Deep Learning Based Process Analytics Model for Predicting Type 2 Diabetes Mellitus

Process analytics is one of the popular research domains that advanced in the recent years. Process analytics encompasses identification, monitoring, and improvement of the processes through knowledge extraction from historical data. The evolution of Artificial Intelligence (AI)-enabled Electronic Health Records (EHRs) revolutionized the medical practice. Type 2 Diabetes Mellitus (T2DM) is a syndrome characterized by the lack of insulin secretion. If not diagnosed and managed at early stages, it may produce severe outcomes and at times, death too. Chronic Kidney Disease (CKD) and Coronary Heart Disease (CHD) are the most common, long-term and life-threatening diseases caused by T2DM. Therefore, it becomes inevitable to predict the risks of CKD and CHD in T2DM patients. The current research article presents automated Deep Learning (DL)-based Deep Neural Network (DNN) with Adagrad Optimization Algorithm i.e., DNN-AGOA model to predict CKD and CHD risks in T2DM patients. The paper proposes a risk prediction model for T2DM patients who may develop CKD or CHD. This model helps in alarming both T2DM patients and clinicians in advance. At first, the proposed DNN-AGOA model performs data preprocessing to improve the quality of data and make it compatible for further processing. Besides, a Deep Neural Network (DNN) is employed for feature extraction, after which sigmoid function is used for classification. Further, Adagrad optimizer is applied to improve the performance of DNN model. For experimental validation, benchmark medical datasets were used and the results were validated under several dimensions. The proposed model achieved a maximum precision of 93.99%, recall of 94.63%, specificity of 73.34%, accuracy of 92.58%, and F-score of 94.22%. The results attained through experimentation established that the proposed DNN-AGOA model has good prediction capability over other methods.     

ACCUGRAM: A novel approach based on classification to frequency band selection for rotating machinery fault diagnosis

Frequency band selection (FBS) in rotating machinery fault diagnosis aims to recognize frequency band location including a fault transient out of a full band spectrum, and thus fault diagnosis can suppress noise influence from other frequency components. Impulsiveness and cyclostationarity have been recently recognized as two distinctive signatures of a transient. Thus, many studies have focused on developing quantification metrics of the two signatures and using them as indicators to guide FBS. However, most previous studies almost ignore another aspect of FBS, i.e. health reference, which significantly affect FBS performance. To address this issue, this paper investigates importance of a health reference and recognize it as the third critical aspect in FBS. With help of the health reference, the frequency band where the fault transient exists could be located. A novel approach based on classification is proposed to integrate all three aspects (impulsiveness, cyclostationarity, and health reference) for FBS. Classification accuracy is developed as a novel indicator to select the most sensitive frequency band for rotating machinery fault diagnosis. The proposed method (coined by accugram) has been validated on benchmark and experiment datasets. Comparison results show its effectiveness and robustness over conventional envelope analysis, the kurtogram, and the infogram.     

Electrochemical growth and characterization of iron doped cadmium sulfide thin films

Cadmium Sulfide and Ferrous doped Cadmium Sulfide thin films have been prepared on different substrates using an electrodeposition technique. Linear sweep voltammetric analysis has been carried out to determine deposition potential of the prepared films. X-ray diffraction analysis showed that the prepared films possess polycrystalline nature with hexagonal structure. Surface morphology and film composition have been analyzed using Scanning electron microscopy and Energy dispersive analysis by X-rays. Optical absorption analysis showed that the prepared films are found to exhibit Band gap value in the range between 2.3, 2.8 eV for Cadmium Sulfide and Ferrous doped Cadmium Sulfide.     

Preliminary Evidence on the Diagnostic and Molecular Role of Circulating Soluble EGFR in Non-Small Cell Lung Cancer

Assessment of biological diagnostic factors providing clinically-relevant information to guide physician decision-making are still needed for diseases with poor outcomes, such as non-small cell lung cancer (NSCLC). Epidermal growth factor receptor (EGFR) is a promising molecule in the clinical management of NSCLC. While the EGFR transmembrane form has been extensively investigated in large clinical trials, the soluble, circulating EGFR isoform (sEGFR), which may have a potential clinical use, has rarely been considered. This study investigates the use of sEGFR as a potential diagnostic biomarker for NSCLC and also characterizes the biological function of sEGFR to clarify the molecular mechanisms involved in the course of action of this protein. Plasma sEGFR levels from a heterogeneous cohort of 37 non-advanced NSCLC patients and 54 healthy subjects were analyzed by using an enzyme-linked immunosorbent assay. The biological function of sEGFR was analyzed in vitro using NSCLC cell lines, investigating effects on cell proliferation and migration. We found that plasma sEGFR was significantly decreased in the NSCLC patient group as compared to the control group (median value: 48.6 vs. 55.6 ng/mL respectively; p = 0.0002). Moreover, we demonstrated that sEGFR inhibits growth and migration of NSCLC cells in vitro through molecular mechanisms that included perturbation of EGF/EGFR cell signaling and holoreceptor internalization. These data show that sEGFR is a potential circulating biomarker with a physiological protective role, providing a first approach to the functional role of the soluble isoform of EGFR. However, the impact of these data on daily clinical practice needs to be further investigated in larger prospective studies.     

