Search

This chapter presents the existing techniques for data acquisition and data preprocessing in general; while the adoption of selected artificial intelligence models for solving the problems in different industries, such as thin‐film‐transistor liquid‐crystal display, solar cell, semiconductor, automotive, aerospace, chemical, and bottle industries. The analog‐to‐digital converter connects to various sensors installed on the equipment side to convert analog sensing signals into digital signals via its analog input/output ports. The chapter presents various sensing techniques and the issues of sensor selection and installation. The goal of data preprocessing is to eliminate the noise imbedded in the signal and extract key‐feature related information. Data preprocessing consists of three steps: segmentation, cleaning, and feature extraction. The chapter demonstrates four practical examples using real‐world data to validate techniques of data acquisition and data preprocessing. These include: detrending of the thermal effect in strain gauge data, automated segmentation of signal data, tool state diagnosis, and tool diagnosis using loading data.

This chapter presents the actual intelligent manufacturing implementation cases adopting all the Industry 4.1 related techniques involving cyber‐physical agent, advanced manufacturing cloud of things, automatic virtual metrology (AVM), intelligent predictive maintenance (IPM), and intelligent yield maintenance (IYM) in seven industries. These industries include: flat panel display, semiconductor, solar cell, automobile, aerospace, carbon fiber, and blow molding. Both AVM and IYM have been deployed in the thin film transistor‐liquid crystal display industry. Tube to Tube control with AVM and IPM has been deployed in the solar cell industry. AVM, IPM, and IYM have been deployed in the semiconductor industry. The virtual metrology (VM) accuracy of each AVM Server can be maintained and the AVM Server is then ready to serve various VM applications. There are three preconditions of applying AVM: cause collection, effect collection, and work‐in‐process tracking.

Background. Sjögrenʼs syndrome is an autoimmune disease characterized primarily by decreased exocrine gland function leading to eye and mouth dryness. Extraglandular manifestations occur less frequently. Case Report. A 74-year-old man with hypertension was admitted with productive cough and fever. On physical examination, he had bilateral lower lung decreased breath sounds. A chest radiograph showed bibasilar patchy infiltrate. Laboratory studies revealed hemoglobin of 11.9 g/dL, white blood cell count of 16,000/uL, and platelet count of 250,000/uL. Empiric antibiotic therapy was begun for suspected community acquired pneumonia, and then he was discharged home. However, his cough recurred. Chest computed tomography demonstrated adenopathy throughout the mediastinum and multiple ill-defined patchy groundglass opacities with a lower lobe prominence. He underwent a transbronchial biopsy to rule out malignancy; however, it showed lymphocytic interstitial pneumonitis. Antinuclear antibody was 1 : 80 homogeneous, and anti-SSA antibody was 6.3 AI (normal

Objective We designed an automatic, computationally efficient, and interpretable algorithm for detecting ventricular ectopic beats in long-term, single-lead electrocardiogram recordings. Methods We built five simple, interpretable, and computationally efficient features from each cardiac cycle, including a novel morphological feature which described the distance to the median beat in the recording. After an unsupervised subject-specific normalization procedure, we trained an ensemble binary classifier using the AdaBoost algorithm Results After our classifier was trained on subset DS1 of the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia database, our classifier obtained an F1 score of 94.35% on subset DS2 of the same database. The same classifier achieved F1 scores of 92.06% on the St. Petersburg Institute of Cardiological Technics (INCART) 12-lead Arrhythmia database and 91.40% on the MIT-BIH Long-term database. A phenotype-specific analysis of model performance was afforded by the annotations included in the St. Petersburg INCART Arrhythmia database Conclusion The five features this novel algorithm employed allowed our ventricular ectopy detector to obtain high precision on previously unseen subjects and databases Significance Our ventricular ectopy detector will be used to study the relationship between premature ventricular contractions and adverse patient outcomes such as congestive heart failure and death.

Primary Subject area Neonatal-Perinatal Medicine Background Hypoxic-ischemic encephalopathy (HIE) is a major contributor to morbidity and mortality. Therapeutic hypothermia (TH) is the standard of care for neonates with moderate to severe HIE. Brain magnetic resonance imaging (MRI) is the imaging modality of choice for confirmation of HIE, assessment of injury severity, and prognostication. Reliable, inexpensive and widely available laboratory measures for early identification of risk for neurological injury can play a critical role in the optimal management of neonatal HIE, especially in the resource-limited setting. Our study examined whether derangements in early routine laboratory measures (acid-base, haematological, metabolic) were worse in neonates with MRI findings of neurological injury. Objectives Primary objective: To evaluate the role of early laboratory measures in predicting neurological injury as detected by MRI at 72 hours. Secondary objective: To evaluate the role of early laboratory measures in predicting survival to NICU discharge in patients with HIE. Design/Methods This single-centre, retrospective cohort study included neonates ≥ 35 weeks gestation with moderate to severe HIE, who had undergone therapeutic hypothermia. Based on findings of brain MRI completed within 72 hours of life, our cohort was divided into 2 groups: neonates with, and without, evidence of neurological injury consistent with HIE. Baseline characteristics, as well as laboratory measures, were compared between groups, and a receiver operating characteristic (ROC) curve analysis was conducted to determine the cut-off for prediction of neurological injury based on the highest sensitivity and specificity values. Results 104 neonates were analyzed. Baseline characteristics (Table 1) were similar between both groups, except for cord venous pH and base excess (BE), which were significantly lower in the abnormal MRI group (p = 0.02). In bivariate analysis, pH (at 1 h of age, p = 0.027), BE (at 1 h, p = 0.001, and 6 h of age, p = 0.004), ionized calcium (at 6 h of age, p = 0.02), and platelets (at 1 h of age, p = 0.004) were significantly different in neonates with abnormal MRI. In ROC curve analysis, BE at 1 h of life was the best predictor of abnormal MRI (AUC = 0.71, p = 0.002), with a cut-off value of ≤ -14.95, sensitivity of 67% and specificity of 66% (Figure 1). Conclusion Among neonates with HIE undergoing TH, early laboratory measures such as acid-base status, ionized calcium, and platelet count were worse in neonates with abnormal MRI, in comparison to neonates with normal MRI. Base excess at 1 h of life is a good predictor of abnormal MRI. Future prospective studies to validate these findings are needed

STUDY OBJECTIVES: Polysomnography is the gold standard in identifying sleep stages; however, there are discrepancies in how technicians use the standards. Because organizing meetings to evaluate this discrepancy and/or reach a consensus among multiple sleep centers is time-consuming, we developed an artificial intelligence system to efficiently evaluate the reliability and consistency of sleep scoring and hence the sleep center quality. METHODS: An interpretable machine learning algorithm was used to evaluate the interrater reliability (IRR) of sleep stage annotation among sleep centers. The artificial intelligence system was trained to learn raters from 1 hospital and was applied to patients from the same or other hospitals. The results were compared with the experts’ annotation to determine IRR. Intracenter and intercenter assessments were conducted on 679 patients without sleep apnea from 6 sleep centers in Taiwan. Centers with potential quality issues were identified by the estimated IRR. RESULTS: In the intracenter assessment, the median accuracy ranged from 80.3%–83.3%, with the exception of 1 hospital, which had an accuracy of 72.3%. In the intercenter assessment, the median accuracy ranged from 75.7%–83.3% when the 1 hospital was excluded from testing and training. The performance of the proposed method was higher for the N2, awake, and REM sleep stages than for the N1 and N3 stages. The significant IRR discrepancy of the 1 hospital suggested a quality issue. This quality issue was confirmed by the physicians in charge of the 1 hospital. CONCLUSIONS: The proposed artificial intelligence system proved effective in assessing IRR and hence the sleep center quality. CITATION: Liu G-R, Lin T-Y, Wu H-T, et al. Large-scale assessment of consistency in sleep stage scoring rules among multiple sleep centers using an interpretable machine learning algorithm. J Clin Sleep Med. 2021;17(2):159–166.

