuracy. To evaluate the efficiency of the proposed model, we use two wild benchmark datasets Real-world Affective Faces Database (RAF-DB) and AffectNet for facial expression recognition. The proposed model classifies the emotions into seven different categories namely: happiness, anger, fear, disgust, sadness, surprise, and neutral. Furthermore, the performance of the proposed model is also compared with other algorithms focusing on the analysis of computational cost, convergence and accuracy based on a standard problem specific to classification applications.     

Standalone noise and anomaly detection in wireless sensor networks: A novel time-series and adaptive Bayesian-network-based approach

Wireless sensor networks (WSNs) consist of small sensors with limited computational and communication capabilities. Reading data in WSN is not always reliable due to open environmental factors such as noise, weakly received signal strength, and intrusion attacks. The process of detecting highly noisy data is called anomaly or outlier detection. The challenging aspect of noise detection in WSN is related to the limited computational and communication capabilities of sensors. The purpose of this research is to design a local time-series-based data noise and anomaly detection approach for WSN. The proposed local outlier detection algorithm (LODA) is a decentralized noise detection algorithm that runs on each sensor node individually with three important features: reduction mechanism that eliminates the noneffective features, determination of the memory size of data histogram to accomplish the effective available memory, and classification for predicting noisy data. An adaptive Bayesian network is used as the classification algorithm for prediction and identification of outliers in each sensor node locally. Results of our approach are compared with four well-known algorithms using benchmark real-life datasets, which demonstrate that LODA can achieve higher (up to 89%) accuracy in the prediction of outliers in real sensory data.     

Enhanced EDCA with Deterministic Transmission Collision Resolution for Real-Time Communication in Vehicular Ad Hoc Networks

The collision prevention system is one of most important research issues on vehicle safety technology. Sending worming messages within the right time and reliable transmission will get prevention of a possible vehicle accident. The communication standards of vehicular networks (VANET) are unable to guarantee the delivery of critical messages within tight deadlines. Indeed, the transmission collisions are handled with probabilistic manner that can reduce the transmission latency; however, it is inept to predict an upper bound value of this delay to verify the deadline. In this paper, we propose a medium access protocol that ensures the delivery of critical messages within a deadline. It is a hard real-time system with delay constant guarantee. We are focusing on improving the EDCA medium access protocol to prioritize critical messages and to get access to the transmission channel within a predictable communication delay. We create a new enhanced access protocol that is compatible with the IEEE 802.11p VANET standards and adapted to real-time communication requirements related to the vehicle collision avoidance problem.     

In vivo study of hybrid biomaterial scaffold bioactive glass–chitosan after incorporation of Ciprofloxacin

The present study aimed to evaluate the effect of bioactive glass as well as the presence of Ciprofloxacin drug (%Cip) into bioactive glass–chitosan composite on the in vivo behavior of these scaffolds. These scaffolds were implanted in the femoral condyl of an ovariectomized rat. The serum and organs (liver and kidney) of the under investigated rats were analyzed. Also the physicochemical properties of the prepared implants were assessed using Fourier transform infrared spectroscopy (FT-IR) and X-ray diffraction (XRD) before and after implantation (at different periods of implantation). Biochemical and histological analyses of the under investigated rats proved the biocompatibility of the prepared scaffolds. The hydroxyapatite like layer was significantly precipitated on the surface of BG–CH scaffold than BG–CH–20Cip. In this same period, FT-IR of BG–CH shows complete disappearance of Si–O–Si. Their characteristics bands were replaced by P–O group arisen form bone apatite bands. Physicochemical results show progressive degradation of BG–CH and BG–CH–20Cip that occurred at the same time as replacement of the implant by an apatite layer. However, the bioresorbability and bioactivity of BG–CH are faster than those of BG–CH–20Cip. Therefore, the incorporation of the Ciprofloxacin in the BG–CH induces a retarding effect on the formation of the hydroxyapatite, and consequently on the ossification, without any side effects on the liver–kidney.     

Essential Oil and Phenolic Compounds of Artemisia herba-alba (Asso.): Composition,Antioxidant, Antiacetylcholinesterase,and Antibacterial Activities

Total phenols, flavonoids, flavonols, and flavanols of the methanolic extract of the aerial part of Artemisia herba-alba were determined. The extract was analyzed by liquid chromatography with photodiode array coupled with electrospray ionisation mass spectrometry and allowed to identify of 10 phenolic compounds. Apigenin-6-C-glycosyl flavonoids and caffeoylquinic acids were identified. Chlorogenic acid and 1,4 dicaffeoylquinic acid being the major constituents. The essential oil obtained by hydrodistillation was analyzed by gas chromatography–mass spectrometry. Twenty-three compounds, representing 97.8% of the total oil, were identified. The most abundant components were β-thujone (41.9%), α-thujone (18.4%), and camphor (13.2%). Methanolic extract and essential oil exhibited a considerable antioxidant activity as evaluated by 2,2-diphenyl-pycrilhydrazil hydrate scavenging activity, reducing power, β-carotene bleaching test, and chelating ability. The methanolic extract was found to be more efficient, while the essential oil exhibited the highest acetylcholinesterase inhibitory activity. Analysis of the antibacterial activity showed that A. herba-alba methanolic extract and essential oil are efficient against gram positive and gram negative bacteria.     

