Digital Library

Vol. 10, No. 3, Sep. 2014  

1. Training-Free Fuzzy Logic Based Human Activity Recognition
   Eunju Kim, Sumi Helal
   Vol. 10, No. 3, pp. 335-354, Sep. 2014  
   10.3745/JIPS.04.0005
   Details
   Keywords: Activity Semantic Knowledge, Fuzzy Logic, Human Activity Recognition, Multi-Layer Neural Network
   Show / Hide Abstract

   The accuracy of training-based activity recognition depends on the training procedure and the extent to which the training dataset comprehensively represents the activity and its varieties. Additionally, training incurs substantial cost and effort in the process of collecting training data. To address these limitations, we have developed a training-free activity recognition approach based on a fuzzy logic algorithm that utilizes a generic activity model and an associated activity semantic knowledge. The approach is validated through experimentation with real activity datasets. Results show that the fuzzy logic based algorithms exhibit comparable or better accuracy than other trainingbased approaches.


2. Improving Database System Performance by Applying NoSQL
   Yong-Lak Choi, Woo-Seong Jeon, Seok-Hwan Yoon
   Vol. 10, No. 3, pp. 355-364, Sep. 2014  
   10.3745/JIPS.04.0006
   Details
   Keywords: Database System Performance, NoSQL, NoSQL Practical Use
   Show / Hide Abstract

   Internet accessibility has been growing due to the diffusion of smartphones in today’s society. Therefore, people can generate data anywhere and are confronted with the challenge that they should process a large amount of data. Since the appearance of relational database management system (RDBMS), most of the recent information systems are built by utilizing it. RDBMS uses foreign-keys to avoid data duplication. The transactions in the database use attributes, such as atomicity, consistency, isolation, durability (ACID), which ensures that data integrity and processing results are stably managed. The characteristic of RDBMS is that there is high data reliability. However, this results in performance degradation. Meanwhile, from among these information systems, some systems only require high-performance rather than high reliability. In this case, if we only consider performance, the use of NoSQL provides many advantages. It is possible to reduce the maintenance cost of the information system that continues to increase in the use of open source software based NoSQL. And has a huge advantage that is easy to use NoSQL. Therefore, in this study, we prove that the leverage of NoSQL will ensure high performance than RDBMS by applying NoSQL to database systems that implement RDBMS.


3. A Novel Framework for Defining and Submitting Workflows to Service-Oriented Systems
   Hayat Bendoukha, Yahya Slimani, Abdelkader Benyettou
   Vol. 10, No. 3, pp. 365-383, Sep. 2014  
   10.3745/JIPS.02.0003
   Details
   Keywords: service composition, Service-Oriented Computing, Service-Oriented Workflow, UML2BPEL, Workflow
   Show / Hide Abstract

   Service-oriented computing offers efficient solutions for executing complex applications in an acceptable amount of time. These solutions provide important computing and storage resources, but they are too difficult for individual users to handle. In fact, Service-oriented architectures are usually sophisticated in terms of design, specifications, and deployment. On the other hand, workflow management systems provide frameworks that help users to manage cooperative and interdependent processes in a convivial manner. In this paper, we propose a workflow-based approach to fully take advantage of new service-oriented architectures that take the users’ skills and the internal complexity of their applications into account. To get to this point, we defined a novel framework named JASMIN, which is responsible for managing service-oriented workflows on distributed systems. JASMIN has two main components: unified modeling language (UML) to specify workflow models and business process execution language (BPEL) to generate and compose Web services. In order to cover both workflow and service concepts, we describe in this paper a refinement of UML activity diagrams and present a set of rules for mapping UML activity diagrams into BPEL specifications.


