Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
425
result(s) for
"Hwang, Kai"
Sort by:
تحليلات البيانات الكبيرة للسحب وإنترنت الأشياء والحوسبة الإدراكية
تستعرض فصول هذا الكتاب علم البيانات، وأدوار السحب، وأجهزة إنترنت الأشياء، و أطر العمل للبيانات الكبيرة، ومبادئ وخوارزميات تعلم الآلة. وتحليلات البيانات، والتعلم العميق في تطبيقات البيانات الكبيرة، وتحليلات البيانات الكبيرة لتعلم الآلة في الرعاية الصحية، والتعلم العميق في التطبيقات الإدراكية ووسائل التواصل الاجتماعي. ويعد هذا الكتاب مرجعا قيما لأعضاء هيئة التدريس وطلاب المرحلة الجامعية والدراسات العليا والباحثين في مجالات هندسة وعلوم الحاسب.
Book
The nuisance of nuisance regression: Spectral misspecification in a common approach to resting-state fMRI preprocessing reintroduces noise and obscures functional connectivity
Recent resting-state functional connectivity fMRI (RS-fcMRI) research has demonstrated that head motion during fMRI acquisition systematically influences connectivity estimates despite bandpass filtering and nuisance regression, which are intended to reduce such nuisance variability. We provide evidence that the effects of head motion and other nuisance signals are poorly controlled when the fMRI time series are bandpass-filtered but the regressors are unfiltered, resulting in the inadvertent reintroduction of nuisance-related variation into frequencies previously suppressed by the bandpass filter, as well as suboptimal correction for noise signals in the frequencies of interest. This is important because many RS-fcMRI studies, including some focusing on motion-related artifacts, have applied this approach. In two cohorts of individuals (n=117 and 22) who completed resting-state fMRI scans, we found that the bandpass–regress approach consistently overestimated functional connectivity across the brain, typically on the order of r=.10–.35, relative to a simultaneous bandpass filtering and nuisance regression approach. Inflated correlations under the bandpass–regress approach were associated with head motion and cardiac artifacts. Furthermore, distance-related differences in the association of head motion and connectivity estimates were much weaker for the simultaneous filtering approach. We recommend that future RS-fcMRI studies ensure that the frequencies of nuisance regressors and fMRI data match prior to nuisance regression, and we advocate a simultaneous bandpass filtering and nuisance regression strategy that better controls nuisance-related variability.
•Bandpass filtering and nuisance regression are intended to reduce noise in RS-fMRI.•When RS-fMRI data are filtered, but regressors are not, noise is poorly controlled.•In addition, this approach reintroduces synchronous noise into RS-fMRI data.•Such noise leads to systematically inflated estimates of functional connectivity.•Simultaneous bandpass filtering and regression eliminates this source of bias.
Journal Article
Graph-generative neural network for EEG-based epileptic seizure detection via discovery of dynamic brain functional connectivity
Dynamic complexity in brain functional connectivity has hindered the effective use of signal processing or machine learning methods to diagnose neurological disorders such as epilepsy. This paper proposed a new graph-generative neural network (GGN) model for the dynamic discovery of brain functional connectivity via deep analysis of scalp electroencephalogram (EEG) signals recorded from various regions of a patient’s scalp. Brain functional connectivity graphs are generated for the extraction of spatial–temporal resolution of various onset epilepsy seizure patterns. Our supervised GGN model was substantiated by seizure detection and classification experiments. We train the GGN model using a clinically proven dataset of over 3047 epileptic seizure cases. The GGN model achieved a 91% accuracy in classifying seven types of epileptic seizure attacks, which outperformed the 65%, 74%, and 82% accuracy in using the
convolutional neural network
(CNN),
graph neural networks
(GNN), and transformer models, respectively. We present the GGN model architecture and operational steps to assist neuroscientists or brain specialists in using dynamic functional connectivity information to detect neurological disorders. Furthermore, we suggest to merge our spatial–temporal graph generator design in upgrading the conventional CNN and GNN models with dynamic convolutional kernels for accuracy enhancement.
Journal Article
Trusted Cloud Computing with Secure Resources and Data Coloring
Trust and security have prevented businesses from fully accepting cloud platforms. To protect clouds, providers must first secure virtualized data center resources, uphold user privacy, and preserve data integrity. The authors suggest using a trust-overlay network over multiple data centers to implement a reputation system for establishing trust between service providers and data owners. Data coloring and software watermarking techniques protect shared data objects and massively distributed software modules. These techniques safeguard multi-way authentications, enable single sign-on in the cloud, and tighten access control for sensitive data in both public and private clouds.
Journal Article
Machine learning for emerging infectious disease field responses
Emerging infectious diseases (EIDs), including the latest COVID-19 pandemic, have emerged and raised global public health crises in recent decades. Without existing protective immunity, an EID may spread rapidly and cause mass casualties in a very short time. Therefore, it is imperative to identify cases with risk of disease progression for the optimized allocation of medical resources in case medical facilities are overwhelmed with a flood of patients. This study has aimed to cope with this challenge from the aspect of preventive medicine by exploiting machine learning technologies. The study has been based on 83,227 hospital admissions with influenza-like illness and we analysed the risk effects of 19 comorbidities along with age and gender for severe illness or mortality risk. The experimental results revealed that the decision rules derived from the machine learning based prediction models can provide valuable guidelines for the healthcare policy makers to develop an effective vaccination strategy. Furthermore, in case the healthcare facilities are overwhelmed by patients with EID, which frequently occurred in the recent COVID-19 pandemic, the frontline physicians can incorporate the proposed prediction models to triage patients suffering minor symptoms without laboratory tests, which may become scarce during an EID disaster. In conclusion, our study has demonstrated an effective approach to exploit machine learning technologies to cope with the challenges faced during the outbreak of an EID.
