检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Jafari, Mahboobeh Sadeghi, Delaram Shoeibi, Afshin Alinejad-Rokny, Hamid Beheshti, Amin García, David López Chen, Zhaolin Acharya, U. Rajendra Gorriz, Juan M. Internship in BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia Data Science and Computational Intelligence Institute University of Granada Spain BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia UNSW Data Science Hub The University of New South Wales SydneyNSW2052 Australia Health Data Analytics Program Centre for Applied Artificial Intelligence Macquarie University Sydney2109 Australia Data Science Lab School of Computing Macquarie University SydneyNSW2109 Australia Monash University Melbourne Australia School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia Department of Psychiatry University of Cambridge United Kingdom

Schizophrenia (SZ) is a prevalent mental disorder characterized by cognitive, emotional, and behavioral changes. Symptoms of SZ include hallucinations, illusions, delusions, lack of motivation, and difficulties in concentration. While the exact causes of SZ remain unproven, factors such as brain injuries, stress, and psychotropic drugs have been implicated in its development. SZ can be classified into different types, including paranoid, disorganized, catatonic, undifferentiated, and residual. Diagnosing SZ involves employing various tools, including clinical interviews, physical examinations, psychological evaluations, the Diagnostic and Statistical Manual of Mental Disorders (DSM), and neuroimaging techniques. Electroencephalography (EEG) recording is a significant functional neuroimaging modality that provides valuable insights into brain function during SZ. However, EEG signal analysis poses challenges for neurologists and scientists due to the presence of artifacts, long-term recordings, and the utilization of multiple channels. To address these challenges, researchers have introduced artificial intelligence (AI) techniques, encompassing conventional machine learning (ML) and deep learning (DL) methods, to aid in SZ diagnosis. This study reviews papers focused on SZ diagnosis utilizing EEG signals and AI methods. The introduction section provides a comprehensive explanation of SZ diagnosis methods and intervention techniques. Subsequently, review papers in this field are discussed, followed by an introduction to the AI methods employed for SZ diagnosis and a summary of relevant papers presented in tabular form. Additionally, this study reports on the most significant challenges encountered in SZ diagnosis, as identified through a review of papers in this field. Future directions to overcome these challenges are also addressed. The discussion section examines the specific details of each paper, culminating in the presentation of conclusions and findings. © 2023,

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

FAST: Fast annotation with synchronized threads

FAST: Fast annotation with synchronized threads

引用

IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology (CIBCB)

作者： Dongjae Kim Aria S. Hahn Niels W. Hanson Kishori M. Konwar Steven J. Hallam Department of Computer Science University of British Columbia Vancouver BC Canada Koonkie Inc. Menlo Park CA USA Department of Microbiology & Immunology University of British Columbia Vancouver BC Canada Data & Analytics KPMG LLC Seattle WA USA Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA USA Graduate Program in Bioinformatics University of British Columbia Vancouver BC Canada

ISBN: (纸本)9781509000128

FAST is a multi-threaded, I/O optimized Seed-and-Extend alignment program. FAST is extensible to nucleotide sequences making it comparable to both BLASTn and BLASTp, and also features several new usage flags reporting only HSPs meeting user defined e-value cut-offs. FASTs threaded database construction allows fast, low memory database construction e.g., RefSeq (9.4GB) can be indexed in under 5 minutes using 20 threads. The threaded database construction gives users the ability to create custom databases on demand which is useful for tasks requiring self-alignment, such as network construction [30]. Finally, FAST supports incremental database construction enabling users to keep their databases up-to-date by adding sequences without suffering the cost of reformatting the entire database. The FAST source is freely available through GitHub https:// ***/hallamlab/FAST and test datasets can be found on Dropbox https://***/sh/xvvavweuzgqybc4/ AAAWCrRnol67ZsXi2qLQWUuOa?

关键词： Instruction sets Synchronization Random access memory Algorithm design and analysis data structures Indexes

来源：评论

学校读者我要写书评

暂无评论

Dual template using P123-gelatin for synthesized large mesoporous silica for enhanced adsorption of dyes

