Integrated Machine Learning Approach for the Early Prediction of Pressure Ulcers in Spinal Cord Injury Patients.

(1) Background: Pressure ulcers (PUs) substantially impact the quality of life of spinal cord injury (SCI) patients and require prompt intervention. This study used machine learning (ML) techniques to develop advanced predictive models for the occurrence of PUs in patients with SCI. (2) Methods: By analyzing the medical records of 539 patients with SCI, we observed a 35% incidence of PUs during hospitalization. Our analysis included 139 variables, including baseline characteristics, neurological status (International Standards for Neurological Classification of Spinal Cord Injury [ISNCSCI]), functional ability (Korean version of the Modified Barthel Index [K-MBI] and Functional Independence Measure [FIM]), and laboratory data. We used a variety of ML methods-a graph neural network (GNN), a deep neural network (DNN), a linear support vector machine (SVM_linear), a support vector machine with radial basis function kernel (SVM_RBF), K-nearest neighbors (KNN), a random forest (RF), and logistic regression (LR)-focusing on an integrative analysis of laboratory, neurological, and functional data. (3) Results: The SVM_linear algorithm using these composite data showed superior predictive ability (area under the receiver operating characteristic curve (AUC) = 0.904, accuracy = 0.944), as demonstrated by a 5-fold cross-validation. The critical discriminators of PU development were identified based on limb functional status and laboratory markers of inflammation. External validation highlighted the challenges of model generalization and provided a direction for future research. (4) Conclusions: Our study highlights the importance of a comprehensive, multidimensional data approach for the effective prediction of PUs in patients with SCI, especially in the acute and subacute phases. The proposed ML models show potential for the early detection and prevention of PUs, thus contributing substantially to improving patient care in clinical settings.

Prediction of Poststroke Depression Based on the Outcomes of Machine Learning Algorithms.

Poststroke depression (PSD) is a major psychiatric disorder that develops after stroke; however, whether PSD treatment improves cognitive and functional impairments is not clearly understood. We reviewed data from 31 subjects with PSD and 34 age-matched controls without PSD; all subjects underwent neurological, cognitive, and functional assessments, including the National Institutes of Health Stroke Scale (NIHSS), the Korean version of the Mini-Mental Status Examination (K-MMSE), computerized neurocognitive test (CNT), the Korean version of the Modified Barthel Index (K-MBI), and functional independence measure (FIM) at admission to the rehabilitation unit in the subacute stage following stroke and 4 weeks after initial assessments. Machine learning methods, such as support vector machine, k-nearest neighbors, random forest, voting ensemble models, and statistical analysis using logistic regression were performed. PSD was successfully predicted using a support vector machine with a radial basis function kernel function (area under curve (AUC) = 0.711, accuracy = 0.700). PSD prognoses could be predicted using a support vector machine linear algorithm (AUC = 0.830, accuracy = 0.771). The statistical method did not have a better AUC than that of machine learning algorithms. We concluded that the occurrence and prognosis of PSD in stroke patients can be predicted effectively based on patients' cognitive and functional statuses using machine learning algorithms.

Nanophotonics for light detection and ranging technology.

Light detection and ranging (LiDAR) technology, a laser-based imaging technique for accurate distance measurement, is considered one of the most crucial sensor technologies for autonomous vehicles, artificially intelligent robots and unmanned aerial vehicle reconnaissance. Until recently, LiDAR has relied on light sources and detectors mounted on multiple mechanically rotating optical transmitters and receivers to cover an entire scene. Such an architecture gives rise to limitations in terms of the imaging frame rate and resolution. In this Review, we examine how novel nanophotonic platforms could overcome the hardware restrictions of existing LiDAR technologies. After briefly introducing the basic principles of LiDAR, we present the device specifications required by the industrial sector. We then review a variety of LiDAR-relevant nanophotonic approaches such as integrated photonic circuits, optical phased antenna arrays and flat optical devices based on metasurfaces. The latter have already demonstrated exceptional functional beam manipulation properties, such as active beam deflection, point-cloud generation and device integration using scalable manufacturing methods, and are expected to disrupt modern optical technologies. In the outlook, we address the upcoming physics and engineering challenges that must be overcome from the viewpoint of incorporating nanophotonic technologies into commercially viable, fast, ultrathin and lightweight LiDAR systems.

A Robust Road Vanishing Point Detection Adapted to the Real-world Driving Scenes.

