Search

Both classification rate and accuracy are crucial for the recyclable PET bottles, and the existing combination methods of SVM all simply use SVM as the unit classifier, ignoring the improvement of SVM’s classification performance in the training process of deep learning. A linear multi hierarchical deep structure based on Support Vector Machine (SVM) is proposed to cover this problem. A novel definition of the input matrix in each layer enhances the optimization of Lagrange multipliers in Sequential Minimal Optimization (SMO) algorithm, thus the datapoint in maximum interval of SVM hyperplane could be recognized, improving the classification performance of SVM classifier in this layer. The loss function defined in this paper could control the depth of Linear Multi Hierarchical SVM (LMHSVM), the generalization parameters are added in the loss function and the input matrix to enhance the generalization performance of LMHSVM. The process of creating Bottle dataset by Histogram of Oriented Gradient (HOG) and Principal Component Analysis (PCA) is introduced meanwhile, reducing the data size of bottles. Experiments are conducted on LMHSVM and multiple typical classification algorithms with Bottle dataset and UCI datasets, the results indicated that LMHSVM has excellent classification performances than FNN classifier, LIBSVM (Gaussian) and GFS-AdaBoost-C in KEEL.

In order to research the multi-year spatial-temporal distribution of Harmful Algal Bloom (HAB) in the South Yellow Sea of China, NDVI method was used to extract HAB from MODIS images after Cloud removal by a comprehensive threshold method explored in this paper. Then, the growth law and spatial-temporal distribution of HAB are analyzed by the method of standard deviation ellipse and superposition analysis. It shows that the periphery of the radial sand ridge area off the coast of Jiangsu Province is the main birthplace of the HAB. Entering the breeding period, the northward drift speed as well as the diffusion speed of HAB accelerates. Until late June, it invades the coast of Shandong Province. In the early stage of HAB growth, preventing the spreading along the northeast-southwest direction will effectively restrain the HAB.

Early detection of influenza-like symptoms can prevent widespread flu viruses and enable timely treatments, particularly in the post-pandemic era. Mobile sensing leverages an increasingly diverse set of embedded sensors to capture fine-grained information of human behaviors and ambient contexts, and can serve as a promising solution for influenza-like symptom recognition. Traditionally, handcrafted and high level features of mobile sensing data are extracted by manual feature engineering and convolutional/recurrent neural network respectively. In this work, we apply graph representation to encode the dynamics of state transitions and internal dependencies in human behaviors, leverage graph embeddings to automatically extract the topological and spatial features from graph inputs, and propose an end-to-end graph neural network (GNN) model with multi-channel mobile sensing input for influenzalike symptom recognition based on people's daily mobility, social interactions, and physical activities. Using data generated from 448 participants, we show that GNN with GraphSAGE convolutional layers significantly outperforms baseline models with handcrafted features. Furthermore, we use GNN interpretability method to generate insights (e.g., important nodes and graph structures) about the importance of mobile sensing for recognizing Influenza-like symptoms. To the best of our knowledge, this is the first work that applies graph representation and graph neural network on mobile sensing data for graph-based human behavior modeling and health symptoms prediction.

Smartphones can collect millions of data points from each of its users daily, contributing to a significant change in how the healthcare community approaches health monitoring. This paper provides a framework for how smartphone sensor data can be collected, cleaned, stored, and modeled to effectively predict human states as a step towards health monitoring. To develop robust contextual models, a three-week study was conducted to collect data through a mobile crowdsensing application named Sensus. In this study, participants used multiple sensing strategies, ranging from infrequent sampling to continuous sampling, to determine the effect each has on data integrity and battery life. For a future study, a dynamic data collection strategy was developed that uses a machine learning model trained on existing data collected from 220 participants to forecast when a smartphone will be active and trigger sensor sampling accordingly. Results of this study include 1) extraction of model features that deliver maximized data quality with minimized battery consumption as compared to pre-existing baseline models, 2) implementation of context-driven modeling of user smartphone data on user's contextual environment, and 3) customization of a time-series database for optimized data queries used in metadata visualizations. The adaptive sensing models produced could be used in future large population studies that efficiently examine patterns of behavior in multiple individuals over extended periods to identify disease indicators present in an average user’s daily life.