Smart city infrastructure has a significant impact on improving the quality of humans life. However, a substantial increase in the urban population from the last few years poses challenges related to resource management, safety, and security. To ensure the safety and security in the smart city environment, this paper presents a novel approach by empowering the authorities to better visualize the threats, by identifying and predicting the highly-reported crime zones in the smart city. To this end, it first investigates the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to detect the hot-spots that have a higher risk of crime occurrence. Second, for crime prediction, Seasonal Auto-Regressive Integrated Moving Average (SARIMA) is exploited in each dense crime region to predict the number of crime incidents in the future with spatial and temporal information. The proposed HDBSCAN and SARIMA based crime prediction model is evaluated on ten years of crime data (2008-2017) for New York City (NYC). The accuracy of the model is measured by considering different time scenarios such as the year-wise, (i.e., for each year), and for the total considered duration of ten years using an 80:20 ratio. The 80% of data was used for training and 20% for testing. The proposed approach outperforms with an average Mean Absolute Error (MAE) of 11.47 as compared to the highest scoring DBSCAN based method with MAE 27.03.

The need for speed and quality in delivering all software engineering artifacts has inevitably remained the biggest challenge in today’s software development environment. While everyone caters to complex software engineering processes, new releases are expected by the market on almost a daily basis. Thus, several Artificial Intelligence (AI) techniques have been introduced that are intensively used in the modern software engineering industry to fulfill market needs. This paper presents the initial results of our review work on software bug detection and prediction studies using AI techniques. Our focus is to (i) identify factors affecting the effectiveness of current software bug detection and prediction techniques and (ii) identify the effectiveness of AI techniques in improving current software bug detection and prediction techniques. The evidence showed that the software engineering domain has utilized artificial intelligence approaches and techniques to facilitate the complex tasks of software bug detection and bug prediction. It mainly demonstrates the significance of merging artificial intelligence with the software engineering domain in terms of reduced overhead and efficient results to enhance the quality of software products.

Background The World Health Organization (WHO) estimated that 29% of global tuberculosis (TB) and almost 47% of childhood TB cases were not reported to national TB programs in 2019. In Cambodia, most childhood TB cases were reported from health facilities supported by the Global Fund to Fight AIDS, Tuberculosis, and Malaria in 2019. This study aimed to compare the healthcare providers' knowledge, attitude, and practices (KAP) on childhood TB case detection in operational districts (ODs) with high and low childhood TB case detection in Cambodia. Methods We conducted a cross-sectional study between November and December 2020 among healthcare providers in 10 purposively selected ODs with high childhood TB case detection and 10 ODs with low childhood TB case detection. A total of 110 healthcare providers from referral hospitals (RHs) and 220 from health centers (HCs) were interviewed. We collected information on socio-demographic characteristics, training, and KAP on childhood TB. Pearson's Chi-square or Fisher's exact and Student's t-tests were performed to explore the differences in KAP of healthcare providers from ODs with low vs. high childhood TB detection. Results Of the 330 respondents, 193 were from ODs with high childhood TB case detection, and 66.67% were from HCs. A significantly higher proportion (46.11%) of respondents from ODs with high childhood TB case detection received training on childhood TB within the past two years than those from low childhood TB case detection ODs (34.31%) (p = 0.03). Key knowledge on childhood TB was not significantly different among respondents from ODs with high and low childhood TB case detection. A significantly higher proportion of respondents from ODs with high childhood TB case detection had a good attitude (98.96 vs. 97.08%, p = 0.002) and performed good practices (58.55 vs. 45.26%, p = 0.02) on contact investigation in the community than those from low childhood TB case detection ODs. Conclusions Healthcare providers from ODs with high childhood TB detection had better attitudes and practices towards childhood TB. The attitudes and practices need to be improved among healthcare providers in ODs with low case detection. Further investment in training and experience sharing on childhood TB case detection among healthcare providers is needed to improve childhood TB case detection.

The goal of software bug prediction is to identify the software modules that will have the likelihood to get bugs by using some fundamental project resources before the real testing starts. Due to high cost in correcting the detected bugs, it is advisable to start predicting bugs at the early stage of development instead of at the testing phase. There are many techniques and approaches that can be used to build the prediction models, such as machine learning. This technique is widely used nowadays because it can give accurate results and analysis. Therefore, we decided to perform a review of past literature on software bug prediction and machine learning so that we can understand better about the process of constructing the prediction model. Not only we want to see the machine learning techniques that past researchers used, we also assess the datasets, metrics and performance measures that are used during the development of the models. In this study, we have narrowed down to 31 main studies and six types of machine learning techniques have been identified. Two public datasets are found to be frequently used and object-oriented metrics are the highly chosen metrics for the prediction model. As for the performance measure, both graphical and numerical measures are often used to evaluate the performance of the models. From the results, we conclude that the machine learning technique can predict the bug, but there are not many applications in this area that exist nowadays. There are a few challenges in constructing the prediction model. Thus, more studies need to be carried out so that a well-formed result is obtained. We also provide a recommendation for future research based on the results we got from this study.

Objective: We hypothesized that prenatal stress (PS) exerts lasting impact on fetal heart rate (fHR). We sought to validate the presence of such PS signature in fHR by measuring coupling between maternal HR (mHR) and fHR. Study design: Prospective observational cohort study in stressed group (SG) mothers with controls matched for gestational age during screening at third trimester using Cohen Perceived Stress Scale (PSS) questionnaire with PSS-10 equal or above 19 classified as SG. Women with PSS-10 less than 19 served as control group (CG). Setting: Klinikum rechts der Isar of the Technical University of Munich. Population: Singleton 3rd trimester pregnant women. Methods: Transabdominal fetal electrocardiograms (fECG) were recorded. We deployed a signal processing algorithm termed bivariate phase-rectified signal averaging (BPRSA) to quantify coupling between mHR and fHR resulting in a fetal stress index (FSI). Maternal hair cortisol was measured at birth. Differences were assumed to be significant for p value less than 0.05. Main Outcome Measures: Differences for FSI between both groups. Results: We screened 1500 women enrolling 538 of which 16.5 % showed a PSS-10 score equal or above 19 at 34+0 weeks. Fifty five women eventually comprised the SG and n=55 served as CG. Median PSS was 22.0 (IQR 21.0-24.0) in the SG and 9.0 (6.0-12.0) in the CG, respectively. Maternal hair cortisol was higher in SG than CG at 86.6 (48.0-169.2) versus 53.0 (34.4-105.9) pg/mg. At 36+5 weeks, FSI was significantly higher in fetuses of stressed mothers when compared to controls [0.43 (0.18-0.85) versus 0.00 (-0.49-0.18)]. Conclusion: Our findings show a persistent effect of PS affecting fetuses in the last trimester.