Vanishing point (VP) provides extremely useful information related to roads in driving scenes for advanced driver assistance systems (ADAS) and autonomous vehicles. Existing VP detection methods for driving scenes still have not achieved sufficiently high accuracy and robustness to apply for real-world driving scenes. This paper proposes a robust motion-based road VP detection method to compensate for the deficiencies. For such purposes, three main processing steps often used in the existing road VP detection methods are carefully examined. Based on the analysis, stable motion detection, stationary point-based motion vector selection, and angle-based RANSAC (RANdom SAmple Consensus) voting are proposed. A ground-truth driving dataset including various objects and illuminations is used to verify the robustness and real-time capability of the proposed method. The experimental results show that the proposed method outperforms the existing motion-based and edge-based road VP detection methods for various illumination conditioned driving scenes.

Color Image Generation from Range and Reflection Data of LiDAR.

Recently, it has been reported that a camera-captured-like color image can be generated from the reflection data of 3D light detection and ranging (LiDAR). In this paper, we present that the color image can also be generated from the range data of LiDAR. We propose deep learning networks that generate color images by fusing reflection and range data from LiDAR point clouds. In the proposed networks, the two datasets are fused in three ways-early, mid, and last fusion techniques. The baseline network is the encoder-decoder structured fully convolution network (ED-FCN). The image generation performances were evaluated according to source types, including reflection data-only, range data-only, and fusion of the two datasets. The well-known KITTI evaluation data were used for training and verification. The simulation results showed that the proposed last fusion method yields improvements of 0.53 dB, 0.49 dB, and 0.02 in gray-scale peak signal-to-noise ratio (PSNR), color-scale PSNR, and structural similarity index measure (SSIM), respectively, over the conventional reflection-based ED-FCN. Besides, the last fusion method can be applied to real-time applications with an average processing time of 13.56 ms per frame. The methodology presented in this paper would be a powerful tool for generating data from two or more heterogeneous sources.

Color Image Generation from LiDAR Reflection Data by Using Selected Connection UNET.

In this paper, a modified encoder-decoder structured fully convolutional network (ED-FCN) is proposed to generate the camera-like color image from the light detection and ranging (LiDAR) reflection image. Previously, we showed the possibility to generate a color image from a heterogeneous source using the asymmetric ED-FCN. In addition, modified ED-FCNs, i.e., UNET and selected connection UNET (SC-UNET), have been successfully applied to the biomedical image segmentation and concealed-object detection for military purposes, respectively. In this paper, we apply the SC-UNET to generate a color image from a heterogeneous image. Various connections between encoder and decoder are analyzed. The LiDAR reflection image has only 5.28% valid values, i.e., its data are extremely sparse. The severe sparseness of the reflection image limits the generation performance when the UNET is applied directly to this heterogeneous image generation. In this paper, we present a methodology of network connection in SC-UNET that considers the sparseness of each level in the encoder network and the similarity between the same levels of encoder and decoder networks. The simulation results show that the proposed SC-UNET with the connection between encoder and decoder at two lowest levels yields improvements of 3.87 dB and 0.17 in peak signal-to-noise ratio and structural similarity, respectively, over the conventional asymmetric ED-FCN. The methodology presented in this paper would be a powerful tool for generating data from heterogeneous sources.

Asymmetric Encoder-Decoder Structured FCN Based LiDAR to Color Image Generation.

In this paper, we propose a method of generating a color image from light detection and ranging (LiDAR) 3D reflection intensity. The proposed method is composed of two steps: projection of LiDAR 3D reflection intensity into 2D intensity, and color image generation from the projected intensity by using a fully convolutional network (FCN). The color image should be generated from a very sparse projected intensity image. For this reason, the FCN is designed to have an asymmetric network structure, i.e., the layer depth of the decoder in the FCN is deeper than that of the encoder. The well-known KITTI dataset for various scenarios is used for the proposed FCN training and performance evaluation. Performance of the asymmetric network structures are empirically analyzed for various depth combinations for the encoder and decoder. Through simulations, it is shown that the proposed method generates fairly good visual quality of images while maintaining almost the same color as the ground truth image. Moreover, the proposed FCN has much higher performance than conventional interpolation methods and generative adversarial network based Pix2Pix. One interesting result is that the proposed FCN produces shadow-free and daylight color images. This result is caused by the fact that the LiDAR sensor data is produced by the light reflection and is, therefore, not affected by sunlight and shadow.

Traffic Light Recognition Based on Binary Semantic Segmentation Network.

