Data resource profile of an online database system for forensic mental health services.

This paper introduces a forensic psychiatry database established in Japan and discusses its significance and future issues. The purpose of this Database, created under the Medical Treatment and Supervision Act (MTSA) Database Project, is to improve the quality of forensic psychiatry treatment. It can collect monthly data on "basic information," "Orders and hospitalizations under the MTSA," "Treatment process," "Criminal and medical treatment history," and "problematic behavior in the unit." The online system has accumulated data on more than 8,000 items in 24 broad categories. Medical data are exported from the medical care assisting system of 32 designated inpatient facilities in XML format and then saved on USB memory sticks. The files are imported into the Database system client, which sends the data to the Database server via a virtual private network. This system minimizes errors and efficiently imports patient data. However, there is a limitation that it is difficult to set items that need to be analyzed to solve everyday clinical problems into the database system because they tend to change over time. By evaluating the effectiveness of the Database, and collecting appropriate data, it is expected to disseminate a wide range of knowledge that will contribute to the future development of mental health and welfare care.

Survey of an online system for information to women with epilepsy of childbearing age and management during pregnancy: A 3-year evaluation.

OBJECTIVE: We developed an online tool for women with epilepsy consisting of two modules: one with information on pregnancy-related issues (information module) and one for reminders about blood test and communication about dose changes (pregnancy module). Our aim was to assess perceived value, user-friendliness and improvement of patient knowledge in users. METHODS: The system was launched in 2019 and patients invited by epilepsy nurses were asked to participate in a survey 1 month after the invitation for the information module, and 1 month postnatally for the pregnancy module. RESULTS: By November 2022, the system had been used by 96 individuals out of 100 invited in the pregnancy module, in a total of 114 pregnancies. One hundred and eleven women had been invited to the information module, and 70 of these accessed it. The survey received 96 answers (44 information, 52 pregnancy). User-friendliness was rated as good or very good by a little over half of the users; 55% in the information module and 52% in the pregnancy module. Among pregnant women, 83% found the TDM part useful and most would prefer a similar system in future pregnancies. Sixty-four percent of users of the information module and 48% of the pregnancy module found that the system had increased their knowledge. Two knowledge questions were answered correctly by a significantly higher proportion of those that had accessed the online information. SIGNIFICANCE: There was great demand for online communication during pregnancy and our experiences of implementation can hopefully assist digitalization of epilepsy care elsewhere. Online information also seems to increase knowledge about pregnancy-related issues, but our invitation-only method of inclusion was not effective for widespread dissemination. Patient-initiated access with optional epilepsy-team contact if questions arise could be an alternative. PLAIN LANGUAGE SUMMARY: We have performed a survey of users of a new Internet-based tool for information to women of childbearing age and communication about dose changes during pregnancy. Users were overall satisfied with the tool and answered some knowledge questions more accurately after accessing the information.

Online Physician-Patient Interaction and Patient Satisfaction: Empirical Study of the Internet Hospital Service.

BACKGROUND: In China, a form of online health service called the internet hospital became a prominent means of patient care when face-to-face visits were not possible during the COVID-19 pandemic to minimize transmission of the SARS-CoV-2 virus. Patients' internet hospital experiences largely depend on online physician-patient interaction. Yet, little is known about how physicians can improve patient satisfaction by using specific communication strategies online. OBJECTIVE: This study aimed to identify specific communication strategies to help physicians deliver better quality internet hospital services. We also outline recommendations for hospitals to operate internet hospital platforms more effectively. METHODS: A longitudinal data set was collected from an internet hospital platform operated by a top hospital in China. By extracting communication patterns from approximately 20,000 records of online health care services and by controlling the features of service requests, we tested the impacts of response load, more detailed style, and emotional comfort on patient satisfaction. We further explored the effects of these communication patterns in different service contexts. RESULTS: Physicians with a low response load, a more detailed style, and expressions of emotional comfort received more positive patient feedback. Response load did not affect patient satisfaction with free online health service, whereas a more detailed style and emotional comfort enhanced satisfaction with free service. Response load significantly reduced patient satisfaction with paid online health service, while a more detailed style had no effect. Compared with free service, emotional comfort more strongly promoted patient satisfaction with paid service. CONCLUSIONS: The communication strategies identified can help physicians provide patients with a better internet hospital experience. These strategies require hospitals to schedule each physician's online service period more appropriately. In addition, tailoring the strategies to service situations can facilitate more targeted and effective internet hospital service for patients.