BackgroundIn December 2019, human infection with a novel coronavirus, known as SARS-CoV-2, was identified in Wuhan, China. The mortality of critical illness was high in Wuhan. Information about critically ill patients with SARS-CoV-2 infection outside of Wuhan is scarce. We aimed to provide the clinical features, treatment, and prognosis of the critically ill patients with SARS-CoV-2 infection in Guangdong Province.MethodsIn this multi-centered, retrospective, observational study, we enrolled critically ill patients with SARS-CoV-2 pneumonia who were admitted to the intensive care unit (ICU) in Guangdong Province. Demographic data, symptoms, laboratory findings, comorbidities, treatments, and prognosis were collected. Data were compared between patients with and without intubation.ResultsForty-five critically ill patients with SARS-CoV-2 pneumonia were identified in 7 ICUs in Guangdong Province. The mean age was 56.7 years, and 29 patients (64.4%) were men. The most common symptoms at the onset of illness were high fever and cough. Majority of patients presented with lymphopenia and elevated lactate dehydrogenase. Treatment with antiviral drugs was initiated in all the patients. Thirty-seven patients (82.2%) had developed acute respiratory distress syndrome, and 13 (28.9%) septic shock. A total of 20 (44.4%) patients required intubation and 9 (20%) required extracorporeal membrane oxygenation. As of February 28th 2020, only one patient (2.2%) had died and half of them had discharged of ICU.ConclusionsInfection with SARS-CoV-2 in critical illness is characterized by fever, lymphopenia, acute respiratory failure and multiple organ dysfunction. Compared with critically ill patients infected with SARS-CoV-2 in Wuhan, the mortality of critically ill patients in Guangdong Province was relatively low. These data provide some general understandings and experience for the critical patients with SARS-CoV-2 outside of Wuhan.

Continuous passive sensing using smartphone embedded sensors can drain the battery quickly, interrupting other usages of the device. In order to improve the energy efficiency in continuous mobile sensing applications, we propose a new adaptive sensing framework using reinforcement learning to optimize the sensing timing. We model our adaptive sensing problem as a Markov Decision Process and dynamically change the sensing timing of targeted sensor(s) so that they are only operating in desired contexts (e.g. collect accelerometer data only when the phone is moving). Using accelerometer data continuously collected from 220 participants for over two weeks, we show that our approach is able to save the energy while attaining high accuracy and data coverage. Specifically, our strategy attains energy saving of 62.4 % at an accuracy of 80.9% and data coverage of 67.4%, which outperforms two baseline strategies, including a random strategy and a strategy using learning automata technique.

Despite the proliferation of mobile interventions that are delivered through smartphones, and their potential impact on promoting mental health in chronic health populations, little research has examined how to leverage the advanced technological capabilities of smartphones to also monitor response to app-based interventions. Current methods used to evaluate response to digital interventions rely on static and retrospective self-report measures to infer crucial behavioral and affective patterns, which provide little contextual information and limits generalizability. Importantly, this approach can also increase burden among chronic health populations that are already experiencing a heavy treatment load. Using data collected from 7 recently diagnosed breast cancer patients undergoing active cancer treatment (average time from initial diagnosis to study enrollment is 13 days), we propose a framework for integrating self-report surveys and fine-grained mobile sensing data. Preliminary results demonstrate the feasibility and utility of this framework to reduce burden and improve detection of mood in response to an app-based intervention among chronic health populations.

With the development of era, innovative thinking crowds into human’s minds. Thus, innovative thinking becomes increasing essential in working field. In order to explore technology of artificial intelligence, we developed a team studying the law of human’s minds. In combination with Extenics theory and mind mapping, we find a new way for innovative thinking that thoughts are printed into a mind mapping with different shapes and colors. Besides, we also analyze some way of innovation and design a software model to verify our way for innovation and study further.

As smartphones become increasingly intimate and continuous companions, many opportunities are arising in human behavior sensing, modeling, and coaching. This position paper explores opportunities and challenges for mobile-based deployment of behavior change interventions. We suggest the adoption and extension of reinforcement learning for addressing these challenges, and we identify several key areas of future research that, on the basis of prior results, appear ripe for extending the benefits of reinforcement learning to human behavior change. These areas include stronger grounding of states in theories of human behavior, RL agent adaptation and decomposition, cooperative reinforcement learning, and in situ evaluation.

Sensor-based activity recognition seeks to provide higher-level knowledge about human activities from multiple sensors such as accelerometer and gyroscope. Thanks to growing ubiquity of sensor-rich smartphones and wearable devices, activity recognition research has made tremendous progress in recent years. Many sensors, such as motion sensors and cameras, have been previously used for this task. In this paper, we present the first work to recognize human activities solely from photoplethysmography (PPG) data. PPG sensors use a light-based technology to sense the rate of blood flow as controlled by the heart's pumping action. Although they are not originally intended to sense body motions and gestures, in this paper, we propose a novel method to extract meaningful features from the PPG to predict human activities. We exploit PPG signals' susceptibility to corruption by noise introduced by motion artifact and extract, as opposed to discard, the motion artifact signals combined with cardiac and respiratory signals to predict the types of activities performed by users. We combine convolutional and recurrent neural networks to predict different types of daily activities (e.g., walking, running, jumping) from the raw PPG signal. Results using data generated by wrist-worn smartwatches of 12 participants demonstrate the feasibility of our approach at predicting five types of activities (standing, walking, jogging, jumping, and sitting), and highlight new insights about how to use PPG sensors for human activity recognition. Results also highlight the importance of extracting motion artifact signals to understand human behaviors.