引用

South African Journal of Chemical Engineering 2023年 43卷 312-326页

作者： Safitri, Widiya Nur Habiddin, Habiddin Ulfa, Maria Trisunaryanti, Wega Bahruji, Hasliza Holilah, Holilah Rohmah, Alya Awinatul Sholeha, Novia Amalia Jalil, Aishah Abdul Santoso, Eko Prasetyoko, Didik Department of Chemistry Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember East Java Keputih Sukolilo Surabaya 60111 Indonesia Chemistry Education Study Program Faculty of Teacher Training and Education Universitas Sebelas Maret Jl. Ir. Sutami 36A Surakarta 57126 Indonesia Department of Chemistry Faculty of Science Universitas Gadjah Mada Sekip Utara Sleman Indonesia Centre for Advanced Material and Energy Sciences Universiti Brunei Darussalam Bandar Seri Begawan BE 1410 Brunei Darussalam Research Center for Biomass and Bioproducts National Research and Innovation Agency of Indonesia (BRIN) Cibinong 16911 Indonesia Department of Food Science and Technology Faculty of Agriculture Halu Oleo University Indonesia College of Vocational Studies Bogor Agricultural University (IPB University) Jalan Kumbang No. 14 Bogor 16151 Indonesia Department of Chemical Engineering Faculty of Chemical and Energy Engineering Universiti Teknologi Malaysia 81310 UTM Johor Skudai Johor Bahru Malaysia

Mesoporous Silica with a large mesopore channel was synthesized using the sol-gel method for dye adsorption. A dual template consisting of P123 and gelatin at different ratios was employed in the sol-gel synthesis to enhance surface area and mesopore diameter. Gelatin is a green pore directing agent that strengthens P123 thermal stability during the calcination of silicate gel. Optimization of P123:gelatin ratio to 1:0.02 increased the surface area of mesoporous silica to 561.9 m²/g and expanded the pore diameter to 10 nm. The large pore diameter and surface area enhanced methylene blue adsorption capacity to 363.63 mg/g. The adsorption of methylene blue on mesoporous silica follows the pseudo second-order kinetic and the Langmuir model. Regeneration studies using thermal and chemical treatments exhibited the potential of mesoporous silica as an adsorbent for multiple adsorption-desorption of dyes. © 2022 The Author(s)

关键词： Dual template Dye Gelatin Mesoporous silica Pluronic P123

来源：评论

学校读者我要写书评

暂无评论

Comparison of multivariate adaptive Poisson Regression spline and multivariate adaptive generalized Poisson Regression spline

引用

AIP Conference Proceedings 2023年第1期2536卷

作者： Septia Devi Prihastuti Yasmirullah Bambang Widjanarko Otok Jerry Dwi Trijoyo Purnomo Dedy Dwi Prastyo Data Science Technology Study Program Faculty of Advanced Technology and Multidiscipline Universitas Airlangga Surabaya 60115 Indonesia Department of Statistics Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Surabaya 60111 Indonesia

The multivariate adaptive regression (MARS) spline is a statistical method introduced by Friedman in 1991. The MARS method has several advantages, especially for data that consider the potential nonlinear pattern. These produce a continuous model on knots where the knot selection process is performed via adaptive procedures, capturing additive effects and interactions between predictor variables, and applied to data modeling with numerical and categorical responses. However, the analyzed data is not only numerical or categorical data, but also count type data. Count type data is often found in the health sector, for example, the number of data on tuberculosis. It invites to modify the MARS model with Poisson regression and generalized Poisson regression, i.e. Multivariate Adaptive Poisson Regression Spline (MAPRS) and Multivariate Adaptive Generalized Poisson Regression Spline (MAGPRS) . In addition, this study aimed to compare MAPRS and MAGPRS when applied to tuberculosis data. By applying MAPRS and MAGPRS to model the number of tuberculosis in Lamongan regency, the MAPRS method outperforms the MAGPRS method. The MAPRS method has a lower RMSE value than the MAGPRS method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Embedding Space Augmentation for Weakly Supervised Learning in Whole-Slide Images

Embedding Space Augmentation for Weakly Supervised Learning ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Imaad Zaffar Guillaume Jaume Nasir Rajpoot Faisal Mahmood Department of Computer Science University College London UK Department of Pathology Harvard Medical School Brigham and Women’s Hospital Boston MA USA Department of Pathology Harvard Medical School Massachusetts General Hospital Boston MA USA Cancer Program Broad Institute of Harvard and MIT Cambridge MA USA Data Science Program Dana-Farber Cancer Institute Boston MA USA Department of Computer Science Tissue Image Analytics Centre University of Warwick Coventry UK Department of Pathology University Hospitals Coventry and Warwickshire NHS Trust Coventry UK The Alan Turing Institute London UK

Multiple Instance Learning (MIL) is a widely employed framework for learning on gigapixel whole-slide images (WSIs) from WSI-level annotations. In most MIL-based analytical pipelines for WSI-level analysis, the WSIs are divided into patches, and deep features for patches (i.e., patch embeddings) are extracted prior to training to reduce the overall computational cost and cope with the GPUs’ limited RAM. Because of this bottleneck, incorporating patch-level data augmentations during training adds an extra computational burden. To overcome this limitation, we present EmbAugmenter, a data augmentation generative adversarial network (DA-GAN) that can synthesize data augmentations in the embedding space rather than in the pixel space, thereby significantly reducing the computational requirements. Experiments on the SICAPv2 dataset show that our approach outperforms MIL without augmentation and is on par with traditional patch-level augmentation for MIL training while being substantially faster.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multivariate Adaptive Regression Splines Segmentation Based on Latent Variable Score in Partial Least Square-Structural Equation Modeling (Case Study: Nutrition Status of Toddlers in Southeast Sulawesi)