AI Supporting AAC Pictographic Symbol Adaptations.

The phenomenal increase in technological capabilities that allow the design and training of systems to cope with the complexities of natural language and visual representation in order to develop other formats is remarkable. It has made it possible to make use of image to image and text to image technologies to support those with disabilities in ways not previously explored. It has opened the world of adaptations from one picture to another in a design style of a user's choosing. Automated text simplification alongside graphical symbol representations to enhance understanding of complex content is already being used to support those with cognitive impairments and learning difficulties. Symbol sets have become embedded within applications as dictionaries and look up systems, but the need for flexibility and personalization remains a challenge. Most pictographic symbols are created over time within the bounds of a certain style and schema for particular groups such as those who use augmentative and alternative forms of communication (AAC). By using generative artificial intelligence, it is proposed that symbols could be produced based on the style of those already used by an individual or adapted to suit different requirements within local contexts, cultures and communities. This paper explores these ideas at the start of a small six-month pilot study to adapt a number of open licensed symbols based on the symbol set's original style. Once a collection has been automatically developed from image to image and text descriptions, potential stakeholders will evaluate the outcomes using an online voting system. Successful symbols will be made available and could potentially be added to the original symbol set offering a flexible personalized approach to AAC symbol generation hitherto not experienced by users.

Memristor-based spiking neural network with online reinforcement learning.

Neural networks implemented in memristor-based hardware can provide fast and efficient in-memory computation, but traditional learning methods such as error back-propagation are hardly feasible in it. Spiking neural networks (SNNs) are highly promising in this regard, as their weights can be changed locally in a self-organized manner without the demand for high-precision changes calculated with the use of information almost from the entire network. This problem is rather relevant for solving control tasks with neural-network reinforcement learning methods, as those are highly sensitive to any source of stochasticity in a model initialization, training, or decision-making procedure. This paper presents an online reinforcement learning algorithm in which the change of connection weights is carried out after processing each environment state during interaction-with-environment data generation. Another novel feature of the algorithm is that it is applied to SNNs with memristor-based STDP-like learning rules. The plasticity functions are obtained from real memristors based on poly-p-xylylene and CoFeB-LiNbO3 nanocomposite, which were experimentally assembled and analyzed. The SNN is comprised of leaky integrate-and-fire neurons. Environmental states are encoded by the timings of input spikes, and the control action is decoded by the first spike. The proposed learning algorithm solves the Cart-Pole benchmark task successfully. This result could be the first step towards implementing a real-time agent learning procedure in a continuous-time environment that can be run on neuromorphic systems with memristive synapses.

Pedi-R-MAPP | the development, testing, validation, and refinement of a digital nutrition awareness tool.

