A power-based sliding window approach to evaluate the clinical impact of rare genetic variants in the nucleotide sequence or the spatial position of the folded protein

Systematic determination of novel variant pathogenicity remains a major challenge, even when there is an established association between a gene and phenotype. Here we present Power Window (PW), a sliding window technique that identifies the impactful regions of a gene using population-scale clinico-genomic datasets. By sizing analysis windows on the number of variant carriers, rather than the number of variants or nucleotides, statistical power is held constant, enabling the localization of clinical phenotypes and removal of unassociated gene regions. The windows can be built by sliding across either the nucleotide sequence of the gene (through 1D space) or the positions of the amino acids in the folded protein (through 3D space). Using a training set of 350k exomes from the UK Biobank (UKB), we developed PW models for well-established gene-disease associations and tested their accuracy in two independent cohorts (117k UKB exomes and 65k exomes sequenced at Helix in the Healthy Nevada Project, myGenetics, or In Our DNA SC studies). The significant models retained a median of 49% of the qualifying variant carriers in each gene (range 2%-98%), with quantitative traits showing a median effect size improvement of 66% compared with aggregating variants across the entire gene, and binary traits' odds ratios improving by a median of 2.2-fold. PW showcases that electronic health record-based statistical analyses can accurately distinguish between novel coding variants in established genes that will have high phenotypic penetrance and those that will not, unlocking new potential for human genomics research, drug development, variant interpretation, and precision medicine.

Wrist-Based Fall Detection: Towards Generalization across Datasets

Increasing age is related to a decrease in independence of movement and with this decrease comes falls, millions of falls occur every year and the most affected people are the older adults. These falls usually have a big impact on health and independence of the older adults, as well as financial impact on the health systems. Thus, many studies have developed fall detectors from several types of sensors. Previous studies related to the creation of fall detection systems models use only one dataset that usually has a small number of samples. Training and testing machine learning models in this small scope: (i) yield overoptimistic classification rates, (ii) do not generalize to real-life situations and (iii) have very high rate of false positives. Given this, the proposal of this research work is the creation of a new dataset that encompasses data from three different datasets, with more than 1300 fall samples and 28 K negative samples. Our new dataset includes a standard way of adding samples, which allow the future addition of other data sources. We evaluate our dataset by using classic cost-sensitive Machine Leaning methods that deal with class imbalance. For the training and validation of this model, a set of temporal and frequency features were extracted from the raw data of an accelerometer and a gyroscope using a sliding window of 2 s with an overlap of 50%. We study the generalization properties of each dataset, by testing on the other datasets and also the performance of our new dataset. The model showed a good ability to distinguish between activities of daily living and falls, achieving a recall of 90.57%, a specificity of 96.91% and an Area Under the Receiver Operating Characteristic curve (AUC-ROC) value of 98.85% against the combination of three datasets.

Decoding the dynamic perception of risk and speed using naturalistic stimuli: A multivariate, whole-brain analysis

Time-resolved decoding of speed and risk perception in car driving is important for understanding the perceptual processes related to driving safety. In this study, we used an fMRI-compatible trackball with naturalistic stimuli to record dynamic ratings of perceived risk and speed and investigated the degree to which different brain regions were able to decode these. We presented participants with first-person perspective videos of cars racing on the same course. These videos varied in terms of subjectively perceived speed and risk profiles, as determined during a behavioral pilot. During the fMRI experiment, participants used the trackball to dynamically rate subjective risk in a first and speed in a second session and assessed overall risk and speed after watching each video. A standard multivariate correlation analysis based on these ratings revealed sparse decodability in visual areas only for the risk ratings. In contrast, the dynamic rating-based correlation analysis uncovered frontal, visual, and temporal region activation for subjective risk and dorsal visual stream and temporal region activation for subjectively perceived speed. Interestingly, further analyses showed that the brain regions for decoding risk changed over time, whereas those for decoding speed remained constant. Overall, our results demonstrate the advantages of time-resolved decoding to help our understanding of the dynamic networks associated with decoding risk and speed perception in realistic driving scenarios.

LiDAR Dynamic Target Detection Based on Multidimensional Features

To address the limitations of LiDAR dynamic target detection methods, which often require heuristic thresholding, indirect computational assistance, supplementary sensor data, or postdetection, we propose an innovative method based on multidimensional features. Using the differences between the positions and geometric structures of point cloud clusters scanned by the same target in adjacent frame point clouds, the motion states of the point cloud clusters are comprehensively evaluated. To enable the automatic precision pairing of point cloud clusters from adjacent frames of the same target, a double registration algorithm is proposed for point cloud cluster centroids. The iterative closest point (ICP) algorithm is employed for approximate interframe pose estimation during coarse registration. The random sample consensus (RANSAC) and four-parameter transformation algorithms are employed to obtain precise interframe pose relations during fine registration. These processes standardize the coordinate systems of adjacent point clouds and facilitate the association of point cloud clusters from the same target. Based on the paired point cloud cluster, a classification feature system is used to construct the XGBoost decision tree. To enhance the XGBoost training efficiency, a Spearman's rank correlation coefficient-bidirectional search for a dimensionality reduction algorithm is proposed to expedite the optimal classification feature subset construction. After preliminary outcomes are generated by XGBoost, a double Boyer-Moore voting-sliding window algorithm is proposed to refine the final LiDAR dynamic target detection accuracy. To validate the efficacy and efficiency of our method in LiDAR dynamic target detection, an experimental platform is established. Real-world data are collected and pertinent experiments are designed. The experimental results illustrate the soundness of our method. The LiDAR dynamic target correct detection rate is 92.41%, the static target error detection rate is 1.43%, and the detection efficiency is 0.0299 s. Our method exhibits notable advantages over open-source comparative methods, achieving highly efficient and precise LiDAR dynamic target detection.

Bi-Directional Long Short-Term Memory-Based Gait Phase Recognition Method Robust to Directional Variations in Subject's Gait Progression Using Wearable Inertial Sensor

Inertial Measurement Unit (IMU) sensor-based gait phase recognition is widely used in medical and biomechanics fields requiring gait data analysis. However, there are several limitations due to the low reproducibility of IMU sensor attachment and the sensor outputs relative to a fixed reference frame. The prediction algorithm may malfunction when the user changes their walking direction. In this paper, we propose a gait phase recognition method robust to user body movements based on a floating body-fixed frame (FBF) and bi-directional long short-term memory (bi-LSTM). Data from four IMU sensors attached to the shanks and feet on both legs of three subjects, collected via the FBF method, are processed through preprocessing and the sliding window label overlapping method before inputting into the bi-LSTM for training. To improve the model's recognition accuracy, we selected parameters that influence both training and test accuracy. We conducted a sensitivity analysis using a level average analysis of the Taguchi method to identify the optimal combination of parameters. The model, trained with optimal parameters, was validated on a new subject, achieving a high test accuracy of 86.43%.

Machine learning analysis reveals aberrant dynamic changes in amplitude of low-frequency fluctuations among patients with retinal detachment

Background

There is increasing evidence that patients with retinal detachment (RD) have aberrant brain activity. However, neuroimaging investigations remain focused on static changes in brain activity among RD patients. There is limited knowledge regarding the characteristics of dynamic brain activity in RD patients.

Aim

This study evaluated changes in dynamic brain activity among RD patients, using a dynamic amplitude of low-frequency fluctuation (dALFF), k-means clustering method and support vector machine (SVM) classification approach.

Methods

We investigated inter-group disparities of dALFF indices under three different time window sizes using resting-state functional magnetic resonance imaging (rs-fMRI) data from 23 RD patients and 24 demographically matched healthy controls (HCs). The k-means clustering method was performed to analyze specific dALFF states and related temporal properties. Additionally, we selected altered dALFF values under three distinct conditions as classification features for distinguishing RD patients from HCs using an SVM classifier.