SSRN

引用

SSRN 2024年

作者： Otok, Bambang Widjanarko Purhadi Purnomo, Jerry Dwi Trijoyo Mulyanto, Angga Dwi Sriningsih, Riry Fadmi, Fitri Rachmillah Khair, Abdul Department of Statistics Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Department of Mathematics Faculty of Mathematics and Natural Sciences Universitas Negeri Padang West Sumatera Indonesia Public Health Study Program Faculty of Health Sciences Universitas Mandala Waluya Southeast Sulawesi Kendari Indonesia Department of Environmental Health Poltekkes Kemenkes Banjarmasin South Kalimantan Indonesia

Nutrition is a crucial factor that profoundly influences children's growth and development, facilitating proper maturation. Child malnutrition, encompassing stunting, underweight, and severe wasting, constitutes a significant issue in Indonesia. The WHO categorizes the nutritional status of children under-five in Indonesia as chronic, especially in Southeast Sulawesi Province. This research examines the factors influencing the nutritional status of children under-five in Southeast Sulawesi by Partial Least Square Structural Equation Modeling (PLS-SEM). Furthermore, Multivariate Adaptive Regression Splines (MARS) was employed to classify the nutritional condition of children under-five according to factor scores. The findings indicated that the nutritional status of children under-five was affected by parenting, illness, and healthcare factors. The MARS Segmentation Model utilizing basis functions yields more accurate outcomes in evaluating the nutritional condition of children under-five. The models generated for each sub-district vary according to the basis function employed. The nutritional status of children under-five, encompassing stunting, wasting, and underweight, comprises seven areas. This study comprises three significant components: MARS is a novel way for assessing route coefficients in PLS-SEM modelsMARS is a spatial model constructed using basis functionsApplication of MARS-SEM in evaluating the nutritional condition of children under-five in Southeast Sulawesi Province. © 2024, The Authors. All rights reserved.

关键词： Least squares approximations

来源：评论

学校读者我要写书评

暂无评论

Machine learning applications for therapeutic tasks with genomics data

arXiv

引用

arXiv 2021年

作者： Huang, Kexin Xiao, Cao Glass, Lucas M. Critchlow, Cathy W. Gibson, Greg Sun, Jimeng Health Data Science Program Harvard University Boston02120 United States Analytics Center of Excellence IQVIA CambridgeMA02139 United States Center for Observational Research Amgen Thousand OaksCA91320 United States Center for Integrative Genomics Georgia Institute of Technology AtlantaGA30332 United States Department of Computer Science Carle's Illinois College of Medicine University of Illinois at Urbana-Champaign Urbana61820 United States

The genome contains instructions for building the function and structure, and guiding the evolution of molecules and organisms. Recent high-throughput techniques allow the generation of a vast amount of genomics data. However, the path of transforming genomics data into tangible therapeutics is filled with obstacles. We observe that genomics data alone are insufficient but rather require investigation of its interplay with data such as compounds, proteins, electronic health records, images, texts, etc. To make sense of these complex data, machine learning techniques are often utilized for identifying patterns and drawing insights from data. In this review, we study twenty-two genomics applications of machine learning that can enable faster and more efficacious therapeutic development, from discovering novel targets, personalized medicine, developing gene-editing tools all the way to clinical trials and post-market studies. Challenges remain, including technical issues such as learning under different contexts given specific low resource constraints, and practical issues such as mistrust of models, privacy, and fairness. Copyright © 2021, The Authors. All rights reserved.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Characterization and Classification of Purity of Limestone in Madura Island for Industrial Application

引用

Journal of Physics: Conference Series 2021年第1期1951卷

作者： F Munawaroh L K Muharrami Triwikantoro Z Arifin Natural Science Education Study Program Universitas Trunojoyo Madura Bangkalan Indonesia Department of Physics Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Surabaya Indonesia

The characterization and classification of purity of limestone at Madura Island was investigated. Sampling was taken from nine quarries from different areas. The chemical analysis was carried out by X-ray fluorescence (XRF); the crystalline phase was characterized by X-ray diffraction (XRD). Analysis of purity classification based on XRF and XRD results according to British Geological Survey. Limestone has different purity, there are very high, medium, low and impure purity. The sample has a very high purity from Pamekasan (P.1) with CaO content of 99.06 wt% and 100% calcite. The samples are medium purity from Bangkalan (B.1, B.3), Pamekasan (P.2), Sumenep (S.1, and S.3) with CaO content of 91.61- 93.67 wt%. The samples are low purity from S.2 with CaO content 85.79 wt% and 100% dolomite. And the sample has impurities from P.3 and B.2 with CaO content 82.3 wt% and 84.7 wt%. Limestone with very high and medium purity which is processed into PCC can be applied in many industries as filler in rubber, paper making, plastic, paint, food, pharmaceutical, ceramic, adhesives, sealants, agriculture, and animal feed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Antioxidant and Antidiabetic Activities of Melastoma Malabathricum Leaves Extracts