BACKGROUND & AIMS: The Remote Malnutrition Application (R-MAPP) was developed during the COVID-19 pandemic to provide support for health care professionals (HCPs) working in the community to complete remote nutritional assessments and provide practical guidance for nutritional care. R-MAPP was adapted into Pediatric Remote Malnutrition Application (Pedi-R-MAPP) using a modified Delphi consensus, with the goal of providing a structured approach to completing a nutrition focused assessment as part of a technology enabled care service (TECS) consultation. The aim of this study was to develop and validate a digital version of Pedi-R-MAPP using the IDEAS framework (Integrate, Design, Assess and Share). METHODS: A ten-step process was completed using the IDEAS framework. This involved the four concept processes; Stage-1, Integrate (Step 1-3) identify the problem, specify the goal, and use an evidence-based approach. Stage-2, (Step 4-7) design iteratively and rapidly with user feedback. Stage 3, (Step 8-9) Assess rigorously, and Stage 4 (Step 9-10) publish and launch of the tool. RESULTS: Stage 1:Evidence-based development, Pedi-R-MAPP was developed using Delphi consensus methodology. Stage 2:Iteration & design, HCPs (n = 22) from UK, Europe, South Africa, and North America were involved four workshops to further develop a paper prototype of the tool and complete small-scale testing of a beta version of the tool which resulted in eight iterations. Stage 3:Assess rigorously, Small scale retrospective testing of the tool on children with congenital heart disease (n = 80) was completed by a single researcher, with iterative changes made to improve agreement with summary advice. Large scale testing amongst (n = 745) children in different settings was completed by specialist paediatric dietitians (n = 15) advice who recorded agreement with the summary advice compared with their own clinical assessment. Paediatric dietitians were in overall agreement with the summary advice in the tool 86% (n = 640), compared to their own clinical practice. The main reasons for disagreement were i) frequency of planned review 57.1% (n = 60/105), ii) need for ongoing dietetic review due to chronic condition 20.0% (n = 21/105), iii) disagreement with recommendation for discharge 16.2% (n = 17/105) and iv) concerns with faltering growth and/or need for condition specific growth charts 6.7% (7/105). Iterative changes were made to the algorithm, leading to an improvement in agreement of the summary advice on re-evaluation to 98% (p=<0.0001). CONCLUSION: A digital version of the Pedi-R-MAPP nutrition awareness tool was developed using the IDEAS framework. The summary advice provided by the tool achieved a high level of agreement when compared to paediatric dietetic assessment, by providing a structured approach to completing a remote nutrition focused assessment, along with identifying the frequency of follow-up or an in-person assessment.

Online recommenders' anthropomorphism improves user response to hedonic and benefit-based product appeals through the recommenders' perceived ability to learn.

Previous studies reveal the limited effectiveness of benefit-based and hedonic-based product recommendations provided by online recommenders, and recommender anthropomorphism is considered a remedy. This paper aims to investigate the positive effect of anthropomorphism by involving the online recommender's perceived ability to learn as a mediator. Based on schema congruity theory, perceived benefit/hedonic appeals appropriateness is considered a dependent variable. In Study 1, subtle anthropomorphic cues within an online recommender had a positive effect on perceived benefit-appeals appropriateness through the perceived ability to learn. Study 2 demonstrated the positive relationship between perceived anthropomorphism and perceived hedonic-appeal appropriateness, with the mediating role of the perceived ability to learn. The results advance the knowledge about consumer response to online recommenders from the perspective of anthropomorphism and schema congruity theory. Marketers and consumer organizations are advised on how to deal with online recommender systems providing benefit and hedonic appeals.

A two-staged adsorption/thermal desorption GC/MS online system for monitoring volatile organic compounds.

Real-time online monitoring of volatile organic compounds (VOCs) in ambient air is crucial for timely and effective human health protection. Here, we developed an innovative, automated two-staged adsorption/thermal desorption gas chromatography/mass spectrometry (GC/MS) system for real-time online monitoring of 117 regulated volatile organic compounds (VOCs). This system comprised a sampling unit, water management trap, two-staged adsorption/thermal desorption unit, thermoelectric coolers (TECs), and a commercial GC/MS system. By implementing a micro-purge-and-trap (MP & T) step and a two-staged adsorption/thermal desorption unit, the presence of interfering substances was effectively minimized. The utilization of a heart-cutting GC, combined with a single MS detector, facilitated the precise separation and detection of 117 C2-C12 VOCs, while circumventing the identification and coelution challenges commonly associated with traditional GC-FID or GC-FID/MS methods. The performance of our newly developed online system was meticulously optimized and evaluated using standard gas mixtures. Under optimal conditions, we achieved impressive results, with R2 values ≥ 0.9946 for the standard linear curves of all 117 VOCs, demonstrating a precision (RSD) ranging from 0.2% to 6.4%. When applied in the field monitoring, the concentration drifts for 10 ppbv standard gas mixtures were 0.01-5.64% within 24 h. Our study developed a system for online monitoring of 117 atmospheric VOCs with relatively high accuracy and robustness.

