Application of a FL Time Series Building Model in Mobile Network Interaction Anomaly Detection in the Internet of Things Environment.

With the continuous development of the social economy, mobile network is becoming more and more popular. However, it should be noted that it is vulnerable to different security risks, so it is extremely important to detect abnormal behaviors in mobile network interaction. This paper mainly introduces how to detect the characteristic data of mobile Internet interaction behavior based on IOT FL time series component model, set the corresponding threshold to screen the abnormal data, and then use K-means++ clustering algorithm to obtain the abnormal set of multiple interactive data, and conduct intersection operation on all abnormal sets, so as to obtain the final abnormal detection object set. The simulation results show that the FL time series component model of the Internet of Things is effective and can support abnormal detection of mobile network interaction behavior.

LSTM-Based Path Prediction for Effective Sensor Filtering in Sensor Registry System.

The Internet of Things (IoT) is expected to provide intelligent services by receiving heterogeneous data from ambient sensors. A mobile device employs a sensor registry system (SRS) to present metadata from ambient sensors, then connects directly for meaningful data. The SRS should provide metadata for sensors that may be successfully connected. This process is location-based and is also known as sensor filtering. In reality, GPS sometimes shows the wrong position and thus leads to a failed connection. We propose a dual collaboration strategy that simultaneously collects GPS readings and predictions from historical trajectories to improve the probability of successful requests between mobile devices and ambient sensors. We also update the evaluation approach of sensor filtering in SRS by introducing a Monte Carlo-based simulation flow to measure the service provision rate. The empirical study shows that the LSTM-based path prediction can compensate for the loss of location abnormalities and is an effective sensor filtering model.

Coastal Waste Detection Based on Deep Convolutional Neural Networks.

Coastal waste not only has a seriously destructive effect on human life and marine ecosystems, but it also poses a long-term economic and environmental threat. To solve the issues of a poor manual coastal waste sorting environment, such as low sorting efficiency and heavy tasks, we develop a novel deep convolutional neural network by combining several strategies to realize intelligent waste recognition and classification based on the state-of-the-art Faster R-CNN framework. Firstly, to effectively detect small objects, we consider multiple-scale fusion to get rich semantic information from the shallower feature map. Secondly, RoI Align is introduced to solve positioning deviation caused by the regions of interest pooling. Moreover, it is necessary to correct key parameters and take on data augmentation to improve model performance. Besides, we create a new waste object dataset, named IST-Waste, which is made publicly to facilitate future research in this field. As a consequence, the experiment shows that the algorithm's mAP reaches 83%. Detection performance is significantly better than Faster R-CNN and SSD. Thus, the developed scheme achieves higher accuracy and better performance against the state-of-the-art alternative.

Data Quality Management in the Internet of Things.

Nowadays, IoT is being used in more and more application areas and the importance of IoT data quality is widely recognized by practitioners and researchers. The requirements for data and its quality vary from application to application or organization in different contexts. Many methodologies and frameworks include techniques for defining, assessing, and improving data quality. However, due to the diversity of requirements, it can be a challenge to choose the appropriate technique for the IoT system. This paper surveys data quality frameworks and methodologies for IoT data, and related international standards, comparing them in terms of data types, data quality definitions, dimensions and metrics, and the choice of assessment dimensions. The survey is intended to help narrow down the possible choices of IoT data quality management technique.

Development of a Risk Score for QT Prolongation in the Intensive Care Unit Using Time-Series Electrocardiogram Data and Electronic Medical Records.

