Search

Performing group analysis on magnetic resonance imaging (MRI) data with linear mixed-effects (LME) models is challenging due to its large dimensionality and inherent multi-level covariance structure. In addition, as large-scale collaborative projects become commonplace in neuroimaging, data must increasingly be stored and analysed at different locations. In such settings, substantial overheads occur in terms of data transfer and coordination between participating research groups. In some cases, data cannot be pooled together due to privacy or regulatory concerns. In this work, we propose a decentralized LME model to perform a large-scale analysis of data from different collaborations without sharing or pooling. This method is efficient as it overcomes the hurdles of data privacy for sharing and has lower bandwidth and memory requirements for analysis than the centralized modeling approach. We evaluate our model using features extracted from structural magnetic resonance imaging (sMRI) data. Results highlight gray matter reductions in the temporal lobe/insula and medical front regions demonstrate the correctness of decentralized LME models. Our analysis also demonstrates that decentralized LME models achieve similar performance compared to the models trained with all the data in one location. We also implement the decentralized LME approach in COINSTAC, a decentralized platform for federating neuroimaging analysis, to demonstrate its value to the neuroimaging community.

With the rapid development of human society, the urbanization of the world's population is also progressing rapidly. Urbanization has brought many challenges and problems to the development of cities. For example, the urban population is under excessive pressure, various natural resources and energy are increasingly scarce, and environmental pollution is increasing, etc. However, the original urban model has to be changed to enable people to live in greener and more sustainable cities, thus providing them with a more convenient and comfortable living environment. The new urban framework, the smart city, provides excellent opportunities to meet these challenges, while solving urban problems at the same time. At this stage, many countries are actively responding to calls for smart city development plans. This paper investigates the current stage of the smart city. First, it introduces the background of smart city development and gives a brief definition of the concept of the smart city. Second, it describes the framework of a smart city in accordance with the given definition. Finally, various intelligent algorithms to make cities smarter, along with specific examples, are discussed and analyzed.

With the growth of decentralized/federated analysis approaches in neuroimaging, the opportunities to study brain disorders using data from multiple sites has grown multi-fold. One such initiative is the Neuromark, a fully automated spatially constrained independent component analysis (ICA) that is used to link brain network abnormalities among different datasets, studies, and disorders while leveraging subject-specific networks. In this study, we implement the neuromark pipeline in COINSTAC, an open-source neuroimaging framework for collaborative/decentralized analysis. Decentralized exploratory analysis of nearly 2000 resting-state functional magnetic resonance imaging datasets collected at different sites across two cohorts and co-located in different countries was performed to study the resting brain functional network connectivity changes in adolescents who smoke and consume alcohol. Results showed hypoconnectivity across the majority of networks including sensory, default mode, and subcortical domains, more for alcohol than smoking, and decreased low frequency power. These findings suggest that global reduced synchronization is associated with both tobacco and alcohol use. This proof-of-concept work demonstrates the utility and incentives associated with large-scale decentralized collaborations spanning multiple sites.

Improving performance of deep learning models and reducing their training times are ongoing challenges in deep neural networks. There are several approaches proposed to address these challenges one of which is to increase the depth of the neural networks. Such deeper networks not only increase training times, but also suffer from vanishing gradients problem while training. In this work, we propose gradient amplification approach for training deep learning models to prevent vanishing gradients and also develop a training strategy to enable or disable gradient amplification method across several epochs with different learning rates. We perform experiments on VGG-19 and resnet (Resnet-18 and Resnet-34) models, and study the impact of amplification parameters on these models in detail. Our proposed approach improves performance of these deep learning models even at higher learning rates, thereby allowing these models to achieve higher performance with reduced training time., 9 page document with 7 figures and one results table