4. Femtocell Subband Selection Method for Managing Cross- and Co-tier Interference in a Femtocell Overlaid Cellular Network
   Young Min Kwon, Hyunseung Choo, Tae-Jin Lee, Min Young Chung, Mihui Kim
   Vol. 10, No. 3, pp. 384-394, Sep. 2014  
   10.3745/JIPS.03.0008
   Details
   Keywords: Clustering method, Femtocell, Frequency Partition, Interference Management
   Show / Hide Abstract

   The femtocell overlaid cellular network (FOCN) has been used to enhance the capacity of existing cellular systems. To obtain the desired system performance, both cross-tier interference and co-tier interference in an FOCN need to be managed. This paper proposes an interference management scheme that adaptively constructs a femtocell cluster, which is a group of femtocell base stations that share the same frequency band. The performance evaluation shows that the proposed scheme can enhance the performance of the macrocell-tier and maintain a greater signal to interference-plus-noise ratio than the outage level can for about 99% of femtocell users.


5. Imputation of Medical Data Using Subspace Condition Order Degree Polynomials
   Klaokanlaya Silachan, Panjai Tantatsanawong
   Vol. 10, No. 3, pp. 395-411, Sep. 2014  
   10.3745/JIPS.04.0007
   Details
   Keywords: Imputation, Personal Temporal Data, Polynomial interpolation
   Show / Hide Abstract

   Temporal medical data is often collected during patient treatments that require personal analysis. Each observation recorded in the temporal medical data is associated with measurements and time treatments. A major problem in the analysis of temporal medical data are the missing values that are caused, for example, by patients dropping out of a study before completion. Therefore, the imputation of missing data is an important step during pre-processing and can provide useful information before the data is mined. For each patient and each variable, this imputation replaces the missing data with a value drawn from an estimated distribution of that variable. In this paper, we propose a new method, called Newton’s finite divided difference polynomial interpolation with condition order degree, for dealing with missing values in temporal medical data related to obesity. We compared the new imputation method with three existing subspace estimation techniques, including the k-nearest neighbor, local least squares, and natural cubic spline approaches. The performance of each approach was then evaluated by using the normalized root mean square error and the statistically significant test results. The experimental results have demonstrated that the proposed method provides the best fit with the smallest error and is more accurate than the other methods.


6. Ultra Low Power Data Aggregation for Request Oriented Sensor Networks
   Kwang-il Hwang, In Jang
   Vol. 10, No. 3, pp. 412-428, Sep. 2014  
   10.3745/JIPS.03.0009
   Details
   Keywords: data aggregation, Energy Efficient, Low Power Listening, Medium Access Control, Request Oriented, Sensor Networks
   Show / Hide Abstract

   Request oriented sensor networks have stricter requirements than conventional event-driven or periodic report models. Therefore, in this paper we propose a minimum energy data aggregation (MEDA), which meets the requirements for request oriented sensor networks by exploiting a low power real-time scheduler, ondemand time synchronization, variable response frame structure, and adaptive retransmission. In addition we introduce a test bed consisting of a number of MEDA prototypes, which support near real-time bidirectional sensor networks. The experimental results also demonstrate that the MEDA guarantees deterministic aggregation time, enables minimum energy operation, and provides a reliable data aggregation service.


7. Fault Detection in the Semiconductor Etch Process Using the Seasonal Autoregressive Integrated Moving Average Modeling
   Muhammad Zeeshan Arshad, Javeria Muhammad Nawaz, Sang Jeen Hong
   Vol. 10, No. 3, pp. 429-442, Sep. 2014  
   10.3745/JIPS.04.0004
   Details
   Keywords: Autoregressive Integrated Moving Average, Dynamic Time Warping, Fault Detection, Seasonal Autoregressive Integrated Moving Average, Semiconductor Process, Time Series Modeling
   Show / Hide Abstract

   In this paper, we investigated the use of seasonal autoregressive integrated moving average (SARIMA) time series models for fault detection in semiconductor etch equipment data. The derivative dynamic time warping algorithm was employed for the synchronization of data. The models were generated using a set of data from healthy runs, and the established models were compared with the experimental runs to find the faulty runs. It has been shown that the SARIMA modeling for this data can detect faults in the etch tool data from the semiconductor industry with an accuracy of 80% and 90% using the parameter-wise error computation and the step-wise error computation, respectively. We found that SARIMA is useful to detect incipient faults in semiconductor fabrication.


