Neural Network-Based Performance Index Model for Enterprise Goals Simulation and Forecasting

Enterprise Information System management has become an increasingly vital factor for many firms. Several organizations have encountered problems when attempting to evaluate organizational performance. Measurement of performance metrics is a key challenge for a huge number of firms. In order to preserve relevance and adaptability in competitive markets, it has become essential to respond proactively to complex events through informed decision-making that is supported by technology. Therefore, the objective of this study was to apply neural networks to the modeling, simulation, and forecasting of the effects of the performance indicators of Enterprise Information Systems on the achievement of corporate objectives and value creation. A set of quantifiable and sizeable conditionally independent associations were derived using a simplified joint probability distribution technique. Bayesian Neural Networks were utilized to describe the link between random variables (features) and to concisely and easily specify the joint probability distribution. The research demonstrated that Bayesian networks could effectively explore complex logical linkages by employing probability to represent uncertainty and probabilistic rules;and by applying impact models from Bayesian taxonomies to achieve learning and reasoning processes.

Research of Enterprise Resource Management Supporting Networked Manufacturing

The nature of networked manufacturing and agile manufacturing is to recognize enterprise resources timely and accurately. This paper mainly discusses an enterprise resource model method and the construction process. Furthermore, the system frameworks of software and application are put forward to realize various enterprise resources management based on a resource business process. Thus, we ensure the integration and sharing of enterprise resources for the requirement of networked manufacturing.

Identification of the Credit Guarantee Network of Steel Trade Enterprises in China

The risk points in the credit guarantee network of steel trade enterprises were identified by using the network analysis method in this paper. Firstly, the formation and operation mechanism of steel trade credit guarantee network was analyzed.Secondly,a guarantee network was established to analyze the related network structure indexes based on the mutual guarantee data of 83 enterprises in a steel trade market. These indexes included centrality,honest broker,and structural hole. The results suggest that network analysis method can be used to find out the risk points of the guarantee network. Additionally,some recommendations are brought forth to reduce or prevent future crises.

Manufacturing enterprise collaboration network:An empirical research and evolutionary model

With the increasingly fierce market competition,manufacturing enterprises have to continuously improve their competitiveness through their collaboration and labor division with each other,i.e.forming manufacturing enterprise collaborative network(MECN)through their collaboration and labor division is an effective guarantee for obtaining competitive advantages.To explore the topology and evolutionary process of MECN,in this paper we investigate an empirical MECN from the viewpoint of complex network theory,and construct an evolutionary model to reproduce the topological properties found in the empirical network.Firstly,large-size empirical data related to the automotive industry are collected to construct an MECN.Topological analysis indicates that the MECN is not a scale-free network,but a small-world network with disassortativity.Small-world property indicates that the enterprises can respond quickly to the market,but disassortativity shows the risk spreading is fast and the coordinated operation is difficult.Then,an evolutionary model based on fitness preferential attachment and entropy-TOPSIS is proposed to capture the features of MECN.Besides,the evolutionary model is compared with a degree-based model in which only node degree is taken into consideration.The simulation results show the proposed evolutionary model can reproduce a number of critical topological properties of empirical MECN,while the degree-based model does not,which validates the effectiveness of the proposed evolutionary model.

A routing algorithm based on clusters and balanced use of energy for wireless sensor networks

In a sensor network, data collected by different sensors are often correlated because they are observations of related phenomena. Efficient sensor data fusion is one of the most important issues in building real sensor networks. To balance energy cost, how to select a cluster head is a key problem that must be addressed. In this paper, we use a compression-centric data collection algorithm for use in wireless sensor networks. Also, we propose a balanced cluster head selection algorithm in each cluster. Simulation results are used to investigate the performance of the algorithm. Compared to the exhaustive search solutions, the proposed algorithm shows a significant improvement in power consumption.

