• A holistic evaluation-taliem-ir

    A holistic evaluation of smart city performance in the context of China

    تومان

    Development of smart city has been increasingly accepted as a new technology-based solution to  itigate urban diseases. The Chinese government has been devoting good efforts to the promotion of smart city through introducing a series of policies. However, policies may have limited effectiveness in application if they do not respond to the practice. There is little study examining what results have been achieved in practice by applying policy measures. This study presents a holistic evaluation of smart city performance in the context of China. The evaluation indicators in this study are selected by applying a hybrid research methodology including literature review and semi structured interviews. Indicator data are collected from 44 sample smart cities. The evaluation was conducted by applying Entropy method and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) technique collectively. This study highlights that the overall smart city performance in China is at a relatively low level. There is also a significant unbalance in performance between five smart city dimensions including smart infrastructure, governance, people, economy and environment. The smart performance between cities varies significantly since cities implement smart city programs in different ways. These differences impede experience sharing between cities. Actions have been recommended in this study for promoting further development of smart city in the context of China, such as increasing the investment on smart infrastructure, providing training programs, and establishing evaluation mechanism.

  • A Neural Network Based-taliem-ir

    A Neural Network Based Expert System for the Diagnosis of Diabetes Mellitus

    تومان

    Diabetes is a disease in which the blood glucose, or blood sugar levels in the body are too high. The damage caused by diabetes can be very severe and even more pronounced in pregnant women due to the tendency of transmitting the hereditary disease to the next generation. Expert systems are now used in medical diagnosis of diseases in patients so as to detect the ailment and help in providing a solution to it. This research developed and trained a neural network model for the diagnosis of diabetes mellitus in pregnant women. The model is a four-layer feed forward network, trained using back-propagation and Bayesian Regulation algorithm. The input layer has 8 neurons, two hidden layers have 10 neurons each, and the output layer has one neuron which is the diagnosis result. The developed model was also incorporated into a web-based application to facilitate its use. Validation by regression shows that the trained network is over 92% accurate.

  • A review of information system integration-taliem-ir

    A review of information system integration in mergers and acquisitions

    تومان

    For three decades, research has investigated the role of information systems integration (ISI) in mergers and acquisitions (M&As). This research has improved our understanding of the M&A IS challenges and their solutions. However, consolidation and integration across the research is limited. To redress this omission, we review 70 articles published between 1989 and 2016. To do this, we adopt and extend the methodology developed by Lacity and her colleagues to review the empirical evidence in a fragmented IT literature. We code 53 dependent variables  and 195 independent variables to identify the robust relationships among them and to model how ISI decisions, including the choice of IS integration methods, partially mediate the effects of the independent variables on ISI outcomes. Examining the relationships in this model, we identify five quasi-independent thematic domains  on which we draw to develop an agenda for future research. Our contribution is the aggregation, organization and structuring of the empirical findings in the M&A ISI literature as a basis on which to develop a cumulative knowledge process.

     

  • Abstracting Massive Data-taliem-ir

    Abstracting Massive Data for Lightweight Intrusion Detection in Computer Networks

    تومان

    Anomaly intrusion detection in big data environments calls for lightweight models that are able to achieve real-time performance during detection. Abstracting audit data provides a solution to improve the efficiency of data processing in intrusion detection. Data abstraction refers to abstract or extract the most relevant information from the massive dataset. In this work, we propose three strategies of data abstraction, namely, exemplar extraction, attribute selection and attribute abstraction. We first propose an effective method called exemplar extraction to extract representative subsets from the original massive data prior to building the detection models. Two clustering algorithms, Affinity Propagation (AP) and traditional k-means, are employed to find the exemplars from the audit data. K-Nearest Neighbor (k-NN), Principal Component Analysis (PCA) and one-class Support Vector Machine (SVM) are used for the detection. We then employ another two strategies, attribute selection and attribute extraction, to abstract audit data for anomaly intrusion detection. Two http streams collected from
    a real computing environment as well as the KDD’99 benchmark data set are used to validate these three strategies of data abstraction. The comprehensive experimental results show that while all the three strategies improve the detection efficiency, the AP-based exemplar extraction achieves the best performance of data abstraction.

  • Applying sentiment analysis-taliem-ir

    Applying sentiment analysis in social web for smart decision support marketing

    تومان

    Because of the rapid development of communication and service in Taiwan, competition among telecommunication companies has become ever fercer. Differences in marketing strategy usually become the key factor in keeping existing customers while attracting new ones. Although electronic word-of-mouth (e-WOM) is one of the most important pieces of information to a consumer making a purchase decision, very few articles on opinion mining have discussed and compared the relationship between multifaceted word-of-mouth (WOM) and marketing strategy. In this paper, we use our Chinese opinion-mining system (Wu et al. in J Supercomput 73:2987–3001, 2017) not only to retrieve articles related to 4G and conduct reputation analysis but also to discuss the relation between WOM and marketing strategy. The results show that (1) e-WOM can immediately and directly reflect the results of marketing strategy, and (2) although users are primarily concerned with aspects of price, online speed, and signal quality, for most Taiwanese customers, price is the key in choosing a telecommunication company. Moreover, although this paper used 4G-related articles from June 2014 to June 2015 for analysis, the results are consistent with the Taiwanese telecommunication companies’ current marketing strategy of attracting customers through low pricing.