OBJECTIVE: Drug-induced QT prolongation can lead to life-threatening arrhythmia. In the intensive care unit (ICU), various drugs are administered concurrently, which can increase the risk of QT prolongation. However, no well-validated method to evaluate the risk of QT prolongation in real-world clinical practice has been established. We developed a risk scoring model to continuously evaluate the quantitative risk of QT prolongation in real-world clinical practice in the ICU. METHODS: Continuous electrocardiogram (ECG) signals measured by patient monitoring devices and Electronic Medical Records data were collected for ICU patients. QT and RR intervals were measured from raw ECG data, and a corrected QT interval (QTc) was calculated by Bazett's formula. A case-crossover study design was adopted. A case was defined as an occurrence of QT prolongation ≥12 hours after any previous QT prolongation. The patients served as their own controls. Conditional logistic regression was conducted to analyze prescription, surgical history, and laboratory test data. Based on the regression analysis, a QTc prolongation risk scoring model was established. RESULTS: In total, 811 ICU patients who experienced QT prolongation were included in this study. Prescription information for 13 drugs was included in the risk scoring model. In the validation dataset, the high-risk group showed a higher rate of QT prolongation than the low-and low moderate-risk groups. CONCLUSIONS: Our proposed model may facilitate risk stratification for QT prolongation during ICU care as well as the selection of appropriate drugs to prevent QT prolongation.

Promoter methylation changes in ALOX12 and AIRE1: novel epigenetic markers for atherosclerosis.

BACKGROUND: Atherosclerosis is the main cause of cardiovascular diseases such as ischemic stroke and coronary heart disease. Gene-specific promoter methylation changes have been suggested as one of the causes underlying the development of atherosclerosis. We aimed to identify and validate specific genes that are differentially expressed through promoter methylation in atherosclerotic plaques. We performed the present study in four steps: (1) profiling and identification of gene-specific promoter methylation changes in atherosclerotic tissues; (2) validation of the promoter methylation changes of genes in plaques by comparison with non-plaque intima; (3) evaluation of promoter methylation status of the genes in vascular cellular components composing atherosclerotic plaques; and (4) evaluation of promoter methylation differences in genes among monocytes, T cells, and B cells isolated from the blood of ischemic stroke patients. RESULTS: Upon profiling, AIRE1, ALOX12, FANK1, NETO1, and SERHL2 were found to have displayed changes in promoter methylation. Of these, AIRE1 and ALOX12 displayed higher methylation levels in plaques than in non-plaque intima, but lower than those in the buffy coat of blood. Between inflammatory cells, the three genes were significantly less methylated in monocytes than in T and B cells. In the vascular cells, AIRE1 methylation was lower in endothelial and smooth muscle cells. ALOX12 methylation was higher in endothelial, but lower in smooth muscle cells. Immunofluorescence staining showed that co-localization of ALOX12 and AIRE1 was more frequent in CD14(+)-monocytes than in CD4(+)-T cell in plaque than in non-plaque intima. CONCLUSIONS: Promoter methylation changes in AIRE1 and ALOX12 occur in atherosclerosis and can be considered as novel epigenetic markers.

Deep Learning-Based Electrocardiogram Signal Noise Detection and Screening Model.

OBJECTIVES: Biosignal data captured by patient monitoring systems could provide key evidence for detecting or predicting critical clinical events; however, noise in these data hinders their use. Because deep learning algorithms can extract features without human annotation, this study hypothesized that they could be used to screen unacceptable electrocardiograms (ECGs) that include noise. To test that, a deep learning-based model for unacceptable ECG screening was developed, and its screening results were compared with the interpretations of a medical expert. METHODS: To develop and apply the screening model, we used a biosignal database comprising 165,142,920 ECG II (10-second lead II electrocardiogram) data gathered between August 31, 2016 and September 30, 2018 from a trauma intensive-care unit. Then, 2,700 and 300 ECGs (ratio of 9:1) were reviewed by a medical expert and used for 9-fold cross-validation (training and validation) and test datasets. A convolutional neural network-based model for unacceptable ECG screening was developed based on the training and validation datasets. The model exhibiting the lowest cross-validation loss was subsequently selected as the final model. Its performance was evaluated through comparison with a test dataset. RESULTS: When the screening results of the proposed model were compared to the test dataset, the area under the receiver operating characteristic curve and the F1-score of the model were 0.93 and 0.80 (sensitivity = 0.88, specificity = 0.89, positive predictive value = 0.74, and negative predictive value = 0.96). CONCLUSIONS: The deep learning-based model developed in this study is capable of detecting and screening unacceptable ECGs efficiently.