Antibacterial and in vivo reactivity of bioactive glass and poly(vinyl alcohol) composites prepared by melting and sol-gel techniques

Bioactive glass particle is used in the repair of bone defects. This material undergoes a series of surface in vivo reactions, which leads to osteointegration. We evaluated the effect of the bioactive glass synthesis, sol-gel (BG(S)) versus melting (BG(M)), associated with polyvinyl-alcohol (PVA) on in vivo bioactivity with biochemical parameters, liver-kidney histological structure and antibacterial in vitro activity. These composites were testified in many bacteria and implanted in ovariectomized rat. The serum and organs (liver and kidney) of all groups, control and treated rats, were collected to investigate the side effects of our composites, BG(S)-PVA and BG(M)-PVA, in comparison with control and ovariectomized rats. Also, the implants, before and after implantation, were prepared for analysis using physicochemical techniques such as Fourier transform infrared spectroscopy and X-ray diffraction. Our results have shown the stability of natremia, kaliemia, calcemia and phosphoremia. The histological structures of liver and kidney in implanted rats are intact compared to control and ovariectomized rats. BG(S)-PVA is characterized by a higher antibacterial effect on negative and positive gram bacteria than BG(M)-PVA. The physicochemical results have confirmed a progressive degradation of BG(S)-PVA and BG(M)-PVA, while replacing the implant by an apatite layer. But this bioactivity of BG(S)-PVA is faster than BG(M)-PVA. We can therefore confirm, on the one hand, the biocompatibility of our two implants and, on the other hand, the beneficial effect of sol-gel synthesis technique versus melting, both on the antibacterial effect and on the rapid formation of layer hydroxyapatite, and consequently on osteogenesis.     

Ergonomics risk assessment among maintenance operators in a Tunisian railway company: A case study

Railway truck maintenance plays a crucial role for rail transport. It aims at ensuring the availability of the equipment and the safety of the operations. However, maintenance activities often involve uncommon work and nonroutine tasks and it is obvious that maintenance operators are more threatened than other employees to be exposed to various hazards in their workplace. In Tunisia, the prevalence of occupational accidents and injuries among maintenance workers is not well documented. The target of this cross‐sectional study is to assess ergonomics risks associated with maintenance activities in a railway company. Data collection was carried out through a self‐administrated questionnaire and via direct observations. The Body Parts Symptom Survey (BPSS) was used to identify the discomfort level of the workers. More than 100 maintenance operators working in nine different workshops were involved in this study. From BPSS results, this paper proposed a new method to calculate the discomfort index related to each body part in order to calculate the global discomfort index (GDI) for each workshop. Results showed that the most hazardous workshop was rail‐car maintenance workshop (GDI = 43.06). Four main tasks were assessed with normalized score. Final scores were found to be extremely high. To remedy the raised problems, new adjustable workstations were proposed, which showed a considerable improvement on workers’ postures.     

Global outliers detection in wireless sensor networks: A novel approach integrating time-series analysis,entropy, and random forest-based classification.

Wireless sensor networks (WSNs) have recently attracted greater attention worldwide due to their practicality in monitoring, communicating, and reporting specific physical phenomena. The data collected by WSNs is often inaccurate as a result of unavoidable environmental factors, which may include noise, signal weakness, or intrusion attacks depending on the specific situation. Sending high-noise data has negative effects not just on data accuracy and network reliability, but also regarding the decision-making processes in the base station. Anomaly detection, or outlier detection, is the process of detecting noisy data amidst the contexts thus described. The literature contains relatively few noise detection techniques in the context of WSNs, particularly for outlier-detection algorithms applying time series analysis, which considers the effective neighbors to ensure a global-collaborative detection. Hence, the research presented in this article is intended to design and implement a global outlier-detection approach, which allows us to find and select appropriate neighbors to ensure an adaptive collaborative detection based on time-series analysis and entropy techniques. The proposed approach applies a random forest algorithm for identifying the best results. To measure the effectiveness and efficiency of the proposed approach, a comprehensive and real scenario provided by the Intel Berkeley Research Laboratory has been simulated. Noisy data have been injected into the collected data randomly. The results obtained from the experiment then conducted experimentation demonstrate that our approach can detect anomalies with up to 99% accuracy.