Relationships and Evolving Networks of Rural Manufacturing Clusters: A Case Study in Yucheng County, Henan Province of China

The evolution of networks in rural industrial clusters,in particular in the context of China has been paid more attention to in the world.Applying the theory and techniques of social network analysis (SNA),this study is with particular regard to the business network relationships and their evolutionary dynamics of steel measuring tape manufacturing clustered in Nanzhuang Village,Yucheng County of Henan Province,China,which is important for better understanding the industrial and regional development in less developed rural areas.From data collected by comprehensive questionnaire survey in 2002 and mass interviews with 60 enterprises and assembling families and several government authorities in 2002,2003,2004,2005 and 2008,four types of networks are identified: spin-off,consulting,communication and cooperative.The characteristic of these networks is outlined in detail.Compared with the high-tech clusters of typical developed areas,the networks that have evolved in traditional manufacturing clusters are more affected by emotive linkages.The cluster networks are shown to exhibit a polycentric hierarchical structure.The family relationships are the dominate spin-off channels of enterprises,while the supply and demand relationships and the mobility of the skilled workers are also important paths of network learning,and the cooperation relationships are comparatively stable.Besides the root enterprises,the middle-sized enterprises are comparatively more active than small-sized enterprises,and the intermediary agencies and the service institutions act as bridges of the inter-enterprises cooperation.By analysis of the structure of networks and the interactions between the networks,the four stages of network evolution are also identified.The four stages are dominated by the family networks,the internal division production networks,the local innovation networks and the global supply networks respectively,and they play different roles in cluster development.

Artificial neural network potential for gold clusters

In cluster science, it is challenging to identify the ground state structures(GSS) of gold(Au) clusters. Among different search approaches, first-principles method based on density functional theory(DFT) is the most reliable one with high precision. However, as the cluster size increases, it requires more expensive computational cost and becomes impracticable.In this paper, we have developed an artificial neural network(ANN) potential for Au clusters, which is trained to the DFT binding energies and forces of 9000 Au N clusters(11 ≤ N ≤ 100). The root mean square errors of energy and force are 13.4 meV/atom and 0.4 eV/A, respectively. We demonstrate that the ANN potential has the capacity to differentiate the energy level of Au clusters and their isomers and highlight the need to further improve the accuracy. Given its excellent transferability, we emphasis that ANN potential is a promising tool to breakthrough computational bottleneck of DFT method and effectively accelerate the pre-screening of Au clusters’ GSS.

Assessment for Production and Operation Ability of Medium and Small-sized Enterprises Based on Neural Network

In order to improve production and operation ability of medium and small-sized enterprises, an assessment-index system of production and operation ability was proposed, and a corresponding assessment model was established based on BP neural network. The conjunction weights of the neural network were continuously modified from output layer to input layer in the process of neural network training to reduce the errors between the anticipated and actual outputs. The results from an example show that this method is reliable and feasible. The production and operation ability of an enterprise with assessed result of 0.833 is fairly powerful, and that with assessed result of 0.644 is average.

Construction Approaches of Enterprise Innovation Network from the Perspective of Social Network

As an important means for enterprises to promote technological progress,product development and service level,innovation has an absolute role in enhancing enterprises'innovation strength and market strength.In the context of frequent and rapid product replacement and shortened technological innovation cycle in modern society,through the embedding of social networks,forming platforms for higher education institutions,governments,capital markets,research institutions and intermediary links to promote the integration of innovation and capital development and make the most of every resource has become an important way.From the perspective of social network,the methods and necessary approaches for the establishment of enterprise innovation network are studied in this article.

Research on Tracing Evaluation System in Virtual Enterprise Based on Neural Network

The tracing evaluation index system was designed to be used in virtual enterprise and established neural network trace evaluation model. As a result, it was more simple and nicer than the traditional method, so it had wider application foreground.

Study on the comprehensive advantage evaluation method of high-tech enterprises based on RBF artificial neural network

This paper designs an intelligent evaluation approach using a Radial Basis Function (RBF) Artificial Neural Network. We based our approach on establishing a comprehensive advantage evaluating index system that offers scientific substance for creating a development plan and the strategic management of high-tech industry and regional clusters of high-tech enterprises. Furthermore, this paper selects some typical high-tech enterprises’ data to make comprehensive training on the network system. Meanwhile, the paper chooses some enterprises as testing samples to test the method, the result of which proves that this method is truly effective. The research of this paper provides a comprehensive advantage evaluating and managing method for high-tech enterprise.

