Mobile-based human emotion recognition is very challenging subject, most of the approaches suggested and built in this field utilized various contexts that can be derived from the external sensors and the smartphone, but these approaches suffer from different obstacles and challenges. The proposed system integrated human speech signal and heart rate, in one system, to leverage the accuracy of the human emotion recognition. The proposed system is designed to recognize four human emotions; angry, happy, sad and normal. In this system, the smartphone is used to record user speech and send it to a server. The smartwatch, fixed on user wrist, is used to measure user heart rate while the user is speaking and send it, via Bluetooth, to the smartphone which in turn sends it to the server. At the server side, the speech features are extracted from the speech signal to be classified by neural network. To minimize the misclassification of the neural network, the user heart rate measurement is used to direct the extracted speech features to either excited (angry and happy) neural network or to the calm (sad and normal) neural network. In spite of the challenges associated with the system, the system achieved 96.49% for known speakers and 79.05% for unknown speakers
CD-nanosponges were prepared by crosslinking B-CD with diphenylcarbonate (DPC) using ultrasound assisted technique. 5-FU was incorporated with NS by freeze drying, and the phase solubility study, complexation efficiency (CE) entrapment efficiency were performed. Also, the particle morphology was studied using SEM and AFM. The in-vitro release of 5-FU from the prepared nanosponges was carried out in 0.1N HCl.
5-FU nanosponges particle size was in the nano size. The optimum formula showed a particle size of (405.46±30) nm, with a polydispersity index (PDI) (0.328±0.002) and a negative zeta potential (-18.75±1.8). Also the drug entrapment efficiency varied with the CD: DPC molar ratio from 15.6 % to 30%. The SEM an
... Show MorePower-electronic converters are essential elements for the effective interconnection of renewable energy sources to the power grid, as well as to include energy storage units, vehicle charging stations, microgrids, etc. Converter models that provide an accurate representation of their wideband operation and interconnection with other active and passive grid components and systems are necessary for reliable steady state and transient analyses during normal or abnormal grid operating conditions. This paper introduces two Laplace domain-based approaches to model buck and boost DC-DC converters for electromagnetic transient studies. The first approach is an analytical one, where the converter is represented by a two-port admittance model via mo
... Show MoreSilica-based mesoporous materials are a class of porous materials with unique characteristics such as ordered pore structure, large surface area, and large pore volume. This review covers the different types of porous material (zeolite and mesoporous) and the physical properties of mesoporous materials that make them valuable in industry. Mesoporous materials can be divided into two groups: silica-based mesoporous materials and non-silica-based mesoporous materials. The most well-known family of silica-based mesoporous materials is the Mesoporous Molecular Sieves family, which attracts attention because of its beneficial properties. The family includes three members that are differentiated based on their pore arrangement. In this review,
... Show MoreAnalyzing plantar pressure trajectories is crucial for assessing foot behavior in dynamic gait stability. We propose the identification of foot symmetry and the detection of deformities by analyzing the trajectories of the center of pressure (CoP) and peak pressure (PP). First, using a foot pressure mapping system, plantar pressure data are acquired during a normal gait cycle. After the data have been acquired, post processing extracts both the CoP and PP trajectories over the spatiotemporal domain of foot motion for each foot independently. For this purpose, we used the optical flow technique which accurately estimates the direction of foot motion. The extracted trajectories of each foot are then segmented into, the medial and lateral regi
... Show MoreData-driven models perform poorly on part-of-speech tagging problems with the square Hmong language, a low-resource corpus. This paper designs a weight evaluation function to reduce the influence of unknown words. It proposes an improved harmony search algorithm utilizing the roulette and local evaluation strategies for handling the square Hmong part-of-speech tagging problem. The experiment shows that the average accuracy of the proposed model is 6%, 8% more than HMM and BiLSTM-CRF models, respectively. Meanwhile, the average F1 of the proposed model is also 6%, 3% more than HMM and BiLSTM-CRF models, respectively.