  • Artificial neural networks-taliem-ir

    Artificial neural networks and intelligent finite elements in non-linear structural mechanics

    تومان

    In recent years, artificial neural networks were included in the prediction of deformations of structural elements, such as pipes or tensile specimens. Following this method, classical mechanical calculations were replaced by a set of matrix multiplications by means of artificial intelligence. This was also continued in finite element approaches, wherein constitutive equations were substituted by an artificial neural network (ANN). However, little is known about predicting complex non-linear structural deformations with artificial intelligence. The aim of the present study is to make ANN accessible to complicated structural deformations. Here, shock-wave loaded plates are chosen, which lead to a boundary value problem taking geometrical and physical non-linearities into account. A wide range of strain-rates and highly dynamic deformations are covered in this type of deformation. One ANN is proposed for the entire structural model and another ANN is developed for replacing viscoplastic constitutive equations, integrated into a finite element code, leading to an intelligent finite element. All calculated results are verified by experiments with a shock tube and short-time measurement techniques.

     

  • CAMP cluster aided multi-path routing protocol-taliem-ir

    CAMP: cluster aided multi-path routing protocol for wireless sensor networks

    تومان

    In this article, we propose a novel routing algorithm for wireless sensor network, which achieves uniform energy depletion across all the nodes and thus leading to prolonged network lifetime. The proposed algorithm, divides the Region of Interest into virtual zones, each having some designated cluster head nodes. In the entire process, a node can either be a part of a cluster or it may remain as an independent entity. A non-cluster member transmits its data to next hop node using IRPIntelligent Routing Process (based on the trade-off between the residual  energy of itself as well as its neighbor, and therequired energy to transmit packets to its neighbor). If on the transmission path, some cluster member is elected as a next hop, it rejects IRP and transmits the packets to cluster head, which later forwards them to sink (adopting multihop communication among cluster heads). Routing is not solely performed using clusters, rather they aid the overall routing process, hence this protocol is named as Cluster Aided Multipath Routing (CAMP). CAMP has been compared with various sensor network routing protocols, viz., LEACH, PEGASIS, DIRECT TRANSMISSION, CEED, and CBMR. It is found that the proposed algorithm outperformed them in network lifetime, energy consumption and coverage ratio.

     

  • Data measurement in research-taliem-ir

    Data measurement in research information systems: metrics for the evaluation of data quality

    تومان

    In recent years, research information systems (RIS) have become an integral part of the university’s IT landscape. At the same time, many universities and research institutions are still working on the implementation of such information systems. Research information systems support institutions in the measurement, documentation, evaluation and communication of research activities. Implementing such integrative systems requires that institutions assure the quality of the information on research activities entered into them. Since many information and data sources are interwoven, these different data sources can have a negative impact on data quality in different research information systems. Because the topic is currently of interest to many institutions, the aim of the present paper is firstly to consider how data quality can be investigated in the context of RIS, and then to explain how various dimensions of data quality described in the literature can be measured in research information systems. Finally, a framework as a process flow according to UML activity diagram notation is developed for monitoring and improvement of the quality of these data; this framework can be implemented by technical personnel in universities and research institutions.

  • Deep Artificia Neura Networks-taliem-ir

    Deep Artificial Neural Networks as a Tool for the Analysis of Seismic Data

    تومان

    The number of seismological studies based on artificial neural networks has been increasing. However, neural networks with one hidden layer have almost reached the limit of their capabilities. In the last few years, there has been a new boom in neuroinformatics associated with the development of third- generationnetworks, deep neural networks. These networks operate with data at a higher level. Unlabeled data can be used to pretrain the network, i.e., there is no need for an expert to determine in advance the phenomenon to which these data correspond. Final training requires a small amount of labeled data. Deep networks have a higher level of abstraction and produce fewer errors. The same network can be used to solve several tasks at the same time, or it is easy to retrain it from one task to another. The paper discusses the possibility of applying deep networks in seismology. We have described what deep networks are, their advantages, how they are trained, how to adapt them to the features of seismic data, and what prospects are opening up in connection with their use.

