检索结果-内蒙古大学图书馆

Automatic classification of AD pathology in FTD phenotypes using natural speech

ALZHEIMERS & DEMENTIA 2024年第5期20卷 3416-3428页

作者： Cho, Sunghye Olm, Christopher A. Ash, Sharon Shellikeri, Sanjana Agmon, Galit Cousins, Katheryn A. Q. Irwin, David J. Grossman, Murray Liberman, Mark Nevler, Naomi Univ Penn Dept Linguist Linguist Data Consortium Philadelphia PA USA Univ Penn Penn Frontotemporal Degenerat Ctr Philadelphia PA USA Univ Penn Linguist Data Consortium 3600 Market St Philadelphia PA 19104 USA

INTRODUCTIONScreening for Alzheimer's disease neuropathologic change (ADNC) in individuals with atypical presentations is challenging but essential for clinical management. We trained automatic speech-based classifiers to distinguish frontotemporal dementia (FTD) patients with ADNC from those with frontotemporal lobar degeneration (FTLD).METHODSWe trained automatic classifiers with 99 speech features from 1 minute speech samples of 179 participants (ADNC = 36, FTLD = 60, healthy controls [HC] = 89). Patients' pathology was assigned based on autopsy or cerebrospinal fluid analytes. Structural network-based magnetic resonance imaging analyses identified anatomical correlates of distinct speech *** classifier showed 0.88 +/-$ \pm $ 0.03 area under the curve (AUC) for ADNC versus FTLD and 0.93 +/-$ \pm $ 0.04 AUC for patients versus HC. Noun frequency and pause rate correlated with gray matter volume loss in the limbic and salience networks, *** naturalistic speech samples can be used for screening FTD patients for underlying ADNC in vivo. This work supports the future development of digital assessment tools for *** We trained machine learning classifiers for frontotemporal dementia patients using natural speech. We grouped participants by neuropathological diagnosis (autopsy) or cerebrospinal fluid biomarkers. Classifiers well distinguished underlying pathology (Alzheimer's disease vs. frontotemporal lobar degeneration) in patients. We identified important features through an explainable artificial intelligence approach. This work lays the groundwork for a speech-based neuropathology screening tool.

关键词： Alzheimer's disease automated speech analysis frontotemporal lobar degeneration machine learning classification natural speech pathology

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of malaria disease by integrating chi-square feature selection algorithm with convolutional neural networks and autoencoder network

引用

TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL 2023年第5期45卷 975-985页

作者： caliskan, Abidin Batman Univ Fac Engn & Architecture Dept Comp Engn Batman Turkiye Batman Univ Fac Engn & Architecture Dept Comp Engn TR-72060 Batman Turkiye

Malaria is a febrile illness caused by a parasite called plasmodium. This life-threatening disease is preventable and treatable if diagnosed early. The World Health Organization aims to reduce the global malaria incidence and death rates by at least 90% until 2030. This disease is diagnosed by visually analyzing red blood cells with a microscope by experienced radiologists. Therefore, this situation may be erroneous due to subjective interpretations. In this study, red blood cells were trained with deep learning-based convolutional neural networks to diagnose malaria, and thus, their deep features were obtained. These obtained features are also trained with autoencoder networks. Thus, the chi-square feature selection algorithm was used to obtain distinctive features. Finally, the unique feature set obtained is given as an introduction to machine learning algorithms, and then a unique diagnostic model is proposed. As a result, 100% accuracy rate was obtained. The results are promising for the diagnosis of malaria disease.

关键词： Malaria convolutional neural network autoencoder chi-square feature selection machine learning classification

来源：评论

学校读者我要写书评

暂无评论

Functional connectivity anomalies in medication-naive children with ADHD: Diagnostic potential, symptoms interpretation, and a mediation model

引用

CLINICAL NEUROPHYSIOLOGY 2025年 174卷 212-219页

作者： Hu, Yingzi Zeng, Yexian Fu, Tong Hong, Danping Yang, Han Zhu, Zhihang Cheng, Daomeng Dang, Caiping Song, Yan Yang, Chanjuan Yin, Weizhen Zhou, Yanling Guangzhou Med Univ Affiliated Brain Hosp Mingxin Rd 3 Guangzhou 510370 Peoples R China Guangzhou Med Univ Sch Hlth Management Guangzhou 511436 Peoples R China Guangzhou Med Univ Key Lab Neurogenet & Channelopathies Guangdong Pro Guangzhou 510370 Peoples R China Guangzhou Med Univ Minist Educ China Guangzhou 510370 Peoples R China Guangzhou Med Univ Affiliated Brain Hosp Inst Psychiat & Psychol Guangzhou 510370 Peoples R China Shanghai Jiao Tong Univ Sch Med Shanghai Mental Hlth Ctr Shanghai 200030 Peoples R China Beijing Normal Univ IDG McGovern Inst Brain Res State Key Lab Cognit Neurosci & Learning Beijing 100875 Peoples R China Beijing Normal Univ Ctr Collaborat & Innovat Brain & Learning Sci Beijing 100875 Peoples R China

