Compression Helps Deep Learning in Image Classification

The impact of JPEG compression on deep learning (DL) in image classification is revisited. Given an underlying deep neural network (DNN) pre-trained with pristine ImageNet images, it is demonstrated that, if, for any original image, one can select, among its many JPEG compressed versions including its original version, a suitable version as an input to the underlying DNN, then the classification accuracy of the underlying DNN can be improved significantly while the size in bits of the selected input is, on average, reduced dramatically in comparison with the original image. This is in contrast to the conventional understanding that JPEG compression generally degrades the classification accuracy of DL. Specifically, for each original image, consider its 10 JPEG compressed versions with their quality factor (QF) values from {100,90,80,70,60,50,40,30,20,10}. Under the assumption that the ground truth label of the original image is known at the time of selecting an input, but unknown to the underlying DNN, we present a selector called Highest Rank Selector (HRS). It is shown that HRS is optimal in the sense of achieving the highest Top k accuracy on any set of images for any k among all possible selectors. When the underlying DNN is Inception V3 or ResNet-50 V2, HRS improves, on average, the Top 1 classification accuracy and Top 5 classification accuracy on the whole ImageNet validation dataset by 5.6% and 1.9%, respectively, while reducing the input size in bits dramatically—the compression ratio (CR) between the size of the original images and the size of the selected input images by HRS is 8 for the whole ImageNet validation dataset. When the ground truth label of the original image is unknown at the time of selection, we further propose a new convolutional neural network (CNN) topology which is based on the underlying DNN and takes the original image and its 10 JPEG compressed versions as 11 parallel inputs. It is demonstrated that the proposed new CNN topology, even when partially trained, can consistently improve the Top 1 accuracy of Inception V3 and ResNet-50 V2 by approximately 0.4% and the Top 5 accuracy of Inception V3 and ResNet-50 V2 by 0.32% and 0.2%, respectively. Other selectors without the knowledge of the ground truth label of the original image are also presented. They maintain the Top 1 accuracy, the Top 5 accuracy, or the Top 1 and Top 5 accuracy of the underlying DNN, while achieving CRs of 8.8, 3.3, and 3.1, respectively.     

Synchronization of networks with time-varying couplings

In this paper, we present a review of our recent works on complete synchro-nization analyses of networks of the coupled dynamical systems with time-varying cou-plings. The main approach is composed of algebraic graph theory and dynamic system method. More precisely, the Hajnal diameter of matrix sequence plays a key role in in-vestigating synchronization dynamics and the joint graph across time periods possessing spanning tree is a doorsill for time-varying topologies to reach synchronization. These techniques with proper modification count for diverse models of networks of the cou-pled systems, including discrete-time and continuous-time models, linear and nonlinear models, deterministic and stochastic time-variations. Alternatively, transverse stability analysis of general time-varying dynamic systems can be employed for synchronization study as a special case and proved to be equivalent to Hajnal diameter.     

乳腺癌易感基因蛋白质网络的构建与研究

本文从复杂网络理论出发,在分析原有乳腺癌易感基因数据的基础上,综合统计分析易感基因彼此之间的关联与乳腺癌疾病之间的关系,并以此构建乳腺癌致病基因蛋白质网络．通过计算和研究网络度,聚类系数等指标发现,此网络具有高度聚集性,即少数核心节点控制着整个网络结构的稳定性．这将为进一步研究和发现乳腺癌致病基因提供新的理论依据和方法．     

合作博弈视角下城市道路交通拥堵收费研究

城市道路交通设施作为准公用物品,其外部效应必然导致交通拥堵的发生,实施拥堵收费的目的则是使交通拥堵产生的外部成本内部化,确保城市道路资源得到高效配置,应用经济杠杆来调节交通需求,以缓解交通拥堵.本文应用合作博弈相关理论对城市道路拥堵网络问题进行了分析,从同一时刻各个路段的通勤者数目这一角度定义拥堵成本,重点证明了拥堵成本为凸函数的城市道路拥堵网络博弈存在非空的核,拥堵成本为凹函数的城市道路交通网络博弈虽不存在非空的核,但总是存在最优的树网络,最后,结合上述结论对城市道路拥堵收费进行讨论,从理论上对拥堵收费的合理性进行了说明,并提出了进一步研究的方向.     

基于网络均衡的电力市场排污权交易政策研究

本文构建了电力供应链网络均衡模型,网络中包含三级决策主体,分别是:发电厂、电力服务商和用电市场.在分析各级决策者行为的基础上,得到了基于变分不等式的均衡条件,研究了针对发电厂的排污权交易政策设计问题.研究发现:排污交易政策实施后,总排污量不会超过给定的排污权总量;发电厂清洁生产能力的差异对排污权交易政策影响显著.     

Complete set of periodic solutions of a discontinuous recurrence equation

A nonlinear three-term recurrence relation arising from seeking the steady states of a cellular neural network with bang‐bang control is studied. We show that each solution is periodic and its prime period can be determined by three of its consecutive terms. By means of this periodicity property, we may then solve the steady state problem which to our knowledge is not solved by other means.     

区域物流的技术网络效应研究

建立了一个基于信息技术网络效应的物流信息化需求模型,来说明信息化带来的技术网络效应是物流厂商加入信息网络的动力所在.并基于1995-2010年30个省、直辖市、自治区的面板数据,运用面板单位根和面板协整方法,证明了区域物流中技术网络效应的存在.     

出行量预测不确定下基于灵敏度分析的拥挤收费定价模型

拥挤收费是改善城市交通的有效手段.对拥挤收费定价的研究方法之一,就是针对固定的出行量进行收费设计.由于出行量预测不确定的因素,应针对长期出行量预测不确定的情况,利用灵敏度分析的方法,对拥挤收费定价的问题进行研究.首先研究了出行者出行的广义费用,然后考虑出行者的出行决策及出行量预测不确定的因素,给出一个拥挤收费定价模型,为交通管理者提供理论依据.