A traffic light recognition system is a very important building block in an advanced driving assistance system and an autonomous vehicle system. In this paper, we propose a two-staged deep-learning-based traffic light recognition method that consists of a pixel-wise semantic segmentation technique and a novel fully convolutional network. For candidate detection, we employ a binary-semantic segmentation network that is suitable for detecting small objects such as traffic lights. Connected components labeling with an eight-connected neighborhood is applied to obtain bounding boxes of candidate regions, instead of the computationally demanding region proposal and regression processes of conventional methods. A fully convolutional network including a convolution layer with three filters of (1 × 1) at the beginning is designed and implemented for traffic light classification, as traffic lights have only a set number of colors. The simulation results show that the proposed traffic light recognition method outperforms the conventional two-staged object detection method in terms of recognition performance, and remarkably reduces the computational complexity and hardware requirements. This framework can be a useful network design guideline for the detection and recognition of small objects, including traffic lights.

Detection abnormal pattern in activities of daily living using sequence alignment method.

As the aging is rapidly coming, the necessity of cares for old people increases. As requests for care services for patients requiring help of others increases, various systems for care services have been developed. For care services, recently, there have been developed technologies of tracking and monitoring daily activities of a person and recognizing the daily activities of the person by analyzing tracked data. Particularly, there have been developed systems for taking care of a person whose state should be periodically checked, such as patients or old persons. General care systems are good for tracking what activity the person executes, but limited to detecting what a person's state is, such as a normal or an abnormal state. So it is necessary to develop a new computational method to detect abnormal signs in a life pattern via changes of a sequence of activities of daily living.

Semi-automated clustering of gene expression data sets.

Clustering, as one of key analysis tools for gene expression data sets, attempts to discover groups of genes having similar expression patterns. In order to get a reasonable biological interpretation, it is desirable that a clustering result be accurate enough. However, conventional clustering methods do not always meet this demand since they require the exact tuning of input parameters and cluster centers for an acceptable quality of result. Through an intuitive user interaction, UI-Cluster solves the problem mentioned above, and yields better clustering results.

Gene-based single nucleotide polymorphisms and linkage disequilibrium patterns of 29 asthma candidate genes in the chromosome 5q31-33 region in Koreans.

BACKGROUND AND METHODS: Numerous genetic studies have mapped asthma susceptibility genes to a region on chromosome 5q31-33 in several populations. This region contains a cluster of cytokines and other immune-related genes important in immune response. In the present study, to determine the genetic variations and patterns of linkage disequilibrium (LD), we resequenced all the exons and promoter regions of the 29 asthma candidate genes in the chromosome 5q31-33 region. RESULTS: We identified a total of 314 genetic variants, including 289 single nucleotide polymorphisms (SNPs), 22 insertion/deletion polymorphisms and 3 microsatellites. Standardized variance data for allele frequency revealed substantial differences in SNP allele frequencies among different ethnic groups. Interestingly, significant ethnic differences were observed mainly in intron SNPs. LD block analysis using 174 common SNPs with a frequency of >10% disclosed strong LD within most candidate genes. No significant LD was observed across genes, except for one LD block (CD14-IK block). Gene-based haplotype analyses showed that 1-5 haplotype-tagging SNPs may be used to define the six or fewer common haplotypes with a frequency of >5%, regardless of the number of SNPs. CONCLUSION: Overall, our results provide useful information for the identification of immune-mediated disease genes in the chromosome 5q31-33 region, as well as valuable evidence for gene-based haplotype analysis in disease association studies.

An automatic block and spot indexing with k-nearest neighbors graph for microarray image analysis.

MOTIVATION: In this paper, we propose a fully automatic block and spot indexing algorithm for microarray image analysis. A microarray is a device which enables a parallel experiment of ten to hundreds of thousands of test genes in order to measure gene expression. Due to this huge size of experimental data, automated image analysis is gaining importance in microarray image processing systems. Currently, most of the automated microarray image processing systems require manual block indexing and, in some cases, spot indexing. If the microarray image is large and contains a lot of noise, it is very troublesome work. In this paper, we show it is possible to locate the addresses of blocks and spots by applying the Nearest Neighbors Graph Model. Also, we propose an analytic model for the feasibility of block addressing. Our analytic model is validated by a large body of experimental results. RESULTS: We demonstrate the features of automatic block detection, automatic spot addressing, and correction of the distortion and skewedness of each microarray image.