Objective: To identify reliable electroencephalography (EEG) biomarkers for attention deficit/hyperactivity disorder (ADHD) by investigating anomalous functional connectivity patterns and their clinical relevance. Methods: Resting-state EEG data were collected from 74 children aged 6-12 (33 unmedicated ADHD;41 typically developing). Functional connectivity was quantified using the imaginary part of coherency (ICOH). machine learning (ML)-based support vector machine (SVM) modeling, regression, and mediation analyses linked connectivity features to symptom severity and diagnostic classification. Results: Children with ADHD exhibited beta (beta) band hypo-connectivity in frontal regions (Fp2-F4, Fp1-Cz, F7-Cz) and theta (0) band hyper-connectivity in left parietal-central networks (C3-P7, P3-P7, etc.). An SVM classifier achieved an average area under the curve of 0.89 using three connectivity features. Left parietal 0 band hyperconnectivity (C3-P7) correlated with both inattention and hyperactivity/impulsivity and mediated their interrelationship. Conclusions: ADHD is characterized by disrupted frontoparietal connectivity, with 0 band hyper-connectivity in sensory-integration networks potentially compensating for impaired frontal regulation. Significance: These findings highlight C3-P7 0 band connectivity as both a diagnostic and mechanistic biomarker, providing novel target for neurofeedback therapies and enhancing the differential diagnosis in neurodevelopmental disorders.

关键词： ADHD biomarkers Resting-state EEG Functional Connectivity machine learning classification Mediation Analysis

来源：评论

学校读者我要写书评

暂无评论

Cost-Efficient RSSI-Based Indoor Proximity Positioning, for Large/Complex Museum Exhibition Spaces

引用

SENSORS 2025年第9期25卷 2713-2713页

作者： Philippopoulos, Panos I. Koutrakis, Kostas N. Tsafaras, Efstathios D. Papadopoulou, Evangelia G. Sigalas, Dimitrios Tselikas, Nikolaos D. Ougiaroglou, Stefanos Vassilakis, Costas Univ Peloponnese Digital Syst Dept GR-23100 Sparta Greece Univ Peloponnese Informat & Telecommun Dept GR-22100 Tripolis Greece Int Hellen Univ Dept Informat & Elect Engn GR-57400 Thessaloniki Greece

RSSI-based proximity positioning is a well-established technique for indoor localization, featuring simplicity and cost-effectiveness, requiring low-price and off-the-shelf hardware. However, it suffers from low accuracy (in NLOS traffic), noise, and multipath fading issues. In large complex spaces, such as museums, where heavy visitor traffic is expected to seriously impact the ability to maintain LOS, RSSI coupled with Bluetooth Low Energy (BLE) seems ideal in terms of market availability, cost-/energy-efficiency and scalability that affect competing technologies, provided it achieves adequate accuracy. Our work reports and discusses findings of a BLE/RSSI-based pilot, implemented at the Museum of Modern Greek Culture in Athens, involving eight buildings with 47 halls with diverse areas, shapes, and showcase layouts. Wearable visitor BLE beacons provided cell-level location determined by a prototype tool (VTT), integrating in its architecture different functionalities: raw RSSI data smoothing with Kalman filters, hybrid positioning provision, temporal methods for visitor cell prediction, spatial filtering, and prediction based on popular machine learning classifiers. Visitor movement modeling, based on critical parameters influencing signal measurements, provided scenarios mapped to popular behavioral models. One such model, "ant", corresponding to relatively slow nomadic cell roaming, was selected for basic experimentation. Pilot implementation decisions and methods adopted at all layers of the VTT architecture followed the overall concept of simplicity, availability, and cost-efficiency, providing a maximum infrastructure cost of 8 Euro per m2 covered. A total 15 methods/algorithms were evaluated against prediction accuracy across 20 RSSI datasets, incorporating diverse hall cell allocations and visitor movement patterns. RSSI data, temporal and spatial management with simple low-processing methods adopted, achieved a maximum prediction accuracy average of 81.53

关键词： large/complex museums indoor proximity positioning Bluetooth Low Energy RSSI temporal/spatial methods machine learning classification museum visitor modeling

