Formation of acrylamide in microwave-roasted sorghum and associated dietary risk

The effect of microwave roasting parameters (300, 450 and 600 W; 5, 10 and 15 min) on acrylamide content in sorghum grain was determined using High Pressure Liquid Chromatography (HPLC)-photo diode array (PDA) detector coupled with C-18 column. Samples roasted at 300 and 450 W did not possess acrylamide, whereas 600 W (15 min) favoured formation of 2740.19 µg/kg of acrylamide, levels far exceeding the defined European Union (EU) limits. The chronic daily intake (CDI) for acrylamide through consumption of such grain flour was 3.25–9.5-fold higher to Joint FAO/WHO Expert Committee on Food Additives (JECFA) defined high exposure limits. The margin of exposure (MOE) values ranged from 4.3 to 12.76 and from 11.07 to 32.27 for neoplastic and neurological effects, respectively, demonstrating high exposure and serious health concerns associated with dietary intake of this toxicant. This study assesses the risk for the Indian population and highlights the importance of optimising process parameters for food product to minimise such exposure risks.     

基于多通道的ICU脑血管疾病死亡风险预测模型

死亡风险预测指根据病人临床体征监测数据来预测未来一段时间的死亡风险。对于ICU病患，通过死亡风险预测可以有针对性地对病人做出临床诊断，以及合理安排有限的医疗资源。基于临床使用的MEWS和Glasgow昏迷评分量表，针对ICU病人临床监测的17项生理参数，提出一种基于多通道的ICU脑血管疾病死亡风险预测模型。引入多通道概念应用于BiLSTM模型，用于突出每个生理参数对死亡风险预测的作用。采用Attention机制用于提高模型预测精度。实验数据来自MIMIC [Ⅲ]数据库，从中提取3?080位脑血管疾病患者的16?260条记录用于此次研究，除了六组超参数实验之外，将所提模型与LSTM、Multichannel-BiLSTM、逻辑回归（logistic regression）和支持向量机（support vector machine, SVM）四种模型进行了对比分析，准确率Accuracy、灵敏度Sensitive、特异性Specificity、AUC-ROC和AUC-PRC作为评价指标，实验结果表明，所提模型性能优于其他模型，AUC值达到94.3%。     

The International Society for the Study of Vascular Anomalies (ISSVA) ontology

The International Society for the Study of Vascular Anomalies (ISSVA) provides a classification for vascular anomalies that enables specialists to unambiguously classify diagnoses. This classification is only available in PDF format and is not machine-readable, nor does it provide unique identifiers that allow for structured registration. In this paper, we describe the process of transforming the ISSVA classification into an ontology. We also describe the structure of this ontology, as well as two applications of the ontology using examples from the domain of rare disease research. We used the expertise of an ontology expert and clinician during the development process. We semi-automatically added mappings to relevant external ontologies using automated ontology matching systems and manual assessment by experts. The ISSVA ontology should contribute to making data for vascular anomaly research more Findable, Accessible, Interoperable, and Reusable (FAIR). The ontology is available at https://bioportal.bioontology.org/ontologies/ISSVA.     

Trade-off study between risk and benefit in safety devices for hydrogen refueling stations using a dynamic physical model

As hydrogen refueling stations become increasingly common, it is clear that a high level of economic efficiency and safety is crucial to promoting their use. One way to reduce costs is to use a simple orifice instead of an excess flow valve, which Japanese safety regulations have identified as a safety device. However, there is concern about its effect on refueling time and on risk due to hydrogen leakage. To clarify the effect, we did a study of model-based refueling time evaluation and quantitative risk assessment for a typical refueling station. This study showed that an orifice is an effective alternative safety device. The increase in refueling time was less than 10%, based on simulations using a dynamic physical model of the station. Neither was there a significant difference in the risk between a configuration with excess flow valves and one with an orifice.     

乌兰矿采矿现状及技术应对方案

本文分析了乌兰矿投产前期采矿现状及存在的主要问题,针对该矿所处蒙古国经济落后、投资风险大的现实状况,为避免生产中断、规避投资风险,早日回收前期投资考虑,采取了双斜坡道开拓、全尾胶结充填、高端壁空场嗣后充填采矿、多中段组合式连续开采等系列技术应对方案。大大降低了一次性投资规模及投资风险,前期投资得以快速回笼的同时,矿山产能也充分释放,确保了矿山的持续稳定,取得了较好的经济和社会效益。为海外地下近地表矿体开采矿山规避投资风险提供了很好的技术方案借鉴。     