8. Extreme Learning Machine Ensemble Using Bagging for Facial Expression Recognition
   Deepak Ghimire, Joonwhoan Lee
   Vol. 10, No. 3, pp. 443-458, Sep. 2014  
   10.3745/JIPS.02.0004
   Details
   Keywords: Bagging, Ensemble Learning, Extreme Learning Machine, Facial Expression Recognition, Histogram of Orientation Gradient
   Show / Hide Abstract

   An extreme learning machine (ELM) is a recently proposed learning algorithm for a single-layer feed forward neural network. In this paper we studied the ensemble of ELM by using a bagging algorithm for facial expression recognition (FER). Facial expression analysis is widely used in the behavior interpretation of emotions, for cognitive science, and social interactions. This paper presents a method for FER based on the histogram of orientation gradient (HOG) features using an ELM ensemble. First, the HOG features were extracted from the face image by dividing it into a number of small cells. A bagging algorithm was then used to construct many different bags of training data and each of them was trained by using separate ELMs. To recognize the expression of the input face image, HOG features were fed to each trained ELM and the results were combined by using a majority voting scheme. The ELM ensemble using bagging improves the generalized capability of the network significantly. The two available datasets (JAFFE and CK+) of facial expressions were used to evaluate the performance of the proposed classification system. Even the performance of individual ELM was smaller and the ELM ensemble using a bagging algorithm improved the recognition performance significantly.


9. Spectrum Sensing and Data Transmission in a Cognitive Relay Network Considering Spatial False Alarms
   Tasnina A. Tishita, Sumiya Akhter, Md. Imdadul Islam, M. R. Amin
   Vol. 10, No. 3, pp. 459-470, Sep. 2014  
   10.3745/JIPS.03.0007
   Details
   Keywords: cognitive network, Conventional False Alarms, Probability of Symbol Error Rate, Spatial False Alarms, Spectrum Sensing
   Show / Hide Abstract

   In this paper, the average probability of the symbol error rate (SER) and throughput are studied in the presence of joint spectrum sensing and data transmission in a cognitive relay network, which is in the environment of an optimal power allocation strategy. In this investigation, the main component in calculating the secondary throughput is the inclusion of the spatial false alarms, in addition to the conventional false alarms. It has been shown that there exists an optimal secondary power amplification factor at which the probability of SER has a minimum value, whereas the throughput has a maximum value. We performed a Monte-Carlo simulation to validate the analytical results.


10. Efficient Greedy Algorithms for Influence Maximization in Social Networks
    Jiaguo Lv, Jingfeng Guo, Huixiao Ren
    Vol. 10, No. 3, pp. 471-482, Sep. 2014  
    10.3745/JIPS.04.0003
    Details
    Keywords: greedy algorithm, Influence Maximization, Social Network
    Show / Hide Abstract

    Influence maximization is an important problem of finding a small subset of nodes in a social network, such that by targeting this set, one will maximize the expected spread of influence in the network. To improve the efficiency of algorithm KK_Greedy proposed by Kempe et al., we propose two improved algorithms, Lv_NewGreedy and Lv_CELF. By combining all of advantages of these two algorithms, we propose a mixed algorithm Lv_MixedGreedy. We conducted experiments on two synthetically datasets and show that our improved algorithms have a matching influence with their benchmark algorithms, while being faster than them.


11. Multifactor Authentication Using a QR Code and a One-Time Password
    Jyoti Malik, Dhiraj Girdhar, Ratna Dahiya, G. Sainarayanan
    Vol. 10, No. 3, pp. 483-490, Sep. 2014  
    10.3745/JIPS.02.0005
    Details
    Keywords: authentication, One-Time Password, Personal Assurance Message, Quick Response Code
    Show / Hide Abstract

    In today’s world, communication, the sharing of information, and money transactions are all possible to conduct via the Internet, but it is important that it these things are done by the actual person. It is possible via several means that an intruder can access user information. As such, several precautionary measures have to be taken to avoid such instances. The purpose of this paper is to introduce the idea of a one-time password (OTP), which makes unauthorized access difficult for unauthorized users. A OTP can be implemented using smart cards, time-based tokens, and short message service, but hardware based methodologies require maintenance costs and can be misplaced Therefore, the quick response code technique and personal assurance message has been added along with the OTP authentication.