检索结果-内蒙古大学图书馆

TAPE-Pero: Using Deep Representation learning Model to Identify and Localize Peroxisomal Proteins 1

19th international conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Sui, Jianan Chen, Yuehui Cao, Yi Zhao, Yaou Univ Jinan Sch Informat Sci & Engn Jinan Peoples R China Univ Jinan Artificial Intelligence Inst Sch Informat Sci & Engn Jinan Peoples R China Univ Jinan Sch Informat Sci & Engn Shandong Prov Key Lab Network Based Intelligent C Jinan Peoples R China

ISBN: (数字)9789819947492

ISBN: (纸本)9789819947485;9789819947492

Peroxisomes, organelles containing one or more oxidases within a single lipid bilayer, play a crucial role in various metabolic pathways. Incorrect localization of peroxisomal proteins can lead to severe diseases. In this study, we introduced the TAPE-Pero model to improve the accuracy of peroxisomal protein identification and localization. This model incorporates two deep representation learning models, ProSE and BERT-based TAPE, trained on large protein databases, to extract peroxisomal protein features. The data set is balanced using SMOTE, and the optimal feature vector is selected using analysis of variance (ANOVA). Subsequently, nine machine learning classifiers are utilized to identify and locate peroxisomal proteins. Our model outperforms existing state-of-the-art methods with an overall prediction accuracy of 98.97% and 92.57% from tenfold cross-validation and double cross-validation tests on the data set, respectively. The proposed model provides a novel approach for the identification and localization of peroxisomal proteins.

关键词： Peroxisomal proteins SMOTE Deep representation learning Feature selection machine learning

来源：评论

学校读者我要写书评

暂无评论

Biomedical Text Mining: Applicability of machine learning-based Natural Language Processing in Medical database

Biomedical Text Mining: Applicability of Machine Learning-ba...

引用

15th international conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS) held as part of 15th international Joint conference on Biomedical Engineering Systems and Technologies (BIOSTEC)

作者： Mollaei, Nafiseh Cepeda, Catia Rodrigues, Joao Gamboa, Hugo Univ Nova Lisboa Dept Phys Fac Ciencias & Tecnol P-2892516 Monte De Caparica Caparica Portugal

ISBN: (纸本)9789897585524

machine learning has demonstrated superior performance in solving many problems in various fields of medicine compared to non-machine learning approaches. The aim of this review is to understand how machine learning-based Natural Language Processing (ML-NLP) has been applied to the clinical notes databases. Optimization algorithms are listed as examples to demonstrate the simplicity and effectiveness of their applications for clinical notes database. We reviewed the literature in clinical applications of ML-NLP, particularly techniques of deep learning such as mainly in pathology reports of diabetes, schizophrenia, cancer and cardiology, where NLP either on a classical algorithm or with deep learning has been actively adopted. We covered 60 different studies in this domain, focusing on a wide range of medical perspective based algorithms. machine learning-based approaches combine the benefits of health systems with the expertise and experience of human well-being. From this review, it is clear that these techniques can improve the quantification of diagnosis and prognosis of cases and may create tools to assist patients during diagnosis and treatment. We complete this work by providing guidelines on the applicability of ML-NLP by describing the most relevant libraries to extract medical expressions from clinical reports text that can support clinical decision-making.

关键词： Natural Language Processing machine learning Medical Text Mining Biomedical science Clinical Notes

来源：评论

学校读者我要写书评

暂无评论

TransACVP: A Transformer-Based Predictive Model for Identifying Anti-Coronavirus Peptides 6

TransACVP: A Transformer-Based Predictive Model for Identify...