来源：评论

学校读者我要写书评

暂无评论

Metagenomic and machine learning Meta-Analyses Characterize Airborne Resistome Features and Their Hosts in China Megacities

引用

ENVIRONMENTAL SCIENCE & TECHNOLOGY 2023年第43期57卷 16414-16423页

作者： Wu, Dong Xie, Jiawen Liu, Yangying Jin, Ling Li, Guiying An, Taicheng East China Normal Univ Chongqing Inst Sch Ecol & Environm Sci Shanghai Engn Res Ctr Biotransformat Organ Solid W Shanghai 200241 Peoples R China Guangdong Univ Technol Inst Environm Hlth & Pollut Control Sch Environm Sci & Engn Guangdong Hong Kong Macao Joint Lab Contaminants E Hong Kong 510006 Guangdong Peoples R China Hong Kong Polytech Univ Dept Civil & Environm Engn Kowloon Hong Kong Peoples R China Hong Kong Polytech Univ Res Inst Sustainable Urban Dev Kowloon Hong Kong Peoples R China Lehigh Univ Dept Comp Sci & Engn Bethlehem PA 18015 USA Hong Kong Polytech Univ Dept Hlth Technol & Informat Kowloon Hong Kong Peoples R China

Urban ambient air contains a cocktail of antibiotic resistance genes (ARGs) emitted from various anthropogenic sites. However, what is largely unknown is whether the airborne ARGs exhibit site-specificity or their pathogenic hosts persistently exist in the air. Here, by retrieving 1.2 Tb metagenomic sequences (n = 136), we examined the airborne ARGs from hospitals, municipal wastewater treatment plants (WWTPs) and landfills, public transit centers, and urban sites located in seven of China's megacities. As validated by the multiple machine learning-based classification and optimization, ARGs' site-specificity was found to be the most apparent in hospital air, with featured resistances to clinical-used rifamycin and (glyco)peptides, whereas the more environmentally prevalent ARGs (e.g., resistance to sulfonamide and tetracycline) were identified being more specific to the nonclinical ambient air settings. Nearly all metagenome-assembled genomes (MAGs) that possessed the site-featured resistances were identified as pathogenic taxa, which occupied the upper-representative niches in all the neutrally distributed airborne microbial community (P < 0.01, m = 0.22-0.50, R-2 = 0.41-0.86). These niche-favored putative resistant pathogens highlighted the enduring antibiotic resistance hazards in the studied urban air. These findings are critical, albeit the least appreciated until our study, to gauge the airborne dimension of resistomes' features and fates in urban atmospheric environments.

关键词： airborne environments antibiotic resistance putative human pathogenic bacteria machine learning classification microbial assembly process

来源：评论

学校读者我要写书评

暂无评论

Impact of Harmonization on MRI Radiomics Feature Variability Across Preprocessing Methods for Parkinson's Disease Motor Subtype classification

引用

JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024年 1-14页

作者： Panahi, Mehdi Hosseini, Mahboube Sadat Payame Noor Univ Dept Comp Engn Erbil Branch Erbil Iraq Shahid Beheshti Univ Dept Med Radiat Engn Tehran Iran

This study aimed to assess the reproducibility of MRI-derived radiomic features across multiple preprocessing methods for classifying Parkinson's disease (PD) motor subtypes and to evaluate the impact of ComBat harmonization on feature stability and machine learning performance. T1-weighted MRI scans from 140 PD patients (70 tremor-dominant and 70 postural instability gait difficulty) and 70 healthy controls were obtained from the Parkinson's Progression Markers Initiative (PPMI) database, acquired using different scanner models. Radiomic features were extracted from 16 brain regions using various preprocessing pipelines. ComBat harmonization was applied using a combined batch variable incorporating both scanner models and preprocessing methods. Intraclass correlation coefficients (ICC) and Kruskal-Wallis tests assessed feature reproducibility before and after harmonization. Feature selection was performed using Linear Support Vector Classifier with L1 regularization. Support vector machine classifiers were used for PD subtype classification. ComBat harmonization significantly improved feature reproducibility across all feature groups. The percentage of features showing excellent robustness (ICC >= 0.90) increased from 40.2 to 56.3% after harmonization. First-order statistic features showed the highest robustness, with 71.11% demonstrating excellent ICC after harmonization. The proportion of features significantly affected by preprocessing methods was reduced following harmonization. classification accuracy improved dramatically, from a range of 34-75% before harmonization to 89-96% after harmonization across all preprocessing methods. AUC values similarly increased from 0.28-0.87 to 0.95-0.99 after harmonization. ComBat harmonization significantly enhanced the reproducibility of radiomic features across preprocessing methods and improved PD motor subtype classification performance. This study highlights the importance of harmonization in radiomics research for PD a