The problem of information fusion from multiple data-sets acquired by multimodal sensors has drawn significant research attention over the years. In this paper, we focus on a particular problem setting consisting of a physical phenomenon or a system of interest observed by multiple sensors. We assume that all sensors measure some aspects of the system of interest with additional sensor-specific and irrelevant components. Our goal is to recover the variables relevant to the observed system and to filter out the nuisance effects of the sensor-specific variables. We propose an approach based on manifold learning, which is particularly suitable for problems with multiple modalities, since it aims to capture the intrinsic structure of the data and relies on minimal prior model knowledge. Specifically, we propose a nonlinear filtering scheme, which extracts the hidden sources of variability captured by two or more sensors, that are independent of the sensor-specific components. In addition to presenting a theoretical analysis, we demonstrate our technique on real measured data for the purpose of sleep stage assessment based on multiple, multimodal sensor measurements. We show that without prior knowledge on the different modalities and on the measured system, our method gives rise to a data-driven representation that is well correlated with the underlying sleep process and is robust to noise and sensor-specific effects.

Objective: While the survival of extremely premature infants has improved over the past decades, the rate of complications – especially for bronchopulmonary dysplasia (BPD) – remains un-acceptably high. Over the past 50 years, no safe therapy has had a substantial impact on the incidence and severity of BPD. Methods: This may stem from the multifactorial disease pathogenesis and the increasing lung imma-turity. Mesenchymal Stromal Cells (MSCs) display pleiotropic effects and show promising results in neonatal rodents in preventing or rescuing lung injury without adverse effects. Early phase clinical trials are now underway to determine the safety and efficacy of this therapy in extremely premature infants. Results and Conclusion: This review summarizes our current knowledge about MSCs, their mecha-nism of action and the results of preclinical studies that provide the rationale for early phase clinical trials and discuss remaining gaps in our knowledge

This paper proposes a novel feature representation approach for heartbeat classification using single-lead electrocardiogram (ECG) signals based on adaptive Fourier decomposition (AFD). AFD is a recently developed signal processing tool that provides useful morphological features, which are referred as AFD-derived instantaneous frequency (IF) features and differ from those provided by traditional tools. The AFD-derived IF features, together with ECG landmark features and RR interval features, are trained by a support vector machine to perform the classification. The proposed method improves the average accuracy of the feature extraction-based methods, reaching a level comparable to deep learning but with less training data, and at the same time being interpretable for the learned features. It also greatly reduces the dimension of the feature set, which is a disadvantage of the feature extraction-based methods, especially for ECG signals. To evaluate the performance, the Association for the Advancement of Medical Instrumentation standard is applied to publicly available benchmark databases, including the MIT-BIH arrhythmia and MIT-BIH supraventricular arrhythmia databases, to classify heartbeats from the single-lead ECG. The overall performance is compared to selected state-of-the-art automatic heartbeat classification algorithms, including one-lead and even several two-lead-based methods. The proposed approach achieves superior balanced performance and real-time implementation.

Many recent studies have shown that various multi-objective evolutionary algorithms have been widely applied in the field of search-based software engineering (SBSE) for optimal solutions. Most of them either focused on solving newly re-formulated problems or on proposing new approaches, while a number of studies performed reviews and comparative studies on the performance of proposed algorithms. To evaluate such performance, it is necessary to consider a number of performance metrics that play important roles during the evaluation and comparison of investigated algorithms based on their best-simulated results. While there are hundreds of performance metrics in the literature that can quantify in performing such tasks, there is a lack of systematic review conducted to provide evidence of using these performance metrics, particularly in the software engineering problem domain. In this paper, we aimed to review and quantify the type of performance metrics, number of objectives, and applied areas in software engineering that reported in primary studies—this will eventually lead to inspiring the SBSE community to further explore such approaches in depth. To perform this task, a formal systematic review protocol was applied for planning, searching, and extracting the desired elements from the studies. After considering all the relevant inclusion and exclusion criteria for the searching process, 105 relevant articles were identified from the targeted online databases as scientific evidence to answer the eight research questions. The preliminary results show that remarkable studies were reported without considering performance metrics for the purpose of algorithm evaluation. Based on the 27 performance metrics that were identified, hypervolume, inverted generational distance, generational distance, and hypercube-based diversity metrics appear to be widely adopted in most of the studies in software requirements engineering, software design, software project management, software testing, and software verification. Additionally, there are increasing interest in the community in re-formulating many objective problems with more than three objectives, yet, currently are dominated in re-formulating two to three objectives.

Despite prolonged and cumulative exposure during gestation, little is known about the fetal response to maternal sleep. Eighty-four pregnant women with obesity (based on pre-pregnancy BMI) participated in laboratory-based polysomnography (PSG) with continuous fetal electrocardiogram monitoring at 36 weeks gestation. Multilevel modeling revealed both correspondence and lack of it in maternal and fetal heart rate patterns. Fetal heart rate (fHR) and variability (fHRV), and maternal heart rate (mHR) and variability (mHRV), all declined during the night, with steeper rates of decline prior to 01:00. fHR declined upon maternal sleep onset but was not otherwise associated with maternal sleep stage; fHRV differed during maternal REM and NREM. There was frequent maternal waking after sleep onset (WASO) and fHRV and mHRV were elevated during these episodes. Cross-correlation analyses revealed little temporal coupling between maternal and fetal heart rate, except during WASO, suggesting that any observed associations in maternal and fetal heart rates during sleep are the result of other physiological processes. Implications of the maternal sleep context for the developing fetus are discussed, including the potential consequences of the typical sleep fragmentation that accompanies pregnancy.

Tree structural defects are a common cause of tree failure. These structural defects often result from progressive wood decay over time. Therefore, special attention is required to study the changes in the lateral responses of trees as defects are introduced. This can show how, using these changes, significant tree defects that can ultimately disrupt tree stability be detected. In this study, a three-dimensional (3D) numerical model was proposed to investigate the mechanical behavior of trees with structural defects under lateral load. The 3D numerical model was verified by non-destructive tree pulling tests with the incorporation of the overall stiffness of the tested trees. Then, trees with structural defects were simulated with different tree geometries and defect sizes. In addition, to examine the effect of decay volume extents and deterioration in elastic modulus due to decay, a simplified two-dimensional (2D) numerical simulation was performed. Through comparison with the results of the tree pulling tests, the 3D numerical model was found to be appropriate and applicable for the evaluation of the tree’s lateral response as well as the effects on tree stability. Numerical analysis results, therefore, confirmed the fact that the mechanical behavior of the tree under lateral load is strongly dependent on the presence of significant decay that can cause whole tree failure. National Parks Board Submitted/Accepted version The research presented in this paper was supported by National Parks Board, Singapore through a collaborative research project with Nanyang Technological University entitled Eye On Trees (EOT).