引用

6th international conference on Information Communication and Signal Processing, ICICSP 2023

作者： Li, Min Chen, Hen He, Bifang Medical College Guizhou University Guiyang China

ISBN: (纸本)9798350339994

Since the outbreak of the Corona Virus Disease 2019 (COVID-19) in 2019, human beings have been struggling with this epidemic. Currently, the novel coronavirus still poses a threat to human health. Therefore, developing effective drugs to suppress or treat related diseases caused by the coronavirus remains an urgent need. Studies have shown that many peptide inhibitors exhibit effective inhibitory activity against the coronavirus. In this study, we collected anti-coronavirus peptide sequences and constructed 24 prediction models using four peptide descriptors and six feature selection methods, combined with four traditional machine learning methods. We also constructed three predictive models using three deep learning methods. By comparing the performance of the 27 prediction models in a five-fold cross-validation, we ultimately developed a Transformer-based predictor for identifying anti-coronavirus peptides, named TransACVP. In a five-fold cross-validation, the accuracy, sensitivity, specificity, Matthew's correlation coefficient, and area under the receiver operating characteristic curve of TransACVP are 0.8879, 0.8667, 0.9091, 0.7791, and 0.9163, respectively. © 2023 IEEE.

关键词： anti-coronavirus peptide deep learning machine learning transformer

来源：评论

学校读者我要写书评

暂无评论

A Case Series in Position-Aware Myoelectric Prosthesis Control using Recurrent Convolutional Neural Network Classification with Transfer learning

A Case Series in Position-Aware Myoelectric Prosthesis Contr...

引用

international conference on Rehabilitation Robotics (ICORR)

作者： Williams, Heather E. Hebert, Jacqueline S. Pilarski, Patrick M. Shehata, Ahmed W. Univ Alberta Dept Biomed Engn Edmonton AB T6G 2V2 Canada Univ Alberta Div Phys Med & Rehabil Dept Med Edmonton AB T6G 2R3 Canada Alberta Machine Intelligence Inst Amii Edmonton AB T5J 3B1 Canada

ISBN: (纸本)9798350342758

Position-aware myoelectric prosthesis controllers require long, data-intensive training routines. Transfer learning (TL) might reduce training burden. A TL model can be pretrained using forearm muscle signal data from many individuals to become the starting point for a new user. A recurrent convolutional neural network (RCNN)-based classifier has already been shown to benefit from TL in offline analysis (95% accuracy). The present real-time study tested whether an RCNNbased classification controller with TL (RCNN-TL) could reduce training burden, offer improved device control (per functional task performance metrics), and mitigate what is known as the "limb position effect". 27 participants without amputation were recruited. 19 participants performed wrist/hand movements across multiple limb positions, with resulting forearm muscle signal data used to pre-train RCNN-TL. 8 other participants donned a simulated prosthesis, retrained (calibrated) and tested RCNN-TL, plus trained and tested a conventional linear discriminant analysis classification controller (LDA-Baseline). Results confirmed that TL reduces user training burden. RCNNTL yielded improved task performance durations over LDABaseline (in specific Grasp and Release phases), yet other metrics worsened. Overall, this work contributes training condition factors necessary for TL success, identifies metrics needed for comprehensive control analysis, and contributes insights towards improved position-aware control.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Improving Oracle Bone Characters Recognition via A CycleGAN-Based data Augmentation Method 1

引用

29th international conference on Neural Information Processing

作者： Wang, Wei Zhang, Ting Zhao, Yiwen Jin, Xinxin Mouchere, Harold Yu, Xinguo Cent China Normal Univ Fac Artificial Intelligence Educ Wuhan Peoples R China Nantes Univ Ecole Cent Nantes UMR 6004 LS2N F-44000 Nantes France

ISBN: (数字)9789819916450

ISBN: (纸本)9789819916443;9789819916450

Oracle bone inscription is the earliest writing system in China which contains rich information about the history of Shang dynasty. Automatically recognizing oracle bone characters is of great significance since it could promote the research on history, philology and archaeology. The proposed solutions for oracle bone characters recognition are mainly based on machine learning or deep learning algorithms which rely on a large number of supervised training data. However, the existing dataset suffers from the problem of severe class imbalance. In this work, we propose a CycleGAN-based data augmentation method to overcome the limitation. Via learning the mapping between the glyph images data domain and the real samples data domain, CycleGAN could generate oracle character images of high-quality. The quality is evaluated using the quantitative measure. Totally, 185362 samples are generated which could serve as a complementary to the existing dataset. With these generated samples, the state of the art results of recognition task on OBC306 are improved greatly in terms of mean accuracy and total accuracy.

