A5087405854- Vibration Control and Rheological Fluids
- Neural Networks and Applications
- Fuzzy Logic and Control Systems
- Emotion and Mood Recognition
- Hydraulic and Pneumatic Systems
- Vehicle Dynamics and Control Systems
- Structural Health Monitoring Techniques
- Speech and Audio Processing
- Machine Fault Diagnosis Techniques
- Music and Audio Processing
- Anomaly Detection Techniques and Applications
- Gear and Bearing Dynamics Analysis
- Elevator Systems and Control
- Advanced Control Systems Design
- Railway Engineering and Dynamics
- Advanced Clustering Algorithms Research
- Complex Network Analysis Techniques
- Tropical and Extratropical Cyclones Research
- Adaptive Control of Nonlinear Systems
- Fault Detection and Control Systems
- Fractional Differential Equations Solutions
- Handwritten Text Recognition Techniques
- Text and Document Classification Technologies
- Optical Systems and Laser Technology
- Software Engineering Research
Van Lang University
2022-2024
Ton Duc Thang University
2014-2022
Industrial University of Ho Chi Minh City
2012-2016
Inha University
2012-2015
Ho Chi Minh City University of Industry and Trade
2012-2014
Recently, speech emotion recognition (SER) has become an active research area in processing, particularly with the advent of deep learning (DL). Numerous DL-based methods have been proposed for SER. However, most existing models are complex and require a large amounts data to achieve good performance. In this study, new framework attention-based dilated convolutional-recurrent neural networks coupled hybrid augmentation method was addressing SER tasks. The constitutes upsampling technique...
This paper focuses on building a controller for active suspension system of train cars in the case that sprung mass and model error are uncertainty parameters. The is always varied due to many reasons such as changing passengers load or impacting wind operating while an unknown difference between used survey real also exists. built based adaptive neuro-fuzzy inference (ANFIS), sliding mode control, observer (NFSmUoC) magnetorheological damper (MRD) which can be seen actuator applying force....
In many real applications, building and updating adaptive neuro-fuzzy inference system (ANFIS) based on noisy measuring data sources need to be performed such that the filtering impulse noise (IN) from initial datasets (IDSs) establishing ANFIS via filtered IDS are carried out simultaneously. Focused this purpose, in paper, a novel recurrent mechanism as well solution for IN Lyapunov stability theory is proposed establish an online filter (AOINF). Using AOINF, kernel fuzzy-C-means clustering...
Vibration control systems using smart dampers (SmDs) such as magnetorheological and electrorheological (MRD ERD), which are classified the integrated structure-SmD (ISSmDCSs), have been actively researched widely used. This work proposes a new controller for class of ISSmDCSs in high accuracy SmD models well increment ability to deal with uncertainty time delay be expected. In order achieve this goal, two formualtion steps required; non-parametric model based on an adaptive neuro-fuzzy...
Speech emotion recognition (SER) has several applications, such as e-learning, human-computer interaction, customer service, and healthcare systems. Although researchers have investigated lots of techniques to improve the accuracy SER, it been challenging with feature extraction, classifier schemes, computational costs. To address aforementioned problems, we propose a new set 1D features extracted by using an overlapping sliding window (OSW) technique for SER in this study. In addition, deep...
This paper proposes a new algorithm, named establishing neuro-fuzzy system (ENFS), to identify dynamic characteristics of smart dampers such as magnetorheological (MR) and electrorheological (ER) dampers. In the ENFS, data clustering is performed based on proposed algorithm partitioning space (PDS). Firstly, PDS builds clusters in joint input–output with appropriate constraints. The role these constraints create reasonable distribution clusters. ENFS then uses perform following tasks. fuzzy...
Bearing is an important machine detail that appears in almost all mechanical systems. Estimating its operating condition online order to hold the initiative exploiting systems, therefore, one of most urgent requirements. In this paper, we propose bearing damage identifying method named ASSBDIM based on adaptive neuro-fuzzy inference system (ANFIS), singular spectrum analysis (SSA), and sparse filtering (SF). It process with offline phases. phase, by applying SSA SF measured data stream typed...
The optimal number of clusters ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</i> <sub xmlns:xlink="http://www.w3.org/1999/xlink">opt</sub> ) is one the determinants clustering efficiency. In this article, we present a new method quantifying for centroid-based clustering. First, propose validity index named fRisk( based on fuzzy set theory. It takes role normalization and accumulation local risks coming from each action either splitting...
This paper focuses on optimal design of an interval type-2 fuzzy logic system (IT-2FLS) to cope with uncertainty issue training set and noisy data. Content the solution is depicted based proposed algorithm optimally IT-2FLS from a dataset, named OD-T2FLS. The major concept OD-T2FLS combination useful method clustering data space establish type-1 (T-1FLS) appropriate way transform T-1FLS into as well adjust parameters IT-2FLS. Firstly, improved adaptive neuro-fuzzy inference (ANFIS), IM-ENFS,...
This paper proposes a multi-modal approach for speech emotion recognition (SER) using both text and audio inputs. The embedding is extracted by vision-based architecture, namely VGGish, while the transformer-based BERT. Then, these embeddings are fused concatenation to recognize emotional states. To evaluate effectiveness of proposed method, benchmark dataset, IEMOCAP, employed in this study. Experimental results indicate that method very competitive better than most latest state-of-the-art...