关键词： Parkinson's disease MRI radiomics ComBat harmonization Preprocessing methods machine learning classification Motor subtypes

来源：评论

学校读者我要写书评

暂无评论

Identifying neuropathies through time series analysis of postural tests

引用

GAIT & POSTURE 2023年 99卷 24-34页

作者： Meneses Villegas, Claudio Littin Curinao, Jorge Coo Aqueveque, David Guerrero-Henriquez, Juan Vargas Matamala, Martin Univ Catolica Norte Dept Comp & Syst Engn Antofagasta Chile Univ Antofagasta Dept Rehabil Sci & Human Movement Antofagasta Chile Univ Catolica Norte Dept Math Antofagasta Chile

Background: In physical therapy, postural tests are frequently used to diagnose neuropathies, particularly in diabetic individuals. This study aims to develop a method based on the analysis of time series that allows discriminating between healthy and diabetic subjects with or without a neuropathic condition. Research question: Do features obtained from time series corresponding to postural tests allow us to reliably discriminate between healthy, diabetic and neuropathic patients? Methods: In this study, 32 people participated in the healthy, diabetic, and neuropathic categories (11, 9, and 12, respectively). The data was collected by positioning each participant on a Wii Balanced Board platform, under 8 different conditions. The analyzed time series are sensed by devices that capture variations in the subject's center of pressure when subjected to a test on different conditions over a short period of time. The method proposed considers statistical techniques used for characterizing the time series combined with machine learning techniques to classify the individual's profile into one of the three categories mentioned. The classification is supported by an underlying probabilistic model, based on the characteristics of the time series, generating average curves for each class, which are then used by the classification methods. Results: The empirical results include classification models for each class, obtaining a performance (F-score) over 98%. In addition, other models considering the particular conditions to which the subject is exposed during the test are developed, revealing that the conditions of eyes open and eyes closed show the highest levels of discrimination to classify participants into one of the three class categories. Significance: These results suggest a test protocol simplification and, at the same time, that the proposed method based on the analysis of the time series associated with the test used is highly predictive and may reliably complement or

关键词： Identification of neuropathies Postural test analysis machine learning classification Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Cryogenic Embedded System to Support Quantum Computing: From 5-nm FinFET to Full Processor

IEEE TRANSACTIONS ON QUANTUM ENGINEERING

引用

IEEE TRANSACTIONS ON QUANTUM ENGINEERING 2023年第1期4卷 1页

作者： Genssler, Paul R. Klemme, Florian Parihar, Shivendra Singh Brandhofer, Sebastian Pahwa, Girish Polian, Ilia Chauhan, Yogesh Singh Amrouch, Hussam Univ Stuttgart Chair Semicond Test & Reliabil STAR D-70174 Stuttgart Germany IIT Kanpur Dept Elect Engn Nanolab Kanpur 208016 India Univ Stuttgart Chair Hardware Oriented Comp Sci D-70174 Stuttgart Germany Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA 94720 USA Tech Univ Munich Chair AI Processor Design D-80333 Munich Germany Tech Univ Munich Munich Inst Robot & Machine Intelligence D-80333 Munich Germany

Quantum computing can enable novel algorithms infeasible for classical computers. For example, new material synthesis and drug optimization could benefit if quantum computers offered more quantum bits (qubits). One obstacle for scaling up quantum computers is the connection between their cryogenic qubits at temperatures between a few millikelvin and a few kelvin (depending on qubit type) and the classical processing system on chip (SoC) at room temperature (300K). Through this connection, outside heat leaks to the qubits and can disrupt their state. Hence, moving the SoC into the cryogenic part eliminates this heat leakage. However, the cooling capacity is limited, requiring a low-power SoC, which, at the same time, has to classify qubit measurements under a tight time constraint. In this work, we explore for the first time if an off-the-shelf SoC is a plausible option for such a task. Our analysis starts with measurements of state-of-the-art 5-nm fin-shaped field-effect transistors (FinFETs) at 10 and 300 K. Then, we calibrate a transistor compact model and create two standard cell libraries, one for each temperature. We perform synthesis and physical layout of a RISC-V SoC at 300 K and analyze its performance at 10 K. Our simulations show that the SoC at 10 K is plausible but lacks the performance to process more than a few thousand qubits under the time constraint.

关键词： Qubit Quantum computing Temperature measurement Cryogenics Transistors Semiconductor device measurement Libraries Cryogenic CMOS 5-nm fin-shaped field-effect transistor (FinFET) hyperdimensional computing machine learning classification quantum computing system on chip (SoC)

来源：评论

学校读者我要写书评

暂无评论

Skill-level classification and performance evaluation for endoscopic sleeve gastroplasty

引用

SURGICAL ENDOSCOPY AND OTHER INTERVENTIONAL TECHNIQUES 2023年第6期37卷 4754-4765页

作者： Dials, James Demirel, Doga Sanchez-Arias, Reinaldo Halic, Tansel Kruger, Uwe De, Suvranu Gromski, Mark A. Florida Polytech Univ Dept Comp Sci Lakeland FL 33805 USA Florida Polytech Univ Dept Data Sci & Business Analyt Lakeland FL USA Intuit Surg Peachtree Corners GA USA Rensselaer Polytech Inst Dept Biomed Engn Troy NY USA Florida A&M Univ Coll Engn Tallahassee FL USA Indiana Univ Sch Med Div Gastroenterol & Hepatol Indianapolis IN USA

BackgroundWe previously developed grading metrics for quantitative performance measurement for simulated endoscopic sleeve gastroplasty (ESG) to create a scalar reference to classify subjects into experts and novices. In this work, we used synthetic data generation and expanded our skill level analysis using machine learning *** used the synthetic data generation algorithm SMOTE to expand and balance our dataset of seven actual simulated ESG procedures using synthetic data. We performed optimization to seek optimum metrics to classify experts and novices by identifying the most critical and distinctive sub-tasks. We used support vector machine (SVM), AdaBoost, K-nearest neighbors (KNN) Kernel Fisher discriminant analysis (KFDA), random forest, and decision tree classifiers to classify surgeons as experts or novices after grading. Furthermore, we used an optimization model to create weights for each task and separate the clusters by maximizing the distance between the expert and novice *** split our dataset into a training set of 15 samples and a testing dataset of five samples. We put this dataset through six classifiers, SVM, KFDA, AdaBoost, KNN, random forest, and decision tree, resulting in 0.94, 0.94, 1.00, 1.00, 1.00, and 1.00 accuracy, respectively, for training and 1.00 accuracy for the testing results for SVM and AdaBoost. Our optimization model maximized the distance between the expert and novice groups from 2 to *** paper shows that feature reduction, in combination with classification algorithms such as SVM and KNN, can be used in tandem to classify endoscopists as experts or novices based on their results recorded using our grading metrics. Furthermore, this work introduces a non-linear constraint optimization to separate the two clusters and find the most important tasks using weights.

关键词： Endoscopic simulator Endoscopic sleeve gastroplasty Non-linear constraint optimization Synthetic data generation machine learning classification

来源：评论

学校读者我要写书评

暂无评论

Towards automated in vivo parcellation of the human cerebral cortex using supervised classification of magnetic resonance fingerprinting residuals

引用

CEREBRAL CORTEX 2023年第5期33卷 1550-1565页

作者： Moinian, Shahrzad Vegh, Viktor Reutens, David Univ Queensland Ctr Adv Imaging Bldg 57Res Rd St Lucia Qld 4072 Australia Univ Queensland ARC Training Ctr Innovat Biomed Imaging Technol Bldg 57Res Rd St Lucia Qld 4072 Australia

Background Accurate parcellation of the cerebral cortex in an individual is a guide to its underlying organization. The most promising in vivo quantitative magnetic resonance (MR)-based microstructural cortical mapping methods are yet to achieve a level of parcellation accuracy comparable to quantitative histology. Methods We scanned 6 participants using a 3D echo-planar imaging MR fingerprinting (EPI-MRF) sequence on a 7T Siemens scanner. After projecting MRF signals to the individual-specific inflated model of the cortical surface, normalized autocorrelations of MRF residuals of vertices of 8 microstructurally distinct areas (BA1, BA2, BA4a, BA6, BA44, BA45, BA17, and BA18) from 3 cortical regions were used as feature vector inputs into linear support vector machine (SVM), radial basis function SVM (RBF-SVM), random forest, and k-nearest neighbors supervised classification algorithms. The algorithms' prediction performance was compared using: (i) features from each vertex or (ii) features from neighboring vertices. Results The neighborhood-based RBF-SVM classifier achieved the highest prediction score of 0.85 for classification of MRF residuals in the central region from a held-out participant. Conclusions We developed an automated method of cortical parcellation using a combination of MR fingerprinting residual analysis and machine learning classification. Our findings provide the basis for employing unsupervised learning algorithms for whole-cortex structural parcellation in individuals.

关键词： cerebral cortex parcellation machine learning classification magnetic resonance fingerprinting residual

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：