Development of Sensor Registry System-Based Predictive Information Service Using a Grid.

A sensor registry system (SRS) registers sensor metadata and provides them for a seamless semantic process. Recently, network coverage information-based SRS (NC-SRS) was developed to provide sensor information filtering by combining path prediction and network coverage checks. However, the NC-SRS has problems caused by issues such as termination of OpenSignal service and pre-building road segments. Therefore, this paper proposes a sensor registry system-based predictive information service (SRS-PIS) using a grid. SRS-PIS predicts a path based on the grid, checks the network coverage, and filters the sensor. This paper presents a grid-based real-time path prediction algorithm and an algorithm for grouping network service-disabled areas. To obtain network coverage information, we constructed and implemented a grid-based coverage map through experiment to measure the signal strength. As an evaluation, we compared features among SRS-based systems and SRS-PIS, and compared advantages and disadvantages between segment-based and grid-based methods.

System for Collecting Biosignal Data from Multiple Patient Monitoring Systems.

OBJECTIVES: Biosignal data include important physiological information. For that reason, many devices and systems have been developed, but there has not been enough consideration of how to collect and integrate raw data from multiple systems. To overcome this limitation, we have developed a system for collecting and integrating biosignal data from two patient monitoring systems. METHODS: We developed an interface to extract biosignal data from Nihon Kohden and Philips monitoring systems. The Nihon Kohden system has a central server for the temporary storage of raw waveform data, which can be requested using the HL7 protocol. However, the Philips system used in our hospital cannot save raw waveform data. Therefore, our system was connected to monitoring devices using the RS232 protocol. After collection, the data were transformed and stored in a unified format. RESULTS: From September 2016 to August 2017, we collected approximately 117 patient-years of waveform data from 1,268 patients in 79 beds of five intensive care units. Because the two systems use the same data storage format, the application software could be run without compatibility issues. CONCLUSIONS: Our system collects biosignal data from different systems in a unified format. The data collected by the system can be used to develop algorithms or applications without the need to consider the source of the data.

Extracting information from free-text electronic patient records to identify practice-based evidence of the performance of coronary stents.

BACKGROUND AND OBJECTIVE: Percutaneous coronary intervention (PCI) using drug-eluting stents (DES) is an indispensable treatment for coronary artery disease. However, to evaluate the performance of various types of stents for PCI, numerous resources are required. We extracted clinical information from free-text records and, using practice-based evidence, compared the efficacy of various DES. MATERIALS AND METHODS: We developed a text mining tool based on regular expression and applied it to PCI reports stored in the electronic health records (EHRs) of Ajou University Hospital from 2010-2014. The PCI data were extracted from EHRs with a sensitivity of 0.996, a specificity of 1.000, and an F-measure of 0.995 when compared with a sample of 200 reports. Using these data, we compared the performance of stents by Kaplan-Meier analysis and the Cox hazard proportional regression. RESULTS: In the self-validation analysis comparing the first-generation to the second-generation DES, the second-generation DES was superior to the first-generation DES (hazard ratio [HR]: 0.423, 95% confidence interval [CI]: 0.284-0.630) in terms of target vessel revascularization (TVR), showing similar findings to the established results of previous studies. Among the second-generation DES, the biodegradable-polymer DES tended to be superior, with a risk of TVR (HR: 0.568, 95% CI: 0.281-1.147) falling below than that for the durable-polymer DES approximately 1 year after the index procedure. The Endeavor stent had the highest TVR risk among the newer generation DES (HR: 2.576, 95% CI: 1.273-5.210). CONCLUSIONS: In this study, we demonstrated how to construct a PCI data warehouse of PCI-related parameters obtained from free-text electronic records with high accuracy for use in the post surveillance of coronary stents in a time- and cost effective manner. Post surveillance of the practice based evidence in the PCI data warehouse indicated that the biodegradable-polymer DES might have a lower risk of TVR than the durable-polymer DES.

