Deep Hierarchical Ensemble Model for Suicide Detection on Imbalanced Social Media Data

As a serious worldwide problem, suicide often causes huge and irreversible losses to families and society. Therefore, it is necessary to detect and help individuals with suicidal ideation in time. In recent years, the prosperous development of social media has provided new perspectives on suicide detection, but related research still faces some difficulties, such as data imbalance and expression implicitness. In this paper, we propose a Deep Hierarchical Ensemble model for Suicide Detection (DHE-SD) based on a hierarchical ensemble strategy, and construct a dataset based on Sina Weibo, which contains more than 550 thousand posts from 4521 users. To verify the effectiveness of the model, we also conduct experiments on a public Weibo dataset containing 7329 users’ posts. The proposed model achieves the best performance on both the constructed dataset and the public dataset. In addition, in order to make the model applicable to a wider population, we use the proposed sentence-level mask mechanism to delete user posts with strong suicidal ideation. Experiments show that the proposed model can still effectively identify social media users with suicidal ideation even when the performance of the baseline models decrease significantly.     

中药复杂组效关系的变结构神经网络辨识方法

针对中药复杂组效关系的辨识问题,研究了变结构多层前馈神经网络,推导出一种新型的变结构网络学习算法,成功地应用于中药川芎药效活性预测计算.该方法从一个规模较小的网络出发,当网络无法达到预定的学习精度时,自动增加隐含层神经元个数,并在原有学习结果的基础上确定新的网络参数,自适应地确定前馈神经网络结构,可用于处理复杂化学模式信息.计算机仿真实验结果表明,该方法能有效地确定多层前馈神经网络的最佳结构,提高网络学习效率和函数逼近精度,解决复杂非线性函数映射关系准确建模问题.     

Novel facile detection of persistent organic pollutants using highly sensitive gas sensor

Persistent organic pollutants (POPs) are greatly noxious chemicals in environment, and they can cumulate in organisms and transfer between different species. Therefore, it is significant to detect POPs for both environmental evaluation and further treatment. However, developing facile approach for the detection of POPs still remains a challenge so far. In this paper, we report an innovative method for facile detection of POPs using gas sensor for the first time. Porous SnO₂ nanostructures with a special tri-walled structure prepared via hydrothermal route and annealing process, were employed as gas-sensing materials. Through gas measurements, it was revealed that the as-fabricated gas sensor exhibited highly sensitive performance towards target POPs, including methoxychlor, mirex, p,p′-DDT, and aldrin. Moreover, we found that target POPs were distinguishable by extracting characteristics in kinetic curves of gas adsorption-desorption. As the presented detecting approach is facile without the requirements of complex operations, expensive and bulky instruments, it is expected that it would be developed as a promising method for the detection of POPs, and thereby showing its significance for environmental monitoring.     

Multi‐responses Methodology Applied in the Electroanalytical Determination of Hair Dye by Using Printed Carbon Electrode Modified with Graphene

This paper describes a rapid and sensitive method for determination of the hair dye Basic Blue 41 in wastewater samples using screen‐printed carbon electrodes modified with graphene (SPCE/Gr). The method is based on the reversible reduction of azo groups of the dye at potential of ?0.23 V/?0.26 V, where both the anodic and cathodic currents increased 1,300 % when compared to screen‐printed carbon (SPCE) and glassy carbon electrodes (GCE). The optimization of a square wave voltammetric method was performed by means of 2³ factorial design, Doehlert matrix and multi‐response assays, and the best parameters were: frequency (54.8 Hz), step potential (6 mV), pulse amplitude (43.7 mV) and pH 4.5. The analytical curve was constructed from 3.00×10^?8 to 2.01×10^?6 mol L^?1, with detection and quantification limits of 5.00×10^?9 and 1.70×10^?8 mol L^?1, respectively. The repeatability of the method evaluated for 10 consecutive measurements at concentrations of 1.70×10^?7 mol L^?1 and 1.70×10^?6 mol L^?1, showed relative standard deviation of 3.56 and 0.57 %, respectively. The sensor based in SPCE/Gr was successfully applied in wastewater samples collected from a drinking water treatment plant and validated by comparison with HPLC‐DAD method with good accuracy.     

用于教学的局域网共享虚拟综合测试系统

随着计算机技术和网络技术的迅猛发展,虚拟实验室和网络实验室已逐渐替代了传统模式的实验室.本文探讨了电子技术教学中虚拟实验室和网络实验室的建设,给出了系统功能分析、硬件平台解决方案和网络组建模式,并且实现了局域网共享的虚拟综合测试系统的各个功能,为电子技术实验室的建设提出了一种成本较低、功能可扩、形式新颖的途径.     

BREW实现机制深入分析

BREW（binary runtime environment for wireless）是目前流行的CDMA手机开发环境。从分析CDMA手机的系统结构入手,详细分析了BREW的层次结构,并尝试从公开资料中剖析BREW实现机制．最后给出了PEK（porting evaluation kit）测试原理。     

换号通业务的应用

换号通业务的应用主要目的是为当用户选择新的运营商之后,用短信自动通知自己的朋友们已更换了新的手机号码,免去要挨个给他们打电话,解决他们自己更换了新的号码的痛苦。此系统主要对网间信令进行采集提取来实现,此系统可以大大提高运营商形象。对换号通业务的结构、功能及其运用进行详细描述。     

基于IMS的下一代网络

IMS（IP多媒体子系统）是目前业界公认实现FMC（固定移动网络融合）的最佳途径,详细阐述了IMS的标准化进程、体系架构。并介绍了IMS的技术特点。     

Bifurcation of a three-unit neural network

Considered is a system of delay differential equations modeling a time-delayed connecting network of three neurons without self-feedback. Discussing the change of the number of eigenvalues with zero real part, we locate the boundary of the stability region and finally determine the largest stability region of trivial solution. We investigate the existence of bifurcation phenomena of codimension one/two of the trivial equilibrium by considering the intersections of some parameter curves, which, in the aτ-half parameter plane, correspond to zero root or pure imaginary roots. In particular, the equivariant bifurcation is studied because of the equivariance of the system. We also present numerical simulations to demonstrate the rich dynamical behavior near the equivariant Pitchfork-Hopf bifurcation points, Hopf-Hopf bifurcation points, and some higher codimension bifurcation points.     

A Hierarchical Scheme for Video-Based Person Re-identification Using Lightweight PCANet and Handcrafted LOMO Features

A two-level hierarchical scheme for video-based person re-identification (re-id) is presented, with the aim of learning a pedestrian appearance model through more complete walking cycle extraction. Specifically, given a video with consecutive frames, the objective of the first level is to detect the key frame with lightweight Convolutional neural network (CNN) of PCANet to reflect the summary of the video content. At the second level, on the basis of the detected key frame, the pedestrian walking cycle is extracted from the long video sequence. Moreover, local features of Local maximal occurrence (LOMO) of the walking cycle are extracted to represent the pedestrian' s appearance information. In contrast to the existing walking-cycle-based person re-id approaches, the proposed scheme relaxes the limit on step number for a walking cycle, thus making it flexible and less affected by noisy frames. Experiments are conducted on two benchmark datasets: PRID 2011 and iLIDS-VID. The experimental results demonstrate that our proposed scheme outperforms the six state-of-art video-based re-id methods, and is more robust to the severe video noises and variations in pose, lighting, and camera viewpoint.