• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권1호
• /
• pp.24-51
• /
• 2011

When supporting both voice and TCP in a wireless multihop network, there are two conflicting goals: to protect the VoIP traffic, and to completely utilize the remaining capacity for TCP. We investigate the interaction between these two popular categories of traffic and find that conventional solution approaches, such as enhanced TCP variants, priority queues, bandwidth limitation, and traffic shaping do not always achieve the goals. TCP and VoIP traffic do not easily coexist because of TCP aggressiveness and data burstiness, and the (self-) interference nature of multihop traffic. We found that enhanced TCP variants fail to coexist with VoIP in the wireless multihop scenarios. Surprisingly, even priority schemes, including those built into the MAC such as RTS/CTS or 802.11e generally cannot protect voice, as they do not account for the interference outside communication range. We present VAGP (Voice Adaptive Gateway Pacer) - an adaptive bandwidth control algorithm at the access gateway that dynamically paces wired-to-wireless TCP data flows based on VoIP traffic status. VAGP continuously monitors the quality of VoIP flows at the gateway and controls the bandwidth used by TCP flows before entering the wireless multihop. To also maintain utilization and TCP performance, VAGP employs TCP specific mechanisms that suppress certain retransmissions across the wireless multihop. Compared to previous proposals for improving TCP over wireless multihop, we show that VAGP retains the end-to-end semantics of TCP, does not require modifications of endpoints, and works in a variety of conditions: different TCP variants, multiple flows, and internet delays, different patterns of interference, different multihop topologies, and different traffic patterns.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권3호
• /
• pp.1100-1118
• /
• 2021

In a wide range of ML applications, the training data contains privacy-sensitive information that should be kept secure. Training the ML systems by privacy-sensitive data makes the ML model inherent to the data. As the structure of the model has been fine-tuned by training data, the model can be abused for accessing the data by the estimation in a reverse process called model inversion attack (MIA). Although, MIA has been applied to shallow neural network models of recognizers in literature and its threat in privacy violation has been approved, in the case of a deep learning (DL) model, its efficiency was under question. It was due to the complexity of a DL model structure, big number of DL model parameters, the huge size of training data, big number of registered users to a DL model and thereof big number of class labels. This research work first analyses the possibility of MIA on a deep learning model of a recognition system, namely a face recognizer. Second, despite the conventional MIA under the white box scenario of having partial access to the users' non-sensitive information in addition to the model structure, the MIA is implemented on a deep face recognition system by just having the model structure and parameters but not any user information. In this aspect, it is under a semi-white box scenario or in other words a gray-box scenario. The experimental results in targeting five registered users of a CNN-based face recognition system approve the possibility of regeneration of users' face images even for a deep model by MIA under a gray box scenario. Although, for some images the evaluation recognition score is low and the generated images are not easily recognizable, but for some other images the score is high and facial features of the targeted identities are observable. The objective and subjective evaluations demonstrate that privacy cyber-attack by MIA on a deep recognition system not only is feasible but also is a serious threat with increasing alert state in the future as there is considerable potential for integration more advanced ML techniques to MIA.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.730-733
• /
• 2004

Recently XML (eXtensible Markup Language) is becoming the standard for exchanging the documents on the web. And as the amount of information is increasing because of the development of the technique in the Internet, semantic web is becoming to appear for more exact result of information retrieval than the existing one on the web. Ontology which is the basis of the semantic web provides the basic knowledge system to express a particular knowledge. So it can show the exact result of the information retrieval. Ontology defines the particular concepts and the relationships between the concepts about specific domain and it has the hierarchy similar to the taxonomy. In this paper, we propose the generation of semi-automatic ontology based on XML documents that are interesting to many researchers as the means of knowledge expression. To construct the ontology in a particular domain, we suggest the algorithm to determine the domain. So we determined that the domain of ontology is to extract the information of movie on the web. And we used the generalized association rules, one of data mining methods, to generate the ontology, using the tag and contents of XML documents. And XTM (XML Topic Maps), ISO Standard, is used to construct the ontology as an ontology language. The advantage of this method is that because we construct the ontology based on the terms frequently used documents related in the domain, it is useful to query and retrieve the related domain.

• 한국인터넷방송통신학회논문지
• /
• 제13권3호
• /
• pp.17-24
• /
• 2013

본 논문은 781MHz 대역에서 안테나 상관도를 고려한 MIMO 채널 측정을 통해, 측정 데이터를 분석하고 채널 특성을 도출하였다. 상기 주파수 대역은 DTV 시스템에서 이동통신 주파수로 할당이 예정된 대역이다. 781MHz 주파수 대역은 900MHz 이동통신 시스템의 채널특성이 일정부분 유사하지만, 상당히 다른 부분이 있음을 기존 연구를 통해 증명하였다. 또한, 안테나의 상관도를 고려할 경우 신호전달 과정에 대한 보다 정확한 예측을 위해서는 채널 특성 연구가 필요하다. 기존 DTV 방송과 혼신을 피하기 위하여 측정은 제주도 인근 도심지역에서 채널사운더와 $4{\times}4$ 안테나로 채널특성을 측정하였다. 측정된 데이터를 바탕으로 도심지역에서 안테나 상관도를 고려한 채널특성을 도출하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권3호
• /
• pp.890-910
• /
• 2014