关键词： Characters recognition Class imbalance data augmentation CycleGAN

来源：评论

学校读者我要写书评

暂无评论

Short-term Electricity Load Prediction Based on machine learning and Improved LSTM Model 6

Short-term Electricity Load Prediction Based on Machine Lear...

引用

6th IEEE international conference on Electronic Information and Communication Technology, ICEICT 2023

作者： Sun, Jinze Wang, Ting Ding, Lijiao Jing, Changqiang School of Information Science and Engineering Linyi University City Shandong Linyi China

ISBN: (纸本)9798350399059

With the continuous development of computers, artificial intelligence is gradually integrated into our lives, and electricity is one of the most important energy sources in today's era. Power load related problems also lead to a lot of power loss, using machine learning to provide reliable power load prediction is of great significance. In this paper, LSTM (Long Short Term Memory Model) is used to forecast power load. The data comes from parts of Linyi City, combined with weather factors such as temperature and sunshine and the daily electricity consumption of continuously developing new energy vehicles to predict the total electricity consumption. LSTM model is used for power load prediction, and the learning rate and iteration times of the model are optimized and adjusted. The short-term power load prediction algorithm of LSTM model with higher accuracy and stronger applicability and stability is obtained by fully considering many influencing factors such as climate and electricity consumption of new energy vehicles that have an impact on power load. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Explainable Artificial Intelligence in Manufacturing Operations: A Bibliometric Analysis 43rd

Explainable Artificial Intelligence in Manufacturing Operati...

引用

43rd IFIP WG 5.7 international conference on Advances in Production Management Systems (APMS)

作者： Presciuttini, Anna Cantini, Alessandra Portioli-Staudacher, Alberto Politecn Milan Dept Management Econ & Ind Engn I-20156 Milan Italy

ISBN: (纸本)9783031716355;9783031716331;9783031716324

This paper presents a bibliometric analysis of explainable artificial intelligence (XAI) within the manufacturing sector, with a focus on the critical areas of quality, maintenance, and production. Despite the increasing integration of XAI in industrial applications, a bibliometric exploration of its impact across these specific dimensions remains uncharted. Our study fills this gap by employing bibliometric methods to map the landscape of XAI research in manufacturing, analyzing publication patterns and thematic evolutions. Understanding this landscape is crucial, as it not only highlights the current state and trajectory of XAI applications in manufacturing but also identifies key areas where further innovation and investigation can significantly enhance efficiency, transparency, and decision-making processes in the industry. Utilizing the Bibliometrix R-package and data from the Scopus database, we analyze 107 publications from 2019 to 2024. We chart the intellectual trajectory of XAI, delving into predominant themes and observing a research progression from foundational machine learning to its sophisticated applications, culminating in Industry 4.0 innovations. The analysis reveals an academic landscape where explainability is increasingly intertwined with the technological advances of smart manufacturing, spotlighting key topics and their evolution that reflect the field's dynamic nature. This investigation offers a novel lens on the bibliometric trends shaping the development of transparent, intelligent systems within the manufacturing sector.

