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.     

Audio watermarking technique in frequency domain: comparative study MDCT Vs DCT

Digital watermarking is the art of hiding information in a digital document in order to protect it. The inserted mark and the marked document can be an image, an audio or a video. In this article, we will present a comparative study between two variants of a digital audio watermarking technique operating in the frequency domain. In the first variant, the time-frequency mapping is performed by Modified Discrete Cosine Transform (MDCT). For the second variant, the time-frequency mapping is performed by the Discrete Cosine Transform (DCT). We will study the contribution of each transformation, point of view robustness against different types of attacks delivered by Stirmark audio, imperceptibility by using a statistical approach by calculating the SNR and an objective approach by calculating the ODG notes given by PEAQ and capacity of insertion. Finally, to highlight our results, we will compare the two variants of the proposed technique with some other existing techniques.

     

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.     

A Novel Hybrid Method for River Discharge Prediction

Accurate prediction of river discharge is essential for the planning and management of water resources. This study proposes a novel hybrid method named HD-SKA by integrating two decomposition techniques (termed as HD) with support vector regression (SVR), K-nearest neighbor (KNN) and ARIMA models (combined as SKA) respectively. Firstly, the proposed method utilizes local mean decomposition (LMD) to decompose the original river discharge series into sub-series. Next, ensemble empirical mode decomposition (EEMD) is employed to further decompose the LMD-based sub-series into intrinsic mode functions. Further, the EEMD decomposed components are used as inputs in three data-driven models to predict river discharge respectively. The prediction of all components is then aggregated to obtain the results of HD-SVR, HD-KNN and HD-ARIMA models. The final prediction is obtained by taking the average prediction of these models. The proposed method is illustrated using five rivers in Indus Basin System. In five case studies, six models were built to compare the performance of the proposed HD-SKA model. The data analysis results show that the HD-SKA model performs better than all other considered models. The Diebold-Mariano test confirms the superiority of the proposed HD-SKA model over ARIMA, SVR, KNN, EEMD-ARIMA, EEMD-KNN, and EEMD-SVR models.

     

Microporous Carbon and Carbon/Metal Composite Materials Derived from Bio-Benzoxazine-Linked Precursor for CO2 Capture and Energy Storage Applications

There is currently a pursuit of synthetic approaches for designing porous carbon materials with selective CO₂ capture and/or excellent energy storage performance that significantly impacts the environment and the sustainable development of circular economy. In this study we prepared a new bio-based benzoxazine (AP-BZ) in high yield through Mannich condensation of apigenin, a naturally occurring phenol, with 4-bromoaniline and paraformaldehyde. We then prepared a PA-BZ porous organic polymer (POP) through Sonogashira coupling of AP-BZ with 1,3,6,8-tetraethynylpyrene (P-T) in the presence of Pd(PPh₃)₄. In situ Fourier transform infrared spectroscopy and differential scanning calorimetry revealed details of the thermal polymerization of the oxazine rings in the AP-BZ monomer and in the PA-BZ POP. Next, we prepared a microporous carbon/metal composite (PCMC) in three steps: Sonogashira coupling of AP-BZ with P-T in the presence of a zeolitic imidazolate framework (ZIF-67) as a directing hard template, affording a PA-BZ POP/ZIF-67 composite; etching in acetic acid; and pyrolysis of the resulting PA-BZ POP/metal composite at 500 °C. Powder X-ray diffraction, thermogravimetric analysis, scanning electron microscopy, transmission electron microscopy, and Brunauer–Emmett–Teller (BET) measurements revealed the properties of the as-prepared PCMC. The PCMC material exhibited outstanding thermal stability (T_d10 = 660 °C and char yield = 75 wt%), a high BET surface area (1110 m² g^–1), high CO₂ adsorption (5.40 mmol g^–1 at 273 K), excellent capacitance (735 F g^–1), and a capacitance retention of up to 95% after 2000 galvanostatic charge–discharge (GCD) cycles; these characteristics were excellent when compared with those of the corresponding microporous carbon (MPC) prepared through pyrolysis of the PA-BZ POP precursors with a ZIF-67 template at 500 °C.     

Application of SrRuO3 Nanoparticles Supported with Reduced Graphene Oxide for Degradation of Thiophene Under Visible Light Irradiation

Journal of Inorganic and Organometallic Polymers and Materials - The existence of thiophene (TP) in fuel processing technology is considered a real threat to the environment. So the development of...     

Bi2O3-sensitized hierarchically mesoporous ZnO nanoparticles for Hg(II) reduction

Herein, an affordable and novel approach to design Bi₂O₃-sensitized hierarchically mesoporous ZnO nanoparticles (NPs) with a variety of Bi₂O₃ contents is achieved for Hg(II) reduction upon visible light exposure. TEM images of both ZnO and 3% Bi₂O₃/ZnO samples exhibit nanoscale spherical-like structures with a regular shape and a particle size of ~30 nm. The incorporation of Bi₂O₃ on hierarchically mesoporous ZnO networks allows visible light to be harvested in a broad range, and the mesoporous 3% Bi₂O₃/ZnO heterostructure demonstrates the best photocatalytic efficiency for Hg(II) reduction with a value of ~100% after 60 min. The photoreduction rate over the 3% Bi₂O₃/ZnO heterostructure is enhanced 10 and 20 times more than that of TiO₂-P25 and ZnO NPs. The rate constant of the 3% Bi₂O₃/ZnO heterostructure is 16.8 and 33.6 fold larger than that of TiO₂-P25 and ZnO NPs. The superior Hg(II) photoreduction performance could be ascribed to the synergistic effect, excellent visible-light harvest, large surface area, and pore volume provided by incorporating Bi₂O₃ and the heterojunction design between p-type Bi₂O₃ and n-type ZnO. This alignment of the electronic bands provides charge carrier separation, thereby decreasing the recombination rate. Finally, the mechanisms and kinetics for the photocatalytic reduction of Hg(II) are proposed.