An automatic accurate T-wave end (T-end) annotation for the electrocardiogram (ECG) has several important clinical applications. While there have been several algorithms proposed, their performance is usually deteriorated when the signal is noisy. Therefore, we need new techniques to support the noise robustness in T-end detection. We propose a new algorithm based on the signal quality index (SQI) for T-end, coined as tSQI, and the optimal shrinkage (OS). For segments with low tSQI, the OS is applied to enhance the signal-to-noise ratio (SNR). We validated the proposed method using eleven short-term ECG recordings from QT database available at Physionet, as well as four 14-day ECG recordings which were visually annotated at a central ECG core laboratory. We evaluated the correlation between the real-world signal quality for T-end and tSQI, and the robustness of proposed algorithm to various additive noises of different types and SNR&rsquo, s. The performance of proposed algorithm on arrhythmic signals was also illustrated on MITDB arrhythmic database. The labeled signal quality is well captured by tSQI, and the proposed OS denoising help stabilize existing T-end detection algorithms under noisy situations by making the mean of detection errors decrease. Even when applied to ECGs with arrhythmia, the proposed algorithm still performed well if proper metric is applied. We proposed a new T-end annotation algorithm. The efficiency and accuracy of our algorithm makes it a good fit for clinical applications and large ECG databases. This study is limited by the small size of annotated datasets.

This paper focuses on the compressive behavior of concrete in case of experimental study and modeling using discrete element method (DEM). The experimental behavior of concrete samples with different fabricated gradations is firstly carried out following ASTM C469. Then, the DEM is used to simulate this behavior. With the DEM, the concrete sample is simulated by the assembly of spheres. The simulating results are compared with the experimental results to verify the discrete element model. In addition, mechanical behavior as well as the propagation of cracks and destruction of material are clearly shown regardless of the meshing as finite elements. This study shows the ability of the discrete element model to simulate the concrete behavior and also the ability to develop the constitutive laws of the model in order to simulate concrete structures.

Obstructive sleep apnea/hypopnea syndrome (OSAHS) is characterized by repeated airflow partial reduction or complete cessation due to upper airway collapse during sleep. OSAHS can induce frequent awake and intermittent hypoxia that is associated with hypertension and cardiovascular events. Full-channel Polysomnography (PSG) is the gold standard for diagnosing OSAHS, however, this PSG evaluation process is unsuitable for home screening. To solve this problem, a measuring module integrating abdominal and thoracic triaxial accelerometers, a pulsed oximeter (SpO2) and an electrocardiogram sensor was devised in this study. Moreover, a long short-term memory recurrent neural network model is proposed to classify four types of sleep breathing patterns, namely obstructive sleep apnea (OSA), central sleep apnea (CSA), hypopnea (HYP) events and normal breathing (NOR). The proposed algorithm not only reports the apnea-hypopnea index (AHI) through the acquired overnight signals but also identifies the occurrences of OSA, CSA, HYP and NOR, which assists in OSAHS diagnosis. In the clinical experiment with 115 participants, the performances of the proposed system and algorithm were compared with those of traditional expert interpretation based on PSG signals. The accuracy of AHI severity group classification was 89.3%, and the AHI difference for PSG expert interpretation was 5.0&plusmn, 4.5. The overall accuracy of detecting abnormal OSA, CSA and HYP events was 92.3%.

We propose a novel unsupervised approach for sleep dynamics exploration and automatic annotation by combining modern harmonic analysis tools. Specifically, we apply diffusion-based algorithms, diffusion map (DM), and alternating diffusion (AD) algorithms, to reconstruct the intrinsic geometry of sleep dynamics by reorganizing the spectral information of an electroencephalogram (EEG) extracted from a nonlinear-type time frequency analysis tool, the synchrosqueezing transform (SST). The visualization is achieved by the nonlinear dimension reduction properties of DM and AD. Moreover, the reconstructed nonlinear geometric structure of the sleep dynamics allows us to achieve the automatic annotation purpose. The hidden Markov model is trained to predict the sleep stage. The prediction performance is validated on a publicly available benchmark database, Physionet Sleep-EDF [extended] SC∗ and ST∗, with the leave-one-subject-out cross-validation. The overall accuracy and macro F1 achieve 82.57% and 76% in Sleep-EDF SC∗ and 77.01% and 71.53% in Sleep-EDF ST∗, which is compatible with the state-of-the-art results by supervised learning-based algorithms. The results suggest the potential of the proposed algorithm for clinical applications.

Aims Detrusor overactivity (DO) of the bladder is a finding on urodynamic studies (UDS) that often correlates with lower urinary tract symptoms and drives management. However, UDS interpretation remains nonstandardized. We sought to develop a mathematical model to reliably identify DO in UDS. Methods We utilized UDS archive files for studies performed at our institution between 2013 and 2019. Raw tracings of vesical pressure, abdominal pressure, detrusor pressure, infused volume, and all annotations during UDS were obtained. Patients less than 1 year old, studies with calibration issues, or those with significant artifacts were excluded. In the training set, five representative DO patterns were identified. Candidate Pdet signal segments were matched to representative DO patterns. Manifold learning and dynamic time warping algorithms were used. Five-fold cross validation (CV) was used to evaluate the performance. Results A total of 799 UDS studies were included. The median age was 9 years (range, 1-33). There were 1,742 DO events that did not overlap with annotated artifacts (cough, cry, valsalva, movements). The AUC of the training sets from the five-fold CV was 0.84 ± 0.01. The five-fold CV leads to an overall accuracy 81.35%, and sensitivity and specificity of detecting DO events are 76.92% and 81.41%, respectively, in the testing set. Conclusions Our predictive model using machine learning algorithms provides promising performance to facilitate automated identification of DO in UDS. This would allow for standardization and potentially more reliable UDS interpretation. Signal processing and machine learning interpretation of the other components of UDS are forthcoming.

Background: Cardiovascular disease is a common comorbidity and cause of mortality among patients with chronic obstructive pulmonary disease (COPD). However, the interaction between the heart and lungs in COPD patients has yet to be fully elucidated. Aim: Our objective in this study was to characterize cardiorespiratory interactions in terms of cardiorespiratory coupling (CRC) using the synchrogram index of the heart rate and respiration flow signals. Methods: This prospective study examined 10 normal subjects and 55 COPD patients. Linear regression and forward stepwise regression were used to determine the correlation between the synchrogram index and the six-minute walking test. Results: K-means clustering analysis was used to separate the 55 COPD patients into a synchronized group (median 0.89 (0.64-0.97), n=43) and a desynchronized group (median 0.23 (0.02-0.51), n=12) based on the synchrogram index. In this study, the synchrogram index was significantly correlated with the six-minute walking distance (r2=0.3, sigma T=0.02) and the distance saturation product (r2=0.3, sigma T =0.03). Note that age was a significant confounding factor. Conclusion: The synchrogram index shows clinical potential for the stratification of COPD patients for treatment.

Joining global supply chain networks helps firms to enhance innovation performance as firms need to satisfy various standard requirements from overseas customers. From the global value chain theory, there is no evidence on what types of supply chain ownership structures help firms to achieve more innovation. This deficiency led us to investigate types of supply chain ownership structures, i.e., Pure Domestic Chain, Pure Joint Venture (JV) Chain, Pure Multinational Corporation (MNC) Chain, Export Chain, and Import Chain, that can help firms to achieve more innovation. One-way ANOVA is used to analyze 856 responses collected from the Thai manufacturing industry during 2012&ndash, 2017. The results indicate that firms in the Pure MNC Chain have the highest levels of product and process innovation. There is less innovation for the Pure JV Chain, Export Chain, Import Chain, and Pure Domestic Chain, in decreasing order. This means that firms in global supply chain networks tend to have better innovation performance than firms in local supply chain networks. The innovation capabilities of local firms can be enhanced through knowledge transfer and knowledge co-creation by joining global supply chain networks.

