Distributed patching for mobile wireless sensor networks

Mobile wireless sensor networks (MWSNs), the continuous movement of sensor nodes, may cause complete disconnection of the network or at best a part of it. The design of such networks should guarantee that all sensor nodes at all times have a path to the sink node(s). Prolonging the lifetimes of the MWSNs is a crucial design issue but should not be at the expense of other essential functions such as connectivity. In this paper, we propose an energy efficient distributed framework for connectivity maintenance of MWSNs. In the proposed framework, sensor nodes of the MWSNs schedule and control their radio frequency (RF) modules based on dynamic coordinated reconstruction mechanism, some senor nodes may lose their connectivity with the network due to mobility, depletion of energy and/or incurred faults. Two protocols are developed to patch up the disconnection of the MWSNs. The first protocol reestablishes the network connection consuming far less energy than state-of-the-art alternatives. However, it is capable of reestablishing the connection when no more than 20% of the MWSN backbone nodes lose connection concurrently. The second protocol extends this limit to operate when up to 35% of the MWSN backbone nodes lose connection simultaneously.     

Optimal pixel aspect ratio for enhanced 3D TV visualization

In multiview 3D TV, a pair of corresponding pixels in adjacent 2D views contributes to the reconstruction of voxels (3D pixels) in the 3D scene. We analyze this reconstruction process and determine the optimal pixel aspect ratio based on which the estimated object position can be improved given specific imaging or viewing configurations and constraints. By applying mathematical modeling, we deduce the optimal solutions for two general stereo configurations: parallel and with vergence. We theoretically show that for a given total resolution a finer horizontal resolution, compared to the usual uniform pixel distribution, in general, provides a better 3D visual experience for both configurations. The optimal value may vary depending on different configuration parameter values. We validate our theoretical results by conducting subjective studies using a set of simulated non-square discretized red–blue stereo pairs and show that human observers indeed have a better 3D viewing experience with an optimized vs. a non-optimized representation of 3D-models.     

MDS-based segmentation model for the fusion of contour and texture cues in natural images

In this paper, we present an original image segmentation model based on a preliminary spatially adaptive non-linear data dimensionality reduction step integrating contour and texture cues. This new dimensionality reduction model aims at converting an input texture image into a noisy color image in order to greatly simplify its subsequent segmentation. In this latter de-texturing model, the (spatially adaptive) non-local constraints based on edge and contour cues allows us to efficiently regularize the reduced data (or the resulting de-textured color image) and to efficiently combine inhomogeneous region and edge based features in a data fusion/reduction model used as pre-processing step for a final segmentation task. In addition, a set of color/texture and edge-based adaptive spatial continuity constraints is imposed during the segmentation step. These improvements lead to an appealing and powerful two-step adaptive segmentation model, integrating contour and texture cues. Extensive experimental evaluation on the Berkeley image segmentation database demonstrates the efficiency of this hybrid segmentation model in terms of classification accuracy of pairwise pixels in the resulting segmentation map and in the precision–recall framework widespread used for evaluating contour detectors.     

An efficient and security dynamic identity based authentication protocol for multi-server architecture using smart cards

Generally, if a user wants to use numerous different network services, he/she must register himself/herself to every service providing server. It is extremely hard for users to remember these different identities and passwords. In order to resolve this problem, various multi-server authentication protocols have been proposed. Recently, Sood et al. analyzed Hsiang and Shih's multi-server authentication protocol and proposed an improved dynamic identity based authentication protocol for multi-server architecture. They claimed that their protocol provides user's anonymity, mutual authentication, the session key agreement and can resist several kinds of attacks. However, through careful analysis, we find that Sood et al.'s protocol is still vulnerable to leak-of-verifier attack, stolen smart card attack and impersonation attack. Besides, since there is no way for the control server CS to know the real identity of the user, the authentication and session key agreement phase of Sood et al.'s protocol is incorrect. We propose an efficient and security dynamic identity based authentication protocol for multi-server architecture that removes the aforementioned weaknesses. The proposed protocol is extremely suitable for use in distributed multi-server architecture since it provides user's anonymity, mutual authentication, efficient, and security.     

