The deaf-mutes population is constantly feeling helpless when others do not understand them and vice versa. To fill this gap, this study implements a CNN-based neural network, Convolutional Based Attention Module (CBAM), to recognise Malaysian Sign Language (MSL) in videos recognition. This study has created 2071 videos for 19 dynamic signs. Two different experiments were conducted for dynamic signs, using CBAM-3DResNet implementing ‘Within Blocks’ and ‘Before Classifier’ methods. Various metrics such as the accuracy, loss, precision, recall, F1-score, confusion matrix, and training time were recorded to evaluate the models’ efficiency. Results showed that CBAM-ResNet models had good performances in videos recognition tasks, with recognition rates of over 90% with little variations. CBAM-ResNet ‘Before Classifier’ is more efficient than ‘Within Blocks’ models of CBAM-ResNet. All experiment results indicated the CBAM-ResNet ‘Before Classifier’ efficiency in recognising Malaysian Sign Language and its worth of future research. 相似文献
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. 相似文献
Journal of Materials Science: Materials in Electronics - The successful preparation of graphene in research laboratory has brought a revolutionary progress in almost all the research fields... 相似文献
Zinc oxide (ZnO) nanoparticles (NPs) were synthesized hydrothermally and doped with 4% Neodymium (Nd). The produced NPs were characterized using UV–Vis spectroscopy, X-ray diffraction (XRD), Energy dispersive X-ray analysis, Scanning electron microscopy (SEM), Fourier transform infrared spectroscopy (FTIR), Thermogravimetric analysis (TGA) and Photoluminescence (PL) spectroscopy. With the addition of 4% Nd, the bandgap reduced from 3.20 to 3.00 eV which confirmed successful doping with Nd which also evident from FTIR study. The XRD study showed hexagonal structure of the synthesized material, while SEM study confirmed that Nd-doped ZnO (Nd–ZnO) NPs are well dispersed as compare to ZnO. TGA study revealed that synthesized NPs were much stable to temperature and only 11.3% and 7.2% the total loss occurred during heating range (40–600 °C) in case of ZnO and Nd–ZnO NPs, respectively. The PL intensity of the visible peaks of ZnO reduced after doping with Nd. The degradation of Acid yellow-3 over both the catalysts followed first-order kinetics. The activation energy calculated for the photodegradation reaction was 43.8 and 33.7 kJ/mol using pure ZnO and Nd–ZnO NPs, respectively. About 91% and 80% dye was degraded at the time interval of 160 min using Nd–ZnO and ZnO NPs, respectively. High percent degradation of dye was found at low concentration (10 ppm) and at optimal dosage (0.035 g) of the catalyst. The rate of Acid yellow-3 dye degradation was found to increase with increase in temperature (up to 50 °C) and pH(8) of the medium. The recyclability study showed that both pure ZnO and Nd–ZnO NPs could be reused for the degradation of the given dye. With the addition of H2O2 up to 5 µL, the rate of reaction increased clearly indicating the effect of OH· generation during photocatalysis. When compared with Nd–ZnO NPs at low concentrations, ZnO NPs at higher concentrations were found to be less hazardous. Both the NPs showed best antibacterial activities against Staphylococcus aureus. The hemolytic study indicated that at low concentration, pure ZnO was non-hemolytic as compared to Nd–ZnO.
Flying Ad-hoc Network (FANET) is a new class of Mobile Ad-hoc Network in which the nodes move in three-dimensional (3-D) ways in the air simultaneously. These nodes are known as Unmanned Aerial Vehicles (UAVs) that are operated live remotely or by the pre-defined mechanism which involves no human personnel. Due to the high mobility of nodes and dynamic topology, link stability is a research challenge in FANET. From this viewpoint, recent research has focused on link stability with the highest threshold value by maximizing Packet Delivery Ratio and minimizing End-to-End Delay. In this paper, a hybrid scheme named Delay and Link Stability Aware (DLSA) routing scheme has been proposed with the contrast of Distributed Priority Tree-based Routing and Link Stability Estimation-based Routing FANET’s existing routing schemes. Unlike existing schemes, the proposed scheme possesses the features of collaborative data forwarding and link stability. The simulation results have shown the improved performance of the proposed DLSA routing protocol in contrast to the selected existing ones DPTR and LEPR in terms of E2ED, PDR, Network Lifetime, and Transmission Loss. The Average E2ED in milliseconds of DLSA was measured 0.457 while DPTR was 1.492 and LEPR was 1.006. Similarly, the Average PDR in %age of DLSA measured 3.106 while DPTR was 2.303 and LEPR was 0.682. The average Network Lifetime of DLSA measured 62.141 while DPTR was 23.026 and LEPR was 27.298. At finally, the Average Transmission Loss in dBm of DLSA measured 0.975 while DPTR was 1.053 and LEPR was 1.227.
