Article
Biochemical Research Methods
Zhou Yao, Wenjing Zhang, Peng Song, Yuxue Hu, Jianxiao Liu
Summary: This study proposed a hybrid deep neural network model called DeepFormer, which is based on convolutional neural network (CNN) and flow-attention mechanism for DNA sequence function prediction. Experimental results showed that DeepFormer significantly outperformed other four methods and demonstrated strong robustness.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biology
Yunchou Yin, Zhimeng Han, Muwei Jian, Gai-Ge Wang, Liyan Chen, Rui Wang
Summary: In recent years, Unet and its variants have achieved remarkable success in medical image processing. However, some Unet variants increase their performance by significantly increasing the number of parameters. To address this issue, we propose a lightweight medical image segmentation network called AMSUnet, which utilizes atrous multi-scale (AMS) convolution. Our model only requires 2.62 M parameters while achieving excellent segmentation performance for small, medium, and large-scale targets.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Shanchen Pang, Yu Zhuang, Sibo Qiao, Fuyu Wang, Shudong Wang, Zhihan Lv
Summary: This study proposes a dual-channel transformer graph model (DCTGM) for predicting miRNA-disease associations by learning multi-scale representations. Experimental results show that the model is effective in predicting potential miRNA-disease associations.
COGNITIVE COMPUTATION
(2022)
Article
Energy & Fuels
Yulong Liu, Tao Jin, Mohamed A. Mohamed
Summary: This paper proposes a novel dual-attention optimization model (DAOM) for the classification of power quality disturbances (PQDs). The model utilizes local feature attention mechanism (LFAM) and channel attention mechanism (CAM) to classify the PQDs and sampling points. The proposed model achieves an average classification accuracy of 98.95% in a 30 dB white noise environment, outperforming other deep learning-based models.
Article
Computer Science, Information Systems
Yizhao Wu, Yanping Chen, Yongbin Qin, Ruizhang Huang, Ruixue Tang
Summary: Recognizing entities and extracting their relations are important tasks in information extraction. Recent works have focused on leveraging entity markers for better span representations and have achieved promising performance. However, existing works have two shortcomings: (1) previous markers are randomly embedded in distributed representations, ignoring semantic information relevant to the targeted tokens; (2) most works simply implant markers into a sentence, lacking the ability to encode the interrelation between multiple tokens. This work proposes a marker collaborating model for entity and relation extraction, consisting of two modules, and achieves state-of-the-art performance on three standard benchmarks (ACE04, ACE05, and SciERC).
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Jerry Chun-Wei Lin, Yinan Shao, Youcef Djenouri, Unil Yun
Summary: The paper introduces an ASRNN model based on a hierarchical attention neural semi-CRF for sequence labeling tasks, which integrates information from different levels through a hierarchical structure and attention mechanism, leading to improved performance.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Chemistry, Analytical
Yang Liu, Jie Jiang, Jiahao Sun, Xianghan Wang
Summary: The authors proposed a new network, InterNet, to improve hand pose estimation accuracy, but there is still room for improvement. By redesigning a feature extractor based on the architecture of MobileNet v3 and MoGA, and introducing the latest achievements in computer vision, the authors achieved greater performance improvement compared to InterNet and other networks.
Article
Computer Science, Artificial Intelligence
Yifan Hou, Ge Cheng, Yun Zhang, Dongliang Zhang
Summary: Law article prediction is a task of predicting relevant laws and regulations in a case based on its description text, with great potential in improving judicial efficiency. Current research often focuses on single cases, using neural network methods to extract features for prediction, neglecting the mining of related information between different data. To address this, we propose a method that integrates common element characteristics for law article prediction, effectively utilizing co-occurrence information to mine relevant common elements and fuse local features. Experimental results demonstrate the effectiveness of our method.
ARTIFICIAL INTELLIGENCE AND LAW
(2023)
Article
Computer Science, Artificial Intelligence
Yu Xue, Chenyi Zhang, Ferrante Neri, Moncef Gabbouj, Yong Zhang
Summary: The study proposes a feature selection method called EAR-FS based on an attention mechanism and hybrid metaheuristic, which reduces the number of features in high-dimensional data while ensuring classification accuracy.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Hao Shen, Zhong-Qiu Zhao, Wenrui Liao, Weidong Tian, De-Shuang Huang
Summary: This paper proposes a joint operation and attention block search algorithm for image restoration tasks. The algorithm searches for optimal combinations of operation blocks and attention blocks to construct a lightweight and effective operation search module and attention search module. The modules are combined to build the final network, and a cross-scale fusion module is introduced to integrate hierarchical features and improve feature expression.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Pengqian Li, Xiaofen Xing, Xiangmin Xu, Bolun Cai, Jun Cheng
Summary: This paper presents a biologically-inspired saliency prediction method that imitates two main characteristics of the human perception process: focalization and orienting. The proposed ACNet consists of two modules, a concentrated module (CM) and a parallel attention module (PAM), which together form the core component ACBlock for progressively refining saliency estimation. Experimental results show that ACNet outperforms state-of-the-art models without prior knowledge or post-processing.
Article
Computer Science, Artificial Intelligence
Nan Jia, Jie Chen, Rongzheng Wang
Summary: This paper proposes an attention-based convolutional neural network for recipe recommendation, which captures users' preferences for different ingredients and provides more accurate recommendations based on user preferences, recipe features, and ingredient features.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Guoquan Dai, Xizhao Wang, Xiaoying Zou, Chao Liu, Si Cen
Summary: This article introduces a new multi-relational graph attention network (MRGAT) that can calculate the importance of different neighboring nodes in a knowledge graph, effectively improving the performance of the network.
Article
Computer Science, Artificial Intelligence
Xin-Cheng Wen, Kun-Hong Liu, Yan Luo, Jiaxin Ye, Liyan Chen
Summary: This study proposes a Capsule Network with Two-Way Attention Mechanism (TWACapsNet) for the Speech Emotion Recognition (SER) problem. Experimental results demonstrate that the proposed method outperforms other neural network models on multiple SER datasets, and the combination of the two ways contributes to the higher and more stable performance of TWACapsNet.
Article
Computer Science, Artificial Intelligence
Yangyang Xu, Zengmao Wang, Jedi S. Shang
Summary: In this study, a personalized attraction enhanced network learning model (PAENL) is proposed for recommendation. By combining user-item feature learning and review feature interaction, PAENL can capture the emotional reviews of different users in a nonlinear manner, outperforming other methods in predicting user behavior.
NEURAL COMPUTING & APPLICATIONS
(2023)