Incorporation of a Regularization Term to Control Negative Correlation in Mixture of Experts

Combining accurate neural networks (NN) in the ensemble with negative error correlation greatly improves the generalization ability. Mixture of experts (ME) is a popular combining method which employs special error function for the simultaneous training of NN experts to produce negatively correlated NN experts. Although ME can produce negatively correlated experts, it does not include a control parameter like negative correlation learning (NCL) method to adjust this parameter explicitly. In this study, an approach is proposed to introduce this advantage of NCL into the training algorithm of ME, i.e., mixture of negatively correlated experts (MNCE). In this proposed method, the capability of a control parameter for NCL is incorporated in the error function of ME, which enables its training algorithm to establish better balance in bias-variance-covariance trade-off and thus improves the generalization ability. The proposed hybrid ensemble method, MNCE, is compared with their constituent methods, ME and NCL, in solving several benchmark problems. The experimental results show that our proposed ensemble method significantly improves the performance over the original ensemble methods.     

Supply chain trust diagnosis (SCTD) using inductive case-based reasoning ensemble (ICBRE): The case of general competence trust diagnosis

General competence trust among supply chain partners, referring to the trust that a partner holds the general ability of fulfilling contracts, is a critical factor to ensure effective cooperation in a supply chain, especially in the current financial crisis. The method of supply chain trust diagnosis (SCTD) is to evaluate whether or not a partner holds such competence. This research devotes to an early investigation on diagnosing competence trust of supply chain with the method of inductive case-based reasoning ensemble (ICBRE). The so-called supply chain trust diagnosis with inductive case-based reasoning ensemble consists of five levels, that is, information level, the level of ratios of general competence states, the level of inductive case-based reasoning, ensemble level, and diagnosis result level. Knowledge for diagnosing competence trust, which composes of a case base, is hidden in data represented by ratios of general competence states. Inductive approach is combined with randomness to construct diverse and good member methods of inductive case-based reasoning. Finally, simple voting is used to integrate outputs of member inductive case-based reasoning methods in order to produce the final diagnosis on whether or not a partner holds the general ability of fulfilling contracts. We statistically validated results of the method of supply chain trust diagnosis with inductive case-based reasoning ensemble by comparing them with those of multivariate discriminant analysis, logistic regression, single Euclidean case-based reasoning, and single inductive case-based reasoning. The results indicate that the method of supply chain trust diagnosis with inductive case-based reasoning ensemble significantly improves predictive capability of case-based reasoning in this problem and outperforms all the comparative models by group decision of several decision-making agents and non-strict assumptions like statistical methods.     

多噪声环境下声音的身份鉴定技术研究与仿真

研究多噪声背景下基于声音的身份准确识别问题。当个体声音混淆在其它声音背景下的时候,个体独特的语音特征由于混有噪声特征,导致自身特征发生退化。造成的传统语音特征进行识别的方法,由于无法克服"噪声"干扰下语音特征的退化,造成识别准确性不高。提出了根据语音特征概率决策的混合语音识别方法。采用对混合语音进行独立的有效特征检测,根据特征概率决策算法将语音特征进行归属概率识别,并通过特征归属度计算完成身份识别,克服由于语音特征混合,造成语音特征退化造成的识别不准问题。实验结果表明,提出的方法能够对混合的语音特征进行有效的识别,提高了识别的准确度。     

基于改进神经网络的湖泊水质污染检测法研究

研究采用图像对湖泊水质污染检测的问题,由于水面较大,像素信息量多,造成检测时间长,速度慢。针对图像的污水检测的水域面积较大,造成检测耗费的时间比较长,最终导致湖泊水质污染检测存在较大滞后且准确性差的问题。提出一种改进神经网络的湖泊水质污染检测方式,首先利用神经网络数学模型对图像相关数据进行二进制编码,并对编码后的数据进行压缩处理,计算输出数据的差异系数,最后利用周期性数据压缩补偿算法对数据中的误差进行补偿,提高了湖泊水质污染检测的速度。实验证明,改进的检测方式能够提高湖泊水质污染检测速度,提高了准确性,取得了令人满意的效果。     

传感器网络中的局部异常检测算法

找到异常数据对于传感器网络来说非常重要。本文通过一个例子首先提出了局部异常的概念。与传统异常不同,局部异常仅取决于节点及其周围节点的取值。我们给出了局部异常的形式化定义,并首先提出了解决局部异常的Nave算法,由于其能耗过大,又提出了分布式的解决方案DLODA。DLODA将网络分成多个区域,每个区域选择一个簇头,簇头能够在网内提前算出部分查询结果,并过滤掉不会成为查询结果的数据,以节约能量开销。最后从能量消耗和响应时间两个方面对DLODA的性能进行了评估,实验显示DLODA具有良好性能。