Architecture training
-
Part 1 book "Hybrid electric power train engineering and technology - Modeling, control, and simulation" included contents: Introduction to the hybrid power train architecture evolution, the energy–power requirements for hev power train modeling and control, electric machines in hybrid power train employed dynamic modeling backgrounds, generic models of electric machine applications in hybrid electric vehicles power train simulations;.... and other contents
218p dianmotminh04 12-07-2024 0 0 Download
-
The research "Transforming tourism experiences: Unleashing the power of ICTA - An intelligent chatbot tourist's assistant" integrates Maslow's Hierarchy of Needs into the development of an Intelligent Chatbot Tourist's Assistant (ICTA) to enhance tourism services. The study reviews existing literature on tourism, chatbot technology, and Maslow's Hierarchy, and curates a dataset aligned with different levels of the hierarchy. Using Convolutional Neural Networks (CNN) within TensorFlow, the ICTA is trained and evaluated for accuracy, response time, and user satisfaction.
9p tonhiemm 07-06-2024 4 1 Download
-
In this paper, we propose the Adapt-TTS model that allows high-quality audio synthesis from a small adaptive sample without training to solve these problems. The main contributions of the paper are: 1) The extracting mel-vector (EMV) architecture allows for a better representation of speaker characteristics and speech style; 2) An improved zero-shot model with a denoising diffusion model (mel-spectrogram denoiser) component allows for new voice synthesis without training with better quality (less noise).
15p vimulcahy 18-09-2023 5 4 Download
-
In this article, we report on evaluating the NLI task of the competition. We first implement the 5-fold cross-validation evaluation method. We following leverage model architectures pre-trained on cross-lingual language datasets such as XLM-RoBERTa and RemBERT to create contextual word embeddings for classification. Our final result reaches 90.00% on the test dataset of the organizers.
8p viberkshire 09-08-2023 13 6 Download
-
In this paper the architecture of the developing system, main features of its building, including training and checking of neural networks are presented. In particular, the problems of a database forming for identification of various stages of an accident on the base of its modeling with system code are considered.
7p visnape 30-01-2023 6 4 Download
-
This paper proposes a system for ultra-light drone (ULD) auto–detection using only one nonstatic optical PTZ camera. The system includes multi-stages of suspect objects detection, clarification, and distance estimation. An AI model for detection and clarification stages is designed based on the YOLOv3 architecture and trained with a practical dataset.
11p viwmotors 02-12-2022 24 4 Download
-
Ebook "Neural network and deep learning: A textbook" provide readers with content about: an introduction to neural networks; machine learning with shallow neural networks; training deep neural networks; teaching deep learners to generalize; radial basis function networks;...
512p tieuduongchi 07-10-2022 13 6 Download
-
Pre-training and fine-tuning ELECTRA models for various Vietnamese natural language processing tasks
In recent years, the Natural Language Processing community was impacted greatly by models based on the BERT architecture (Devlin et al., 2018). The Transformer-based Masked Language Model (MLM) has yielded significant improvement on many Natural Language Processing problems. However, it requires huge computing power and makes pre-training models a resource-consuming process.
7p visherylsandberg 18-05-2022 25 2 Download
-
In recent years with the explosion of research in artificial intelligence, deep learning models based on convolutional neural networks (CNNs) are one of the promising architectures for practical applications thanks to their reasonably good achievable accuracy. However, CNNs characterized by convolutional layers often have a large number of parameters and computational workload, leading to large energy consumption for training and network inference.
10p vikissinger 03-03-2022 11 2 Download
-
Aim to develop their knowledge and experience in the study field in accordance to their interest, ability and personality. By sharing its experience on student-centered approach in architecture training, AAU also expects to learn the experience and view of the wider architectural community, including both educators and practitioners, to move forwards in this trend.
