• Journal of Multimedia Information System
• /
• v.2 no.2
• /
• pp.233-240
• /
• 2015

Mobile devices are becoming increasingly sophisticated and the latest generation of smartphones now incorporates many diverse and powerful sensors. These sensors include acceleration sensor, magnetic field sensor, light sensor, proximity sensor, gyroscope sensor, pressure sensor, rotation vector sensor, gravity sensor and orientation sensor. The availability of these sensors in mass-marketed communication devices creates exciting new opportunities for data mining and data mining applications. In this paper, we describe and evaluate a system that uses phone-based accelerometers to perform activity recognition, a task which involves identifying the physical activity that a user is performing. To implement our system, we collected labeled accelerometer data from 10 users as they performed daily activities such as "phone detached", "idle", "walking", "running", and "jumping", and then aggregated this time series data into examples that summarize the user activity 5-minute intervals. We then used the resulting training data to induce a predictive model for activity recognition. This work is significant because the activity recognition model permits us to gain useful knowledge about the habits of millions of users-just by having them carry cell phones in their pockets.

• Journal of Integrative Natural Science
• /
• v.4 no.3
• /
• pp.238-242
• /
• 2011

For any pattern matching based algorithm in WLAN environment, the characteristics of signal to noise ratio(SNR) to multiple access points(APs) are utilized to establish database in the training phase, and in the estimation phase, the actual two dimensional coordinates of mobile unit(MU) are estimated based on the comparison between the new recorded SNR and fingerprints stored in database. The system that uses the artificial neural network(ANN) falls in a local minima when it learns many nonlinear data, and its classification accuracy ratio becomes low. To make up for this risk, the SVM/ANN hybrid algorithm is proposed in this paper. The proposed algorithm is the method that ANN learns selectively after clustering the SNR data by SVM, then more improved performance estimation can be obtained than using ANN only and The proposed algorithm can make the higher classification accuracy by decreasing the nonlinearity of the massive data during the training procedure. Experimental results indicate that the proposed SVM/ANN hybrid algorithm generally outperforms ANN algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.4
• /
• pp.81-90
• /
• 2014

As mobile devices have become widely used and developed, PC based malwares can be moving towards mobile-based units. In particular, mobile Botnet reuses powerful malicious behavior of PC-based Botnet or add new malicious techniques. Different from existing PC-based Botnet detection schemes, mobile Botnet detection schemes are generally host-based. It is because mobile Botnet has various attack vectors and it is difficult to inspect all the attack vector at the same time. In this paper, to overcome limitations of host-based scheme, we compare two network-based schemes which detect mobile Botnet by applying HMM and SVM techniques. Through the verification analysis under real Botnet attacks, we present detection rates and detection properties of two schemes.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.353-362
• /
• 2005

Recently, study of Bimodal recognition has become very active. In this paper we propose a Bimodal user recognition system that uses face information and audio information. Face recognition consists of face detection step and face recognition step. Face detection uses AdaBoost to find face candidate area. After finding face candidates, PCA feature extraction is applied to decrease the dimension of feature vector. And then, SVM classifiers are used to detect and recognize face. Audio recognition uses MFCC for audio feature extraction and HMM is used for audio recognition. Experimental results show that the Bimodal recognition can improve the user recognition rate much more than audio only recognition, especially in the Presence of noise.

• The Journal of Korean Association of Computer Education
• /
• v.13 no.6
• /
• pp.79-89
• /
• 2010

In this paper, we proposed a method to find out similar sentences from documents to detect plagiarized documents. The proposed model adapts LSA and N-gram techniques to detect every type of Korean plagiarized sentence type. To evaluate the performance of the model, we constructed experimental data using students' essays on the same theme. Students made their essay by intentionally plagiarizing some reference documents. The experimental results showed that our proposed model outperforms the conventional N-gram model, Vector model, LSA model in precision, recall, and F measures.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.1236-1239
• /
• 2002