Results

RD patients exhibited dynamic changes in local intrinsic indicators of brain activity. Compared with HCs, RD patients displayed increased dALFF in the bilateral middle frontal gyrus, left putamen (Putamen_L), left superior occipital gyrus (Occipital_Sup_L), left middle occipital gyrus (Occipital_Mid_L), right calcarine (Calcarine_R), right middle temporal gyrus (Temporal_Mid_R), and right inferior frontal gyrus (Frontal_Inf_Tri_R). Additionally, RD patients showed significantly decreased dALFF values in the right superior parietal gyrus (Parietal_Sup_R) and right paracentral lobule (Paracentral_Lobule_R) [two-tailed, voxel-level p < 0.05, Gaussian random field (GRF) correction, cluster-level p < 0.05]. For dALFF, we derived 3 or 4 states of ALFF that occurred repeatedly. There were differences in state distribution and state properties between RD and HC groups. The number of transitions between the dALFF states was higher in the RD group than in the HC group. Based on dALFF values in various brain regions, the overall accuracies of SVM classification were 97.87, 100, and 93.62% under three different time windows; area under the curve values were 0.99, 1.00, and 0.95, respectively. No correlation was found between hamilton anxiety (HAMA) scores and regional dALFF.

Conclusion

Our findings offer important insights concerning the neuropathology that underlies RD and provide robust evidence that dALFF, a local indicator of brain activity, may be useful for clinical diagnosis.

Human Interaction Classification in Sliding Video Windows Using Skeleton Data Tracking and Feature Extraction

A "long short-term memory" (LSTM)-based human activity classifier is presented for skeleton data estimated in video frames. A strong feature engineering step precedes the deep neural network processing. The video was analyzed in short-time chunks created by a sliding window. A fixed number of video frames was selected for every chunk and human skeletons were estimated using dedicated software, such as OpenPose or HRNet. The skeleton data for a given window were collected, analyzed, and eventually corrected. A knowledge-aware feature extraction from the corrected skeletons was performed. A deep network model was trained and applied for two-person interaction classification. Three network architectures were developed-single-, double- and triple-channel LSTM networks-and were experimentally evaluated on the interaction subset of the "NTU RGB+D" data set. The most efficient model achieved an interaction classification accuracy of 96%. This performance was compared with the best reported solutions for this set, based on "adaptive graph convolutional networks" (AGCN) and "3D convolutional networks" (e.g., OpenConv3D). The sliding-window strategy was cross-validated on the "UT-Interaction" data set, containing long video clips with many changing interactions. We concluded that a two-step approach to skeleton-based human activity classification (a skeleton feature engineering step followed by a deep neural network model) represents a practical tradeoff between accuracy and computational complexity, due to an early correction of imperfect skeleton data and a knowledge-aware extraction of relational features from the skeletons.

Lane Detection Algorithm in Curves Based on Multi-Sensor Fusion

Identifying lane markings is a key technology in assisted driving and autonomous driving. The traditional sliding window lane detection algorithm has good detection performance in straight lanes and curves with small curvature, but its detection and tracking performance is poor in curves with larger curvature. Large curvature curves are common scenes in traffic roads. Therefore, in response to the problem of poor lane detection performance of traditional sliding window lane detection algorithms in large curvature curves, this article improves the traditional sliding window algorithm and proposes a sliding window lane detection calculation method, which integrates steering wheel angle sensors and binocular cameras. When a vehicle first enters a bend, the curvature of the bend is not significant. Traditional sliding window algorithms can effectively detect the lane line of the bend and provide angle input to the steering wheel, enabling the vehicle to travel along the lane line. However, as the curvature of the curve increases, traditional sliding window lane detection algorithms cannot track lane lines well. Considering that the steering wheel angle of the car does not change much during the adjacent sampling time of the video, the steering wheel angle of the previous frame can be used as input for the lane detection algorithm of the next frame. By using the steering wheel angle information, the search center of each sliding window can be predicted. If the number of white pixels within the rectangular range centered around the search center is greater than the threshold, the average of the horizontal coordinate values of these white pixels will be used as the horizontal coordinate value of the sliding window center. Otherwise, the search center will be used as the center of the sliding window. A binocular camera is used to assist in locating the position of the first sliding window. The simulation and experimental results show that compared with traditional sliding window lane detection algorithms, the improved algorithm can better recognize and track lane lines with large curvature in bends.

LiDAR Inertial Odometry Based on Indexed Point and Delayed Removal Strategy in Highly Dynamic Environments

Simultaneous localization and mapping (SLAM) is considered a challenge in environments with many moving objects. This paper proposes a novel LiDAR inertial odometry framework, LiDAR inertial odometry-based on indexed point and delayed removal strategy (ID-LIO) for dynamic scenes, which builds on LiDAR inertial odometry via smoothing and mapping (LIO-SAM). To detect the point clouds on the moving objects, a dynamic point detection method is integrated, which is based on pseudo occupancy along a spatial dimension. Then, we present a dynamic point propagation and removal algorithm based on indexed points to remove more dynamic points on the local map along the temporal dimension and update the status of the point features in keyframes. In the LiDAR odometry module, a delay removal strategy is proposed for historical keyframes, and the sliding window-based optimization includes the LiDAR measurement with dynamic weights to reduce error from dynamic points in keyframes. We perform the experiments both on the public low-dynamic and high-dynamic datasets. The results show that the proposed method greatly increases localization accuracy in high-dynamic environments. Additionally, the absolute trajectory error (ATE) and average RMSE root mean square error (RMSE) of our ID-LIO can be improved by 67% and 85% in the UrbanLoco-CAMarketStreet dataset and UrbanNav-HK-Medium-Urban-1 dataset, respectively, when compared with LIO-SAM.

Exploring Tactile Temporal Features for Object Pose Estimation during Robotic Manipulation

Dexterous robotic manipulation tasks depend on estimating the state of in-hand objects, particularly their orientation. Although cameras have been traditionally used to estimate the object's pose, tactile sensors have recently been studied due to their robustness against occlusions. This paper explores tactile data's temporal information for estimating the orientation of grasped objects. The data from a compliant tactile sensor were collected using different time-window sample sizes and evaluated using neural networks with long short-term memory (LSTM) layers. Our results suggest that using a window of sensor readings improved angle estimation compared to previous works. The best window size of 40 samples achieved an average of 0.0375 for the mean absolute error (MAE) in radians, 0.0030 for the mean squared error (MSE), 0.9074 for the coefficient of determination (R2), and 0.9094 for the explained variance score (EXP), with no enhancement for larger window sizes. This work illustrates the benefits of temporal information for pose estimation and analyzes the performance behavior with varying window sizes, which can be a basis for future robotic tactile research. Moreover, it can complement underactuated designs and visual pose estimation methods.

