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.     

An IoT-Aware System for Managing Patients’ Waiting Time Using Bluetooth Low-Energy Technology

It is a common observation that whenever patients arrives at the front desk of a hospital, outpatient clinic, or other health-associated centers, they have to first queue up in a line and wait to fill in their registration form to get admitted. The long waiting time without any status updates is the most common complaint, concerning health officials. In this paper, UrNext, a location-aware mobile-based solution using Bluetooth low-energy (BLE) technology is presented to solve the problem. Recently, a technology-oriented method, the Internet of Things (IoT), has been gaining popularity in helping to solve some of the healthcare sector’s problems. The implementation of this solution could be illustrated through a simple example of when a patient arrives at a clinic for a consultation. Instead of having to wait in long lines, that patient will be greeted automatically, receive a push notification of an admittance along with an estimated waiting time for a consultation session. This will not only provide the patients with a sense of freedom but would also reduce the uncertainty levels that are generally observed, thus saving both time and money. This work aims to improve the clinics’ quality of services, organize queues and minimize waiting times, leading to patients’ comfort while reducing the burden on nurses and receptionists. The results demonstrate that the presented system is successful in its performance and helps achieves a pleasant and conducive clinic visitation process with higher productivity.     

Convolutional Neural Network Auto Encoder Channel Estimation Algorithm in MIMO-OFDM System

Higher transmission rate is one of the technological features of prominently used wireless communication namely Multiple Input Multiple Output-Orthogonal Frequency Division Multiplexing (MIMO–OFDM). One among an effective solution for channel estimation in wireless communication system, specifically in different environments is Deep Learning (DL) method. This research greatly utilizes channel estimator on the basis of Convolutional Neural Network Auto Encoder (CNNAE) classifier for MIMO-OFDM systems. A CNNAE classifier is one among Deep Learning (DL) algorithm, in which video signal is fed as input by allotting significant learnable weights and biases in various aspects/objects for video signal and capable of differentiating from one another. Improved performances are achieved by using CNNAE based channel estimation, in which extension is done for channel selection as well as achieve enhanced performances numerically, when compared with conventional estimators in quite a lot of scenarios. Considering reduction in number of parameters involved and re-usability of weights, CNNAE based channel estimation is quite suitable and properly fits to the video signal. CNNAE classifier weights updation are done with minimized Signal to Noise Ratio (SNR), Bit Error Rate (BER) and Mean Square Error (MSE).     

超高效液相色谱⁃四极杆⁃飞行时间质谱对含PET食品接触材料中可迁移非挥发性物质的筛查研究

采用超高效液相色谱⁃四极杆⁃飞行时间高分辨质谱（UPLC⁃Q⁃TOF）对4类不同类型的含聚对苯二甲酸乙二醇酯（PET）材质的食品接触材料在4 %乙酸和50 %乙醇模拟物中的迁移出的非挥发性未知物进行筛查解析。结果表明，产品在4 %乙酸模拟物的迁移风险远小于50 %乙醇模拟物，主要迁移物质为聚合单体形成的寡聚物，抗氧剂、润滑剂、胶黏剂等加工助剂以及生产加工、迁移过程中形成的非有意添加物（NIAS）物质；纯PET材质的产品迁移物质较少，多层复合材料迁移物质较多。复合材质的产品中，PET材质可能在生产时添加了己二酸、癸二酸、新戊二醇等物质，进行了改性处理；此外，部分迁移物质会与模拟物中的乙醇发生反应，生成新的NIAS物质。     

“方变圆”变径筒状结构滑模施工技术

为解决塔式光热的核心构筑物吸热塔"方变圆"变径超高筒体结构施工难题,选用一套可变形的滑模平台系统,通过操作系统上可调千斤顶支座、门架横向液压千斤顶装置、多处可调节模板角度和收缩模板的丝杆等,使得滑模根据施工需求可在一定的范围内调节模板倾角、间距,并逐步完成收缩变形,其理论滑模允许偏角20°,最终高效完成异形结构施工。该滑模系统刚度大、承载及堆料能力强、空间大、机械化程度高,施工操作简单,安全性高,适应沙漠极端环境。全过程仅需使用一套滑模体系,就能完成方形段、方变圆的变形段及圆形段施工,大大提高了施工效率,为类似环境下相似结构的施工提供了一定的参考。     

ZnO·2.7Al2O3 nanocomposite with high optical transparency

Here we report a transparent dual-phase ZnO·2.7Al₂O₃ ceramic. The composite is pore-free and consists of thin nanosheets with a spinel phase and a hexagonal phase, while the two phases match closely in both lattice and refractive index. Such features result in excellent optical transmittance (maximum value >80% in the visible spectrum) at comparable phase volume. This work may provide a new thought for the rational structural design of optical nanocomposites.     

Synthesis of thermoresponsive copolymer/silica-coated magnetite nanoparticle composite and its application for heavy metal ion recovery

To enhance chemical stability and suppress of aggregation of magnetite nanoparticles (MNPs), which are used as a support for thermoresponsive copolymer immobilization, silica coating of the MNPs is applied via the electrooxidation method. Although the resulting silica coated-MNPs also formed aggregates, the size distribution of the aggregate shifted to smaller size range. Because of that, the surface area available for copolymer immobilization increased approximately 6.7 times at maximum as compared with that of the uncoated MNPs. It contributed to the increase of the amount of the immobilized copolymer on the silica-coated MNPs, which is approximately four times larger than that on the uncoated MNPs. Fe₃O₄ dissolution test confirmed enhancement of chemical stability of MNPs. The thermoresponsive copolymer immobilized on the silica-coated MNPs shows the ability to recycle Cu(II) ion from Cu(II) containing solution by changing temperature with significantly shorter time than those in other thermoresponsive adsorbents in gel form.     

Centrifugally spun carbon fibers prepared from aqueous poly(vinylpyrrolidone) solutions as binder-free anodes in lithium-ion batteries

Aqueous solutions of poly(vinylpyrrolidone) (PVP) of various concentrations (20, 25, and 28 wt%) were successfully spun into fibers by centrifugal spinning. The pristine PVP fibers were annealed and carbonized to produce flexible carbon fibers for use as binder-free anodes in lithium-ion batteries. These flexible carbon fibers were prepared by developing a novel three-step heat treatment to reduce the residual stresses in the pristine PVP precursor fibers, and to prevent fiber degradation during carbonization. The thermogravimetric analysis data showed that the annealed fibers yielded a residual mass percentage of 36.0% while the pristine PVP fibers suffered a higher mass loss and only retained 26.5% of original mass above 450 °C (under nitrogen). The electrochemical performance of the carbon-fiber anodes was evaluated by conducting galvanostatic charge/discharge, rate performance, and cycle voltammetry experiments. The 20, 25, and 28 wt% derived binder-free anodes delivered specific charge capacities of 205, 189, and 275 mAh g⁻¹, respectively, after the first cycle at a current density of 100 mA g⁻¹. The results obtained in this work indicate that a feasible pathway towards a large-scale production of carbon-fiber anodes from a 100% aqueous solution can be achieved via centrifugal spinning and subsequent heat treatment.