The Strategy of Industrial Clusters to Deal with Disruptive Innovation

Disruptive innovation may be a fatal threat to industrial clusters, or it may be a major development opportunity. The key lies in how industrial clusters respond to disruptive innovation. The main obstacles to the development of disruptive innovation in industrial clusters are lock-in and cluster inertia, which originate from the negative effects of cluster system isomorphism. In order to break through the development barriers, industrial clusters need to adopt a targeted overall response strategy, including adopting bottom-up local subversive innovation policies, introducing external knowledge, encouraging spin-off entrepreneurial enterprises, and encouraging alliances and cooperation between incumbent enterprises and entrepreneurial enterprises, etc.

Attributes-based person re-identification via CNNs with coupled clusters loss

Person re-identification(re-id)involves matching a person across nonoverlapping views,with different poses,illuminations and conditions.Visual attributes are understandable semantic information to help improve the issues including illumination changes,viewpoint variations and occlusions.This paper proposes an end-to-end framework of deep learning for attribute-based person re-id.In the feature representation stage of framework,the improved convolutional neural network(CNN)model is designed to leverage the information contained in automatically detected attributes and learned low-dimensional CNN features.Moreover,an attribute classifier is trained on separate data and includes its responses into the training process of our person re-id model.The coupled clusters loss function is used in the training stage of the framework,which enhances the discriminability of both types of features.The combined features are mapped into the Euclidean space.The L2 distance can be used to calculate the distance between any two pedestrians to determine whether they are the same.Extensive experiments validate the superiority and advantages of our proposed framework over state-of-the-art competitors on contemporary challenging person re-id datasets.

Research and Implementation of the Enterprise Evaluation Based on a Fusion Clustering Model of AHP-FCM

Traditional clustering method is easy to slow convergence speed because of high data dimension and setting random initial clustering center. To improve these problems, a novel method combining subtractive clustering with fuzzy C-means( FCM)clustering will be advanced. In the method, the initial cluster number and cluster center can be obtained using subtractive clustering. On this basis,clustering result will be further optimized with FCM. In addition,the data dimension will be reduced through the analytic hierarchy process( AHP) before clustering calculating.In order to verify the effectiveness of fusion algorithm,an example about enterprise credit evaluation will be carried out. The results show that the fusion clustering algorithm is suitable for classifying high-dimension data,and the algorithm also does well in running up processing speed and improving visibility of result. So the method is suitable to promote the use.

Multiple k-hop clusters based routing scheme to preserve source-location privacy in WSNs

Privacy is becoming one of the most notable challenges threatening wireless sensor networks(WSNs).Adversaries may use RF(radio frequency) localization techniques to perform hop-by-hop trace back to the source sensor's location.A multiple k-hop clusters based routing strategy(MHCR) is proposed to preserve source-location privacy as well as enhance energy efficiency for WSNs.Owing to the inherent characteristics of intra-cluster data aggregation,each sensor of the interference clusters is able to act as a fake source to confuse the adversary.Moreover,dummy traffic could be filtered efficiently by the cluster heads during the data aggregation,ensuring no energy consumption be burdened in the hotspot of the network.Through careful analysis and calculation on the distribution and the number of interference clusters,energy efficiency is significantly enhanced without reducing the network lifetime.Finally,the security and delay performance of MHCR scheme are theoretically analyzed.Extensive analysis and simulation results demonstrate that MHCR scheme can improve both the location privacy security and energy efficiency markedly,especially in large-scale WSNs.

Estimating the number of data clusters via the contrast statistic

A new method (the Contrast statistic) for estimating the number of clusters in a set of data is proposed. The technique uses the output of self-organising map clustering algorithm, comparing the change in dependency of “Contrast” value upon clusters number to that expected under a uniform distribution. A simulation study shows that the Contrast statistic can be used successfully either, when variables describing the object in a multi-dimensional space are independent (ideal objects) or dependent (real biological objects).