A Time-Domain Signal Processing Algorithm for Data-Driven Drive-by Inspection Methods: An Experimental Study

Constructional material deterioration and member damage can cause changes in the dynamic characteristics of bridge structures, and such changes can be tracked in the responses of passing vehicles via the vehicle-bridge interaction (VBI). Though data-driven methods have shown promising results in damage inspection for drive-by methods, there is still much room for improvement in their performance. Given this background, this paper proposes a novel time-domain signal processing algorithm for the raw vehicle acceleration data of data-driven drive-by inspection methods. To achieve the best data processing performance, an optimizing strategy is designed to automatically search for the optimal parameters, tuning the algorithm. The proposed method intentionally overcomes the difficulties in the application of drive-by methods, such as measurement noise, speed variance, and enormous data volumes. Meanwhile, the use of this method can greatly improve the accuracy and efficiency of Machine Learning (ML) models in vehicle-based damage detection. It consists of a filtering process to denoise the data, a pooling process to reduce data redundancy, and an optimizing procedure to maximize algorithm performance. A dataset is obtained to validate the proposed algorithm through laboratory experiments with a scale truck model and a steel beam. The results show that, compared to using raw data, the present algorithm can increase the average accuracy by 12.2-15.0%, and the average efficiency by 35.7-96.7% for different damaged cases and ML models. Additionally, the functions of filtering and pooling operations, the influence of window function parameters, as well as the performance of different sensor locations, are also investigated in the paper. The goal is to present a signal processing algorithm for data-driven drive-by inspection methods to improve their detection performance of bridge damage caused by material deterioration or structural change.

Facial Expression Recognition Using Local Sliding Window Attention

There are problems associated with facial expression recognition (FER), such as facial occlusion and head pose variations. These two problems lead to incomplete facial information in images, making feature extraction extremely difficult. Most current methods use prior knowledge or fixed-size patches to perform local cropping, thereby enhancing the ability to acquire fine-grained features. However, the former requires extra data processing work and is prone to errors; the latter destroys the integrity of local features. In this paper, we propose a local Sliding Window Attention Network (SWA-Net) for FER. Specifically, we propose a sliding window strategy for feature-level cropping, which preserves the integrity of local features and does not require complex preprocessing. Moreover, the local feature enhancement module mines fine-grained features with intraclass semantics through a multiscale depth network. The adaptive local feature selection module is introduced to prompt the model to find more essential local features. Extensive experiments demonstrate that our SWA-Net model achieves a comparable performance to that of state-of-the-art methods with scores of 90.03% on RAF-DB, 89.22% on FERPlus, 63.97% on AffectNet.

sEMG-Based Continuous Hand Action Prediction by Using Key State Transition and Model Pruning

Conventional classification of hand motions and continuous joint angle estimation based on sEMG have been widely studied in recent years. The classification task focuses on discrete motion recognition and shows poor real-time performance, while continuous joint angle estimation evaluates the real-time joint angles by the continuity of the limb. Few researchers have investigated continuous hand action prediction based on hand motion continuity. In our study, we propose the key state transition as a condition for continuous hand action prediction and simulate the prediction process using a sliding window with long-term memory. Firstly, the key state modeled by GMM-HMMs is set as the condition. Then, the sliding window is used to dynamically look for the key state transition. The prediction results are given while finding the key state transition. To extend continuous multigesture action prediction, we use model pruning to improve reusability. Eight subjects participated in the experiment, and the results show that the average accuracy of continuous two-hand actions is 97% with a 70 ms time delay, which is better than LSTM (94.15%, 308 ms) and GRU (93.83%, 300 ms). In supplementary experiments with continuous four-hand actions, over 85% prediction accuracy is achieved with an average time delay of 90 ms.

Analysis of instantaneous brain interactions contribution to a motor imagery classification task

The purpose of this study is to analyze the contribution of the interactions between electrodes, measured either as correlation or as Jaccard distance, to the classification of two actions in a motor imagery paradigm, namely, left-hand movement and right-hand movement. The analysis is performed in two classifier models, namely, a static (linear discriminant analysis, LDA) model and a dynamic (hidden conditional random field, HCRF) model. The impact of using the sliding window technique (SWT) in the static and dynamic models is also analyzed. The study proved that their combination with temporal features provides significant information to improve the classification in a two-class motor imagery task for LDA (average accuracy: 0.7192 no additional features, 0.7617 by adding correlation, 0.7606 by adding Jaccard distance; p < 0.001) and HCRF (average accuracy: 0.7370 no additional features, 0.7764 by adding correlation, 0.7793 by adding Jaccard distance; p < 0.001). Also, we showed that adding interactions between electrodes improves significantly the performance of each classifier, regarding the nature of the interaction measure or the classifier itself.

Crack detection for concrete bridges with imaged based deep learning

Within the framework of intelligent bridge detection, a number of crack detection methods based on image processing techniques have been implemented. In this study, a combined novel approach with deep learning of a single shot multibox detector (SSD) and the eight neighborhood algorithm is proposed and applied to bridge crack image identification to provide an automatic method for crack detection. First, a large number of concrete crack images collected from the site were segmented and preprocessed for the establishment of a crack image dataset. Deep learning of the SSD algorithm was introduced on the training set to establish the detection model, where the model parameters were adjusted by the validation set. Sliding window technology was integrated to identify the cracks in the test set. The effects of the sliding window size and dataset size on the crack detection results were discussed. Moreover, the eight neighborhood algorithm was adopted for further crack detection correction. The results show that the configuration achieves good crack detection by the deep learning of the SSD algorithm with high precision and recall. The introduction of the eight neighborhood correction algorithm further improves the detection results by eliminating some misjudged results. Finally, the developed algorithm was placed into a portable device, with which cracks were effectively identified. The introduced method shows significantly better performance in crack detection, and the system installed on the portable device provides a way to broaden its application in the automatic crack detection of concrete bridges.

Research on Positioning Method in Underground Complex Environments Based on Fusion of Binocular Vision and IMU

Aiming at the failure of traditional visual slam localization caused by dynamic target interference and weak texture in underground complexes, an effective robot localization scheme was designed in this paper. Firstly, the Harris algorithm with stronger corner detection ability was used, which further improved the ORB (oriented FAST and rotated BRIEF) algorithm of traditional visual slam. Secondly, the non-uniform rational B-splines algorithm was used to transform the discrete data of inertial measurement unit (IMU) into second-order steerable continuous data, and the visual sensor data were fused with IMU data. Finally, the experimental results under the KITTI dataset, EUROC dataset, and a simulated real scene proved that the method used in this paper has the characteristics of stronger robustness, better localization accuracy, small size of hardware equipment, and low power consumption.

DBSCAN-SWA: An Integrated Tool for Rapid Prophage Detection and Annotation

As an intracellular form of a bacteriophage in the bacterial host genome, a prophage usually integrates into bacterial DNA with high specificity and contributes to horizontal gene transfer (HGT). With the exponentially increasing number of microbial sequences uncovered in genomic or metagenomics studies, there is a massive demand for a tool that is capable of fast and accurate identification of prophages. Here, we introduce DBSCAN-SWA, a command line software tool developed to predict prophage regions in bacterial genomes. DBSCAN-SWA runs faster than any previous tools. Importantly, it has great detection power based on analysis using 184 manually curated prophages, with a recall of 85% compared with Phage_Finder (63%), VirSorter (74%), and PHASTER (82%) for (Multi-) FASTA sequences. Moreover, DBSCAN-SWA outperforms the existing standalone prophage prediction tools for high-throughput sequencing data based on the analysis of 19,989 contigs of 400 bacterial genomes collected from Human Microbiome Project (HMP) project. DBSCAN-SWA also provides user-friendly result visualizations including a circular prophage viewer and interactive DataTables. DBSCAN-SWA is implemented in Python3 and is available under an open source GPLv2 license from https://github.com/HIT-ImmunologyLab/DBSCAN-SWA/.