Synergy of circulating miR-212 with markers for cardiovascular risks to enhance estimation of atherosclerosis presence.

Synergy of specific microRNAs (miRNAs) with cardiovascular risk factors to estimate atherosclerosis presence in ischemic stroke patients has not been investigated. The present study aimed to identify atherosclerosis-related circulating miRNAs and to evaluate interaction with other cardiovascular markers to improve the estimation of atherosclerosis presence. We performed a miRNA profiling study using serum of 15 patients with acute ischemic stroke who were classified by the presence of no (n = 8) or severe (n = 7) stenosis on intracranial and extracranial vessels, which identified miR-212, -372, -454, and -744 as miRNAs related with atherosclerosis presence. Of the 4 miRNAs, only miR-212 showed a significant increase in expression in atherosclerosis patients in a validation study (atherosclerotic patients, n = 32, non-atherosclerotic patients, n = 33). Hemoglobin A1c, a high-density lipoprotein cholesterol, and lipoprotein(a), both established risk markers, were independently related with atherosclerosis presence in the validation population. miR-212 enhanced the accuracy of atherosclerosis presence by the three existing markers (three markers, 78.5%; three markers+miR-212, 84.6%, P<0.05) and significantly added to the area under the receiver operating characteristic curve (three markers, 0.8258; three markers+miR-212, 0.8646, P<0.05). The inclusion of miR-212 increased the reclassification index calculated using net reclassification improvement (0.4527, P<0.05) and integrated discrimination improvement (0.0737, P<0.05). We identified circulating miR-212 as a novel marker of atherosclerosis. miR-212 enhanced the estimation of atherosclerosis presence in combination with hemoglobin A1c, high-density lipoprotein cholesterol, and lipoprotein(a). Thus, miR-212 is expected to improve the estimation of atherosclerosis using peripheral blood of patients.

ECG-ViEW II, a freely accessible electrocardiogram database.

The Electrocardiogram Vigilance with Electronic data Warehouse II (ECG-ViEW II) is a large, single-center database comprising numeric parameter data of the surface electrocardiograms of all patients who underwent testing from 1 June 1994 to 31 July 2013. The electrocardiographic data include the test date, clinical department, RR interval, PR interval, QRS duration, QT interval, QTc interval, P axis, QRS axis, and T axis. These data are connected with patient age, sex, ethnicity, comorbidities, age-adjusted Charlson comorbidity index, prescribed drugs, and electrolyte levels. This longitudinal observational database contains 979,273 electrocardiograms from 461,178 patients over a 19-year study period. This database can provide an opportunity to study electrocardiographic changes caused by medications, disease, or other demographic variables. ECG-ViEW II is freely available at http://www.ecgview.org.

A Feasibility Study of Moxibustion for Treating Anorexia and Improving Quality of Life in Patients With Metastatic Cancer: A Randomized Sham-Controlled Trial.

OBJECTIVE: The aim of this study was to determine the feasibility, acceptability, and safety of using moxibustion for treating anorexia and improving quality of life in patients with metastatic cancer. METHODS: We conducted a randomized sham-controlled trial of moxibustion. Sixteen patients with metastatic cancer were recruited from Daejeon, South Korea. The patients were randomly placed into a true or a sham moxibustion group and received 10 true or sham moxibustion treatments administered to the abdomen (CV12, CV8, CV4) and legs (ST36) over a 2-week period. Outcome measures included interest in participating in the trial, identification of successful recruitment strategies, the appropriateness of eligibility criteria, and compliance with the treatment plan (ie, attendance at treatment sessions). Clinical outcomes included results of the Functional Assessment of Anorexia/Cachexia Therapy (FAACT), answers on the European Organization for Research and Treatment of Cancer 30-item core quality of life (EORTC QLQ-C30) questionnaires, scores on the visual analogue scale (VAS), and the results from blood tests and a safety evaluation. RESULTS: Moxibustion was an acceptable intervention in patients with metastatic cancer. Compliance with the treatment protocol was high, with 11 patients completing all 10 treatments. No serious adverse events related to moxibustion occurred, but 4 patients in the true moxibustion group reported mild rubefaction, which disappeared in a few hours. CONCLUSION: This study suggests that moxibustion may be safely used to treat anorexia and improve quality of life in patients with metastatic cancer. However, further research is needed to confirm this result.