引用

Hunan Daxue Xuebao/Journal of Hunan University Natural sciences 2022年第7期49卷 144-153页

作者： Idris, Muddatstsir Purnomo, Adi Setyo Martak, Fahimah Fatmawati, Sri Department of Chemistry Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Jalan Arif Rahman Hakim Sukolilo Surabaya East Java60111 Indonesia Program of Pharmacy Study Faculty of Mathematics and Natural Sciences University of Lambung Mangkurat A. Yani KM. 35.8 Banjarbaru South Kalimantan70714 Indonesia Agri-Food and Biotechnology Research Center Institut Teknologi Sepuluh Nopember Jalan Arif Rahman Hakim Sukolilo Surabaya East Java60111 Indonesia

Currently, no effective medication is available to treat diabetes despite this disease is a serious health problem. As part of our project to explore Indonesian medicinal plants for antidiabetic agents, this study aimed to investigate the total phenolic and flavonoid contents, antioxidant and antidiabetic properties of Melastoma malabathricum leaves extracts. Spectrophotometric methods were used to determine the total phenolic and flavonoid contents. Antioxidant activity was performed using DPPH, ABTS, and FRAP methods. The in vitro antidiabetic test was conducted through an inhibitory evaluation of α-glucosidase and α-amylase, while STZ-induced diabetic rats were used for in vivo study. The highest value of total phenolic (183.71 ± 0.11 mg GAE/g Extract) was recorded in the methanolic extract and flavonoid (24.10 ± 0.04 mg QE/g Extract) contents were recorded in the EtOAc extract. The methanolic extract has the highest DPPH and ABTS activities with IC50 values of 8.58 ± 0.03 and 4.59 ± 0.03 μg/mL, respectively. It also showed the highest FRAP activity with a 51.15 ± 0.10 µM Fe2+/g. In vitro antidiabetic testing of the methanolic extract of leaves against α-glucosidase and α-amylase was reported for the first time. This novel result showed that the methanolic extract inhibited α-glucosidase and α-amylase with IC50 values of 75.25±1.60 and 52.38±1.32 μg/mL, respectively. A dose of 200 mg/Kg body weight of the methanolic extract reduced rats’ blood glucose rate and serum blood glucose by 51.01% and 37.82%, respectively, after 15 days of treatments. These findings suggested that the methanolic extract of M. malabathricum leaves can be used as a potential source of antioxidant and antidiabetic agents. © 2022 Hunan University. All rights reserved.

关键词： Antioxidants

来源：评论

学校读者我要写书评

暂无评论

EMBEDDING SPACE AUGMENTATION FOR WEAKLY SUPERVISED LEARNING IN WHOLE-SLIDE IMAGES

arXiv

引用

arXiv 2022年

作者： Zaffar, Imaad Jaume, Guillaume Rajpoot, Nasir Mahmood, Faisal Department of Computer Science University College London United Kingdom Department of Pathology Brigham and Women's Hospital Harvard Medical School BostonMA United States Department of Pathology Massachusetts General Hospital Harvard Medical School BostonMA United States Cancer Program Broad Institute of Harvard and MIT CambridgeMA United States Data Science Program Dana-Farber Cancer Institute BostonMA United States Tissue Image Analytics Centre Department of Computer Science University of Warwick Coventry United Kingdom Department of Pathology University Hospitals Coventry and Warwickshire NHS Trust Coventry United Kingdom The Alan Turing Institute London United Kingdom

Multiple Instance Learning (MIL) is a widely employed framework for learning on gigapixel whole-slide images (WSIs) from WSI-level annotations. In most MIL based analytical pipelines for WSI-level analysis, the WSIs are often divided into patches and deep features for patches (i.e., patch embeddings) are extracted prior to training to reduce the overall computational cost and cope with the GPUs' limited RAM. To overcome this limitation, we present EMBAUGMENTER, a data augmentation generative adversarial network (DA-GAN) that can synthesize data augmentations in the embedding space rather than in the pixel space, thereby significantly reducing the computational requirements. Experiments on the SICAPv2 dataset show that our approach outperforms MIL without augmentation and is on par with traditional patch-level augmentation for MIL training while being substantially faster. © 2022, CC BY.

关键词： Generative adversarial networks

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：