Multivariable identification based MPC for closed-loop glucose regulation subject to individual variability.

The controller is important for the artificial pancreas to guide insulin infusion in diabetic therapy. However, the inter- and intra-individual variability and time delay of glucose metabolism bring challenges to control glucose within a normal range. In this study, a multivariable identification based model predictive control (mi-MPC) is developed to overcome the above challenges. Firstly, an integrated glucose-insulin model is established to describe insulin absorption, glucose-insulin interaction under meal disturbance, and glucose transport. On this basis, an observable glucose-insulin dynamic model is formed, in which the individual parameters and disturbances can be identified by designing a particle filtering estimator. Next, embedded with the identified glucose-insulin dynamic model, a mi-MPC method is proposed. In this controller, plasma glucose concentration (PGC), an important variable and indicator of glucose regulation, is estimated and controlled directly. Finally, the method was tested on 30 in-silico subjects produced by the UVa/Padova simulator. The results show that the mi-MPC method including the model, individual identification, and the controller can regulate glucose with the mean value of 7.45 mmol/L without meal announcement.

Classification of breast density categories based on SE-Attention neural networks.

BACKGROUND AND OBJECTIVE: Breast density (BD) is an independent predictor of breast cancer risk factor. The automatic classification of BD has yet to resolve. In this paper, we propose an improved convolutional neural network (CNN) framework that integrates innovative SE-Attention mechanism to learn discriminative features, aiming for automatic BD classification in mammography. METHODS: A new benchmarking dataset was constructed from 18157 BD images, manually segmented into 4 levels based on Breast Imaging and Reporting Data System (BI-RADS): A (fatty), B (fibro-glandular), C (heterogeneously dense) and D (extremely dense). The proposed method consists of three main phases: (i) data enhancement and normalization of breast images (ii) SE-Attention training for feature re-calibration and fusion to better classify density and (iii) designing the auxiliary loss. We adopt an attention approach where SE-Attention mechanism is used to learn the density features, which is different from previous works. RESULTS: Experimental results demonstrate that the proposed framework obtains higher classification accuracy than the original network, such as Inception-V4, ResNeXt, DenseNet, increasing the performance from 89.97% to 92.17%, 89.64% to 91.57%, 89.20% to 91.79% respectively. Among them, improved Inception-V4 possesses the highest accuracy meanwhile DenseNet improves in the largest extent, both the original and improved methods are more effective than other state-of-the-art image descriptors regarding classification. CONCLUSIONS: We insist that our method will help radiologists provide reliable BD diagnostic services at the expert level, allowing them to focus on patients who are really in need.

Channel Prediction Based on BP Neural Network for Backscatter Communication Networks.

Backscatter communication networks are receiving a lot of attention thanks to the application of ultra-low power sensors. Because of the large amount of sensor data, increasing network throughput becomes a key issue, so rate adaption based on channel quality is a novel direction. Most existing methods share common drawbacks; that is, spatial and frequency diversity cannot be considered at the same time or channel probe is expensive. In this paper, we propose a channel prediction scheme for backscatter networks. The scheme consists of two parts: the monitoring module, which uses the data of the acceleration sensor to monitor the movement of the node itself, and uses the link burstiness metric ß to monitor the burstiness caused by the environmental change, thereby determining that new data of channel quality are needed. The prediction module predicts the channel quality at the next moment using a prediction algorithm based on BP (back propagation) neural network. We implemented the scheme on readers. The experimental results show that the accuracy of channel prediction is high and the network goodput is improved.

Intelligent Management of Chemical Warehouses with RFID Systems.

At present, most chemical warehouses rely on human management, which is a time-consuming and laborious process. Therefore, it is very meaningful to use radio frequency identification (RFID) systems for the intelligent management of chemicals. Detecting the remaining amount of chemicals is an important process in the management of a chemical warehouse. It helps managers find the chemicals that are going to run out and replenish them in time. However, in a traditional chemical warehouse, managers usually inspect each chemical on the shelf in turn manually, which is a waste of time and labor. Although some solutions using RFID technology have been proposed, they are expensive and difficult to deploy in a real environment. In order to solve this problem, we propose an intelligent system called the RF-Detector in this paper, which combines robotics and RFID technology. An RFID reader and an antenna are installed on the robot, which achieves automatic scanning of the chemicals. The RF-Detector can achieve two functions: One function is to detect the remaining amount of chemicals using the changes in received signal strength indication (RSSI) and read rate, and the other is to locate chemicals using the phase curve, so that managers can quickly find the chemicals with an insufficient amount remaining. In this paper we implement the RF-Detector and evaluate its performance. The experimental results show that the RF-Detector achieves about 93% detection accuracy and 92% positioning accuracy for chemicals.

An effective way of J wave separation based on multilayer NMF.

J wave is getting more and more important in the clinical diagnosis as a new index of the electrocardiogram (ECG) of ventricular bipolar, but its signal often mixed in normal ST segment, using the traditional electrocardiograph, and diagnosed by experience cannot meet the practical requirements. Therefore, a new method of multilayer nonnegative matrix factorization (NMF) in this paper is put forward, taking the hump shape J wave, for example, which can extract the original J wave signal from the ST segment and analyze the accuracy of extraction, showing the characteristics of hump shape J wave from the aspects of frequency domain, power spectrum, and spectral type, providing the basis for clinical diagnosis and increasing the reliability of the diagnosis of J wave.