Article
Mathematical & Computational Biology
Jin Xie, Longfei Wang, Paula Webster, Yang Yao, Jiayao Sun, Shuo Wang, Huihui Zhou
Summary: This study uses a deep learning framework to identify and understand abnormal visual attention in autism spectrum disorder (ASD), finding new discriminative features and achieving accurate classification at the individual level, providing a potentially effective method for the clinical diagnosis of ASD.
INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Weijie Wei, Zhi Liu, Lijin Huang, Alexis Nebout, Olivier Le Meur, Tianhong Zhang, Jijun Wang, Lihua Xu
Summary: This paper models the atypical visual saliency in individuals with ASD using a deep neural network, achieving state-of-the-art performance in predicting atypical attention patterns.
Article
Agronomy
Xin Jin, Cheng Lin, Jiangtao Ji, Wenhao Li, Bo Zhang, Hongbin Suo
Summary: This study proposes a method of ridge navigation route extraction, based on deep learning, to address the real-time performance and light interference issues in navigation path recognition in agricultural robots. The technique utilizes the Res2net50 model and integrates the Squeeze-and-Excitation Networks (SE) attention mechanism to focus on key aspects of the image. The results show improved Mean Intersection over Union (MIOU) and F-measure values compared to the Res2net50 network, and the technique proves effective in various illumination situations with low pixel and angle errors.
Article
Behavioral Sciences
Ning Qiang, Jie Gao, Qinglin Dong, Jin Li, Shu Zhang, Hongtao Liang, Yifei Sun, Bao Ge, Zhengliang Liu, Zihao Wu, Tianming Liu, Huiji Yue, Shijie Zhao
Summary: In this study, a hierarchical recurrent variational auto-encoder (HRVAE) was proposed to model fMRI data and a classification framework for brain disorder identification was constructed based on the hierarchical functional brain networks (FBNs). The experimental results showed that the HRVAE model can effectively derive hierarchical FBNs and achieve a high accuracy in identifying autism spectrum disorder (ASD).
BEHAVIOURAL BRAIN RESEARCH
(2023)
Article
Engineering, Electrical & Electronic
Feiniu Yuan, Kang Li, Chunmei Wang, Jinting Shi, Yaowen Zhu
Summary: Feature correlation plays a key role in improving accuracy of semantic segmentation. In this paper, a Multi-scale Feature Attention Network (MFANet) is proposed to fully extract correlation information. Special structures such as Channel Attention Module and Feature Attention Fusion module are designed to capture internal and external correlation, achieving significant improvement in accuracy for semantic segmentation.
DIGITAL SIGNAL PROCESSING
(2022)
Article
Computer Science, Information Systems
Xin Xu, Gang Lv, Yining Sun, Yuxia Hu, Fudong Nian
Summary: This paper focuses on the task of visual grounding (VG) that localizes regions in an image using sentence queries. By utilizing Transformer-based frameworks, the development of VG has made significant progress in capturing image and text contexts without proposals. However, the lack of exploration on hierarchical semantics and cross-interactions between uni-modal encoders has driven the proposal of a Hierarchical Cross-modal Contextual Attention Network (HCCAN) in this study. The HCCAN model incorporates visual-guided and text-guided contextual attention modules, as well as a Transformer-based multi-modal feature fusion module, enabling the capturing of intra-modality and inter-modality relationships along with the hierarchical semantics of textual and visual content. Experimental results on four standard benchmarks demonstrate the effectiveness of the proposed method. The code is publicly available.
MULTIMEDIA SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jiazhong Chen, Qingqing Li, Hefei Ling, Dakai Ren, Ping Duan
Summary: This paper introduces a multisensory framework for video saliency prediction using audio and visual signals, which includes four modules to be implemented through a deep learning network architecture. The method shows a significant improvement over existing saliency models that do not take into account audio stimuli, according to numerical and visual results.
Article
Computer Science, Artificial Intelligence
Chengling Gao, Hailiang Ye, Feilong Cao, Chenglin Wen, Qinghua Zhang, Feng Zhang
Summary: In this study, deep learning technology and a novel approach called multiscale fused network with additive channel-spatial attention (MSF-ACSA) are utilized to effectively address class imbalance in medical image segmentation. The MSF-ACSA method focuses on regions of interest while adaptively recalibrating the channel significance of feature maps, achieving the best performance compared to state-of-the-art approaches for medical image segmentation.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Information Systems
Tianhao She, Fuji Ren
Summary: Autism spectrum disorder (ASD) is a lifelong neurological disability that begins early in childhood. Early intervention can improve the quality of life for individuals with ASD. Researchers have integrated a conversation model into a robot system to support children with autism, using a neural network model as the generative conversational agent to produce meaningful and coherent dialogue responses.
Review
Biology
Marjane Khodatars, Afshin Shoeibi, Delaram Sadeghi, Navid Ghaasemi, Mahboobeh Jafari, Parisa Moridian, Ali Khadem, Roohallah Alizadehsani, Assef Zare, Yinan Kong, Abbas Khosravi, Saeid Nahavandi, Sadiq Hussain, U. Rajendra Acharya, Michael Berk
Summary: Accurate diagnosis and effective rehabilitation are crucial for managing Autism Spectrum Disorder (ASD), and artificial intelligence (AI) techniques, including deep learning methods, play a significant role in assisting physicians with automatic diagnosis and treatment. Neuroimaging techniques, such as structural and functional imaging, provide important insights for ASD diagnosis. Utilizing AI techniques like deep learning is essential for proposing optimal procedures for diagnosing ASD using neuroimaging data due to the complex structure and function of the brain.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Remote Sensing
Tang Liu, Ling Yao, Jun Qin, Ning Lu, Hou Jiang, Fan Zhang, Chenghu Zhou
Summary: In this study, a Multi-Scale Geoscience Network (MS-GeoNet) is proposed for automatic building footprint extraction. The proposed method optimizes for the multi-scale nested characteristics and spatial correlation between buildings and surroundings in remote sensing images, resulting in significant improvements in accuracy compared to traditional methods.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Psychology, Developmental
Maria Eleonora Minissi, Irene Alice Chicchi Giglioli, Fabrizia Mantovani, Mariano Alcaniz Raya
Summary: The study discusses 11 papers on the early assessment of Autism Spectrum Disorder (ASD) using machine learning techniques and children's social visual attention, highlighting the importance of machine learning in early ASD assessment and suggesting ML as a valid biomarker-based procedure for objective diagnosis.
JOURNAL OF AUTISM AND DEVELOPMENTAL DISORDERS
(2022)
Article
Robotics
Nikhil Varma Keetha, Michael Milford, Sourav Garg
Summary: This study introduces a novel approach to estimate the utility of Vector of Locally Aggregated Descriptors (VLAD) clusters in Visual Place Recognition (VPR) using contrastive learning principles. By combining two utility measures, the approach achieves state-of-the-art performance on benchmark datasets while reducing storage and compute time. The study also demonstrates the importance of finer grained categorization for VPR and how utility measures vary across different places and environments.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Psychiatry
Doha Bemmouna, Sebastien Weibel, Markus Kosel, Roland Hasler, Luisa Weiner, Nader Perroud
Summary: The co-occurrence of ADHD and ASD in adults is common. The utility of the AQ as a screening tool for ASD in the context of ADHD is limited, but the imagination subscale can be useful for distinguishing between individuals with ADHD and ASD.
PSYCHIATRY RESEARCH
(2022)
Article
Psychology, Developmental
Lilja Kristin Jonsdottir, Janina Neufeld, Terje Falck-Ytter, Johan Lundin Kleberg
Summary: Studies have shown that individuals with Autism Spectrum Disorder (ASD) tend to avert their gaze from both eyes and mouths. This attentional avoidance is not specific to eyes and is not related to anxiety symptoms.
JOURNAL OF AUTISM AND DEVELOPMENTAL DISORDERS
(2023)
Letter
Dermatology
Zhongxia Zhou, Yutong Yang, Linglin Zhang, Haiyan Zhang, Xiaofei Sun, Yan Zhao, Kang Zeng, Guolong Zhang, Xiuli Wang
JOURNAL OF THE AMERICAN ACADEMY OF DERMATOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Yuming Fang, Haiyan Zhang, Jiebin Yan, Wenhui Jiang, Yang Liu
Summary: Most existing deep learning based salient object detection models have made remarkable progress by adopting multi-level feature fusion strategies. However, these models still face the uncertainty dilemma when predicting salient probabilities of the pixels surrounding the contour of salient objects. To address this, we propose a novel uncertainty-aware SOD model that utilizes multiple supervision signals to guide the network's attention to both the pixels within the salient object and those surrounding its contour. Experimental results on benchmark datasets demonstrate the superiority of our proposed method over existing state-of-the-art SOD methods, particularly in handling challenging scenarios.
PATTERN RECOGNITION
(2023)
Article
Microbiology
Congling Fan, Sheng Liu, Wenfang Dai, Lin He, Hongqiang Xu, Haiyan Zhang, Qinggang Xue
Summary: Marine bivalves play an important role in global aquaculture and estuary ecology. This study identified Vibrio mediterranei as a major bacterium causing mortality in bivalve larvae and juveniles. The research characterized the pathogenicity and mechanisms of V. mediterranei.
MICROBIOLOGY SPECTRUM
(2023)
Article
Energy & Fuels
Haiyan Zhang, Yufei Teng, Josep M. Guerrero, Pierluigi Siano, Xiaorong Sun
Summary: This study proposes a two-layer interdependent network model to investigate failure propagation in network systems. Each subnetwork adopts the Susceptible-Infected-Susceptible (SIS) epidemic-spreading model. Based on this, a failure cooperation propagation model of network systems is constructed, and a node protection mechanism is introduced to ensure the normal operation of key nodes. Simulation using a scale-free cyber network and IEEE118-bus power system is performed to analyze the influence of the coupling effect between them on the final failure scale.
Article
Energy & Fuels
Haiyan Zhang, Kejia Zhu, Zhiwei Guo, Yuguang Chen, Yong Sun, Jun Jiang, Yunhui Li, Zhuoping Yu, Hong Chen
Summary: Recently, wireless power transfer (WPT) technology has shown rapid development and attracted much attention. However, achieving robust power transfer against operating condition fluctuations remains a fundamental challenge. In this article, a theoretical proposal and experimental demonstration show that the robustness of a parity-time (PT) asymmetric system can be significantly improved compared to a PT-symmetric system, under the condition that the PT-asymmetric system operates at a fixed optimal frequency. The improved performance is attributed to a pure real mode known as bound state in the continuum (BIC) in the weak coupling region of the PT-asymmetric system. Experimental verification confirms the higher efficiency of the PT-asymmetric system. The presented framework extends the field of non-Hermitian physics and introduces a novel WPT mechanism for flexible application scenarios.
Review
Environmental Sciences
Haiyan Zhang, Zhigang Yu, Chengcheng Zhu, Ruiqiang Yang, Bing Yan, Guibin Jiang
Summary: The increasing demand for energy and the push towards low-carbon sources have led to the construction of photovoltaic solar energy facilities worldwide. While PV solar energy has lower emissions compared to fossil-based power systems, it still has adverse environmental consequences such as biodiversity loss, climate effects, resource consumption, and disposal of end-of-life PV panels. This review highlights the benefits and potential environmental impacts of PV technologies and proposes recommendations for improving their sustainability.
ENVIRONMENTAL POLLUTION
(2023)
Article
Chemistry, Physical
Shuai Zhang, Shihao Li, Haiyan Zhang, Juanlang Guo, Xianggang Gao, Hongbing Shi, Fangyan Liu, Zeyu Huang, Simin Li, Zhian Zhang
Summary: Li-rich Mn-based layered oxides (LLos) have been identified as promising cathode materials for lithium-ion batteries (LIBs) due to their high energy density, high specific capacity, and environmental friendliness. However, they suffer from capacity degradation and poor rate performance. This study presents a facile method of triphenyl phosphate (TPP) surface treatment to enhance the performance of LLOs by creating an integrated surface structure. The treated LLOs exhibit improved initial coulombic efficiency, capacity retention, and kinetic property, making them a potential choice for high-energy cathode materials in LIBs.
JOURNAL OF COLLOID AND INTERFACE SCIENCE
(2023)
Article
Chemistry, Multidisciplinary
Haiyan Zhang, Youlin Yang, Yi Chen, Xiahui Zhang, Xiaopei Chen
Summary: A nanoparticle-based drug delivery technology has the potential to develop combination cancer therapy more effectively, but the insufficient delivery of drugs into tumor cells reduces the therapeutic efficiency of nanomedicines.
JOURNAL OF EXPERIMENTAL NANOSCIENCE
(2023)
Article
Nursing
Keye Li, Haiyan Zhang, Jiakun Song, Zhufeng Zhang
Summary: This study aimed to explore the effects of hierarchical nursing management on the quality of nursing care and the prognosis of patients with acute PE. The results showed that using hierarchical nursing management can shorten the rescue time, reduce the rate of complications, and improve the nursing quality.
INTERNATIONAL EMERGENCY NURSING
(2023)
Article
Pharmacology & Pharmacy
Ling Wu, Yingda Lin, Songyu Gao, Yongfang Wang, Huiji Pan, Zhaozhi Wang, Marina Pozzolini, Fengling Yang, Haiyan Zhang, Yi Yang, Liang Xiao, Yuan Xu
Summary: Luteolin inhibits triple-negative breast cancer through inducing apoptosis and autophagy via the SGK1-FOXO3a-BNIP3 signaling pathway.
FRONTIERS IN PHARMACOLOGY
(2023)
Article
Pharmacology & Pharmacy
Qingyu Zeng, Jia Liu, Yu Yan, Guolong Zhang, Periru Wang, Haiyan Zhang, Xiaojing Liu, Linglin Zhang, Xiuli Wang
Summary: This study found that modified 5-aminolevulinic acid photodynamic therapy (M-PDT) is effective and painless in the treatment of cutaneous squamous cell carcinoma (cSCC). The regulatory mechanism of M-PDT in cSCC involves blocking the Akt/mTOR-mediated autophagic flux.
FRONTIERS IN PHARMACOLOGY
(2023)
Article
Pharmacology & Pharmacy
Fang-e Shi, Zhe Yu, Chengyue Sun, Peiliang Gao, Haiyan Zhang, Jihong Zhu
Summary: This study aims to monitor, identify, and compare the adverse events (AEs) related to tenecteplase and alteplase, with the objective of exploring the potential safety of tenecteplase for acute ischemic stroke (AIS) and guiding its use to enhance patient safety.
EXPERT OPINION ON DRUG SAFETY
(2023)
Article
Integrative & Complementary Medicine
Senhui Weng, Linwen Huang, Bingxing Cai, Long He, Shuting Wen, Jinghao Li, Zhuotai Zhong, Haiyan Zhang, Chongyang Huang, Yunying Yang, Qilong Jiang, Fengbin Liu
Summary: This study found that Astragaloside IV (AS-IV) improves experimental autoimmune myasthenia gravis (EAMG) by regulating CD4 + T cells and altering the structure and species of gut microbiota of EAMG.
Article
Environmental Studies
Suizi Wang, Jiangwen Fan, Haiyan Zhang, Yaxian Zhang, Huajun Fang
Summary: In this study, the supply and demand of land resources in the Northeast Farming-Pastoral Ecotone (NFPE) were analyzed based on the population-grain relationship. The results showed an increasing carrying capacity of land resources, with a surplus of grain. Most areas in the region were in a state of grain surplus, with some counties having a balanced population-grain relationship and others being overpopulated. The study also identified spatial variations in the carrying capacity of land resources. This research provides valuable insights for informed decision making and sustainable development in the NFPE and similar regions globally.
Article
Engineering, Chemical
Li Wang, Qianhui Tang, Wenhao Li, Xiaoyi Wang, Haiyan Zhang, Jiping Xu, Zhiyao Zhao, Jiabin Yu, Huiyan Zhang, Qian Sun, Yuting Bai
Summary: In this paper, a method of remote sensing image time series pre-processing is proposed, followed by a ACL3DPix2Pix model for pixel-level prediction of remote sensing images. Based on the existing cyanobacterial bloom prediction methods, the spatial and temporal distribution prediction of cyanobacterial blooms is realized by adjusting the existing eutrophication grading criteria. Experimental results demonstrate the effectiveness of this method in predicting cyanobacterial blooms.
DESALINATION AND WATER TREATMENT
(2023)
Article
Engineering, Electrical & Electronic
Xueyu Han, Ishtiaq Rasool Khan, Susanto Rahardja
Summary: This paper proposes a clustering-based TMO method by embedding human visual system models to adapt to different HDR scenes. The method reduces computational complexity using a hierarchical scheme for clustering and enhances local contrast by superimposing details and controlling color saturation by limiting the adaptive saturation parameter. Experimental results show that the proposed method achieves improvements in generating high quality tone-mapped images compared to competing methods.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2024)
Article
Engineering, Electrical & Electronic
Zuopeng Zhao, Tianci Zheng, Kai Hao, Junjie Xu, Shuya Cui, Xiaofeng Liu, Guangming Zhao, Jie Zhou, Chen He
Summary: The research team developed a handheld phone detection network called YOLO-PAI, which successfully achieved real-time detection and underwent testing under various conditions. Experimental results show that YOLO-PAI reduces network structure parameters and computational costs while maintaining accuracy, outperforming other popular networks in terms of speed and accuracy.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2024)
Article
Engineering, Electrical & Electronic
Vivek Sharma, Ashish Kumar Tripathi, Purva Daga, M. Nidhi, Himanshu Mittal
Summary: In this study, a novel ClGan method is proposed for automated plant disease detection. The method reduces the number of parameters and addresses the issues of vanishing gradients, training instability, and non-convergence by using an encoder-decoder network. Additionally, an improved loss function is introduced to stabilize the learning process and optimize weights effectively. Furthermore, a new plant leaf classification method called ClGanNet is introduced, achieving 99.97% training accuracy and 99.04% testing accuracy using the least number of parameters.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2024)
Article
Engineering, Electrical & Electronic
Seongeun Kim, Chang-Ock Lee
Summary: This article introduces a method for segmenting individual teeth in human teeth images by using deep neural networks to obtain pseudo edge-regions and applying active contour models for segmentation.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2024)