Prompt identification of struggling candidates in near peer-led basic life support training: piloting an online performance scoring system.

BACKGROUND: Bristol Medical School has adopted a near peer-led teaching approach to deliver Basic Life Support training to first year undergraduate medical students. Challenges arose when trying to identify early in the course which candidates were struggling with their learning, in sessions delivered to large cohorts. We developed and piloted a novel, online performance scoring system to better track and highlight candidate progress. METHODS: During this pilot, a 10-point scale was used to evaluate candidate performance at six time-points during their training. The scores were collated and entered on an anonymised secure spreadsheet, which was conditionally formatted to provide a visual representation of the score. A One-Way ANOVA was performed on the scores and trends analysed during each course to review candidate trajectory. Descriptive statistics were assessed. Values are presented as mean scores with standard deviation (x̄±SD). RESULTS: A significant linear trend was demonstrated (P < 0.001) for the progression of candidates over the course. The average session score increased from 4.61 ± 1.78 at the start to 7.92 ± 1.22 at the end of the final session. A threshold of less than 1SD below the mean was used to identify struggling candidates at any of the six given timepoints. This threshold enabled efficient highlighting of struggling candidates in real time. CONCLUSIONS: Although the system will be subject to further validation, our pilot has shown the use of a simple 10-point scoring system in combination with a visual representation of performance helps to identify struggling candidates earlier across large cohorts of students undertaking skills training such as Basic Life Support. This early identification enables effective and efficient remedial support.

On-line monitoring of total sugar during kombucha fermentation process by near-infrared spectroscopy: Comparison of linear and non-linear multiple calibration methods.

Kombucha is widely recognized for its health benefits, and it facilitates high-quality transformation and utilization of tea during the fermentation process. Implementing on-line monitoring for the kombucha production process is crucial to promote the valuable utilization of low-quality tea residue. Near-infrared (NIR) spectroscopy, together with partial least squares (PLS), backpropagation neural network (BPANN), and their combination (PLS-BPANN), were utilized in this study to monitor the total sugar of kombucha. In all, 16 mathematical models were constructed and assessed. The results demonstrate that the PLS-BPANN model is superior to all others, with a determination coefficient (R2p) of 0.9437 and a root mean square error of prediction (RMSEP) of 0.8600 g/L and a good verification effect. The results suggest that NIR coupled with PLS-BPANN can be used as a non-destructive and on-line technique to monitor total sugar changes.

Comparative re-analysis evaluation of the Fukushima accident atmospheric radioactive emissions.

In this paper, two decision support systems have been used to re-analyze the Fukushima accident emissions: the European Realtime Online Decision Support System for Nuclear Emergency Management (RODOS, version JRodos 2019)-providing a set of modules for the dispersion of nuclides following atmospheric and aquatic releases, dosimetry modules for dose estimation to individuals and communities for all exposure pathways with application of countermeasures, and modules for time estimation of the radiological situation in inhabited and agricultural areas-and CBRNE Platform, developed by IFIN-HH within a research project on anticipative and prognostic evaluation of chemical, biological, radiological, nuclear and explosive events (CBRNE), which is a tool for effect diagnosis functions, response measures and consecutive recommendation for a large variety of scenarios. We have reproduced the event on both systems, using accident time weather data and updated source terms. Current and initial results were cross-compared and evaluated.

On-the-fly parameter estimation based on item response theory in item-based adaptive learning systems.

Online learning systems are able to offer customized content catered to individual learner's needs, and have seen growing interest from industry and academia alike in recent years. In contrast to the traditional computerized adaptive testing setting, which has a well-calibrated item bank with new items added periodically, the online learning system has two unique features: (1) the number of items is large, and they have likely not gone through costly field testing for item calibration; and (2) the individual's ability may change as a result of learning. The Elo rating system has been recognized as an effective method for fast updating of item and person parameters in online learning systems to enable personalized learning. However, the updating parameter in Elo has to be tuned post hoc, and Elo is only suitable for the Rasch model. In this paper, we propose the use of a moment-matching Bayesian update algorithm to estimate item and person parameters on the fly. With sequentially updated item and person parameters, a modified maximum posterior weighted information criterion (MPWI) is proposed to adaptively assign items to individuals. The Bayesian updated algorithm along with MPWI is validated in a simulated multiple-session online learning setting, and the results show that the new combo can achieve fast and reasonably accurate parameter estimations that are comparable to random selection, match-difficulty selection, and traditional online calibration. Moreover, the combo can still function reasonably well with as low as 20% of items being pre-calibrated in the item bank.