A self-adaptive synthetic over-sampling technique for imbalanced classification

Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50%-80%) is used for training and the rest—for validation. In many problems, however, the data are highly imbalanced in regard to different classes or does not have good coverage of the feasible data space which, in turn, creates problems in validation and usage phase. In this paper, we propose a technique for synthesizing feasible and likely data to help balance the classes as well as to boost the performance in terms of confusion matrix as well as overall. The idea, in a nutshell, is to synthesize data samples in close vicinity to the actual data samples specifically for the less represented (minority) classes. This has also implications to the so-called fairness of machine learning. In this paper, we propose a specific method for synthesizing data in a way to balance the classes and boost the performance, especially of the minority classes. It is generic and can be applied to different base algorithms, for example, support vector machines, k-nearest neighbour classifiers deep neural, rule-based classifiers, decision trees, and so forth. The results demonstrated that (a) a significantly more balanced (and fair) classification results can be achieved and (b) that the overall performance as well as the performance per class measured by confusion matrix can be boosted. In addition, this approach can be very valuable for the cases when the number of actual available labelled data is small which itself is one of the problems of the contemporary machine learning.     

Ergonomics interventions to reduce musculoskeletal risk factors in a truck manufacturing plant

Ergonomic interventions may potentially reduce MSDs, but the context of industries (barriers, ever-changing situations, dialogue processes) might play a significant role in the success of interventions. This study evaluates the effectiveness of ergonomic interventions including engineering/technical and organizational interventions, and the involvement of the stakeholders in reducing musculoskeletal risk factors/symptoms. A pre-post-test experimental study in non-randomized groups was performed over three years in a sector of a truck assembly plant. The mean age of the operators in the sector for the initial and second assessment time was 42.0 (±7.6) years and 39.0 (±8.7), respectively. The mean length of work experience in the current job was 15.2 (±7.2) years and 13.9 (±7.3) for the initial and second assessment times, respectively. Five engineering ergonomic solutions and organizational interventions were implemented after a comprehensive ergonomic analysis. The organizational interventions consisted mostly of transferring and redistributing the tasks, i.e., ergonomically balancing and redesigning of the workstations. Before performing the interventions, the findings of the ergonomic study were presented at several meetings to encourage the involvement of the stakeholders (including managers, engineers, and operators) in the interventions. This study showed that a combination of ergonomic measures—engineering and organizational interventions—could reduce physical workloads. Musculoskeletal symptoms decreased after interventions although the difference was not significant.     

Sustainable disassembly line balancing model based on triple bottom line

End of life (EOL) phase of a product is receiving more attention due to increase in environmental concerns, and many studies have been conducted for value creation in EOL, focusing on concepts as remanufacturing, reuse and recycling in sustainable production manner. This study especially focuses on one of global problem, e-waste. To minimise the amount of wastes and maximise recovered materials from EOL, disassembly is one of the most important concept, associated with reuse, and balancing disassembly line in an optimal way is essential for organisations. In disassembly line balancing (DLB), not only precedence of tasks, but also risk criteria related to environment and human safety should be considered for sustainability. The aim of this study is to propose a model based on triple bottom line (TBL) dimensions, i.e. human safety, environmental safety and business criteria. To achieve sustainability in DLB, and for risk assessment in sustainable DLB, it had been decided to use a multi-criteria method, i.e. TODIM, acronym in Portuguese of ‘Tomada de Decisão Iterativa Multicritério’. The proposed model included 22 disassembly criteria categorised under TBL dimensions, which are derived from the literature. Implementation of the study was conducted for computer disassembly processes, and as a result of the study approximately 12% an improvement in cycle time was succeeded. In the long run, the integration of sustainability in disassembly operations may contribute to the competitive advantage of the company in terms of differentiation and corporate image by achieving business, environment and human targets simultaneously.     

TCBR-HMM: An HMM-based text classifier with a CBR system

This paper presents an innovative solution to model distributed adaptive systems in biomedical environments. We present an original TCBR-HMM (Text Case Based Reasoning-Hidden Markov Model) for biomedical text classification based on document content. The main goal is to propose a more effective classifier than current methods in this environment where the model needs to be adapted to new documents in an iterative learning frame. To demonstrate its achievement, we include a set of experiments, which have been performed on OSHUMED corpus. Our classifier is compared with Naive Bayes and SVM techniques, commonly used in text classification tasks. The results suggest that the TCBR-HMM Model is indeed more suitable for document classification. The model is empirically and statistically comparable to the SVM classifier and outperforms it in terms of time efficiency.