May–Thurner syndrome (MTS) is an underdiagnosed cause of lower limb deep vein thrombosis (DVT). The clinical prevalence of MTS-related DVT is likely underestimated, particularly in patients with other more recognisable risk factors. MTS is classically described in females between the age group of 20–50 years. In patients with acute iliofemoral thrombosis, medical treatment with anticoagulation alone has been associated with higher risk of postthrombotic syndrome (PTS) and lower iliofemoral patency rates, as compared to endovascular correction. We describe a case of MTS-related extensive iliofemoral DVT occurring in a middle age male who presented with acute onset of left lower limb swelling and pain, complicated by pulmonary embolism. Doppler compression ultrasonography of the left lower limb showed partial DVT extending from the left external iliac to the popliteal veins, and contrasted computed tomography (CT) of the thorax abdomen and pelvis established features of MTS, together with right pulmonary embolism. He was started on low molecular weight heparin (LMWH) and then underwent left lower limb AngioJet pharmacomechanical thrombolysis/thrombectomy, iliac vein stenting, and temporary inferior vena cava (IVC) filter insertion. After the procedure, the patient recovered and improved symptomatically with rapid resolution of this left lower limb swelling and pain. He was switched to an oral Factor Xa inhibitor and was subsequently discharged. After 1-month follow-up, he remained well with stent patency visualised on repeat ultrasound and underwent an uneventful elective IVC filter retrieval with subsequent plans for a 1-year follow-up.

BACKGROUND Cardiovascular waveforms contain information for clinical diagnosis. By learning and organizing the subtle change of waveform morphology from large amounts of raw waveform data, unsupervised manifold learning helps delineate a high-dimensional structure and display it as a novel 3-dimensional (3D) image. We hypothesize that the shape of this structure conveys clinically relevant inner dynamics information. METHODS To validate this hypothesis, we investigate the electrocardiography (ECG) waveform for ischemic heart disease and arterial blood pressure (ABP) waveform in dynamic vasoactive episodes. We model each beat or pulse to be a point lying on a manifold-like a surface-and use the diffusion map (DMap) to establish the relationship among those pulses. The output of the DMap is converted to a 3D image for visualization. For ECG datasets, first we analyzed the non-ST-elevation ECG waveform distribution from unstable angina to healthy control in the 3D image, and we investigated intraoperative ST-elevation ECG waveforms to show the dynamic ECG waveform changes. For ABP datasets, we analyzed waveforms collected under endotracheal intubation and administration of vasodilator. To quantify the dynamic separation, we applied the support vector machine (SVM) analysis and reported the total accuracy and macro-F1 score. We further performed the trajectory analysis and derived the moving direction of successive beats (or pulses) as vectors in the high-dimensional space. RESULTS For the non-ST-elevation ECG, a hierarchical tree structure comprising consecutive ECG waveforms spanning from unstable angina to healthy control is presented in the 3D image (accuracy = 97.6%, macro-F1 = 96.1%). The DMap helps quantify and visualize the evolving direction of intraoperative ST-elevation myocardial episode in a 1-hour period (accuracy = 97.58%, macro-F1 = 96.06%). The ABP waveform analysis of Nicardipine administration shows interindividual difference (accuracy = 95.01%, macro-F1 = 96.9%) and their common directions from intraindividual moving trajectories. The dynamic change of the ABP waveform during endotracheal intubation shows a loop-like trajectory structure, which can be further divided using the manifold learning knowledge obtained from Nicardipine. CONCLUSIONS The DMap and the generated 3D image of ECG or ABP waveforms provides clinically relevant inner dynamics information. It provides clues of acute coronary syndrome diagnosis, shows clinical course in myocardial ischemic episode, and reveals underneath physiological mechanism under stress or vasodilators.

Based on the well-established biopotential theory, we hypothesize that the high frequency spectral information, like that higher than 100Hz, of the EEG signal recorded in the off-the-shelf EEG sensor contains muscle tone information. We show that an existing automatic sleep stage annotation algorithm can be improved by taking this information into account. This result suggests that if possible, we should sample the EEG signal with a high sampling rate, and preserve as much spectral information as possible., Sensors, 20 (7), ISSN:1424-8220

Global statistics have placed colorectal cancer (CRC) as the third most frequently diagnosed cancer and the fourth principal cause of cancer-related deaths worldwide. Improving survival for CRC is as important as early detection. Personalized medicine is important in maximizing an individual’s treatment success and minimizing the risk of adverse reactions. Approaches in achieving personalized therapy in CRC have included analyses of specific genes with its clinical implications. Tumour genotyping via next-generation sequencing has become a standard practice to guide clinicians into predicting tumor behaviour, disease prognosis, and treatment response. Nevertheless, better prognostic markers are necessary to further stratify patients for personalized treatment plans. The discovery of new markers remains indispensable in providing the most effective chemotherapy in order to improve the outcomes of treatment and survival in CRC patients. This review aims to compile and discuss newly discovered, less frequently mutated genes in CRC. We also discuss how these mutations are being used to assist therapeutic decisions and their potential prospective clinical utilities. In addition, we will summarize the importance of profiling the large genomic rearrangements, gene amplification, and large deletions and how these alterations may assist in determining the best treatment option for CRC patients.

Background: Fluctuating hearing loss is characteristic of Meniere's Disease (MD) during acute episodes. However, no reliable audiometric hallmarks are available for counselling the hearing recovery possibility. Aims/Objectives: To find parameters for predicting MD hearing outcomes. Material and Methods: We applied machine learning techniques to analyse transient-evoked otoacoustic emission (TEOAE) signals recorded from patients with MD. Thirty unilateral MD patients were recruited prospectively after onset of acute cochleo-vestibular symptoms. Serial TEOAE and pure-tone audiogram (PTA) data were recorded longitudinally. Denoised TEOAE signals were projected onto the three most prominent principal directions through a linear transformation. Binary classification was performed using a support vector machine (SVM). TEOAE signal parameters, including signal energy and group delay, were compared between improved and nonimproved groups using Welchs t-test. Results: Signal energy did not differ (p = 0.64) but a significant difference in 1-kHz (p = 0.045) group delay was recorded between improved and nonimproved groups. The SVM achieved a cross-validated accuracy of >80% in predicting hearing outcomes. Conclusions and Significance: This study revealed that baseline TEOAE parameters obtained during acute MD episodes, when processed through machine learning technology, may provide information on outer hair cell function to predict hearing recovery., This is a journal version accepted by Acta Oto-Laryngologica on December 6, 2019