ABSTRACT Functionalization of multiwalled carbon nanotubes (MWCNTs) with amine group using 4,4′-diaminodiphenyl sulfone (DDS) is achieved after carboxylation of pure MWCNTs (p-MWCNTs). p-MWCNTs, a-MWCNTs (acid functional MWCNTs) and f-MWCNTs (amine functional MWCNTs) were used to fabricate their nanocomposite with PMMA. A comparative study of the humidity characteristics of p-MWCNTs/PMMA, a-MWCNTs/PMMA and f-MWCNTs/PMMA-based capacitive humidity sensors was carried. f-MWCNTs/PMMA-based capacitive humidity sensor shows low hysteresis loss (5%), good response recovery behavior and highest sensitivity (S ~ 9736%) among all the studied composites. The maximum capacitance drift under different relative humidity was 1%RH. 相似文献
Vehicular ad-hoc network (VANET) is characterized as a highly dynamic wireless network due to the dynamic connectivity of the network nodes. To achieve better connectivity under such dynamic conditions, an optimal transmission strategy is required to direct the information flow between the nodes. Earlier studies on VANET’s overlook the characteristics of heterogeneity in vehicle types, traffic structure, flow for density estimation, and connectivity observation. In this paper, we have proposed a heterogeneous traffic flow based dual ring connectivity model to enhance both the message disseminations and network connectivity. In our proposed model the availability of different types of vehicles on the road, such as, cars, buses, etc., are introduced in an attempt to propose a new communication structure for moving vehicles in VANETl under cooperative transmission in heterogeneous traffic flow. The model is based on the dual-ring structure that forms the primary and secondary rings of vehicular communication. During message disseminations, Slow speed vehicles (buses) on the secondary ring provide a backup path of communication for high speed vehicles (cars) moving on the primary ring. The Slow speed vehicles act as the intermediate nodes in the aforementioned connectivity model that helps improve the network coverage and end-to-end data delivery. For the evaluation and the implementation of dual-ring model a clustering routing scheme warning energy aware cluster-head is adopted that also caters for the energy optimization. The implemented dual-ring message delivery scheme under the cluster-head based routing technique does show improved network coverage and connectivity dynamics even under the multi-hop communication system. 相似文献
Conventional approaches of regulating natural biochemical and biological processes are greatly hampered by the complexity of natural systems. Therefore, current biotechnological research is focused on improving biological systems and processes using advanced technologies such as genetic and metabolic engineering. These technologies, which employ principles of synthetic and systems biology, are greatly motivated by the diversity of living organisms to improve biological processes and allow the manipulation and reprogramming of target bioreactions and cellular systems. This review describes recent developments in cell biology, as well as genetic and metabolic engineering, and their role in enhancing biological processes. In particular, we illustrate recent advancements in genetic and metabolic engineering with respect to the production of bacterial cellulose (BC) using the model systems Gluconacetobacter xylinum and Gluconacetobacter hansenii. Besides, the cell-free enzyme system, representing the latest engineering strategies, has been comprehensively described. The content covered in the current review will lead readers to get an insight into developing novel metabolic pathways and engineering novel strains for enhanced production of BC and other bioproducts formation. 相似文献
SEM and light microscopy are of special interest for biologist to observe various features of the living bodies. In the current study we observed the foliar epidermal micro‐morphological characters of 44 grass species using SEM and Light microscopy to assess their taxonomic utility for taxonomists in the identification process. The aim of this study is to use the foliar epidermal structural variations in both upper and lower surfaces for identification of grasses. Significant diversity was observed in both qualitative and quantitative characters using SEM and Light microscopy. Variations were observed in stomatal number, size, guard cells shape, silica bodies, macro‐hairs, micro‐hairs, epidermal cell number, subsidiary cells, prickles, hooks, papillae, and short and long cells. A taxonomic key is prepared using these variations for the identification of grass species. Based on these findings, SEM and Light microscopy of foliar epidermal features can be of special interest for taxonomists in the identification of complex grass taxa. 相似文献