Constructing an Open-Access Bio-Signal Repository from Intensive Care Units.

Bio-signals can be crucial evidence in detecting urgent clinical events. However, until now, access to this data was limited. We aim to construct and provide a new open bio-signal repository with data gathered from more than 40 intensive care unit (ICU) beds. For doing so, we completed the interfacing system with the patient monitors at the target beds and plan to expand this data set to more than 100 ICU beds. Once completed, we plan to publicly open the data to catalyze interesting clinical-event detection research.

Anti-Fatigue Effects of Enzyme-Modified Ginseng Extract: A Randomized, Double-Blind, Placebo-Controlled Trial.

OBJECTIVES: Ginseng saponin is known to have biological activities in maintaining homeostasis and enhancing vital energy. Enzyme-modified ginseng extract (EMGE) was designed to increase the content of its active constituents and to intensify biological activity. The present study investigated the anti-fatigue effects of EMGE in healthy adults in a randomized, double-blind, placebo-controlled trial. DESIGN: Fifty-two healthy subjects met the diagnostic criteria and were randomly allocated into one of two groups: EMGE (2,000 mg/day) or placebo. EMGE or placebo were administered to each group for 4 weeks. Fatigue scores using the Visual Analogue Fatigue Scale (VAFS) and Revised Piper Fatigue Scale (RPFS) were considered as the primary outcome measure. Life-quality scores were investigated using the Short-Form Health Survey (SF-36). The safety and adverse effects of EMGE were also assessed. RESULTS: A repeated-measures analysis of variance showed that there was a significant difference in the VAFS scores VAFS between the treatment and placebo groups after 4 weeks. The treatment group's score decreased more than that of the placebo group. There was no difference in the RPFS and SF-36 scores between the two groups. There were no fatal adverse effects. CONCLUSION: EMGE treatment for 4 weeks decreased fatigue severity in a healthy population. Adverse effects were rare, and EMGE was generally well tolerated. Randomized, placebo-controlled trials of EMGE are justified in order to elucidate the underlying mechanism of EMGE in combating fatigue.

A Network Coverage Information-Based Sensor Registry System for IoT Environments.

The Internet of Things (IoT) is expected to provide better services through the interaction of physical objects via the Internet. However, its limitations cause an interoperability problem when the sensed data are exchanged between the sensor nodes in wireless sensor networks (WSNs), which constitute the core infrastructure of the IoT. To address this problem, a Sensor Registry System (SRS) is used. By using a SRS, the information of the heterogeneous sensed data remains pure. If users move along a road, their mobile devices predict their next positions and obtain the sensed data for that position from the SRS. If the WSNs in the location in which the users move are unstable, the sensed data will be lost. Consider a situation where the user passes through dangerous areas. If the user's mobile device cannot receive information, they cannot be warned about the dangerous situation. To avoid this, two novel SRSs that use network coverage information have been proposed: one uses OpenSignal and the other uses the probabilistic distribution of the users accessing SRS. The empirical study showed that the proposed method can seamlessly provide services related to sensing data under any abnormal circumstance.

Decreased efficacy of drugs targeting the vascular endothelial growth factor pathway by the epigenetic silencing of FLT1 in renal cancer cells.