  • Deep Artificial Neural Networks-taliem-ir

    Deep Artificial Neural Networks as a Tool for the Analysis of Seismic Data

    تومان

    The number of seismological studies based on artificial neural networks has been increasing. However, neural networks with one hidden layer have almost reached the limit of their capabilities. In the last few years, there has been a new boom in neuroinformatics associated with the development of third-generation networks, deep neural networks. These networks operate with data at a higher level. Unlabeled data can be used to pretrain the network, i.e., there is no need for an expert to determine in advance the phenomenon to which these data correspond. Final training requires a small amount of labeled data. Deep networks have a higher level of abstraction and produce fewer errors. The same network can be used to solve several tasks at the same time, or it is easy to retrain it from one task to another. The paper discusses the possibility of applying deep networks in seismology. We have described what deep networks are, their advantages, how they are trained, how to adapt them to the features of seismic data, and what prospects are opening up in connection with their use.

     

  • Detecting Human Emotions-taliem-ir

    Detecting Human Emotions Using Electroencephalography (EEG) using Dynamic Programming Approach

    تومان

    The relation between human emotions and EEG signals have been actively studied during the last few decades. In this paper, we study a novel attempt to measure the human brain activity and analyze its signals using electroencephalography (EEG) in order to classify the human emotions  indicated by thebrain wavelets. The study will measure the brain wavelets of female students in order to detect the emotions of happiness, sadness, and fear. This study will use specially designed sensors placed around  the scalp. The measured signals transfer to a computing device. The data collected analyze by a software system, which developed by our team. We use dynamic programming to extract the maximum number of quality service that provides to the user when the device captures specific signals for each emotion.

     

  • Emotional modeling of the green purchase intention-taliem-ir

    Emotional modeling of the green purchase intention improvement using the viral marketing in the social networks

    تومان

    This study explores a model of viral marketing emotional methods to increase the green purchase intention in the social networks. In the process of this research, 500 forms were distributed to respondents, and 384 responses used for analysis. All of the viral marketing emotional method items were created by Delphi method. The study discovered that the viral marketing-based joy and surprise have a signifcant positive effect on the social value of the green product consumption. Also, the effect of the social value of green product consumption on the green purchase intention was confrmed. The green activists and marketers can improve their green product markets for  the future using this approach to viral marketing. In this way, the marketers in all green product industries can increase the consumption of the green product. The main contribution of this study is the light it sheds on how the viral marketing emotions have an effect on the green purchase intention in the social network.

     

  • Enhanced Artificial Neural-taliem-ir

    Enhanced Artificial Neural Network for Protein Fold Recognition and Structural Class Prediction

    تومان

    In Bioinformatics Protein Fold Recognition (PFR) and Structural Class Prediction (SCP) is a significant problem in predicting protein with a three dimensional structure. Extraction of valuable features of protein that consists of 20 amino acids to acquire more desirable classifiers is fundamental to this PFR and SCP. Feature extraction technique predominantly exploits Forward Consecutive Search Scheme (FCS) that supplements syntacticalbased,  volutionary-based and physicochemical-based information. In this research work, a classifier known as Enhanced Artificial Neural Network (ANN) is employed as it is more efficient than Forward Consecutive Search scheme in order to improve the performance of PFR and SCP. The Enhanced ANN algorithm is an improved version of rtificial Neural Network when compared with various existing algorithms such as Support Vector Machine (SVM), ANN, K-Nearest Neighbor (KNN) and the Bayesian. The experiments are conducted on four datasets namely DD, EDD, TG and RDD. Ultimately, the statistical imputation of Enhanced ANN algorithm hypothesizes gives better results than other algorithms to improve the performance of PFR and SCP.

  • Fast face recognition-taliem-ir

    Fast face recognition based on fractal theory

    تومان

    Nowadays, people are more and more concerned about accuracy, rapidity and convenience in the process of personal identification. In the field of biology and computer vision, a variety of methods have been proposed, while a proper method for face recognition is still a challenge. Although some reliable systems and advanced methods have been introduced under relatively controlled conditions, their recognition rate or speed is not satisfactory in the general settings. This is especially true when there are variations in pose, illumination, and facial expression. This paper proposed a fast face recognition method based on fractal theory. This method is to compress the facial images to obtain fractal codes and complete face recognition with these codes. Experimental results on Yale, FERET and CMU PIE databases demonstrate the high efficiency of our method in runtime and correct rate.

     

  • Faster rollout search for the vehicle-taliem-ir

    Faster rollout search for the vehicle routing problem with stochastic demands and restocking

    تومان

    Rollout algorithms lead to effective heuristics for the single vehicle routing problem with stochastic demands (VRPSD), a prototypical model of logistics under uncertainty. However, they can be computationally intensive. To reduce their run time, we introduce a novel approach to approximate the  expected cost of a route when executing any rollout algorithm for VRPSD with restocking. With a sufficiently large number of customers its theoretical speed-up factor is of big-o order 1/3. On a set of instances from the literature, our proposed technique applied to a known rollout algorithm and three variants thereof achieves speed-up factors that range from 0.26 to 0.34 when there are more than fifty customers, degrading only marginally the quality of the resulting routes. Our method also applies to the a priori case, in which case it is exact.