关键词： Explainable Artificial Intelligence Manufacturing operations Literature Review Advanced Analytics machine learning

来源：评论

学校读者我要写书评

暂无评论

An effective and practical gradient inversion attack

引用

international JOURNAL OF INTELLIGENT SYSTEMS 2022年第11期37卷 9373-9389页

作者： Luo, Zeren Zhu, Chuangwei Fang, Lujie Kou, Guang Hou, Ruitao Wang, Xianmin Guangzhou Univ Sch Comp Sci & Cyber Engn Guangzhou Peoples R China Pazhou Lab Guangzhou Peoples R China Def Innovat Inst Artificial Intelligence Res Ctr Beijing Peoples R China Guangzhou Univ Inst Artificial Intelligence & Blockchain Guangzhou Peoples R China

While gradient aggregation playing a vital role in federated or collaborative learning, recent studies have revealed that gradient aggregation may suffer from some attacks, such as gradient inversion, where the private training data can be recovered from the shared gradients. However, the performance of the existing attack methods is limited because they usually require prior knowledge in Batch Normalization and could only reconstruct a single image or a small batch one. To make the attacks less restrictive and more applicable, we propose an effective and practical gradient inversion method in this paper. Specifically, we use cosine similarity to measure the difference of gradients between the synthesized and ground-truth images, and then construct an input regularization for the fully connected layer to ensure the fidelity of the image. Moreover, we apply the total variation denoising strategy to the convolution feature map for further improving the smoothness of the reconstructed image. Experimental results demonstrate that our method can reconstruct high fidelity training data on a large batch size for complex data sets, such as ImageNet.

关键词： federated learning gradient sharing machine learning privacy protection

来源：评论

学校读者我要写书评

暂无评论

Explainable Exploration of the Interplay Between HRV Features and EEG Local Connectivity Patterns in Dyslexia 10th

Explainable Exploration of the Interplay Between HRV Feature...

引用

10th international Work-conference on the Interplay Between Natural and Artificial Computation (IWINAC)

作者： Formoso, Marco A. Gallego-Molina, Nicolas J. Ortiz, A. Rodriguez-Rodriguez, Ignacio Gimenez, Almudena Univ Malaga Commun Engn Dept Malaga 29004 Spain Andalusian Data Sci & Computat Intelligence Inst Granada Germany Univ Malaga Dept Basic Psychol Malaga 29019 Spain

ISBN: (纸本)9783031611391;9783031611407

Heart Rate Variability (HRV) is a measure of the variation in time between successive heartbeats, reflecting the influence of the autonomic nervous system on the heart. It can provide insights into the balance between sympathetic and parasympathetic activity. The relationship between autonomic nervous system function, specifically parasympathetic activity, and certain learning disorders, including dyslexia, is currently under study. In this paper, we propose the use of explainable techniques to explore the relationships between HRV markers and local functional brain activity, estimated by cross-frequency coupling (CFC) from electroencephalography (EEG) signals recorded while auditory stimuli were applied to 7-year-old children. We analyze EEG data to examine the phase-to-phase brainwave coupling and use machine learning tools such as XGBoost and Shapley values to reveal brain regions that most contribute to different HRV features, with a focus on parasympathetic activity. Our findings suggest that HRV features related to stress can explain differential activations in the auditory cortex (Brodmann areas 39 and 40) during auditory stimulation in dyslexic children.

关键词： EEG NIRS HRV markers Explainable Artificial Intelligence Dyslexia

来源：评论

学校读者我要写书评

暂无评论

Prediction method for college student's mental health state based on association rules 23

Prediction method for college student's mental health state ...

引用

3rd international conference on Bioinformatics and Intelligent Computing, BIC 2023

作者： Wang, Zhengli Chen, Zhenxiang Jiang, Xiaoqing Wang, Peicheng Wang, Hucheng School of Information Science and Engineering University of Jinan Jinan China

ISBN: (纸本)9798400700200

Student's mental health problem has been more prevalent in recent years. The common method for predicting mental health involves using machine learning algorithms to dig student's psychological traits based on their network behavior. However, there is a risk that data about network behavior could be exposed. In this paper, we propose a prediction method for college student's mental health based on association rules, whereby, following the privacy calculation of psychological assessment data, the internal and external factors affecting student's mental health are digged with the aid of the improved FP-growth algorithm, and the prediction model of mental health status is constructed. The experimental results show that under the premise of satisfying the privacy protection, the model constructed by the improved association rules algorithm can predict the student's mental health state more accurate. © 2023 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：