BACKGROUND: The vascular endothelial growth factor (VEGF)-VEGF receptor (VEGFR) signaling pathway is involved in cancer-related biological functions and is a therapeutic target in cancer. However, the influence of epigenetic regulation of VEGF-VEGFR signaling-related genes remains unclear. Here, we evaluated the effects of FLT1 and KDR promoter hypermethylation combined with drugs targeting VEGF-VEGFR signaling on cancer-related phenotypes in renal cancer cells (RCCs) and examined changes in FLT1 and KDR promoter hypermethylation in tissues from patients with renal cancer. RESULTS: In vitro experiments were performed to evaluate the effects of beavacizumab (an anti-VEGF antibody), an anti-FLT1 peptide, an anti-KDR antibody, and the VEGFR tyrosine kinase inhibitors (TKIs) sunitinib and axitinib in 13 RCC lines with different levels of FLT1 and/or KDR promoter methylation and in 2 FLT1 or KDR in vitro knockdown models. The synergistic effects of sunitinib and axitinib treatment were also evaluated in four RCC lines having different levels of FLT1 and/or KDR methylation. In our in vitro experiments, bevacizumab and an anti-KDR antibody did not affect the proliferation of RCCs having FLT1 and/or KDR hypermethylation. In contrast, in RCCs with FLT1 hypermethylation, proliferation inhibition was counteracted by treatment with an anti-FLT1 peptide and both VEGF-TKIs (sunitinib and axitinib). Demethylation with sunitinib or axitinib synergistically increased proliferation inhibition in the RCCs exhibiting FLT1 hypermethylation. Using in vitro FLT1 or KDR knockdown models, decreased proliferation inhibition following anti-FLT1 peptide, sunitinib, and axitinib treatment was observed only in FLT1-knockdown cells. In patients with renal cancer who received sunitinib, FLT1 promoter methylation was higher in renal cancer tissues from eight nonresponders (stable or progressive disease assessed by the Response Evaluation Criteria in Solid Tumors) than in cancer tissues from five responders (complete response or partial response). CONCLUSIONS: The present data showed that hypermethylated FLT1 was important for the efficacy of anti-VEGF/VEGFR drugs targeting FLT1 or intracellular VEGFR signaling. FLT1 hypermethylation causing alterations of FLT1 function could serve as a useful biomarker for predicting changes in FLT1 status in RCCs.

Effect of acupuncture for radioactive-iodine-induced anorexia in thyroid cancer patients: a randomized, double-blinded, sham-controlled pilot study.

OBJECTIVE: The aim of this study is to evaluate the efficacy and safety of acupuncture for radioactive iodine (RAI)-induced anorexia in thyroid cancer patients. METHODS: Fourteen thyroid cancer patients with RAI-induced anorexia were randomized to a true acupuncture or sham acupuncture group. Both groups were given 6 true or sham acupuncture treatments in 2 weeks. Outcome measures included the change of the Functional Assessment of Anorexia and Cachexia Treatment (FAACT; Anorexia/Cachexia Subscale [ACS], Functional Assessment of Cancer Therapy-General [FACT-G]), Visual Analogue Scale (VAS), weight, body mass index (BMI), ACTH, and cortisol levels. RESULTS: The mean FAACT ACS scores of the true and sham acupuncture groups increased from baseline to exit in intention-to-treat (ITT) and per protocol (PP) analyses; the true acupuncture group showed higher increase but with no statistical significance. Between groups, from baseline to the last treatment, statistically significant differences were found in ITT analysis of the Table of Index (TOI) score (P = .034) and in PP analysis of the TOI (P = .016), FACT-G (P = .045), FAACT (P = .037) scores. There was no significant difference in VAS, weight, BMI, ACTH, and cortisol level changes between groups. CONCLUSION: Although the current study is based on a small sample of participants, our findings support the safety and potential use of acupuncture for RAI-induced anorexia and quality of life in thyroid cancer patients.