Implementation of an Online Reporting System to Identify Unprofessional Behaviors and Mistreatment Directed at Trainees at an Academic Medical Center.

Importance: Unprofessional behaviors and mistreatment directed at trainees continue to challenge the learning environment. Academic medical institutions should encourage reports of inappropriate behavior and address such reports directly to create a safe learning environment. Objective: To determine the feasibility of creating and implementing an online reporting system for receiving and reviewing complaints of unprofessional behavior directed toward or experienced by students, postdoctoral trainees, and residents. Design, Setting, and Participants: This cohort study assessed implementation of an online reporting system (feedback form) with a method for triaging reports, providing both positive and negative feedback, as well as adjudication and transparent public disclosure of aggregate data. The system was launched at a large urban academic medical center with numerous trainees that is fully integrated with a health system of 8 hospitals. Participants included faculty who interact with trainees, medical students, graduate students and postdoctoral fellows, and residents and clinical fellows. Follow-up began in October 2019 (at the time of tool launch) and lasted through December 2021. Data were analyzed from January to March 2022. Main Outcomes and Measures: The primary outcomes were the numbers and types of reports according to the reporter and the person reported about. Results: Participants included 2900 faculty who interact with trainees, 600 medical students, more than 1000 graduate students and postdoctoral fellows, and 2600 residents and clinical fellows. Trainees submitted 196 reports, 173 (88.3%) of which described unprofessional interactions. Among the reports describing unprofessional behavior, 60 (34.7%) were from medical students, 96 (55.5%) were from residents and fellows, 17 (9.8%) were from graduate students or postdoctoral trainees, and 78 (45.1%) were from men. The majority of negative reports described behaviors by faculty (106 [61.3%]), followed by residents and fellows (24 [13.9%]). Twenty faculty (<1.0%) accounted for 52 (50.0%) of the 104 reports describing unprofessional behaviors. Since implementation, most trainees are aware of this process. An increasing number have reported instances of mistreatment, and those who shared concerns through the online system report satisfaction with the outcome of the response to the report. Conclusions and Relevance: In this cohort study, the new reporting mechanism facilitated identification of the small number of individuals associated with unprofessional behaviors toward trainees and increased awareness of the school's commitment to creating a safe learning environment.

An Online Rail Track Fastener Classification System Based on YOLO Models.

In order to save manpower on rail track inspection, computer vision-based methodologies are developed. We propose utilizing the YOLOv4-Tiny neural network to identify track defects in real time. There are ten defects covering fasteners, rail surfaces, and sleepers from the upward and six defects about the rail waist from the sideward. The proposed real-time inspection system includes a high-performance notebook, two sports cameras, and three parallel processes. The hardware is mounted on a flat cart running at 30 km/h. The inspection results about the abnormal track components could be queried by defective type, time, and the rail hectometer stake. In the experiments, data augmentation by a Cycle Generative Adversarial Network (GAN) is used to increase the dataset. The number of images is 3800 on the upward and 967 on the sideward. Five object detection neural network models-YOLOv4, YOLOv4-Tiny, YOLOX-Tiny, SSD512, and SSD300-were tested. The YOLOv4-Tiny model with 150 FPS is selected as the recognition kernel, as it achieved 91.7%, 92%, and 91% for the mAP, precision, and recall of the defective track components from the upward, respectively. The mAP, precision, and recall of the defective track components from the sideward are 99.16%, 96%, and 94%, respectively.

An Intelligent Online Drunk Driving Detection System Based on Multi-Sensor Fusion Technology.