Marginal cost and congestion in the Italian electricity market: An indirect estimation approach

In this paper we construct an indirect measure of the supply marginal cost function for the main generators from the observed bid data in the Italian electricity market in the period 2004–2007. We compute the residual demand function for each generator, taking explicitly into account the issue of transmission line congestion. This procedure allows recovering correct zonal Lerner index and the implied measure of the marginal cost function. We find evidence of a stable U-shaped marginal cost function for three main Italian generators, but a flat function for ENEL, the former national monopolist. The policy relevance of our approach lies in the possibility to offer some empirical knowledge of the marginal cost function of each generator to the regulator to design appropriate policy measures geared to the promotion of competitive market conditions. We propose a new market surveillance mechanism, which is based on the principle of sanctioning excessive deviations from the estimated measure of the marginal cost function presented in this work.     

Study on metamerism degree evaluation based on wavelength sensitive cone weighting algorithm

Metamerism phenomenon can be used in illuminant detection to ensure the accuracy of light source. A method based on Long‐, Middle‐, Short‐ wavelength cones(LMS) weighting algorithm to evaluate metamerism degree is proposed. The chromatic relationship between the degree of metamerism mismatch and the light source is studied. Herein, the consistency between the metameric indices (MIs) and CIE1976 L*a*b* color difference ranking is analyzed by SRCC, KRCC, PLCC and RMSE. A statistically sampling method to obtain practical LMS cone fundamentals to evaluate metamerism degree is employed. The analysis results obtained show that the method based on LMS weighting algorithm has good evaluation ability and stability in simulation experiments and statistically sampling experiments, which are in line with visual characteristics of human. Proposed method meets the requirements of selecting metameric pairs used in light source detection. The analysis results have certain guiding significance.     

An ideal host-guest system to accomplish high-performance greenish yellow and hybrid white organic light-emitting diodes

Greenish yellow organic light-emitting diodes (GYOLEDs) have steadily attracted researcher's attention since they are important to our life. However, their performance significantly lags behind compared with the three primary colors based OLEDs. Herein, for the first time, an ideal host-guest system has been demonstrated to accomplish high-performance phosphorescent GYOLEDs, where the guest concentration is as low as 2%. The GYOLED exhibits a forward-viewing power efficiency of 57.0 lm/W at 1000 cd/m², which is the highest among GYOLEDs. Besides, extremely low efficiency roll-off and voltages are achieved. The origin of the high performance is unveiled and it is found that the combined mechanisms of host-guest energy transfer and direct exciton formation on the guest are effective to furnish the greenish yellow emission. Then, by dint of this ideal host-guest system, a simplified but high-performance hybrid white OLED (WOLED) has been developed. The WOLED can exhibit an ultrahigh color rendering index (CRI) of 92, a maximum total efficiency of 27.5 lm/W and a low turn-on voltage of 2.5 V (1 cd/m²), unlocking a novel avenue to simultaneously achieve simplified structure, ultrahigh CRI (>90), high efficiency and low voltage.     

以IBAC为核心处理洗浴废水的试验研究

根据洗浴废水的水质特征,采用原水→混凝沉淀-过滤→固定化生物活性炭(Immobilized Biological Activated Carbon,IBAC)→微滤膜(MF)→UV消毒→出水的工艺流程.混凝沉淀-过滤物化预处理单元可以有效地减少洗浴废水中的各类污染物.IBAC生化处理单元,实现有机污染物、LAS、浴臭等有效去除,是保证出水合格的根本措施.微滤膜发挥物理截留作用、UV消毒杀死细菌和总大肠菌群.出水水质达到＜城市供水水质标准＞(CJ/T 206-2005).     

RI/VI联用测定聚乙烯相对分子质量及其分布

150℃测试温度下，以1，2，4-三氯苯为溶剂，采用示差折光指数器，毛细管黏度计双检测器联用凝胶渗透色谱技术测定了聚乙烯的相对分子质量及其分布。与常规凝胶渗透色谱法对比，该方法不仅能直接得到聚乙烯较精确的相对分子质量和分布形态，同时可以得到聚乙烯的特性黏数分布。     

天然气产业链下游市场风险评价模型探讨

随着我国天然气主干管网的逐步形成，天然气产业链下游市场正在进入快速成长阶段，建立风险预警系统的重要性开始显现，而风险评价模型是其基础工作之一。文章在天然气产业链下游区域市场风险评价指标体系的基础上，综合运用层次分析法和灰色系统理论，建立了对天然气产业链下游区域市场风险评价的模型，并以各区域市场的用气量占全国总用气量的比重为权重，建立起完整的市场风险评价模型，可为评价天然气产业链下游市场整体市场风险时参考。