A stiffened cylindrical shell is normally used in refuge chambers of a coal mine. Based on the method of application and shape characteristics of a refuge chamber, we simplified its shell as an orthotropic cylinder. The basic buckling equation of the stiffened cylindrical shell under uniform axial compression was deduced by using a Donnell function. The factors affecting its buckling capacity were studied by theoretical analysis and numerical calculations. The results reveal that the torsional rigidity of the longitudinal stiffener had little effect on the buckling capacity of the shell and that the critical load of an externally stiffened cylindrical shell is higher than that of an internally stiffened cylindrical shell. Keywords: Refuge chamber, Buckling, Axial compression, Stiffened cylindrical shell

This paper presents a microwave bandpass filter using a triplet configuration to realize cross coupling. A structure called quarter-mode substrate integrated waveguide (QMSIW) is applied in these resonators to achieve the planar form. QMSIW is an isosceles right triangular microstrip patch loaded with an array of metallic via-holes along its hypotenuse which can be equivalent as an electric wall and the other two edges are equal to magnetic walls. The filter was simulated and fabricated at the center of 2.35GHz with a bandwidth of 330 MHz and good agreement was achieved between the simulated results and those measured.

Type 2 diabetes, which is a complex metabolic disease influenced by genetic and environment, has become a worldwide problem. Previous published results focused on genetic components through genome-wide association studies that just interpret this disease to some extent. Recently, two research groups published metagenome-wide association studies (MGWAS) result that found meta-biomarkers related with type 2 diabetes. However, One key problem of analyzing genomic data is that how to deal with the ultra-high dimensionality of features. From a statistical viewpoint it is challenging to filter true factors in high dimensional data. Various methods and techniques have been proposed on this issue, which can only achieve limited prediction performance and poor interpretability. New statistical procedure with higher performance and clear interpretability is appealing in analyzing high dimensional data. To address this problem, we apply an excellent statistical variable selection procedure called iterative sure independence screening to gene profiles that obtained from metagenome sequencing, and 48/24 meta-markers were selected in Chinese/European cohorts as predictors with 0.97/0.99 accuracy in AUC (area under the curve), which showed a better performance than other model selection methods, respectively. These results demonstrate the power and utility of data mining technologies within the large-scale and ultra-high dimensional genomic-related dataset for diagnostic and predictive markers identifying.

The stiffened rectangular plate was usually adopted in the blast airtight doors. In order to improve the buckling capacity of stiffened rectangular plate under uniform normal compression, the optimization model of stiffened rectangular plate was set up based on APDL and ANSYS commands, and the sequential linear programming method was executed to optimize the thickness of plate and the sizes of stiffeners. Moreover, we compared the mechanical property of the optimized stiffened rectangular plate with the theoretical value of no-stiffener plate with equal volume, and obtained the reasonable stiffener distribution based on the optimization results of five different longitudinal and transverse stiffener patterns. The results showed that the buckling capacity of stiffened rectangular plate under uniform normal compression could be improved by approximately 50% on the condition of reasonable stiffeners distribution.

Long chain series resonance cavity is suitable for transferring slow optical wave, which can be served as the basic device for optical storage technology. Micro-ring resonator is one kind of such a long chain structure, which is considered to be the basic component of optical integrated circuit and optical computer in the future. The discrete energy level has the potential to distinguish digital optical data. The optical delay characteristics make such a device possible to store the information for some time. The advantage of this device is that it has the potential to construct an optical storage device in small geometrical dimension and could use mature semiconductor manufacture capability to lower the design and manufacturing expenses. Many experimental results have proved a lot of material and geometrical coefficients are very important for such an optical delay device. New theory method is needed to calculate the periodical energy transfer and time delay characteristics, which can be compared with experimental result. The Bloch FDTD is presented for analysis of such a new optical device, based on the optical Bloch energy band theory. The energy band characteristics of micro-ring periodical optical waveguide device is discussed used that analytical method. This precise calculated method could be served as a useful tool for design the structure of such resonance cavity to achieve desired slow optical wave transfer performance. 2013 SPIE.