No abstract available.
Proceeding Downloads
Crowd Counting Using Scale Enhanced Network with Dual Attention Booster
Crowd counting has been a fundamental yet challenging problem in pattern recognition. Most recent deep models for crowd counting rely on Convolutional Neural Networks (CNNs). Although CNN visual features comprise the spatial and channel features, ...
Retrieval Augmented via Execution Guidance in Open-domain Table QA
The goal of the open-domain table QA task is to answer a question based on retrieving and extracting information from a large corpus of structured tables. Currently, the accuracy of the most popular framework in open-domain QA: the two-stage retrieval, ...
An Improving List Scheduling Algorithm Based on Reinforcement Learning and Task Duplication
Task scheduling plays an important role in query execution, which affects the response time and system throughput of queries. Current database systems use simple heuristic algorithms to determine the order of scheduled tasks and executor allocation. ...
A multi branch feature learning approach for fine-grained visual recognition
Fine-grained visual classification (FGVC) has always been subjecting to large intra-class variances and fine inter-class variances. How to seek discriminative features as many as possible is key factor for FGVC. Traditional FGVC methods tended to adopt ...
Part-GCNet: Partitioning Graph Convolutional Network for Multi-Label Recognition
During the rapid development of deep learning, the multi-label recognition task has achieved pretty performance. Recently, the emergence of graph convolution network (GCN) has further improved the accuracy of multi-label recognition. However, in the ...
Prediction of Protein-ATP Binding Sites Based on Word Vector Convolution Model
Recent studies have shown that the interaction between protein and ATP is closely related to human diseases, and the ATP-binding sites in protein sequences have become the focus of drug design. In order to improve the prediction accuracy of Protein-ATP ...
Regularization Strength Impact on Neural Network Ensembles
In the last decade, several approaches have been proposed for regularizing deeper and wider neural networks (NNs), which is of importance in areas like image classification. It is now common practice to incorporate several regularization approaches in ...
A transmission line fault identification method based on long short-term memory network and random matrix principle
In the past decade, driven by the policy of maximizing the consumption of renewable energy, renewable energy is being integrated into the power grid in the form of centralized power generation or decentralized power generation. The volatility and ...
A Method for the Optimization of Active Power in AC/DC Hybrid System
With the continuous expansion of the scale of wind power, it is necessary to adapt to the change of wind farm output to achieve the consumption of wind power, in order to reduce the total power loss of the entire alternating current (AC) and direct ...
Research on the medication regularity of traditional Chinese medicine for common chronic diseases based on association rules
Chronic diseases are the kind of diseases that cause the most severe disease burden in China and have brought significant challenges to the health of our people. With the increase of its global prevalence, it has become a serious global public health ...
Infrared detector fault classification and prediction technology based on sensitive parameter learning
Infrared detector is an important device with a wide range of applications. Based on the fault sensitive parameter data of infrared detectors, this paper studies the fault classification and fault prediction model of infrared detectors by using machine ...
Customer Churn Combination Prediction Model Based on Convolutional Neural Network and Gradient Boosting Decision Tree
In order to improve the hit ratio of lost customers in telecom industry, a combination prediction model of customer churn based on one-dimensional convolutional neural network(1DCNN) and gradient boosting decision tree(GBDT) is proposed. Firstly, ...
Three-stage Logical Table-to-Text Generation based on Type Control
Table-to-Text generation is to express the information in the table in words. Considering the simplicity and logic of the statement, the task of logical Table-to-Text generation is derived. Logical Table-to-Text generation is to generate logically ...
Self-attention mechanism-based SAR for YOLO-v3 maritime ships image target detection
In recent years, China's maritime construction has been gradually strengthened, and the security of our territorial waters has become a top priority. In this paper, we propose a self-attentive mechanism-based target detection model for YOLO-v3SAR images,...
Life assessment method of electronic components based on reliability factor sharing model
An important problem to be solved in reliability simulation of electronic components is to build component-level reliability models based on device-level evaluation results. When the structure or device information and connection composition information ...