Background. Colchicine has been used in conditions such as periodic febrile illness, acute pericarditis, and gouty arthritis, all having a common hyperinflammatory response as seen in moderate to severe forms of coronavirus disease 2019 (COVID-19). This project was carried out during the rapid surge of cases in New York City, and the goal was to assess the efficacy of colchicine in treating patients with COVID-19. Methods. Patients admitted to two distinct pulmonary oriented floors of the BronxCare Hospital Center were compared. Patients on one floor were given colchicine in addition to standard of care, while control patients from another floor received only standard of care. Patients who had at least two separate timepoint measurements for at least two out of four serum inflammatory markers (C-reactive protein (CRP), D-dimer, ferritin, or lactate dehydrogenase (LDH)) were selected for the final comprehensive analysis. Results. An initial analysis performed on all patients, irrespective of the availability of two timepoint inflammatory markers, revealed a lower mortality (49.1% versus 72.9%, P = 0.002 ), a lower percentage of intubations (52.8% versus 73.6%, P = 0.006 ), and a higher discharge rate (50.9% versus 27.1%, P = 0.002 ), in the patients who received colchicine. Patients in the final comprehensive analysis groups (34 in the colchicine group and 78 in the control group) had a similar prevalence of comorbid medical conditions, except for renal failure, which was higher in the control group (65.3% versus 35.2%, P = 0.015 ). HTN (71.8% versus 52.9%, P = 0.053 ) and DM (51.3% versus 32.4%, P = 0.064 ) were also more prevalent in the control group, although the difference was not statistically significant. Patients who received colchicine had a lower mortality than the control group (47.1% versus 80.8%, P = 0.0003 ), lower rate of intubations (47.1% versus 87.2%, P < 0.0001 ), and a higher discharge rate (52.9% versus 19.2%, P = 0.0003 ). Patients in the colchicine group also showed a more significant decrease in inflammatory markers for D-dimer ( P = 0.037 ), CRP ( P = 0.014 ), and ferritin ( P = 0.012 ). Conclusions. Our study demonstrates that colchicine improved outcomes in patients with COVID-19 receiving standard of care therapy. Future randomized, placebo-controlled clinical trials to assess the potential benefit of colchicine in COVID-19 are warranted.

Background: Polysomnography is the gold standard in identifying sleep stages; however, there are discrepancies in the standards used by technicians. Because organizing meetings to reach a consensus among multiple sleep centers is time consuming, we developed an artificial intelligence (AI) system to evaluate the reliability and consistency of sleep scoring. Methods: An interpretable machine learning algorithm was used to evaluate interrater reliability (IRR) among sleep centers. Intra-center and inter-center assessments were conducted on 679 subjects without sleep apnea in six sleep centers in Taiwan. IRR was estimated based on prediction outcomes. Findings: In the intra-center assessment, the median accuracy of the databases ranged from 78·8% to 81·9% with the exception of one hospital (designated E) with an accuracy of 72·5%. In the inter-center assessment, the median accuracy ranged from 74·4% to 79·9% when hospital E was excluded from testing and training. The performance of the proposed method was higher for N2, awake, and REM, compared to N1 and N3. There was a significant difference in the prediction models learned from hospital E and others. Interpretation: The proposed AI system proved highly effective in assessing IRR. Increasing the interrater agreement rate would lead to further improvements in the accuracy of the proposed sleep stage annotation system. Funding: This research was supported by grants from the Ministry of Science and Technology, Taiwan (MOST-109-2119-M-002-014), and the Chang Gung Medical Research Program (CMRPG3K0201). Declaration of Interest: The authors declare no competing interests. Ethical Approval: The study protocol was approved by the Institutional Review Board of each hospital (Chang Gung Memorial Hospital’s IRB No: 201800609B0; MacKay Memorial Hospital’s IRB No: 18MMHIS142e; Shuanh-Ho Hospital’s IRB No: N201911007, N201903142; Taipei Tzu Chi Hospital’s IRB No: 07-XD-083; Taichung Tzu Chi Hospital’s IRB No: REC107-37, and Taipei Veterans General Hospital’s IRB No: 2018-12-009AC).

Prenatal stress (PS) impacts early postnatal behavioural and cognitive development. This process of 'fetal programming' is mediated by the effects of the prenatal experience on the developing hypothalamic-pituitary-adrenal (HPA) axis and autonomic nervous system (ANS). The HPA axis is a dynamic system regulating homeostasis, especially the stress response, and is highly sensitive to adverse early life experiences. We review the evidence for the effects of PS on fetal programming of the HPA axis and the ANS. We derive a multi-scale multi-species approach to devising preclinical and clinical studies to identify early non-invasively available pre- and postnatal biomarkers of these programming effects. Such approach would identify adverse postnatal brain developmental trajectories, a prerequisite for designing therapeutic interventions. The multiple scales include the biomarkers reflecting changes in the brain epigenome, metabolome, microbiome and the ANS activity gauged via an array of advanced non-invasively obtainable properties of fetal heart rate fluctuations. The proposed framework has the potential to reveal mechanistic links between maternal stress during pregnancy and changes across these physiological scales. Such biomarkers may hence be useful as early and non-invasive predictors of neurodevelopmental trajectories influenced by the PS. We conclude that studies into PS effects must be conducted on multiple scales derived from concerted observations in multiple animal models and human cohorts performed in an interactive and iterative manner and deploying machine learning for data synthesis, identification and validation of the best non-invasive biomarkers., Comment: Focused review, 13 pages, 5 figures

Industry 4.0 paves the way to smart factory through integrating Internet of Things, cyber-physical systems, cloud manufacturing, and big data analytics for various industrial fields. Especially, the machinery industry significantly benefits from these automation techniques in machine-tool quality inspection, cutting-tool remaining-useful-life, surface roughness prediction, etc. However, these innovation technologies are still not executable in the aerospace-component production due to their complex machining conditions, which result in long metrology delays and severe component deformations. To overcome these two challenges of the aerospace industry, this letter proposes to apply the automatic virtual metrology (AVM) system to successfully convert sampling inspections with metrology delay into real-time and online total inspection and to utilize the so-called deformation fusion (DF) scheme for dealing with the component-deformation problem. The application of the flange operation of aerospace engine-case manufacturing is adopted to illustrate the performance of the AVM-plus-DF approach.

Finding faults in a program correctly is crucial in software maintenance. In this light, many techniques have been proposed such as program slicing, code coverage, program state and mutation analysis. While all these techniques give us good insight on fault localization, but it appears that these techniques are made based on the assumption that the faults are caused by a single fault. However, in a reality, one fault could also possibly caused by multiple faults. This requires a technique which is specifically designed to handle multiple faults. With this regards, application of mutation analysis to localize faults might generate a vast number of mutants. As a result, these will lead to difficulty in choosing important mutants that are capable of localizing faults. Therefore, there is a need for a technique which able to localize a fault effectively with less number of mutants generated. Genetic algorithm (GA) is well known in finding an optimal solution to a problem while local search is capable of removing duplication. Since both had their own advantage, we have combined both techniques to enhance multiple localization of software fault. The result of the experiment shows that our technique able to detect multiple faults in various java programs but there is a need for improvement especially in prioritize fault that occurs simultaneously.

From the acute management of cardiac arrest and stroke to traumatic brain injury, the implementation of hypothermia therapy since the past two decades has progressed from various guidelines committees’ consideration of minimal benefit to mixed favorable outcomes being obtained from numerous randomized controlled trials [1]. As far as cases of traumatic brain injury are concerned, there were evidences of positive benefit in terms of mortality rates and neurological outcomes. According to a systematic analysis by Peterson et al. (2008), the relative risks (RR) of mortality (95% confidence interval) in comparison with control treatment groups were lower in subgroups of hypothermic procedures which utilized a cooling duration of over 48 hours (RR = 0.51), delivered at a temperature range of 33 degrees Celsius and above that was defined as milder than below 33 degrees Celsius (RR = 0.77), and when the patient was rewarmed passively (RR = 0.49).