Since drunk driving poses a significant threat to road traffic safety, there is an increasing demand for the performance and dependability of online drunk driving detection devices for automobiles. However, the majority of current detection devices only contain a single sensor, resulting in a low degree of detection accuracy, erroneous judgments, and car locking. In order to solve the problem, this study firstly designed a sensor array based on the gas diffusion model and the characteristics of a car steering wheel. Secondly, the data fusion algorithm is proposed according to the data characteristics of the sensor array on the steering wheel. The support matrix is used to improve the data consistency of the single sensor data, and then the adaptive weighted fusion algorithm is used for multiple sensors. Finally, in order to verify the reliability of the system, an online intelligent detection device for drunk driving based on multi-sensor fusion was developed, and three people using different combinations of drunk driving simulation experiments were conducted. According to the test results, a drunk person in the passenger seat will not cause the system to make a drunk driving determination. When more than 50 mL of alcohol is consumed and the driver is seated in the driver's seat, the online intelligent detection of drunk driving can accurately identify drunk driving, and the car will lock itself as soon as a real-time online voice prompt is heard. This study enhances and complements theories relating to data fusion for online automobile drunk driving detection, allowing for the online identification of drivers who have been drinking and the locking of their vehicles to prevent drunk driving. It provides technical support for enhancing the accuracy of online systems that detect drunk driving in automobiles.

Pilot trial comparing COVID-19 publication database to conventional online search methods.

BACKGROUND AND OBJECTIVES: Literature review using search engines results in a list of manuscripts but does not provide the content contained in the manuscripts. Our goal was to evaluate user performance-based criteria of concept retrieval accuracy and efficiency using a new database system that contained information extracted from 1000 COVID-19 articles. METHODS: A sample of 17 students from the University of Vermont were randomly assigned to use the COVID-19 publication database or their usual preferred search methods to research eight prompts about COVID-19. The relevance and accuracy of the evidence found for each prompt were graded. A Cox proportional hazards' model with a sandwich estimator and Kaplan-Meier plots were used to analyse these data in a time-to-correct answer context. RESULTS: Our findings indicate that students using the new information management system answered significantly more prompts correctly and, in less time, than students using conventional research methods. Bivariate models for demographic factors indicated that previous research experience conferred an advantage in study performance, though it was found to be independent from the assigned research method. CONCLUSIONS: The results from this pilot randomised trial present a potential tool for more quickly and thoroughly navigating the literature on expansive topics such as COVID-19.

Nationwide, large-scale implementation of an online system for remote entry of patient-reported outcomes in rheumatology: characteristics of users and non-users and time to first entry.

AIMS: In May 2020, a nationwide, web-based system for remote entry of patient-reported outcomes (PROs) in inflammatory rheumatic diseases was launched and implemented in routine care (DANBIO-from-home). After 1.5 years of use, we explored clinical characteristics of patients who did versus did not use the system, and the time to first entry of PROs. METHODS: All patients followed in DANBIO were informed about DANBIO-from-home by electronic invitations or when attending their clinic. Characteristics of patients who did/did not use DANBIO-from-home in the period after implementation were explored by multivariable logistic regression analyses including demographic and clinical variables (gender, age group, diagnosis, disease duration, use of biological disease-modifying agent (bDMARD), Health Assessment Questionnaire (HAQ), Patient Acceptable Symptom Scale (PASS)). Time from launch to first entry was presented as cumulative incidence curves by age group (<40/40-60/61-80/>80 years). RESULTS: Of 33 776 patients, 68% entered PROs using DANBIO-from-home at least once. Median (IQR) time to first entry was 27 (11-152) days. Factors associated with data entry in multivariate analyses (OR (95% CI)) were: female gender (1.19 (1.12 to 1.27)), bDMARD treatment (1.41 (1.33 to 1.50)), age 40-60 years (1.79 (1.63 to 1.97)), 61-80 years (1.87 (1.70 to 2.07), or age >80 years (0.57 (0.50 to 0.65)) (reference: age <40 years), lower HAQ (0.68 (0.65 to 0.71)) and PASS 'no' (1.09 (1.02 to 1.17). Diagnosis was not associated. Time to first entry of PROs was longest in patients <40 years of age (119 (24-184) days) and shortest in the 61-80 years age group (25 (8-139) days). CONCLUSION: A nationwide online platform for PRO in rheumatology achieved widespread use. Higher age, male gender, conventional treatment and disability were associated with no use.