11p wangxinling 23-07-2021 11 0 Download
-
This paper resolves the problem of detecting small drones in surveillance videos using deep learning algorithms. Single Shot Detector (SSD) object detection algorithm and MobileNet-v2 architecture as the backbone were used for our experiments. The pretrained model was re-trained on custom drone synthetic dataset by using transfer learning’s fine-tune technique. The results of detecting drone in our experiments were around 90.8%.
10p cothumenhmong12 08-07-2021 33 1 Download
-
Keyword spotting (KWS) is one of the important systems on speech applications, such as data mining, call routing, call center, customer-controlled smartphone, smart home systems with voice control, etc. With the goals of researching some factors affecting the Vietnamese Keyword spotting system, we study the combination architecture of CNN (Convolutional Neural Networks)-RNN (Recurrent Neural Networks) on both clean and noise environments with 2 distance speaker cases: 1m and 2m.
11p kethamoi6 01-07-2020 28 2 Download
-
A proper design of the architecture of Artificial Neural Network (ANN) models can provide a robust tool in water resources modelling and forecasting. The performance of different neural networks in groundwater level forecasting was examined in order to identify an optimal ANN model for groundwater level forecast. The Devasugur nala watershed was selected for the study, located at northern part of Raichur district Karnataka and comes under middle Krishna river basin.
10p nguaconbaynhay6 23-06-2020 38 1 Download
-
This leaves a huge gap as to the appropriate awareness and literacy of the world as a collective to be receptive of the massive IoT technology overhaul coming in the nearest future. This paper gives a little insight into the basics of IoT, its core fundamentals, its architecture and furthermore contributes to knowledge the application of IoT to the education sector. Considering the number of connected devices expected to be produced, it is expected also that sufficient amount of personnel are trained in IoT systems adequately to meet with the rising demand.
15p cleopatrahuynh 01-06-2020 14 1 Download
-
Hydrological modelling is a powerful technique of hydrologic system investigation for both the research hydrologists and the practicing water resources engineers involved in the planning and development of integrated approach for management of water resources. In present study, the observed rainfall and runoff data of 2010, 2011, 2013 and 2014years were used as input data. In ANN, input data was divided in 70 per cent, 15 per cent and 15 per cent for training, testing and validation purpose, respectively.
7p nguathienthan2 19-12-2019 23 0 Download
-
The aim of our research is to present a context-awareness multi-agent-based mobile educational game that can generate a series of learning activities for users doing On-the-Job training and make users interact with specific objects in their working environment. We reveal multi-agent architecture (MAA) into the mobile educational game design to achieve the goals of developing a lightweight, flexible, and scalable game on the platform with limited resources such as mobile phones.
30p quenchua1 06-11-2019 20 1 Download
-
The design of Serious Games for training in complex areas of expertise presents many difficulties related to trainers’ participation in the design phase, the formalization of scenarios describing highly complex situations, the limited number of scenarios in Serious Games due to their high costs, and the low re-use level of real-life scenarios. This study proposes functional and technical infrastructure with ARGILE (Architecture for Representations, Games, Interactions, and Learning among Experts) for design of Serious Games.
24p kequaidan1 05-11-2019 15 1 Download
-
This paper proposes a new curriculum framework based on the current situation as well as other advanced training programs in the world.
5p viedison2711 03-09-2019 7 0 Download
-
In this paper, we first describe our efforts in collecting a large data set that covers all 3 major accents of Vietnam located in the Northern, Center, and Southern regions. Then, we detail our ASR system development procedure utilizing the collected data set and evaluating different model architectures to find the best structure for Vietnamese.
14p viconandoyle2711 29-08-2019 25 3 Download
-
In this paper, we present our first Vietnamese speech synthesis system based on deep neural networks. To improve the training data collected from the Internet, a cleaning method is proposed. The experimental results indicate that by using deeper architectures we can achieve better performance for the TTS than using shallow architectures such as hidden Markov model.
15p viconandoyle2711 29-08-2019 21 1 Download