Background Analysis of heterogeneous populations such as viral quasispecies is one of the most challenging bioinformatics problems. Although machine learning models are becoming to be widely employed for analysis of sequence data from such populations, their straightforward application is impeded by multiple challenges associated with technological limitations and biases, difficulty of selection of relevant features and need to compare genomic datasets of different sizes and structures. Results We propose a novel preprocessing approach to transform irregular genomic data into normalized image data. Such representation allows to restate the problems of classification and comparison of heterogeneous populations as image classification problems which can be solved using variety of available machine learning tools. We then apply the proposed approach to two important problems in molecular epidemiology: inference of viral infection stage and detection of viral transmission clusters using next-generation sequencing data. The infection staging method has been applied to HCV HVR1 samples collected from 108 recently and 257 chronically infected individuals. The SVM-based image classification approach achieved more than 95% accuracy for both recently and chronically HCV-infected individuals. Clustering has been performed on the data collected from 33 epidemiologically curated outbreaks, yielding more than 97% accuracy. Conclusions Sequence image normalization method allows for a robust conversion of genomic data into numerical data and overcomes several issues associated with employing machine learning methods to viral populations. Image data also help in the visualization of genomic data. Experimental results demonstrate that the proposed method can be successfully applied to different problems in molecular epidemiology and surveillance of viral diseases. Simple binary classifiers and clustering techniques applied to the image data are equally or more accurate than other models.

The co-existence of multistable rhythms generated by oscillatory neural circuits made up of 4 and more cells, their onset, stability conditions, and the transitions between such rhythms are not well understood. This is partly due to the lack of appropriate visual and computational tools. In this study, we employ modern computational approaches including unsupervised machine learning (clustering) algorithms and fast parallel simulations powered by graphics processing units (GPUs) to further extend our previously developed techniques based on the theory of dynamical systems and bifurcations. This allows us to analyze the fundamental principles and mechanisms that ensure the robustness and multifunctionality of such neural circuits. In addition, we examine how network topology affects the dynamics, and the rhythmic patterns transition/bifurcate as network configurations are altered and the intrinsic properties of the cells and the synapses are varied. This study elaborates on a set of inhibitory coupled 4-cell circuits that can exhibit a variety of mono- and multistable rhythms including pacemakers, paired half-centers, traveling-waves, synchronized states, as well as various chimeras. Our detailed analysis is helpful to generate verifiable hypotheses for neurophysiological experiments with biological central pattern generators.

Identification of Hepatitis C virus (HCV) infections is crucial in determining viral outbreaks. HCV has an affinity to lead towards chronic infection with time due to its highly mutable nature. This leads to increase in heterogeneous population of genetically related HCV variants in the affected individuals. To our knowledge, there are no reliable diagnostic assays for distinguishing acute and chronic HCV infections. Providing a robust classification scheme for the staging of viral infection requires identification of prominent features which in this case can be done using domain knowledge. Simple genetic heterogeneity metrics are not sufficient to represent HCV infections accurately as features for the classification algorithms. This is due to complexity of structural development of intra-host populations, which are affected by bouts of selective sweeps and negative selection during chronic infection [1], [2]. Although some machine learning models are known to work well for sequence data for classification problems, their straightforward application to viral genomic data is problematic, since the number of viral sequences and the structures of intra-host viral populations are not consistent across various samples. We propose a novel preprocessing approach to transform irregular viral genomic data into a normalized image data. Such representation allows to apply powerful machine learning algorithms to the problem of classification of recent and chronic HCV infections. Our dataset consists of intra-host HCV populations of a highly heterogeneous genomic region HVR1, collected from 108 recently and 257 chronically infected individuals sampled by next-generation sequencing. We train several classification models using stratified 10-fold cross validation on the transformed image data. SVM classification model achieves the highest accuracy of 98% and also has more than 95% of precision, recall and F1_Score metrics, for both acute and chronically HCV infected individuals.

Cybersecurity in smart grids plays a crucial role in determining its reliable functioning and availability. Data integrity attacks at the physical layer of smart grids are mainly addressed in this paper. State vector estimation (SVE) methods are widely used to detect such attacks, but such methods fail to identify attacks that comply with physical properties of the grid, known as unobservable attacks. In this paper, we formulate a distance measure to be employed as the cost function in deep-learning models using feed-forward neural network architectures to classify malicious and secured measurements. Efficiency and performance of these models are compared with existing state-of-the-art detection algorithms and supervised machine learning models. Our analysis shows better performance for deep learning models in detecting centralised data attacks.