Journal Article
The Contribution of Network Organization and Integration to the Development of Cognitive Control
Cognitive control, which continues to mature throughout adolescence, is supported by the ability for well-defined organized brain networks to flexibly integrate information. However, the development of intrinsic brain network organization and its relationship to observed improvements in cognitive control are not well understood. In the present study, we used resting state functional magnetic resonance imaging (RS-fMRI), graph theory, the antisaccade task, and rigorous head motion control to characterize and relate developmental changes in network organization, connectivity strength, and integration to inhibitory control development. Subjects were 192 10-26-y-olds who were imaged during 5 min of rest. In contrast to initial studies, our results indicate that network organization is stable throughout adolescence. However, cross-network integration, predominantly of the cingulo-opercular/salience network, increased with age. Importantly, this increased integration of the cingulo-opercular/salience network significantly moderated the robust effect of age on the latency to initiate a correct inhibitory control response. These results provide compelling evidence that the transition to adult-level inhibitory control is dependent upon the refinement and strengthening of integration between specialized networks. Our findings support a novel, two-stage model of neural development, in which networks stabilize prior to adolescence and subsequently increase their integration to support the cross-domain incorporation of information processing critical for mature cognitive control.
Journal Article
Process optimization and mechanical properties analysis of Inconel 718/stainless steel 316 L multi-material via direct energy deposition
Additive manufacturing (AM), also known as 3D printing, is a recent innovation in manufacturing, employing additive techniques rather than traditional subtractive methods. This study focuses on Directed Energy Deposition (DED), utilizing a blend of nickel-based superalloy IN 718 and stainless steel SS316 powders in varying ratios (25%+75%, 50%, and 75%+25%). The objective is to assess the impact of process parameters on quality and optimize them. Mechanical properties of the different powder mixtures are compared. In the study, Taguchi-grey relational analysis is employed for parameter optimization, with four key factors identified: laser power, overlap ratio, powder feed rate, and scanning speed, affecting cladding efficiency, deposition rate, and porosity. Verification experiments confirm optimization repeatability, and further fine-tuning is achieved through one-factor-at-a-time experiments. Optimized parameters yield varied tensile properties among different powder mixtures; for example, a 25% SS316L and 75% IN718 blend demonstrates the highest ultimate tensile strength (499.37 MPa), while a 50% SS316L and 50% IN718 blend exhibits the best elongation (13.53%). This study offers an effective approach for using DED technology to create mixed SS316 and IN718 powders, enabling tailored mechanical performance based on mixing ratios.
Journal Article
A 5G Cognitive System for Healthcare
Developments and new advances in medical technology and the improvement of people’s living standards have helped to make many people healthier. However, there are still large design deficiencies due to the imbalanced distribution of medical resources, especially in developing countries. To address this issue, a video conference-based telemedicine system is deployed to break the limitations of medical resources in terms of time and space. By outsourcing medical resources from big hospitals to rural and remote ones, centralized and high quality medical resources can be shared to achieve a higher salvage rate while improving the utilization of medical resources. Though effective, existing telemedicine systems only treat patients’ physiological diseases, leaving another challenging problem unsolved: How to remotely detect patients’ emotional state to diagnose psychological diseases. In this paper, we propose a novel healthcare system based on a 5G Cognitive System (5G-Csys). The 5G-Csys consists of a resource cognitive engine and a data cognitive engine. Resource cognitive intelligence, based on the learning of network contexts, aims at ultra-low latency and ultra-high reliability for cognitive applications. Data cognitive intelligence, based on the analysis of healthcare big data, is used to handle a patient’s health status physiologically and psychologically. In this paper, the architecture of 5G-Csys is first presented, and then the key technologies and application scenarios are discussed. To verify our proposal, we develop a prototype platform of 5G-Csys, incorporating speech emotion recognition. We present our experimental results to demonstrate the effectiveness of the proposed system. We hope this paper will attract further research in the field of healthcare based on 5G cognitive systems.
Journal Article
Neuropsychological evidence of multi-domain network hubs in the human thalamus
Hubs in the human brain support behaviors that arise from brain network interactions. Previous studies have identified hub regions in the human thalamus that are connected with multiple functional networks. However, the behavioral significance of thalamic hubs has yet to be established. Our framework predicts that thalamic subregions with strong hub properties are broadly involved in functions across multiple cognitive domains. To test this prediction, we studied human patients with focal thalamic lesions in conjunction with network analyses of the human thalamocortical functional connectome. In support of our prediction, lesions to thalamic subregions with stronger hub properties were associated with widespread deficits in executive, language, and memory functions, whereas lesions to thalamic subregions with weaker hub properties were associated with more limited deficits. These results highlight how a large-scale network model can broaden our understanding of thalamic function for human cognition.
Journal Article
The thalamus encodes and updates context representations during hierarchical cognitive control
Cognitive flexibility relies on hierarchically structured task representations that organize task contexts, relevant environmental features, and subordinate decisions. Despite ongoing interest in the human thalamus, its role in cognitive control has been understudied. This study explored thalamic representation and thalamocortical interactions that contribute to hierarchical cognitive control in humans. We found that several thalamic nuclei, including the anterior, mediodorsal, ventrolateral, and pulvinar nuclei, exhibited stronger evoked responses when subjects switch between task contexts. Decoding analysis revealed that thalamic activity encodes task contexts within the hierarchical task representations. To determine how thalamocortical interactions contribute to task representations, we developed a thalamocortical functional interaction model to predict task-related cortical representation. This data-driven model outperformed comparison models, particularly in predicting activity patterns in cortical regions that encode context representations. Collectively, our findings highlight the significant contribution of thalamic activity and thalamocortical interactions for contextually guided hierarchical cognitive control.
Journal Article