Colorectal cancer (CRC) is ranked second for cancer-related deaths worldwide with approximately half of the patients being diagnosed at the late stages. The untimely detection of CRC results in advancement to the metastatic stage and nearly 90% of cancer-related deaths. The early detection of CRC is crucial to decrease its overall incidence and mortality rates. The recent introduction of circulating tumor cells (CTCs) has enabled a less invasive sampling method from liquid biopsies, besides revealing key information toward CRC metastasis. The current gold standard for CTC identification is the CellSearch® system (Veridex). This first-generation instrumentation relies on a single cell surface marker (CSM) to capture and count CTCs. Detection of CTCs allows the identification of patients at risk for metastasis, whereas CTC enumeration could improve risk assessment, monitoring of systemic therapy, and detection of therapy resistance in advanced metastatic CRC. In this review, we compared the pros and cons between single CSM-based CTC enrichment techniques and multi-marker-based systems. We also highlighted the challenges faced in the routine implementation of CSM-dependent CTC detection methods in CRC screening, prediction, prognosis, disease monitoring, and therapy selection toward precision medicine, as well as the dwelling on post-CTC analysis and characterization methods.

The Surfacer Inside-Out Access Catheter System (Surfacer) is a novel approach to restore access in total central vein occlusion (TCVO). We report a series of three cases, with mean 18-months follow up, in our institution where this technique was safely and effectively used in tandem with Hemodialysis Reliable Outflow (HeRO) graft for creation of upper limb vascular access in patients with TCVO. Although there have been reports describing the simultaneous combination of Surfacer and HeRO graft, to our knowledge, this is the first time where the outcomes with 18-months mean follow-up are reported. All three patients had failed prior conventional attempts at TCVO crossing and had exhausted most conventional upper limb vascular access methods. The above technique yielded a 100% technical success rate with mean operative time of 140 min. Cannulation rate was 100% with all undergoing successful early cannulation by post-operative day 3. Mean primary patency of 199 days was achieved. Average intervention rate of 1.2 a year was required to maintain patency. The Surfacer device used together with HeRO graft is a feasible technique to avoid femoral catheter in patients where conventional attempts to cross the TCVO have failed.

Fetal Alcohol Spectrum Disorders encompass a wide range of birth defects in children born to mothers who consumed alcohol during pregnancy. Typical mental impairments in FASD include difficulties in life adaptation and learning and memory, deficits in attention, visuospatial skills, language and speech disabilities, mood disorders and motor disabilities. Multimodal imaging methods have enabled in vivo studies of the teratogenic effects of alcohol on the central nervous system, giving more insight into the FASD phenotype. This paper offers an up-to-date comprehensive review of radiological findings in the central nervous system in studies of prenatal alcohol exposure in both humans and translational animal models, including Magnetic Resonance Imaging, Computed Tomography, Positron Emission Tomography, Single Photon Emission Tomography and Ultrasonography.

One of the core values of Industry 4.0 targets to integrate people's demand into manufacturing for enhanced products, systems, and services for a wider variety of increasingly personalized customization of products. Thus, Industry 4.0 advances the traditional manufacturing techniques from mass production toward mass customization (MC). Take wheel machining automation (WMA) as an example. To meet MC expectations, manufacturers should offer customized wheels at a large scale with low cost, short lead-time, and high quality. Thus, WMA cells with MC capability are requested to be designed to have a high degree of quick responsiveness to accurately react on machining-condition changes for manufacturing different wheel types. To meet the requirements of MC production, this work proposes to apply the automatic virtual metrology (AVM) system together with the so-called target-value-adjustment (TVA) scheme. The AVM system was developed by the authors to convert sampling inspections with metrology delay into real-time and on-line total inspection, while the TVA scheme is designed to enhance AVM's adaptive customization capability for automatically and rapidly accomplishing the goals of MC production. To demonstrate the versatility of the AVM-plus-TVA approach, the other example in semiconductor etching process is also illustrated.

We propose a novel algorithm to recover fetal electrocardiogram (ECG) for both the fetal heart rate analysis and morphological analysis of its waveform from two or three trans-abdominal maternal ECG channels. We design an algorithm based on the optimal-shrinkage and the nonlocal Euclidean median under the wave-shape manifold model. For the fetal heart rate analysis, the algorithm is evaluated on publicly available database, 2013 PhyioNet/Computing in Cardiology Challenge, set A. For the morphological analysis, we propose to simulate semi-real databases by mixing the MIT-BIH Normal Sinus Rhythm Database and MITDB Arrhythmia Database. For the fetal R peak detection, the proposed algorithm outperforms all algorithms under comparison. For the morphological analysis, the algorithm provides an encouraging result in recovery of the fetal ECG waveform, including PR, QT and ST intervals, even when the fetus has arrhythmia. To the best of our knowledge, this is the first work focusing on recovering the fetal ECG for morphological analysis from two or three channels with an algorithm potentially applicable for continuous fetal electrocardiographic monitoring, which creates the potential for long term monitoring purpose., Comment: 25 pages, 6 figures

Recent studies from high-risk countries such as the US, Denmark and Ireland have shown rising incidence rates of hormone receptor (HR)-positive and falling rates of HR-negative breast cancers (BC). However, it remains unclear whether a similar pattern occurs in low-risk countries. Detailed clinical and risk factor data were collected from 2,977 female invasive BC patients (≥20 years) in Sarawak General Hospital, Malaysia, representing 93% of the population. The population-at-risk was obtained from the Department of Statistics Malaysia. Secular trends in age-standardized incidence rates were assessed using estimated average annual percent changes. Associations between established BC risk factors and tumor subtypes defined by HR or joint human epidermal growth factor receptor 2 (HR/HER2) status were examined by case-case comparisons using logistic regression. From 2006 to 2015, incidence rates increased for HR-positive cancers by 4.46%/year (95% CI = 2.19-6.78) and decreased for HR-negative cancers by 2.29%/year (95% CI = -4.31 to -0.24). When further stratified by HER2, the most contrasting difference in linear trends was observed between HR+/HER2- and HR-/HER2- subtypes. After controlling for potential confounders, cases with excess body weight (ORoverweight vs. normal = 0.82; 95% CI = 0.69-0.98; ORobese vs. normal = 0.62; 95% CI = 0.48-0.80), later age at first birth (OR≥26 years vs.

Extracting the instantaneous heart rate (iHR) from face videos has been well studied in recent years. It is well known that changes in skin color due to blood flow can be captured using conventional cameras. One of the main limitations of methods that rely on this principle is the need of an illumination source. Moreover, they have to be able to operate under different light conditions. One way to avoid these constraints is using infrared cameras, allowing the monitoring of iHR under low light conditions. In this work, we present a simple, principled signal extraction method that recovers the iHR from infrared face videos. We tested the procedure on 7 participants, for whom we recorded an electrocardiogram simultaneously with their infrared face video. We checked that the recovered signal matched the ground truth iHR, showing that infrared is a promising alternative to conventional video imaging for heart rate monitoring, especially in low light conditions. Code is available at https://github.com/natalialmg/IR_iHR.