Conflict over the eukaryote root resides in strong outliers, mosaics and missing data sensitivity of site-specific (CAT) mixture models

Phylogenetic reconstruction using concatenated loci ("phylogenomics" or "supermatrix phylogeny") is a powerful tool for solving evolutionary splits that are poorly resolved in single gene/protein trees (SGTs). However, recent phylogenomic attempts to resolve the eukaryote root have yielded conflicting results, along with claims of various artefacts hidden in the data. We have investigated these conflicts using two new methods for assessing phylogenetic conflict. ConJak uses whole marker (gene or protein) jackknifing to assess deviation from a central mean for each individual sequence, while ConWin uses a sliding window to screen for incongruent protein fragments (mosaics). Both methods allow selective masking of individual sequences or sequence fragments in order to minimize missing data, an important consideration for resolving deep splits with limited data. Analyses focused on a set of 76 eukaryotic proteins of bacterial-ancestry previously used in various combinations to assess the branching order among the three major divisions of eukaryotes: Amorphea (mainly animals, fungi and Amoebozoa), Diaphoretickes (most other well-known eukaryotes and nearly all algae) and Excavata, represented here by Discoba (Jakobida, Heterolobosea, and Euglenozoa). ConJak analyses found strong outliers to be concentrated in under-sampled lineages, while ConWin analyses of Discoba, the most under-sampled of the major lineages, detected potentially incongruent fragments scattered throughout. Phylogenetic analyses of the full data using an LG-gamma model support a Discoba sister scenario (neozoan-excavate root), which rises to 99-100% bootstrap support with data masked according to either protocol. However, analyses with two site-specific (CAT) mixture models yielded widely inconsistent results and a striking sensitivity to missing data. The neozoan-excavate root places Amorphea and Diaphoretickes as more closely related to each other than either is to Discoba, a fundamental relationship that should remain unaffected by additional taxa.

Airborne SAR Radiometric Calibration Based on Improved Sliding Window Integral Method

To verify the performance of the high-resolution fully polarimetric synthetic aperture radar (SAR) sensor carried by the Xinzhou 60 remote-sensing aircraft, we used corner reflectors to calibrate the acquired data. The target mechanism in high-resolution SAR images is more complex than it is in low-resolution SAR images, the impact of the point target pointing error on the calibration results is more obvious, and the target echo signal of high-resolution images is more easily affected by speckle noise; thus, more accurate extraction of the point target position and the response energy is required. To solve this problem, this paper introduces image context information and proposes a method to precisely determine the integration region of the corner reflector using sliding windows based on the integral method. The validation indicates that the fully polarimetric SAR sensor on the Xinzhou 60 remote-sensing aircraft can accurately reflect the radiometric characteristics of the ground features and that the integral method can obtain more stable results than the peak method. The sliding window allows the position of the point target to be determined more accurately, and the response energy extracted from the image via the integral method is closer to the theoretical value, which means that the high-resolution SAR system can achieve a higher radiometric calibration accuracy. Additionally, cross-validation reveals that the airborne SAR images have similar quality levels to Sentinel-1A and Gaofen-3 images.

Real-Time Stress Level Feedback from Raw Ecg Signals for Personalised, Context-Aware Applications Using Lightweight Convolutional Neural Network Architectures

Human stress is intricately linked with mental processes such as decision making. Public protection practitioners, including Law Enforcement Agents (LEAs), are forced to make difficult decisions during high-pressure operations, under strenuous circumstances. In this respect, systems and applications that assist such practitioners to take decisions, are increasingly incorporating user stress level information for their development, adaptation, and evaluation. To that end, our goal is to accurately detect and classify the level of acute, short-term stress, in real time, for the development of personalized, context-aware solutions for LEAs. Deep Neural Networks (DNNs), and in particular Convolutional Neural Networks (CNNs), have been gaining traction in the field of stress analysis, exhibiting promising results. Furthermore, the electrocardiogram (ECG) signals, have also been widely adopted for estimating levels of stress. In this work, we propose two CNN architectures for the stress detection and 3-level (low, moderate, high) stress classification tasks, using ultra short-term raw ECG signals (3 s). One architecture is simple and with a low memory footprint, suitable for running in wearable edge-computing nodes, and the other is able to learn more complex features, having more trainable parameters. The models were trained on the two publicly available stress classification datasets, after applying pre-processing techniques, such as data pruning, down-sampling, and data augmentation, using a sliding window approach. After hyperparameter tuning, using 4-fold cross-validation, the evaluation on the test set demonstrated state-of-the-art accuracy both on the 3- and 2-level stress classification task using the DriveDB dataset, reporting an accuracy of 83.55% and 98.77% respectively.

Identification of Methamphetamine Abstainers by Resting-State Functional Magnetic Resonance Imaging

Methamphetamine (MA) can cause brain structural and functional impairment, but there are few studies on whether this difference will sustain on MA abstainers. The purpose of this study is to investigate the correlation of brain networks in MA abstainers. In this study, 47 people detoxified for at least 14 months and 44 normal people took a resting-state functional magnetic resonance imaging (RS-fMRI) scan. A dynamic (i.e., time-varying) functional connectivity (FC) is obtained by applying sliding windows in the time courses on the independent components (ICs). The windowed correlation data for each IC were then clustered by k-means. The number of subjects in each cluster was used as a new feature for individual identification. The results show that the classifier achieved satisfactory performance (82.3% accuracy, 77.7% specificity, and 85.7% sensitivity). We find that there are significant differences in the brain networks of MA abstainers and normal people in the time domain, but the spatial differences are not obvious. Most of the altered functional connections (time-varying) are identified to be located at dorsal default mode network. These results have shown that changes in the correlation of the time domain may play an important role in identifying MA abstainers. Therefore, our findings provide valuable insights in the identification of MA and elucidate the pathological mechanism of MA from a resting-state functional integration point of view.

Research on the Fastest Detection Method for Weak Trends under Noise Interference

Trend anomaly detection is the practice of comparing and analyzing current and historical data trends to detect real-time abnormalities in online industrial data-streams. It has the advantages of tracking a concept drift automatically and predicting trend changes in the shortest time, making it important both for algorithmic research and industry. However, industrial data streams contain considerable noise that interferes with detecting weak anomalies. In this paper, the fastest detection algorithm "sliding nesting" is adopted. It is based on calculating the data weight in each window by applying variable weights, while maintaining the method of trend-effective integration accumulation. The new algorithm changes the traditional calculation method of the trend anomaly detection score, which calculates the score in a short window. This algorithm, SNWFD-DS, can detect weak trend abnormalities in the presence of noise interference. Compared with other methods, it has significant advantages. An on-site oil drilling data test shows that this method can significantly reduce delays compared with other methods and can improve the detection accuracy of weak trend anomalies under noise interference.

Lagged and dormant season climate better predict plant vital rates than climate during the growing season

Understanding the effects of climate on the vital rates (e.g., survival, development, reproduction) and dynamics of natural populations is a long-standing quest in ecology, with ever-increasing relevance in the face of climate change. However, linking climate drivers to demographic processes requires identifying the appropriate time windows during which climate influences vital rates. Researchers often do not have access to the long-term data required to test a large number of windows, and are thus forced to make a priori choices. In this study, we first synthesize the literature to assess current a priori choices employed in studies performed on 104 plant species that link climate drivers with demographic responses. Second, we use a sliding-window approach to investigate which combination of climate drivers and temporal window have the best predictive ability for vital rates of four perennial plant species that each have over a decade of demographic data (Helianthella quinquenervis, Frasera speciosa, Cylindriopuntia imbricata, and Cryptantha flava). Our literature review shows that most studies consider time windows in only the year preceding the measurement of the vital rate(s) of interest, and focus on annual or growing season temporal scales. In contrast, our sliding-window analysis shows that in only four out of 13 vital rates the selected climate drivers have time windows that align with, or are similar to, the growing season. For many vital rates, the best window lagged more than 1 year and up to 4 years before the measurement of the vital rate. Our results demonstrate that for the vital rates of these four species, climate drivers that are lagged or outside of the growing season are the norm. Our study suggests that considering climatic predictors that fall outside of the most recent growing season will improve our understanding of how climate affects population dynamics.