When we see an object, we usually can say what it is easily even for the case where the object isn't shown in the frontal view. However, it is difficult to believe that all views of every object we have ever seen are fully memorized in our brain. Possibly, when an object is shown, we have some typical views of the object in our brain through our past experience and reconstruct the view to recognize what the presented object is. Non-negative Matrix Factorization (NMF) is one of the methods to extract the basis images from sample data set. The prominent feature of this method is that the reconstructed image is obtained by only additions of the basis images with suitable positive weights. So NMF can be seen more biologically plausible method than any other feature extraction methods such as Vector Quantization (VQ) and principal Component Analysis (PCA). In this paper, we adopt NMF to extract the aspect features from the set of images, which consists of various views of a given object. Some experiments are shown how much well NMF can extract the aspect features than any other methods such as VQ and PCA.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.1-10
• /
• 2005

In this Paper, we propose a new block matching a1gorithm that extracts motion vectors from consecutive range data. The proposed method defines a matching metric that integrates intensity, hue, and range. Our algorithm begins matching with a small matching template. If the matching degree is not good enough, we slightly expand the size of a matching template and then repeat the matching process until our matching criterion is satisfied or the predetermined maximum size has been reached. As the iteration proceeds, we adaptively adjust weights of the matching metric by considering the importance of each feature. In the experiments, we show that our block matching approach can work as a promising solution by comparing the proposed method with previously known method in terms of performance.

• Journal of the Ergonomics Society of Korea
• /
• v.29 no.4
• /
• pp.533-540
• /
• 2010

This study was to suggest the proper level of touch sensibility for twenties while flicking touch phones. A rapid prototype of $480{\times}800$ pixel size was developed for the experiment. Participants were 20 undergraduates, not visually and physically handicapped in using touch phones. 15 different modes, with each mode changing in velocity when flicking the prototype were randomly presented to each subject. The subjects were asked to score what they felt in each mode on a 1-to-6 Likert scale. The data was analyzed by the one-way ANOVA procedure. Each mode showed significant differences in 8 representative emotions except for exclusivity feeling and fresh feeling. Each velocity mode was scaled by the multidimensional scaling technique. Then, vector coordinates in each emotion were obtained by simple regression analysis. 15 velocity modes and each emotion were joint-plotted by the MDS, PROXSCAL. The findings in this study could be basic data for studying affective touch sensibilities in multiple ways.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.3
• /
• pp.1330-1347
• /
• 2018

Mobile Ad hoc Network (MANET) is a collection of nodes or communication devices that wish to communicate without any fixed infrastructure and predetermined organization of available links. The effort has been made by proposing a scheme to overcome the critical security issue in MANET. The insufficiency of security considerations in the design of Ad hoc On-Demand Distance Vector protocol makes it vulnerable to the threats of collaborative black hole attacks, where hacker nodes attack the data packets and drop them instead of forwarding. To secure mobile ad hoc networks from collaborative black hole attacks, we implement our scheme and considered sensor's energy as a key feature with a better packet delivery ratio, less delay time and high throughput. The proposed scheme has offered an improved solution to diminish collaborative black hole attacks with high performance and benchmark results as compared to the existing schemes EDRIAODV and DRIAODV respectively. This paper has shown that throughput and packet delivery ratio increase while the end to end delay decreases as compared to existing schemes. It also reduces the overall energy consumption and network traffic by maintaining accuracy and high detection rate which is more safe and reliable for future work.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.693-699
• /
• 2018

CNN based object recognitions have reported splendid results. However, the recognition of mobile apps raises an interesting challenge that recognition performance of similar widgets is not consistent. In order to improve the performance, we propose a noble method utilizing relations between input widgets. The recognition process flows from the Faster R-CNN based recognition to enhancement using a relation recognizer. The relations are represented as vector translation between objects in a relation space. Experiments on 323 apps show that our method significantly enhances the Faster R-CNN only approach.