Finding appropriate low-dimensional representations of high-dimensional multimodal data can be challenging, since each modality embodies unique deformations and interferences. In this paper, we address the problem using manifold learning, where the data from each modality is assumed to lie on some manifold. In this context, the goal is to characterize the relations between the different modalities by studying their underlying manifolds. We propose two new diffusion operators that allow us to isolate, enhance, and attenuate the hidden components of multimodal data in a data-driven manner. Based on these new operators, efficient low-dimensional representations can be constructed for such data, which characterize the common structures and the differences between the manifolds underlying the different modalities. The capabilities of the proposed operators are demonstrated on 3D shapes and on a fetal heart rate monitoring application.

Inverse problems are some of the most important mathematical problems in science and mathematics because their solution yields information about parameters that are not directly observable. Artificial neural networks have long been used as a mathematical modelling method and have been used successfully to solve inverse problems for application including denoising and medical image reconstruction. Many inverse problems result from integral processes that can be modelled using a linear formulation. These can be efficiently solved via simple networks which are easily trained with reasonable datasets. An innovative simple neural network architecture, the iterative linear neural network (ILNN), consisting of two non-hidden layer networks, one for the forward model and one for the inverse model, is proposed to solve linear inverse problems. Iteration between the two models refines network outcomes with greater accuracy than a network with only the inverse model. A training procedure accompanying the network is also introduced. The network needs to train only the inverse model with one-hot vectors as targets. The training inputs of the inverse model define the weights of the forward model. The number of targets is finite and equal to the length of the vector. With the defined targets, the training process ensures that the inverse model is at least a left inverse of the forward model. This leads to generalizable networks. The experimental results show that the ILNN produces good results even if its inverse model is not perfectly trained. The proposed network is applied to solve two linear inverse problems, deconvolution and the inverse Radon transform. The network successfully reconstructed original data following blurring and Radon transformation.

Systemically-administered bleomycin causes inflammation, arrested lung growth, and pulmonary hypertension (PHT) in the neonatal rat, similar to human infants with severe bronchopulmonary dysplasia (BPD). Leukotrienes (LTs) are inflammatory lipid mediators produced by multiple cell types in the lung. The major LTs, LTB4and cysteinyl LTs, are suggested to contribute to BPD, but their specific roles remain largely unexplored in experimental models. We hypothesized that LTs are increased in bleomycin-induced BPD-like injury, and that inhibition of LT production would prevent inflammatory cell influx and thereby ameliorate lung injury. Rat pups were exposed to bleomycin (1 mg·kg−1·day−1ip) or vehicle (control) from postnatal days 1–14 and were treated with either zileuton (5-lipoxygenase inhibitor), montelukast (cysteinyl LT1 receptor antagonist), or SC57461A (LTA4 hydrolase inhibitor) 10 mg·kg−1·day−1ip. Bleomycin led to increased lung content of LTB4, but not cysteinyl LTs. Bleomycin-induced increases in tissue neutrophils and macrophages and lung contents of LTB4and tumor necrosis factor-α were all prevented by treatment with zileuton. Treatment with zileuton or SC57461A also prevented the hemodynamic and structural markers of chronic PHT, including raised pulmonary vascular resistance, increased Fulton index, and arterial wall remodeling. However, neither treatment prevented impaired alveolarization or vascular hypoplasia secondary to bleomycin. Treatment with montelukast had no effect on macrophage influx, PHT, or on abnormal lung structure. We conclude that LTB4plays a crucial role in lung inflammation and PHT in experimental BPD. Agents targeting LTB4or LTB4-mediated signaling may have utility in infants at risk of developing BPD-associated PHT.

See Mormann and Andrzejak (doi:10.1093/brain/aww091) for a scientific commentary on this article. Seizures are thought to arise from an identifiable pre-ictal state. Brinkmann et al. report the results of an online, open-access seizure forecasting competition using intracranial EEG recordings from canines with naturally occurring epilepsy and human patients undergoing presurgical monitoring. The winning algorithms forecast seizures at rates significantly greater than chance., See Mormann and Andrzejak (doi:10.1093/brain/aww091) for a scientific commentary on this article. Accurate forecasting of epileptic seizures has the potential to transform clinical epilepsy care. However, progress toward reliable seizure forecasting has been hampered by lack of open access to long duration recordings with an adequate number of seizures for investigators to rigorously compare algorithms and results. A seizure forecasting competition was conducted on kaggle.com using open access chronic ambulatory intracranial electroencephalography from five canines with naturally occurring epilepsy and two humans undergoing prolonged wide bandwidth intracranial electroencephalographic monitoring. Data were provided to participants as 10-min interictal and preictal clips, with approximately half of the 60 GB data bundle labelled (interictal/preictal) for algorithm training and half unlabelled for evaluation. The contestants developed custom algorithms and uploaded their classifications (interictal/preictal) for the unknown testing data, and a randomly selected 40% of data segments were scored and results broadcasted on a public leader board. The contest ran from August to November 2014, and 654 participants submitted 17 856 classifications of the unlabelled test data. The top performing entry scored 0.84 area under the classification curve. Following the contest, additional held-out unlabelled data clips were provided to the top 10 participants and they submitted classifications for the new unseen data. The resulting area under the classification curves were well above chance forecasting, but did show a mean 6.54 ± 2.45% (min, max: 0.30, 20.2) decline in performance. The kaggle.com model using open access data and algorithms generated reproducible research that advanced seizure forecasting. The overall performance from multiple contestants on unseen data was better than a random predictor, and demonstrates the feasibility of seizure forecasting in canine and human epilepsy.

Summary Background Due to increasing concerns about post-chikungunya (pCHIK) rheumatic disorders in Latin America we aimed to evaluate its occurrence in travelers returning to NYC from the Caribbean. Method Patients diagnosed with chikungunya (CHIK) during 2014 at the Bronx-Lebanon Hospital Center (Bronx, NewYork) were identified by reviewing laboratory and electronic medical records. Patients and caregivers of pediatric patients were interviewed by phone ≥9 months after the CHIK diagnosis to survey for chronic symptomatology and current health care needs. Reported chronic musculoskeletal complaints were categorized according to validated criteria. Results A total of 28 patients (54% females, median age [range] of 51.5 [0, 88] years) diagnosed with CHIK at our center were identified. Most (82%) had returned from the Dominican Republic. Nineteen (68%) patients were successfully contacted at a median (range) of 13 (9, 16) months since the acute diagnosis. A third (37%) reported ongoing complaints related to CHIK including joint pain (32%), muscle pain (32%), and joint swelling (26%). A presumptive diagnosis of pCHIK chronic inflammatory arthritis ( n = 4) and pCHIK musculoskeletal disorder ( n = 3) was established. Conclusions A third of travelers with CHIK acquired in the Caribbean may be at risk for developing persistent symptoms suggestive of pCHIK rheumatic disorder.

Industry 4.0 is set to be one of the new manufacturing objectives. The technologies involved to achieve Industry 4.0 are Internet of Things (IoT), cyber physical systems (CPS), and cloud manufacturing (CM). However, the current objectives defined by Industry 4.0 do not include zero defects; it only keeps the faith of achieving nearly zero-defects state. The purpose of this paper is to propose a platform denoted advanced manufacturing cloud of things (AMCoT) to not only achieve the objectives of Industry 4.0 but also accomplish the goal of zero defects by applying the technology of automatic virtual metrology (AVM). As such, by applying Industry 4.0 together with AVM to achieve the goal of zero defects, the era of Industry 4.1 is taking place. The application of wheel machining automation is adopted in this letter to illustrate how AMCoT and Industry 4.1 work.