A Pedestrian Detection Algorithm Based on Score Fusion for Multi-LiDAR Systems

Pedestrian detection plays an essential role in the navigation system of autonomous vehicles. Multisensor fusion-based approaches are usually used to improve detection performance. In this study, we aimed to develop a score fusion-based pedestrian detection algorithm by integrating the data of two light detection and ranging systems (LiDARs). We first evaluated a two-stage object-detection pipeline for each LiDAR, including object proposal and fine classification. The scores from these two different classifiers were then fused to generate the result using the Bayesian rule. To improve proposal performance, we applied two features: the central points density feature, which acts as a filter to speed up the process and reduce false alarms; and the location feature, including the density distribution and height difference distribution of the point cloud, which describes an object’s profile and location in a sliding window. Extensive experiments tested in KITTI and the self-built dataset show that our method could produce highly accurate pedestrian detection results in real-time. The proposed method not only considers the accuracy and efficiency but also the flexibility for different modalities.

Implementation of an Online Auditory Attention Detection Model with Electroencephalography in a Dichotomous Listening Experiment

Auditory attention detection (AAD) is the tracking of a sound source to which a listener is attending based on neural signals. Despite expectation for the applicability of AAD in real-life, most AAD research has been conducted on recorded electroencephalograms (EEGs), which is far from online implementation. In the present study, we attempted to propose an online AAD model and to implement it on a streaming EEG. The proposed model was devised by introducing a sliding window into the linear decoder model and was simulated using two datasets obtained from separate experiments to evaluate the feasibility. After simulation, the online model was constructed and evaluated based on the streaming EEG of an individual, acquired during a dichotomous listening experiment. Our model was able to detect the transient direction of a participant's attention on the order of one second during the experiment and showed up to 70% average detection accuracy. We expect that the proposed online model could be applied to develop adaptive hearing aids or neurofeedback training for auditory attention and speech perception.

Recognition of Cognitive Impairment in Adult Moyamoya Disease: A Classifier Based on High-Order Resting-State Functional Connectivity Network

Objective: Vascular cognitive impairment (VCI) is a common complication in adult patients with moyamoya disease (MMD), and is reversible by surgical revascularization in its early stage of mild VCI. However, accurate diagnosis of mild VCI is difficult based on neuropsychological examination alone. This study proposed a method of dynamic resting-state functional connectivity (FC) network to recognize global cognitive impairment in MMD. Methods: For MMD, 36 patients with VCI and 43 patients with intact cognition (Non-VCI) were included, as well as 26 normal controls (NCs). Using resting-state fMRI, dynamic low-order FC networks were first constructed with multiple brain regions which were generated through a sliding window approach and correlated in temporal dimension. In order to obtain more information of network interactions along the time, high-order FC networks were established by calculating correlations among each pair of brain regions. Afterwards, a sparse representation-based classifier was constructed to recognize MMD (experiment 1) and its cognitive impairment (experiment 2) with features extracted from both low- and high-order FC networks. Finally, the ten-fold cross-validation strategy was proposed to train and validate the performance of the classifier. Results: The three groups did not differ significantly in demographic features (p > 0.05), while the VCI group exhibited the lowest MMSE scores (p = 0.001). The Non-VCI and NCs groups did not differ significantly in MMSE scores (p = 0.054). As for the classification between MMD and NCs, the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the classifier reached 90.70, 88.57, 93.67, and 73.08%, respectively. While for the classification between VCI and Non-VCI, the AUC, accuracy, sensitivity, and specificity of the classifier reached 91.02, 84.81, 80.56, and 88.37%, respectively. Conclusion: This study not only develops a promising classifier to recognize VCI in adult MMD in its early stage, but also implies the significance of time-varying properties in dynamic FC networks.

Fast Wearable Sensor-Based Foot-Ground Contact Phase Classification Using a Convolutional Neural Network with Sliding-Window Label Overlapping

Classification of foot–ground contact phases, as well as the swing phase is essential in biomechanics domains where lower-limb motion analysis is required; this analysis is used for lower-limb rehabilitation, walking gait analysis and improvement, and exoskeleton motion capture. In this study, sliding-window label overlapping of time-series wearable motion data in training dataset acquisition is proposed to accurately detect foot–ground contact phases, which are composed of 3 sub-phases as well as the swing phase, at a frequency of 100 Hz with a convolutional neural network (CNN) architecture. We not only succeeded in developing a real-time CNN model for learning and obtaining a test accuracy of 99.8% or higher, but also confirmed that its validation accuracy was close to 85%.

Real-Time Stress Assessment Using Sliding Window Based Convolutional Neural Network

Mental stress has been identified as a significant cause of several bodily disorders, such as depression, hypertension, neural and cardiovascular abnormalities. Conventional stress assessment methods are highly subjective and tedious and tend to lack accuracy. Machine-learning (ML)-based computer-aided diagnosis systems can be used to assess the mental state with reasonable accuracy, but they require offline processing and feature extraction, rendering them unsuitable for real-time applications. This paper presents a real-time mental stress assessment approach based on convolutional neural networks (CNNs). The CNN-based approach afforded real-time mental stress assessment with an accuracy as high as 96%, the sensitivity of 95%, and specificity of 97%. The proposed approach is compared with state-of-the-art ML techniques in terms of accuracy, time utilisation, and quality of features.

Estimation of Dynamic Bivariate Correlation Using a Weighted Graph Algorithm

Dynamic correlation is the correlation between two time series across time. Two approaches that currently exist in neuroscience literature for dynamic correlation estimation are the sliding window method and dynamic conditional correlation. In this paper, we first show the limitations of these two methods especially in the presence of extreme values. We present an alternate approach for dynamic correlation estimation based on a weighted graph and show using simulations and real data analyses the advantages of the new approach over the existing ones. We also provide some theoretical justifications and present a framework for quantifying uncertainty and testing hypotheses.

Quantitative Identification of Major Depression Based on Resting-State Dynamic Functional Connectivity: A Machine Learning Approach

Introduction

Developing a machine learning-based approach which could provide quantitative identification of major depressive disorder (MDD) is essential for the diagnosis and intervention of this disorder. However, the performances of traditional algorithms using static functional connectivity (SFC) measures were unsatisfactory. In the present work, we exploit the hidden information embedded in dynamic functional connectivity (DFC) and developed an accurate and objective image-based diagnosis system for MDD.

Methods

MRI images were collected from 99 participants including 56 healthy controls and 43 MDD patients. DFC was calculated using a sliding-window algorithm. A non-linear support vector machine (SVM) approach was then used with the DFC matrices as features to distinguish MDD patients from healthy controls. The spatiotemporal characteristics of the most discriminative features were then investigated.

Results

The area under the curve (AUC) of the SVM classifier with DFC measures reached 0.9913, while this value is only 0.8685 for the algorithm using SFC measures. Spatially, the most discriminative 28 connections distributed in the visual network (VN), somatomotor network (SMN), dorsal attention network (DAN), ventral attention network (VAN), limbic network (LN), frontoparietal network (FPN), and default mode network (DMN), etc. Notably, a large portion of these connections were associated with the FPN, DMN, and VN. Temporally, the most discriminative connections transited from the cortex to deeper regions.

Conclusion

The results clearly suggested that DFC is superior to SFC and provide a reliable quantitative identification method for MDD. Our findings may furnish a better understanding of the neural mechanisms of MDD as well as improve accurate diagnosis and early intervention of this disorder.