Cross-Individual Obstructive Obstructive Apnea Detection in Snoring Signals Using Hybrid Deep Neural Networks
Sleep apnea syndrome (SAS) is a common sleep problem, among which obstructive sleep apnea (OSA) is the most common. It is estimated that 936 million adults aged 30-69 years suffer from mild to severe obstructive sleep apnea that can result in poor sleep ...
Hybrid Feature Measurement based on Linear and Nonlinear Nonnegative Matrix Factorization
The nonnegative matrix factorization algorithm is an effective data dimensionality reduction method. The principle is to convert the image into a nonnegative linear combination of low dimensional basis images. Nonnegative matrix factorization can be ...
High-quality rainy image generation method for autonomous driving based on few-shot learning
Rainy image generation aims to transfer images from standard domains such as daytime into rainy domains. Related researches can be divided into unsupervised methods and supervised methods according to use of semantic label constraints. The ...
A Tailored Physics-informed Neural Network Method for Solving Singularly Perturbed Differential Equations
Physics-informed neural networks (PINNs) have recently been demonstrated to be effective for the numerical solution of differential equations, with the advantage of small real labelled data needed. However, the performance of PINN greatly depends on ...
Analyses of Software Data and Their Interpretations: A Framework of Information Granules
Data collected from software applications such as issue management systems or version control systems are abstract and require their thorough and comprehensive analysis. Automated issue generation is an understudied area in automated software ...
A deep learning based scene text detector combining two strategies
Detecting scene text has been a challenging task due to the complex geometric layouts of texts. We can broadly classify the state-of-the-art scene text detection methods into two categories. The first category is the top-down methods, which view text ...
Lip Reading Bengali Words
- Md. Masudur Rahman,
- Md Rashad Tanjim,
- Saraf Sumaita Hasan,
- Sayeed Md. Shaiban,
- Mohammad Ashrafuzzaman Khan
This work aims to lip-read Bengali words from talking faces without using audio. Lip reading for English words and sentences is well explored in literature. However, to our knowledge, we are the first to explore this for Bengali words, a language spoken ...
High-performance ultrasonic beamforming algorithm based on deep learning
In this paper, a new deep neural network (DNN) ultrasonic beamformer was proposed to suppress off-axis scattering and improve image quality. The simulated channel signals from cysts and single point targets were decomposed by wavelet, and then the ...
Electromagnetic Pattern Cluster in Latent Space in Near Filed Scanning of a Device
Electromagnetic pattern is an image generated from near field electromagnetic field of a device such as microprogrammed control unit (MCU) when it is working. Many Electro-Magnetic Interference (EMI) sources can be located using the electromagnetic ...
High-Quality-High-Quantity Semantic Distillation for Incremental Object Detection
Model is required to learn from dynamic data stream under incremental object detection task. However, traditional object detection model fails to deal with this scenario. Fine-tuning on new task suffers from a fast performance decay of early learned ...
Research on Ship target recognition based on attention mechanism
Abstract: Marine ship target recognition can effectively identify the categories of sailing ships and realize effective management of ships. It is strategically important for both civil and military domains, but it is highly demanding in terms of ...
A New Handwritten Essay Dataset for Automatic Essay Scoring with A New Benchmark
The study of algorithms for Automatic Essay Scoring (AES) currently is motivated by textual essay-scoring datasets constructed by anonymous teachers from schools. We propose VisEssay, the first essay-scoring dataset containing handwriting images. ...
Matching Long-form Document with Topic Extraction and Aggregation
BERT-based models have been widely used for document matching, but they generally do not perform well on the matching of long-form documents, as the sequence length limitation could lead to loss of information in the document. Also, the increased noise ...
A method for accelerating relations search over big data scenario
We propose an acceleration method for relations search over big data scenario. The relations search is in essence an induced subgraph search of graph data model, which is to search all edges with all adjacent vertices falling into a given vertex set. ...
Evaluating Quality of DIBR-synthesized Views based on Texture and Perceptual Hashing Similarity
Depth-Image-Based Rendering (DIBR) technology is widely used in 3D video systems to synthesize virtual views. However, the DIBR rendering process tends to introduce local and global distortions, especially local geometric distortion, that will severely ...
Index Terms
- Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence