Pub Date : 2024-11-28DOI: 10.1016/j.displa.2024.102905
Huining Pei, Jingru Cao, Man Ding, Ziyu Wang, Yunfeng Chen
The Rapid Upper Limb Assessment method depends mainly on the subjective perception of the assessor, resulting in inconsistent results and a low sensitivity to changes in input variables. In this study, a new scoring system is developed using the Fennec Fox Optimization Algorithm and the Generalized Regression Neural Network approach to overcome the drawbacks of traditional method. First, the deep convolutional neural network was used to identify the keypoints of the human working posture in an image and calculate the joint angle. Second, the new model was used to improve the traditional method, and the prediction results for different postural risk scores were output. The proposed network was trained and tested, and the data were analyzed for comparison. Finally, the correlation between the top 15 predictions in the dataset and the scores was verified. The comparison results show that the proposed method performed better than the other methods in terms of the mean absolute error, mean square error, root-mean-square error, mean absolute percentage error, coefficient of determination, runtime, and spatial complexity. Additionally, the proposed method is more sensitive to small variations in inputs, reducing the likelihood of obtaining the same assessment scores for different postures. This increased sensitivity makes the scoring method more conservative, resulting in a more accurate risk assessment, minimizing potential oversights, and effectively reducing occupational risk. These results underscore the effectiveness of the proposed method in improving the traditional assessment.
{"title":"A assessment method for ergonomic risk based on fennec fox optimization algorithm and generalized regression neural network","authors":"Huining Pei, Jingru Cao, Man Ding, Ziyu Wang, Yunfeng Chen","doi":"10.1016/j.displa.2024.102905","DOIUrl":"10.1016/j.displa.2024.102905","url":null,"abstract":"<div><div>The Rapid Upper Limb Assessment method depends mainly on the subjective perception of the assessor, resulting in inconsistent results and a low sensitivity to changes in input variables. In this study, a new scoring system is developed using the Fennec Fox Optimization Algorithm and the Generalized Regression Neural Network approach to overcome the drawbacks of traditional method. First, the deep convolutional neural network was used to identify the keypoints of the human working posture in an image and calculate the joint angle. Second, the new model was used to improve the traditional method, and the prediction results for different postural risk scores were output. The proposed network was trained and tested, and the data were analyzed for comparison. Finally, the correlation between the top 15 predictions in the dataset and the scores was verified. The comparison results show that the proposed method performed better than the other methods in terms of the mean absolute error, mean square error, root-mean-square error, mean absolute percentage error, coefficient of determination, runtime, and spatial complexity. Additionally, the proposed method is more sensitive to small variations in inputs, reducing the likelihood of obtaining the same assessment scores for different postures. This increased sensitivity makes the scoring method more conservative, resulting in a more accurate risk assessment, minimizing potential oversights, and effectively reducing occupational risk. These results underscore the effectiveness of the proposed method in improving the traditional assessment.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"86 ","pages":"Article 102905"},"PeriodicalIF":3.7,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142759725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-26DOI: 10.1016/j.displa.2024.102896
Jing Liu , Xin Li , Guangtao Zhai
To enhance the visualization of images on high dynamic range (HDR) monitors, it is essential to employ bit-depth enhancement (BDE) methods for converting low bit-depth contents into high bit-depth contents. While many methods have been proposed in recent years, to the best of our knowledge, there is no benchmark to analyze the state-of-the-art methods thoroughly. In this paper, we provide a detailed review of current bit-depth enhancement algorithms, and categorized them into four types: classic pixel-independent methods, traditional spatial context-aware methods, deep learning based spatial BDE methods and fusion based spatio-temporal BDE methods. Meanwhile, we have conducted extensive and fair experimental comparisons to evaluate the effectiveness of each algorithm. Two typical evaluation metrics PSNR and SSIM are employed, and accordingly, we provide a thorough analysis and guidance for future work. This benchmark for bit-depth enhancement aims to benefit related researches in image restoration. The relevant codes and datasets are available at https://github.com/TJUMMG/BDE.
{"title":"An overview of bit-depth enhancement: Algorithm datasets and evaluation","authors":"Jing Liu , Xin Li , Guangtao Zhai","doi":"10.1016/j.displa.2024.102896","DOIUrl":"10.1016/j.displa.2024.102896","url":null,"abstract":"<div><div>To enhance the visualization of images on high dynamic range (HDR) monitors, it is essential to employ bit-depth enhancement (BDE) methods for converting low bit-depth contents into high bit-depth contents. While many methods have been proposed in recent years, to the best of our knowledge, there is no benchmark to analyze the state-of-the-art methods thoroughly. In this paper, we provide a detailed review of current bit-depth enhancement algorithms, and categorized them into four types: classic pixel-independent methods, traditional spatial context-aware methods, deep learning based spatial BDE methods and fusion based spatio-temporal BDE methods. Meanwhile, we have conducted extensive and fair experimental comparisons to evaluate the effectiveness of each algorithm. Two typical evaluation metrics PSNR and SSIM are employed, and accordingly, we provide a thorough analysis and guidance for future work. This benchmark for bit-depth enhancement aims to benefit related researches in image restoration. The relevant codes and datasets are available at <span><span>https://github.com/TJUMMG/BDE</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"86 ","pages":"Article 102896"},"PeriodicalIF":3.7,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-24DOI: 10.1016/j.displa.2024.102900
Baozhen Du , Haiyong Xu , Qunxin Chen
Due to the attenuation and scattering of light in the water, there is a serious degradation for the quality of underwater imaging, severely hindering underwater exploration and research. Therefore, implementing quality assessment is crucial for the application of underwater visual tasks. To effectively assess the quality of underwater images, a novel no-reference underwater image quality assessment based on multi-scale and mutual information analysis (MMIQA) is proposed. Specifically, considering the issues of color cast and the importance of colorfulness in underwater images, chroma difference maps and chroma saturation maps were created based on chroma components. The statistical features of these maps were then extracted at multiple scales as chroma component features. Additionally, considering the importance of texture and structure, the multi-scale fractal dimension and high-frequency sub-band energy distribution features of the luminance component were extracted as statistical features of multi-scale underwater local texture and structure. Finally, considering the correlation between the chroma and luminance components of the image, the mutual information between chroma and luminance, as well as between luminance sub-band images, was extracted as a statistical measure of underwater mutual information distribution. Experimental results show that, compared to state-of-the-art methods, the proposed MMIQA has the highest correlation with actual quality scores.
{"title":"No-reference underwater image quality assessment based on Multi-Scale and mutual information analysis","authors":"Baozhen Du , Haiyong Xu , Qunxin Chen","doi":"10.1016/j.displa.2024.102900","DOIUrl":"10.1016/j.displa.2024.102900","url":null,"abstract":"<div><div>Due to the attenuation and scattering of light in the water, there is a serious degradation for the quality of underwater imaging, severely hindering underwater exploration and research. Therefore, implementing quality assessment is crucial for the application of underwater visual tasks. To effectively assess the quality of underwater images, a novel no-reference underwater image quality assessment based on multi-scale and mutual information analysis (MMIQA) is proposed. Specifically, considering the issues of color cast and the importance of colorfulness in underwater images, chroma difference maps and chroma saturation maps were created based on chroma components. The statistical features of these maps were then extracted at multiple scales as chroma component features. Additionally, considering the importance of texture and structure, the multi-scale fractal dimension and high-frequency sub-band energy distribution features of the luminance component were extracted as statistical features of multi-scale underwater local texture and structure. Finally, considering the correlation between the chroma and luminance components of the image, the mutual information between chroma and luminance, as well as between luminance sub-band images, was extracted as a statistical measure of underwater mutual information distribution. Experimental results show that, compared to state-of-the-art methods, the proposed MMIQA has the highest correlation with actual quality scores.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"86 ","pages":"Article 102900"},"PeriodicalIF":3.7,"publicationDate":"2024-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-23DOI: 10.1016/j.displa.2024.102899
Xiaoting Zhang , Pengyu Zhao , Ruru Pan , Weidong Gao
Common fabric image retrieval methods ignore the diversity and dynamism of user demands, the results are determined by the query image and cannot be dynamically adjusted. To solve this problem, this study proposes a novel image retrieval method for plaid fabrics based on hand-crafted features and relevant feedback. First, local texture descriptors are extracted by the local binary pattern on the separated images which are processed by Fourier transform. Global texture descriptors are extracted by scale-invariant feature transform (SIFT) and vector of locally aggregated descriptors (VLAD). Second, color moments with image partitioning are extracted to characterize spatial color information of plaid fabric images. Third, the extracted features are fused by the weight allocation for similarity measurement. Finally, the relevant feedback based on meta learning is involved to realize personalized adjustment and optimization of retrieval results. An image retrieval database is built as the benchmark by collecting over 44, 000 plaid fabric samples from the factory. Experiments show that precision and recall at rank eight reach to 70.6% and 62.6%, respectively, and mAP reaches to 0.690. Results prove that the proposed strategy is feasible and effective, which can realize plaid fabric image retrieval fast and efficiently.
{"title":"Plaid fabric image retrieval based on hand-crafted features and relevant feedback","authors":"Xiaoting Zhang , Pengyu Zhao , Ruru Pan , Weidong Gao","doi":"10.1016/j.displa.2024.102899","DOIUrl":"10.1016/j.displa.2024.102899","url":null,"abstract":"<div><div>Common fabric image retrieval methods ignore the diversity and dynamism of user demands, the results are determined by the query image and cannot be dynamically adjusted. To solve this problem, this study proposes a novel image retrieval method for plaid fabrics based on hand-crafted features and relevant feedback. First, local texture descriptors are extracted by the local binary pattern on the separated images which are processed by Fourier transform. Global texture descriptors are extracted by scale-invariant feature transform (SIFT) and vector of locally aggregated descriptors (VLAD). Second, color moments with image partitioning are extracted to characterize spatial color information of plaid fabric images. Third, the extracted features are fused by the weight allocation for similarity measurement. Finally, the relevant feedback based on meta learning is involved to realize personalized adjustment and optimization of retrieval results. An image retrieval database is built as the benchmark by collecting over 44, 000 plaid fabric samples from the factory. Experiments show that precision and recall at rank eight reach to 70.6% and 62.6%, respectively, and mAP reaches to 0.690. Results prove that the proposed strategy is feasible and effective, which can realize plaid fabric image retrieval fast and efficiently.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"86 ","pages":"Article 102899"},"PeriodicalIF":3.7,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-23DOI: 10.1016/j.displa.2024.102892
Yifan Zhao , Changhong Wang , Yifan Ouyang , Jiapeng Zhong , Yuanwei Li , Nannan Zhao
The key to a semantic SLAM system lies in the data association between measurements and landmarks, using the association results to provide constraints for the pose estimation of robot. However, to address the issues in data association models where data continuity and similarity are not sufficiently emphasized and single-level association strategies exhibit low robustness, we propose a data association method based on the Dynamic Hierarchical Dirichlet Process (DHDP), which is an online data association model that can make full use of the continuity and similarity between data to improve the convergence speed of the model, and at the same time, it can also dynamically take into account the influence of previous data on the current data. Additionally, DHDP has a more robust two-level association strategy to improve the accuracy of data association. In the experiments, three different datasets (Simulation dataset, KITTI dataset and TUM dataset) were selected to validate the proposed method, and the results show that DHDP has faster convergence speed and higher association accuracy, and it is able to provide additional constraints to the system when integrating it into the SLAM system, and by compared it with the state-of-the-art SLAM methods, the DHDP-SLAM exhibits higher localization accuracy.
语义 SLAM 系统的关键在于测量值与地标之间的数据关联，并利用关联结果为机器人的姿态估计提供约束条件。然而，针对数据关联模型中存在的数据连续性和相似性不够突出、单层关联策略鲁棒性较低等问题，我们提出了一种基于动态分层狄利克特过程（DHDP）的数据关联方法，它是一种在线数据关联模型，可以充分利用数据间的连续性和相似性来提高模型的收敛速度，同时还能动态考虑先前数据对当前数据的影响。此外，DHDP 还采用了更稳健的两级关联策略，以提高数据关联的准确性。实验选取了三个不同的数据集（Simulation 数据集、KITTI 数据集和 TUM 数据集）来验证所提出的方法，结果表明 DHDP 具有更快的收敛速度和更高的关联精度，并且在将其集成到 SLAM 系统中时能够为系统提供额外的约束，与最先进的 SLAM 方法相比，DHDP-SLAM 表现出更高的定位精度。
{"title":"DHDP-SLAM: Dynamic Hierarchical Dirichlet Process based data association for semantic SLAM","authors":"Yifan Zhao , Changhong Wang , Yifan Ouyang , Jiapeng Zhong , Yuanwei Li , Nannan Zhao","doi":"10.1016/j.displa.2024.102892","DOIUrl":"10.1016/j.displa.2024.102892","url":null,"abstract":"<div><div>The key to a semantic SLAM system lies in the data association between measurements and landmarks, using the association results to provide constraints for the pose estimation of robot. However, to address the issues in data association models where data continuity and similarity are not sufficiently emphasized and single-level association strategies exhibit low robustness, we propose a data association method based on the Dynamic Hierarchical Dirichlet Process (DHDP), which is an online data association model that can make full use of the continuity and similarity between data to improve the convergence speed of the model, and at the same time, it can also dynamically take into account the influence of previous data on the current data. Additionally, DHDP has a more robust two-level association strategy to improve the accuracy of data association. In the experiments, three different datasets (Simulation dataset, KITTI dataset and TUM dataset) were selected to validate the proposed method, and the results show that DHDP has faster convergence speed and higher association accuracy, and it is able to provide additional constraints to the system when integrating it into the SLAM system, and by compared it with the state-of-the-art SLAM methods, the DHDP-SLAM exhibits higher localization accuracy.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"86 ","pages":"Article 102892"},"PeriodicalIF":3.7,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-23DOI: 10.1016/j.displa.2024.102897
Tianxi Yang , Jie Sun , Yiren Chen , Zhibing Yan , Yang Li , Yijian Zhou , Zhonghang Huang , Chang Lin , Qun Yan
Indium is acknowledged as a preferred material for micro-light-emitting diodes (micro-LEDs) flip-chip bonding within the industry, due to its favorable economic characteristics and low melting point. However, indium bumps fabricated via photolithography and thermal evaporation often exhibit irregular shapes and varying heights, and they readily oxidize in air to form a tightly adhered oxide layer (In2O3), leading to flip-chip bonding failures and blind pixels. The reflow process can not only remove the oxide layer but also enhance bump uniformity. Nevertheless, literature on indium reflow predominantly focuses on planar substrates, with limited studies on high-resolution micro-LED chips for flip-chip bonding. This paper details the preparation of micro-LED chips with a pixel density (pixel per inch, PPI) of 3175. An indium bump array with a diameter of approximately 5 μm was prepared on the micro-LED chips using thermal evaporation technology. The influence of reflow time and temperature on indium bumps was thoroughly investigated by the formic acid reflow process, revealing that under the conditions of 270 °C and 180 s, the indium bumps with a narrower size distribution could be reflowed into spherical shapes on the micro-LED structure. Furthermore, an inversely proportional relationship was discovered between mesa/metal layer height and indium bump growth, which influenced the reflow effect. Ultimately, micro-LED chips were integrated with si complementary metal–oxide–semiconductor (CMOS) driver chips through flip-chip bonding technology, resulting in the successful functioning of the devices.
铟因其良好的经济特性和低熔点，被业界公认为微型发光二极管（micro-LED）倒装芯片键合的首选材料。然而，通过光刻法和热蒸发法制造的铟凸块通常形状不规则、高度不一，而且容易在空气中氧化形成紧密附着的氧化层（In2O3），从而导致倒装芯片键合失败和像素盲区。回流工艺不仅能去除氧化层，还能提高凸点的均匀性。然而，有关铟回流焊的文献主要集中在平面基底上，对用于倒装芯片键合的高分辨率微型 LED 芯片的研究有限。本文详细介绍了像素密度（每英寸像素，PPI）为 3175 的微型 LED 芯片的制备方法。采用热蒸发技术在微型 LED 芯片上制备了直径约为 5 μm 的铟凸点阵列。通过甲酸回流工艺深入研究了回流时间和温度对铟凸点的影响，结果表明在 270 °C 和 180 秒的条件下，尺寸分布较窄的铟凸点可以在微型 LED 结构上回流成球形。此外，还发现介质层/金属层高度与铟凸点生长之间存在反比关系，这也影响了回流效果。最终，通过倒装芯片键合技术，微型 LED 芯片与 si 互补金属氧化物半导体（CMOS）驱动芯片实现了集成，并成功运行。
{"title":"Fabrication and Reflow of Indium Bumps for Active-Matrix Micro-LED Display of 3175 PPI","authors":"Tianxi Yang , Jie Sun , Yiren Chen , Zhibing Yan , Yang Li , Yijian Zhou , Zhonghang Huang , Chang Lin , Qun Yan","doi":"10.1016/j.displa.2024.102897","DOIUrl":"10.1016/j.displa.2024.102897","url":null,"abstract":"<div><div>Indium is acknowledged as a preferred material for micro-light-emitting diodes (micro-LEDs) flip-chip bonding within the industry, due to its favorable economic characteristics and low melting point. However, indium bumps fabricated via photolithography and thermal evaporation often exhibit irregular shapes and varying heights, and they readily oxidize in air to form a tightly adhered oxide layer (In<sub>2</sub>O<sub>3</sub>), leading to flip-chip bonding failures and blind pixels. The reflow process can not only remove the oxide layer but also enhance bump uniformity. Nevertheless, literature on indium reflow predominantly focuses on planar substrates, with limited studies on high-resolution micro-LED chips for flip-chip bonding. This paper details the preparation of micro-LED chips with a pixel density (pixel per inch, PPI) of 3175. An indium bump array with a diameter of approximately 5 μm was prepared on the micro-LED chips using thermal evaporation technology. The influence of reflow time and temperature on indium bumps was thoroughly investigated by the formic acid reflow process, revealing that under the conditions of 270 °C and 180 s, the indium bumps with a narrower size distribution could be reflowed into spherical shapes on the micro-LED structure. Furthermore, an inversely proportional relationship was discovered between mesa/metal layer height and indium bump growth, which influenced the reflow effect. Ultimately, micro-LED chips were integrated with si complementary metal–oxide–semiconductor (CMOS) driver chips through flip-chip bonding technology, resulting in the successful functioning of the devices.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"86 ","pages":"Article 102897"},"PeriodicalIF":3.7,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-23DOI: 10.1016/j.displa.2024.102886
Tongtong Zhang , Xiangyue Zhou , Xin Li , Yongjie Wang , Qimeng Fan , Juping Liang , Fan Wu , Xuan Zhou , Qing Du
Background:
Brain–computer interface (BCI)-mediated neurofeedback training (BCI-NFT) has emerged as a highly promising treatment in the field of neurorehabilitation. Many previous studies have demonstrated the efficacy of BCI techniques in clinical rehabilitation, but children are largely neglected in BCI research.
Purpose:
This systematic review aimed to synthesize existing studies from technical and clinical application perspectives to identify the current state of research on noninvasive brain–computer interface (NBCI) technology in children with two major neurodevelopmental disorders, autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD).
Methods:
Five relevant electronic databases were searched (PubMed, Web of Science, the Cochrane Library, Embase, and the Cumulative Index of Nursing and Allied Health Literature). The publication dates ranged from the inception of each database to June 2024. Randomized controlled trials (RCTs) investigating the use of NBCI technology in children with ASD or ADHD were included. Manual searches of the clinical trial registry platforms and the reference lists of reviews related to the study topic were also conducted. Two independent reviewers performed the literature screening, data extraction, and risk of bias assessment.
Results:
A total of 24 RCTs involving 1998 children with ASD or ADHD were included in this systematic review. With respect to input brain signals, functional magnetic resonance imaging (fMRI) (4.2%), electroencephalography (EEG) combined with fMRI (4.2%), and EEG combined with galvanic skin response (GSR) sensors (4.2%) were utilized in one study each. Seven studies employed EEG combined with electrooculogram (EOG) (29.1%), and the remaining fourteen studies used EEG alone (58.3%). Compared with those of the controls, significant improvements in both behavioral aspects and brain activity in patients were observed in eleven studies (45.8%). NBCI technology has a positive effect on both the behavioral and brain activity levels of children with ASD or ADHD, while it still faces challenges in the paediatric population, particularly in terms of signal processing and the unique cognitive and physiological developmental stages of children, which may complicate the application of these technologies in this population.
Conclusion:
It demonstrated that there has a high potential for NBCI application in the field of neurodevelopmental disorders. Future research should focus on developing advanced machine learning algorithms to improve neural signal decoding capabilities and on creating child-appropriate application paradigms to explore the long-term efficacy of these algorithms.
{"title":"Noninvasive brain–computer interfaces for children with neurodevelopmental disorders: Attention deficit hyperactivity disorder and autism spectrum disorder","authors":"Tongtong Zhang , Xiangyue Zhou , Xin Li , Yongjie Wang , Qimeng Fan , Juping Liang , Fan Wu , Xuan Zhou , Qing Du","doi":"10.1016/j.displa.2024.102886","DOIUrl":"10.1016/j.displa.2024.102886","url":null,"abstract":"<div><h3>Background:</h3><div>Brain–computer interface (BCI)-mediated neurofeedback training (BCI-NFT) has emerged as a highly promising treatment in the field of neurorehabilitation. Many previous studies have demonstrated the efficacy of BCI techniques in clinical rehabilitation, but children are largely neglected in BCI research.</div></div><div><h3>Purpose:</h3><div>This systematic review aimed to synthesize existing studies from technical and clinical application perspectives to identify the current state of research on noninvasive brain–computer interface (NBCI) technology in children with two major neurodevelopmental disorders, autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD).</div></div><div><h3>Methods:</h3><div>Five relevant electronic databases were searched (PubMed, Web of Science, the Cochrane Library, Embase, and the Cumulative Index of Nursing and Allied Health Literature). The publication dates ranged from the inception of each database to June 2024. Randomized controlled trials (RCTs) investigating the use of NBCI technology in children with ASD or ADHD were included. Manual searches of the clinical trial registry platforms and the reference lists of reviews related to the study topic were also conducted. Two independent reviewers performed the literature screening, data extraction, and risk of bias assessment.</div></div><div><h3>Results:</h3><div>A total of 24 RCTs involving 1998 children with ASD or ADHD were included in this systematic review. With respect to input brain signals, functional magnetic resonance imaging (fMRI) (4.2%), electroencephalography (EEG) combined with fMRI (4.2%), and EEG combined with galvanic skin response (GSR) sensors (4.2%) were utilized in one study each. Seven studies employed EEG combined with electrooculogram (EOG) (29.1%), and the remaining fourteen studies used EEG alone (58.3%). Compared with those of the controls, significant improvements in both behavioral aspects and brain activity in patients were observed in eleven studies (45.8%). NBCI technology has a positive effect on both the behavioral and brain activity levels of children with ASD or ADHD, while it still faces challenges in the paediatric population, particularly in terms of signal processing and the unique cognitive and physiological developmental stages of children, which may complicate the application of these technologies in this population.</div></div><div><h3>Conclusion:</h3><div>It demonstrated that there has a high potential for NBCI application in the field of neurodevelopmental disorders. Future research should focus on developing advanced machine learning algorithms to improve neural signal decoding capabilities and on creating child-appropriate application paradigms to explore the long-term efficacy of these algorithms.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"86 ","pages":"Article 102886"},"PeriodicalIF":3.7,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142759027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-23DOI: 10.1016/j.displa.2024.102895
Yuan Liu , Lifeng Gao , Yong Jiang , Tongkai Xu , Li Peng , Xiaoting Zhao , Mengting Yang , Jiaqing Li , Sheng Liang
This study explored the construction and application of efficient deep-learning models to assist the diagnosis of periodontitis in panoramic radiographs. A periodontitis auxiliary diagnosis dataset was constructed in collaboration with the Peking University School of Stomatology. The dataset included 238 panoramic images, covering different stages of healthy teeth and periodontitis. The Labelme annotation tool was used to label tooth instances, alveolar bone contours, and the cemento-enamel junction. A Mask R-CNN model was developed for tooth segmentation, and a U-Net model was developed for segmenting alveolar bone contours and cemento-enamel junctions. Based on the results of tooth instance segmentation, principal component analysis was utilized to fit the direction of the dental long axis. The minimal bounding rectangle of the tooth prediction mask was used to determine the length of the tooth axis. The proportion of alveolar bone loss was calculated based on the distance of the cemento-enamel junction and the alveolar bone level along the dental long axis. An evaluation was conducted on 20 panoramic images comprising 496 teeth. The study achieved an accuracy rate of 90.73% in the staging of periodontitis.
{"title":"AI-aided diagnosis of periodontitis in oral X-ray images","authors":"Yuan Liu , Lifeng Gao , Yong Jiang , Tongkai Xu , Li Peng , Xiaoting Zhao , Mengting Yang , Jiaqing Li , Sheng Liang","doi":"10.1016/j.displa.2024.102895","DOIUrl":"10.1016/j.displa.2024.102895","url":null,"abstract":"<div><div>This study explored the construction and application of efficient deep-learning models to assist the diagnosis of periodontitis in panoramic radiographs. A periodontitis auxiliary diagnosis dataset was constructed in collaboration with the Peking University School of Stomatology. The dataset included 238 panoramic images, covering different stages of healthy teeth and periodontitis. The Labelme annotation tool was used to label tooth instances, alveolar bone contours, and the cemento-enamel junction. A Mask R-CNN model was developed for tooth segmentation, and a U-Net model was developed for segmenting alveolar bone contours and cemento-enamel junctions. Based on the results of tooth instance segmentation, principal component analysis was utilized to fit the direction of the dental long axis. The minimal bounding rectangle of the tooth prediction mask was used to determine the length of the tooth axis. The proportion of alveolar bone loss was calculated based on the distance of the cemento-enamel junction and the alveolar bone level along the dental long axis. An evaluation was conducted on 20 panoramic images comprising 496 teeth. The study achieved an accuracy rate of 90.73% in the staging of periodontitis.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"86 ","pages":"Article 102895"},"PeriodicalIF":3.7,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-22DOI: 10.1016/j.displa.2024.102877
Zhuo Li , Xiaoer Li , Jiangli Shi , Feng Shao
Image quality assessment (IQA) and image enhancement (IE) of night-time images are highly correlated tasks. On the one hand, IQA task could obtain more complementary information from the enhanced image. On the other hand, IE task would benefit from the prior knowledge of quality-aware attributes. Thus, we propose a Perceptually-calibrated Synergy Network (PCSNet) to simultaneously predict and enhance image quality of night-time images. More specifically, a shared shallow network is applied to extract the shared features for both tasks by leveraging complementary in-formation. The shared features are then fed to task-specific sub-networks to predict quality scores and generate enhanced images in parallel. In order to better exploit the interaction of complementary information, intermediate Cross-Sharing Modules are used to form efficient feature representations for the image quality assessment (IQA) and image enhancement (IE) subnetworks. Experimental results of the night-time image datasets show that the proposed approach achieves state-of-the-art performance on both quality prediction and image enhancement tasks.
{"title":"Perceptually-calibrated synergy network for night-time image quality assessment with enhancement booster and knowledge cross-sharing","authors":"Zhuo Li , Xiaoer Li , Jiangli Shi , Feng Shao","doi":"10.1016/j.displa.2024.102877","DOIUrl":"10.1016/j.displa.2024.102877","url":null,"abstract":"<div><div>Image quality assessment (IQA) and image enhancement (IE) of night-time images are highly correlated tasks. On the one hand, IQA task could obtain more complementary information from the enhanced image. On the other hand, IE task would benefit from the prior knowledge of quality-aware attributes. Thus, we propose a Perceptually-calibrated Synergy Network (PCSNet) to simultaneously predict and enhance image quality of night-time images. More specifically, a shared shallow network is applied to extract the shared features for both tasks by leveraging complementary in-formation. The shared features are then fed to task-specific sub-networks to predict quality scores and generate enhanced images in parallel. In order to better exploit the interaction of complementary information, intermediate Cross-Sharing Modules are used to form efficient feature representations for the image quality assessment (IQA) and image enhancement (IE) subnetworks. Experimental results of the night-time image datasets show that the proposed approach achieves state-of-the-art performance on both quality prediction and image enhancement tasks.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"86 ","pages":"Article 102877"},"PeriodicalIF":3.7,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142706218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-22DOI: 10.1016/j.displa.2024.102894
Congwei Liao , Yunfei Liu , Shengdong Zhang
This paper explores the transition speed of A-PWM (Analog Pulse Width Modulation) pixel circuits and feasibility of integration oxide thin-film transistors (TFTs) for MicroLED (µLED) display. A new fast A-PWM type µLED display pixel circuit design is proposed using double gate oxide TFT in the depletion mode as the pull-up transistor of the inverter, while both the main gate and the auxiliary gate electrodes are connected to the source electrode to obtain a constant Zero-VGS biasing. Consequently, the pull-up TFT acts as a constant current source for increasing the output resistance. Meanwhile the pull-down transistor is a single-gate device, and the transconductance is modulated by the input sweep voltage via a coupling capacitor. The advantage of this structure is that even using IGZO (indium-gallium-zinc-oxide) TFTs with a mobility of only 6 cm2/V.s, the PWM transition time of the A-PWM pixel can be reduced from 500 µs to 50 µs. Furthermore, this pixel circuit integrates a switched-capacitor structure to extract and compensate for VT shift. Even with a VT shift of 2 V, the error rate of the PWM fall time remains as low as 0.74 %. Feasibility of the double gate inverter was well verified through measurement of fabrication results.
{"title":"High performance A-PWM μLED pixel circuit design using double gate oxide TFTs","authors":"Congwei Liao , Yunfei Liu , Shengdong Zhang","doi":"10.1016/j.displa.2024.102894","DOIUrl":"10.1016/j.displa.2024.102894","url":null,"abstract":"<div><div>This paper explores the transition speed of A-PWM (Analog Pulse Width Modulation) pixel circuits and feasibility of integration oxide thin-film transistors (TFTs) for MicroLED (µLED) display. A new fast A-PWM type µLED display pixel circuit design is proposed using double gate oxide TFT in the depletion mode as the pull-up transistor of the inverter, while both the main gate and the auxiliary gate electrodes are connected to the source electrode to obtain a constant Zero-V<sub>GS</sub> biasing. Consequently, the pull-up TFT acts as a constant current source for increasing the output resistance. Meanwhile the pull-down transistor is a single-gate device, and the transconductance is modulated by the input sweep voltage via a coupling capacitor. The advantage of this structure is that even using IGZO (indium-gallium-zinc-oxide) TFTs with a mobility of only 6 cm<sup>2</sup>/V.s, the PWM transition time of the A-PWM pixel can be reduced from 500 µs to 50 µs. Furthermore, this pixel circuit integrates a switched-capacitor structure to extract and compensate for V<sub>T</sub> shift. Even with a V<sub>T</sub> shift of 2 V, the error rate of the PWM fall time remains as low as 0.74 %. Feasibility of the double gate inverter was well verified through measurement of fabrication results.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"86 ","pages":"Article 102894"},"PeriodicalIF":3.7,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号