Beam flatness modulation for a flattening filter free photon beam utilizing a novel direct leaf trajectory optimization model

Flattening filter free (FFF) linear accelerators produce a fluence distribution that is forward peaked. Various dosimetric benefits, such as increased dose rate, reduced leakage and out of field dose has led to the growth of FFF technology in the clinic. The literature has suggested the idea of vendors offering dedicated FFF units where the flattening filter (FF) is removed completely and manipulating the beam to deliver conventional flat radiotherapy treatments. This work aims to develop an effective way to deliver modulated flat beam treatments, rather than utilizing a physical FF. This novel optimization model is an extension of the direct leaf trajectory optimization (DLTO) previously developed for volumetric modulated radiation therapy (VMAT) and is capable of accounting for all machine and multileaf collimator (MLC) dynamic delivery constraints, using a combination of linear constraints and a convex objective function. Furthermore, the tongue and groove (T&G) effect was also incorporated directly into our model without introducing nonlinearity to the constraints, nor nonconvexity to the objective function. The overall beam flatness, machine deliverability, and treatment time efficiency were assessed. Regular square fields, including field sizes of 10 × 10 cm² to 40 × 40 cm² were analyzed, as well as three clinical fields, and three arbitrary contours with "concave" features. Quantitative flatness was measured for all modulated FFF fields, and the results were comparable or better than their open FF counterparts, with the majority having a quantitative flatness of less than 3.0%. The modulated FFF beams, due to the included efficiency constraint, were able to achieve acceptable delivery time compared to their open FF counterpart. The results indicated that the dose uniformity and flatness for the modulated FFF beams optimized with the DLTO model can successfully match the uniformity and flatness of their conventional FF counterparts, and may even provide further benefit by taking advantage of the unique FFF beam characteristics.

DMS-SLAM: A General Visual SLAM System for Dynamic Scenes with Multiple Sensors

Presently, although many impressed SLAM systems have achieved exceptional accuracy in a real environment, most of them are verified in the static environment. However, for mobile robots and autonomous driving, the dynamic objects in the scene can result in tracking failure or large deviation during pose estimation. In this paper, a general visual SLAM system for dynamic scenes with multiple sensors called DMS-SLAM is proposed. First, the combination of GMS and sliding window is used to achieve the initialization of the system, which can eliminate the influence of dynamic objects and construct a static initialization 3D map. Then, the corresponding 3D points of the current frame in the local map are obtained by reprojection. These points are combined with the constant speed model or reference frame model to achieve the position estimation of the current frame and the update of the 3D map points in the local map. Finally, the keyframes selected by the tracking module are combined with the GMS feature matching algorithm to add static 3D map points to the local map. DMS-SLAM implements pose tracking, closed-loop detection and relocalization based on static 3D map points of the local map and supports monocular, stereo and RGB-D visual sensors in dynamic scenes. Exhaustive evaluation in public TUM and KITTI datasets demonstrates that DMS-SLAM outperforms state-of-the-art visual SLAM systems in accuracy and speed in dynamic scenes.

A Hybrid Sliding Window Optimizer for Tightly-Coupled Vision-Aided Inertial Navigation System

The fusion of visual and inertial measurements for motion tracking has become prevalent in the robotic community, due to its complementary sensing characteristics, low cost, and small space requirements. This fusion task is known as the vision-aided inertial navigation system problem. We present a novel hybrid sliding window optimizer to achieve information fusion for a tightly-coupled vision-aided inertial navigation system. It possesses the advantages of both the conditioning-based method and the prior-based method. A novel distributed marginalization method was also designed based on the multi-state constraints method with significant efficiency improvement over the traditional method. The performance of the proposed algorithm was evaluated with the publicly available EuRoC datasets and showed competitive results compared with existing algorithms.

How Sensitive Are Conventional MEG Functional Connectivity Metrics With Sliding Windows to Detect Genuine Fluctuations in Dynamic Functional Connectivity?

Despite advances in the field of dynamic connectivity, fixed sliding window approaches for the detection of fluctuations in functional connectivity are still widely used. The use of conventional connectivity metrics in conjunction with a fixed sliding window comes with the arbitrariness of the chosen window lengths. In this paper we use multivariate autoregressive and neural mass models with a priori defined ground truths to systematically analyze the sensitivity of conventional metrics in combination with different window lengths to detect genuine fluctuations in connectivity for various underlying state durations. Metrics of interest are the coherence, imaginary coherence, phase lag index, phase locking value and the amplitude envelope correlation. We performed analysis for two nodes and at the network level. We demonstrate that these metrics show indeed higher variability for genuine temporal fluctuations in connectivity compared to a static connectivity state superimposed by noise. Overall, the error of the connectivity estimates themselves decreases for longer state durations (order of seconds), while correlations of the connectivity fluctuations with the ground truth was higher for longer state durations. In general, metrics, in combination with a sliding window, perform poorly for very short state durations. Increasing the SNR of the system only leads to a moderate improvement. In addition, at the network level, only longer window widths were sufficient to detect plausible resting state networks that matched the underlying ground truth, especially for the phase locking value, amplitude envelope correlation and coherence. The length of these longer window widths did not necessarily correspond to the underlying state durations. For short window widths resting state network connectivity patterns could not be retrieved. We conclude that fixed sliding window approaches for connectivity can detect modulations of connectivity, but mostly if the underlying dynamics operate on moderate to slow timescales. In practice, this can be a drawback, as state durations can vary significantly in empirical data.

Fault Identification for a Closed-Loop Control System Based on an Improved Deep Neural Network

Fault identification for closed-loop control systems is a future trend in the field of fault diagnosis. Due to the inherent feedback adjustment mechanism, a closed-loop control system is generally very robust to external disturbances and internal noises. Closed-loop control systems often encourage faults to propagate inside the systems, which may lead to the consequence that faults amplitude becomes smaller and fault characteristics difference becomes more inapparent. Hence, it has been challenging to achieve fault identification for such systems. Traditional fault identification methods are not particularly designed for closed-loop control systems and thus cannot be applied directly. In this work, a new fault identification method is proposed, which is based on the deep neural network for closed-loop control systems. Firstly, the fault propagation mechanism in closed-loop control systems is theoretically derived, and the influence of fault propagation on system variables is analyzed. Then deep neural network is applied to find fault characteristics difference between different data modes, and a sliding window is used to amplify the fault-to-noise ratio and characteristics difference, with an aim to increase the identification performance. To verify this method, the simulations that are based on a numerical simulation model, the Tennessee industrial system and the satellite attitude control system are conducted. The results show that the proposed method is more feasible and more effective in fault identification for closed-loop control systems compared with traditional data-driven identification methods, including distance-based and angle-based identification methods.

Beyond Adherence Thresholds: A Simulation Study of the Optimal Classification of Longitudinal Adherence Trajectories From Medication Refill Histories

Background: The description of adherence based on medication refill histories relies on the estimation of continuous medication availability (CMA) during an observation period. Thresholds to distinguish adherence from non-adherence typically refer to an aggregated value across the entire observation period, disregarding differences in adherence over time. Sliding windows to divide the observation period into smaller portions, estimating adherence for these increments, and classify individuals with similar trajectories into clusters can retain this temporal information. Optimal methods to estimate adherence trajectories to identify underlying patterns have not yet been established. This simulation study aimed to provide guidance for future studies by analyzing the effect of different longitudinal adherence estimates, sliding window parameters, and sample characteristics on the performance of a longitudinal clustering algorithm.

Methods: We generated samples of 250–25,000 individuals with one of six longitudinal refill patterns over a 2-year period. We used two longitudinal CMA estimates (LCMA1 and LCMA2) and their dichotomized variants (with a threshold of 80%) to create adherence trajectories. LCMA1 assumes full adherence until the supply ends while LCMA2 assumes constant adherence between refills. We assessed scenarios with different LCMA estimates and sliding window parameters for 350 independent samples. Individual trajectories were clustered with kml, an implementation of k-means for longitudinal data in R. We compared performance between the four LCMA estimates using the adjusted Rand Index (cARI).

Results: Cluster analysis with LCMA2 outperformed other estimates in overall performance, correct identification of groups, and classification accuracy, irrespective of sliding window parameters. Pairwise comparison between LCMA estimates showed a relative cARI-advantage of 0.12–0.22 (p < 0.001) for LCMA2. Sample size did not affect overall performance.

Conclusion: The choice of LCMA estimate and sliding window parameters has a major impact on the performance of a clustering algorithm to identify distinct longitudinal adherence trajectories. We recommend (a) to assume constant adherence between refills, (b) to avoid dichotomization based on a threshold, and (c) to explore optimal sliding windows parameters in simulation studies or selecting shorter non-overlapping windows for the identification of different adherence patterns from medication refill data.

Assessing genome-wide significance for the detection of differentially methylated regions

DNA methylation plays an important role in human health and disease, and methods for the identification of differently methylated regions are of increasing interest. There is currently a lack of statistical methods which properly address multiple testing, i.e. control genome-wide significance for differentially methylated regions. We introduce a scan statistic (DMRScan), which overcomes these limitations. We benchmark DMRScan against two well established methods (bumphunter, DMRcate), using a simulation study based on real methylation data. An implementation of DMRScan is available from Bioconductor. Our method has higher power than alternative methods across different simulation scenarios, particularly for small effect sizes. DMRScan exhibits greater flexibility in statistical modeling and can be used with more complex designs than current methods. DMRScan is the first dynamic approach which properly addresses the multiple-testing challenges for the identification of differently methylated regions. DMRScan outperformed alternative methods in terms of power, while keeping the false discovery rate controlled.

Automated image segmentation-assisted flattening of atomic force microscopy images

Atomic force microscopy (AFM) images normally exhibit various artifacts. As a result, image flattening is required prior to image analysis. To obtain optimized flattening results, foreground features are generally manually excluded using rectangular masks in image flattening, which is time consuming and inaccurate. In this study, a two-step scheme was proposed to achieve optimized image flattening in an automated manner. In the first step, the convex and concave features in the foreground were automatically segmented with accurate boundary detection. The extracted foreground features were taken as exclusion masks. In the second step, data points in the background were fitted as polynomial curves/surfaces, which were then subtracted from raw images to get the flattened images. Moreover, sliding-window-based polynomial fitting was proposed to process images with complex background trends. The working principle of the two-step image flattening scheme were presented, followed by the investigation of the influence of a sliding-window size and polynomial fitting direction on the flattened images. Additionally, the role of image flattening on the morphological characterization and segmentation of AFM images were verified with the proposed method.

Brain dynamics in ASD during movie-watching show idiosyncratic functional integration and segregation

To refine our understanding of autism spectrum disorders (ASD), studies of the brain in dynamic, multimodal and ecological experimental settings are required. One way to achieve this is to compare the neural responses of ASD and typically developing (TD) individuals when viewing a naturalistic movie, but the temporal complexity of the stimulus hampers this task, and the presence of intrinsic functional connectivity (FC) may overshadow movie‐driven fluctuations. Here, we detected inter‐subject functional correlation (ISFC) transients to disentangle movie‐induced functional changes from underlying resting‐state activity while probing FC dynamically. When considering the number of significant ISFC excursions triggered by the movie across the brain, connections between remote functional modules were more heterogeneously engaged in the ASD population. Dynamically tracking the temporal profiles of those ISFC changes and tying them to specific movie subparts, this idiosyncrasy in ASD responses was then shown to involve functional integration and segregation mechanisms such as response inhibition, background suppression, or multisensory integration, while low‐level visual processing was spared. Through the application of a new framework for the study of dynamic experimental paradigms, our results reveal a temporally localized idiosyncrasy in ASD responses, specific to short‐lived episodes of long‐range functional interplays.

Chronnectome fingerprinting: Identifying individuals and predicting higher cognitive functions using dynamic brain connectivity patterns

The human brain is a large, interacting dynamic network, and its architecture of coupling among brain regions varies across time (termed the "chronnectome"). However, very little is known about whether and how the dynamic properties of the chronnectome can characterize individual uniqueness, such as identifying individuals as a "fingerprint" of the brain. Here, we employed multiband resting-state functional magnetic resonance imaging data from the Human Connectome Project (N = 105) and a sliding time-window dynamic network analysis approach to systematically examine individual time-varying properties of the chronnectome. We revealed stable and remarkable individual variability in three dynamic characteristics of brain connectivity (i.e., strength, stability, and variability), which was mainly distributed in three higher order cognitive systems (i.e., default mode, dorsal attention, and fronto-parietal) and in two primary systems (i.e., visual and sensorimotor). Intriguingly, the spatial patterns of these dynamic characteristics of brain connectivity could successfully identify individuals with high accuracy and could further significantly predict individual higher cognitive performance (e.g., fluid intelligence and executive function), which was primarily contributed by the higher order cognitive systems. Together, our findings highlight that the chronnectome captures inherent functional dynamics of individual brain networks and provides implications for individualized characterization of health and disease.

Integrating Statistical Machine Learning in a Semantic Sensor Web for Proactive Monitoring and Control

Proactive monitoring and control of our natural and built environments is important in various application scenarios. Semantic Sensor Web technologies have been well researched and used for environmental monitoring applications to expose sensor data for analysis in order to provide responsive actions in situations of interest. While these applications provide quick response to situations, to minimize their unwanted effects, research efforts are still necessary to provide techniques that can anticipate the future to support proactive control, such that unwanted situations can be averted altogether. This study integrates a statistical machine learning based predictive model in a Semantic Sensor Web using stream reasoning. The approach is evaluated in an indoor air quality monitoring case study. A sliding window approach that employs the Multilayer Perceptron model to predict short term PM2.5 pollution situations is integrated into the proactive monitoring and control framework. Results show that the proposed approach can effectively predict short term PM2.5 pollution situations: precision of up to 0.86 and sensitivity of up to 0.85 is achieved over half hour prediction horizons, making it possible for the system to warn occupants or even to autonomously avert the predicted pollution situations within the context of Semantic Sensor Web.

SEGMA: An Automatic SEGMentation Approach for Human Brain MRI Using Sliding Window and Random Forests

Quantitative volumes from brain magnetic resonance imaging (MRI) acquired across the life course may be useful for investigating long term effects of risk and resilience factors for brain development and healthy aging, and for understanding early life determinants of adult brain structure. Therefore, there is an increasing need for automated segmentation tools that can be applied to images acquired at different life stages. We developed an automatic segmentation method for human brain MRI, where a sliding window approach and a multi-class random forest classifier were applied to high-dimensional feature vectors for accurate segmentation. The method performed well on brain MRI data acquired from 179 individuals, analyzed in three age groups: newborns (38–42 weeks gestational age), children and adolescents (4–17 years) and adults (35–71 years). As the method can learn from partially labeled datasets, it can be used to segment large-scale datasets efficiently. It could also be applied to different populations and imaging modalities across the life course.

Task-related functional connectivity dynamics in a block-designed visual experiment

Studying task modulations of brain connectivity using functional magnetic resonance imaging (fMRI) is critical to understand brain functions that support cognitive and affective processes. Existing methods such as psychophysiological interaction (PPI) and dynamic causal modeling (DCM) usually implicitly assume that the connectivity patterns are stable over a block-designed task with identical stimuli. However, this assumption lacks empirical verification on high-temporal resolution fMRI data with reliable data-driven analysis methods. The present study performed a detailed examination of dynamic changes of functional connectivity (FC) in a simple block-designed visual checkerboard experiment with a sub-second sampling rate (TR = 0.645 s) by estimating time-varying correlation coefficient (TVCC) between BOLD responses of different brain regions. We observed reliable task-related FC changes (i.e., FCs were transiently decreased after task onset and went back to the baseline afterward) among several visual regions of the bilateral middle occipital gyrus (MOG) and the bilateral fusiform gyrus (FuG). Importantly, only the FCs between higher visual regions (MOG) and lower visual regions (FuG) exhibited such dynamic patterns. The results suggested that simply assuming a sustained FC during a task block may be insufficient to capture distinct task-related FC changes. The investigation of FC dynamics in tasks could improve our understanding of condition shifts and the coordination between different activated brain regions.

Spontaneous functional network dynamics and associated structural substrates in the human brain

Recent imaging connectomics studies have demonstrated that the spontaneous human brain functional networks derived from resting-state functional MRI (R-fMRI) include many non-trivial topological properties, such as highly efficient small-world architecture and densely connected hub regions. However, very little is known about dynamic functional connectivity (D-FC) patterns of spontaneous human brain networks during rest and about how these spontaneous brain dynamics are constrained by the underlying structural connectivity. Here, we combined sub-second multiband R-fMRI data with graph-theoretical approaches to comprehensively investigate the dynamic characteristics of the topological organization of human whole-brain functional networks, and then employed diffusion imaging data in the same participants to further explore the associated structural substrates. At the connection level, we found that human whole-brain D-FC patterns spontaneously fluctuated over time, while homotopic D-FC exhibited high connectivity strength and low temporal variability. At the network level, dynamic functional networks exhibited time-varying but evident small-world and assortativity architecture, with several regions (e.g., insula, sensorimotor cortex and medial prefrontal cortex) emerging as functionally persistent hubs (i.e., highly connected regions) while possessing large temporal variability in their degree centrality. Finally, the temporal characteristics (i.e., strength and variability) of the connectional and nodal properties of the dynamic brain networks were significantly associated with their structural counterparts. Collectively, we demonstrate the economical, efficient, and flexible characteristics of dynamic functional coordination in large-scale human brain networks during rest, and highlight their relationship with underlying structural connectivity, which deepens our understandings of spontaneous brain network dynamics in humans.

Novel R tools for analysis of genome-wide population genetic data with emphasis on clonality

To gain a detailed understanding of how plant microbes evolve and adapt to hosts, pesticides, and other factors, knowledge of the population dynamics and evolutionary history of populations is crucial. Plant pathogen populations are often clonal or partially clonal which requires different analytical tools. With the advent of high throughput sequencing technologies, obtaining genome-wide population genetic data has become easier than ever before. We previously contributed the R package poppr specifically addressing issues with analysis of clonal populations. In this paper we provide several significant extensions to poppr with a focus on large, genome-wide SNP data. Specifically, we provide several new functionalities including the new function mlg.filter to define clone boundaries allowing for inspection and definition of what is a clonal lineage, minimum spanning networks with reticulation, a sliding-window analysis of the index of association, modular bootstrapping of any genetic distance, and analyses across any level of hierarchies.

Determining leaf trajectories for dynamic multileaf collimators with consideration of marker visibility: an algorithm study

The purpose of this study was to develop a leaf-setting algorithm for Dynamic Multileaf Collimator-Intensity-Modulated Radiation Therapy (DMLC-IMRT) for optimal marker visibility. Here, a leaf-setting algorithm (called a Delta algorithm) was developed with the objective of maximizing marker visibility so as to improve the tracking effectiveness of fiducial markers during treatment delivery. The initial leaf trajectories were generated using a typical leaf-setting algorithm, then the leaf trajectories were adjusted by Delta algorithm operations (analytical computations and a series of matrix calculations) to achieve the optimal solution. The performance of the Delta algorithm was evaluated with six test fields (with randomly generated intensity profiles) and 15 clinical fields from IMRT plans of three prostate cancer patients. Compared with the initial solution, the Delta algorithm kept the total delivered intensities (TDIs) constant (without increasing the beam delivery time), but improved marker visibility (the percentage ratio of marker visibility time to beam delivery time). For the artificial fields (with three markers), marker visibility increased from 68.00-72.00% for a small field (5 × 5), from 38.46-43.59% for a medium field (10 × 10), and from 28.57-37.14% for a large field (20 × 20). For the 15 clinical fields, marker visibility increased 6-30% for eight fields and > 50% for two fields but did not change for five fields. A Delta algorithm was proposed to maximize marker visibility for DMLC-IMRT without increasing beam delivery time, and this will provide theoretical fundamentals for future studies of 4D DMLC tracking radiotherapy.

Dosimetric comparison between IMRT delivery modes: Step-and-shoot, sliding window, and volumetric modulated arc therapy - for whole pelvis radiation therapy of intermediate-to-high risk prostate adenocarcinoma

THIS STUDY WAS PERFORMED TO EVALUATE DOSIMETRIC DIFFERENCES BETWEEN CURRENT INTENSITY MODULATED RADIATION THERAPY (IMRT) DELIVERY MODES: Step-and-shoot (SS), sliding window (SW), and volumetric modulated arc therapy (VMAT). Plans for 15 prostate cancer patients with 10 MV photon beams using each IMRT mode were generated. Patients had three planning target volumes (PTVs) including prostate, prostate plus seminal vesicles, and pelvic lymphatics. Dose volume histograms (DVHs) of PTVs and organs at risk (OARs), tumor control probability (TCP) and normal tissue complication probabilities (NTCPs), conformation number, and monitor units (MUs) used were compared. Statistical analysis was performed using the analysis of variance (ANOVA) technique. The TCPs were < 99% with insignificant differences among modalities (P > 0.99). Doses to all critical structures were higher on average with SW method compared to SS, but insignificant. NTCP values were lowest for VMAT in all structures excepting bladder. Normal tissue volumes receiving doses in the 20-30 Gy range were reduced for VMAT compared to SS. Percentage of MUs required for VMAT to deliver a comparable plan to SS and SW was at least 40% less. In conclusion, similar target coverage and normal tissue doses were found by the three compared modes and the dosimetric differences were small.

Clinical implementation of dynamic intensity-modulated radiotherapy: Dosimetric aspects and initial experience

This paper describes the initial experience of quality assurance (QA) tests performed on the millennium multi-leaf collimator (mMLC) for clinical implementation of intensity-modulated radiotherapy (IMRT) using sliding window technique. The various QA tests verified the mechanical and dosimetric stability of the mMLC of linear accelerator when operated in dynamic mode (dMLC). The mechanical QA tests also verified the positional accuracy and kinetic properties of the dMLC. The stability of dMLC was analyzed qualitatively and quantitatively using radiographic film and Omnipro IMRT software. The output stability, variation in output for different sweeping gap widths, and dosimetric leaf separation were measured. Dose delivery with IMRT was verified against the dose computed by the treatment planning system (TPS). Monitor units (MUs) calculated by the planning system for the IMRT were cross-checked with independent commercial dose management software. Visual inspection and qualitative analysis showed that the leaf positioning accuracy was well within the acceptable limits. Dosimetric QA tests confirmed the dosimetric stability of the mMLC in dynamic mode. The verification of MUs using commercial software confirmed the reliability of the IMRT planning system for dose computation. The dosimetric measurements validated the fractional dose delivery.