Online Detection System for Wheat Machine Harvesting Impurity Rate Based on DeepLabV3.

Wheat, one of the most important food crops in the world, is usually harvested mechanically by combine harvesters. The impurity rate is one of the most important indicators of the quality of wheat obtained by mechanized harvesting. To realize the online detection of the impurity rate in the mechanized harvesting process of wheat, a vision system based on the DeepLabV3+ model of deep learning for identifying and segmenting wheat grains and impurities was designed in this study. The DeepLabV3+ model construction considered the four backbones of MobileNetV2, Xception-65, ResNet-50, and ResNet-101 for training. The optimal DeepLabV3+ model was determined through the accuracy rate, comprehensive evaluation index, and average intersection ratio. On this basis, an online detection method of measuring the wheat impurity rate in mechanized harvesting based on image information was constructed. The model realized the online detection of the wheat impurity rate. The test results showed that ResNet-50 had the best recognition and segmentation performance; the accuracy rate of grain identification was 86.86%; the comprehensive evaluation index was 83.63%; the intersection ratio was 0.7186; the accuracy rate of impurity identification was 89.91%; the comprehensive evaluation index was 87.18%; the intersection ratio was 0.7717; and the average intersection ratio was 0.7457. In terms of speed, ResNet-50 had a fast segmentation speed of 256 ms per image. Therefore, in this study, ResNet-50 was selected as the backbone network for DeepLabV3+ to carry out the identification and segmentation of mechanically harvested wheat grains and impurity components. Based on the manual inspection results, the maximum absolute error of the device impurity rate detection in the bench test was 0.2%, and the largest relative error was 17.34%; the maximum absolute error of the device impurity rate detection in the field test was 0.06%; and the largest relative error was 13.78%. This study provides a real-time method for impurity rate measurement in wheat mechanized harvesting.

Screening of small molecule inhibitors against RhoA protein from Alisma using an online detection system.

Targeted high-throughput screening of inhibitors from natural products is an effective approach in the treatment of cancer progression. RhoA protein is essential for many signaling pathways. It is closely related to the occurrence and development of tumor. So far, there are only a few reports on the screening of small molecule inhibitors of RhoA protein from natural products. In this study, an online UHPLC-PDA-MS2-RhoA-FLD screening system was established for the first time to identify RhoA inhibitors from medicinal Alisma. Using this online system by adding fluorescent probes protopine [LZ1] to proteins, 17 active components were identified from Alisma, including 14 terpenoids. Their binding abilities were evaluated by Surface Plasmon Resonance experiments. The activities of representative compounds were tested and showed anti-proliferative effect in cancer cells. Mechanistic studies showed that these compounds were able to downregulate the cellular expressions of RhoA associated proteins. This study provides potential lead compounds as small molecule inhibitors of RhoA protein for cancer therapy. This reported method can be used for targeted screening of small molecule inhibitors against tumors, and provides an approach for screening tumor inhibitors from natural products.

A converging reputation ranking iteration method via the eigenvector.

Ranking user reputation and object quality in online rating systems is of great significance for the construction of reputation systems. In this paper we put forward an iterative algorithm for ranking reputation and quality in terms of eigenvector, named EigenRank algorithm, where the user reputation and object quality interact and the user reputation converges to the eigenvector associated to the greatest eigenvalue of a certain matrix. In addition, we prove the convergence of EigenRank algorithm, and analyse the speed of convergence. Meanwhile, the experimental results for the synthetic networks show that the AUC values and Kendall's τ of the EigenRank algorithm are greater than the ones from the IBeta method and Vote Aggregation method with different proportions of random/malicious ratings. The results for the empirical networks show that the EigenRank algorithm performs better in accuracy and robustness compared to the IBeta method and Vote Aggregation method in the random and malicious rating attack cases. This work provides an expectable ranking algorithm for the online user reputation identification.