This paper investigates the spectrum hole utilization of cooperative schemes for the two-way relaying model in order to improve the utilization efficiency of limited spectrum holes in cognitive radio networks with imperfect spectrum sensing. We propose two specific bidirectional secondary data transmission (BSDT) schemes with two-step and three-step two-way relaying models, i.e., two-BSDT and three-BSDT schemes, where the spectrum sensing and the secondary data transmission are jointly designed. In the proposed cooperative schemes, the best two-way relay channel between two secondary users is selected from a group of secondary users serving as cognitive relays and assists the bi-directional communication between the two secondary users without a direct link. The closed-form asymptotic expressions for outage probabilities of the two schemes are derived with a primary user protection constraint over Rayleigh fading channels. Based on the derived outage probabilities, the spectrum hole utilization is calculated to evaluate the percentage of spectrum holes used by the two secondary users for their successful information exchange without channel outage. Numerical results show that the spectrum hole utilization depends on the spectrum sensing overhead and the channel gain from a primary user to secondary users. Additionally, we compare the spectrum hole utilization of the two schemes as the varying of secondary signal to noise ratio, the number of cognitive relays, and symmetric and asymmetric channels.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권6호
• /
• pp.3230-3253
• /
• 2017

Android malware steals users' private information, and embedded unsafe advertisement (ad) libraries, which execute unsafe code causing damage to users. The majority of such traffic is HTTP and is mixed with other normal traffic, which makes the detection of malware and unsafe ad libraries a challenging problem. To address this problem, this work describes a novel HTTP traffic flow mining approach to detect and categorize Android malware and unsafe ad library. This work designed AndroCollector, which can automatically execute the Android application (app) and collect the network traffic traces. From these traces, this work extracts HTTP traffic features along three important dimensions: quantitative, timing, and semantic and use these features for characterizing malware and unsafe ad libraries. Based on these HTTP traffic features, this work describes a supervised classification scheme for detecting malware and unsafe ad libraries. In addition, to help network operators, this work describes a fine-grained categorization method by generating fingerprints from HTTP request methods for each malware family and unsafe ad libraries. This work evaluated the scheme using HTTP traffic traces collected from 10778 Android apps. The experimental results show that the scheme can detect malware with 97% accuracy and unsafe ad libraries with 95% accuracy when tested on the popular third-party Android markets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5301-5323
• /
• 2017

Small cell deployment offers a low-cost solution for the boosted traffic demand in heterogeneous cellular networks (HCNs). Besides improved spatial spectrum efficiency and energy efficiency, future HCNs are also featured with the trend of network architecture convergence and feasibility for flexible mobile applications. To achieve these goals, dual connectivity (DC) is playing a more and more important role to support control/user-plane splitting, which enables maintaining fixed control channel connections for reliability. In this paper, we develop a tractable framework for the downlink SINR analysis of DC assisted HCN. Based on stochastic geometry model, the data-control joint coverage probabilities under multi-frequency and single-frequency tiering are derived, which involve quick integrals and admit simple closed-forms in special cases. Monte Carlo simulations confirm the accuracy of the expressions. It is observed that the increase in mobility robustness of DC is at the price of control channel SINR degradation. This degradation severely worsens the joint coverage performance under single-frequency tiering, proving multi-frequency tiering a more feasible networking scheme to utilize the advantage of DC effectively. Moreover, the joint coverage probability can be maximized by adjusting the density ratio of small cell and macro cell eNBs under multi-frequency tiering, though changing cell association bias has little impact on the level of the maximal coverage performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권5호
• /
• pp.1396-1412
• /
• 2023

Conversation modeling is an important and challenging task in the field of natural language processing because it is a key component promoting the development of automated humanmachine conversation. Most recent research concerning conversation modeling focuses only on the current utterance (considered as the current question) to generate a response, and thus fails to capture the conversation's logic from its beginning. Some studies concatenate the current question with previous conversation sentences and use it as input for response generation. Another approach is to use an encoder to store all previous utterances. Each time a new question is encountered, the encoder is updated and used to generate the response. Our approach in this paper differs from previous studies in that we explicitly separate the encoding of the question from the encoding of its context. This results in different encoding models for the question and the context, capturing the specificity of each. In this way, we have access to the entire context when generating the response. To this end, we propose a deep neural network-based model, called the Context Model, to encode previous utterances' information and combine it with the current question. This approach satisfies the need for context information while keeping the different roles of the current question and its context separate while generating a response. We investigate two approaches for representing the context: Long short-term memory and Convolutional neural network. Experiments show that our Context Model outperforms a baseline model on both ConvAI2 Dataset and a collected dataset of conversational English.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권5호
• /
• pp.1413-1432
• /
• 2023

Recommender systems aim to recommend items to users by taking into account their probable interests. This study focuses on creating a model that utilizes multiple sources of information about users and items by employing a multimodality approach. The study addresses the task of how to gather information from different sources (modalities) and transform them into a uniform format, resulting in a multi-modal feature description for users and items. This work also aims to transform and represent the features extracted from different modalities so that the information is in a compatible format for integration and contains important, useful information for the prediction model. To achieve this goal, we propose a novel multi-modal recommendation model, which involves extracting latent features of users and items from a utility matrix using matrix factorization techniques. Various transformation techniques are utilized to extract features from other sources of information such as user reviews, item descriptions, and item categories. We also proposed the use of Principal Component Analysis (PCA) and Feature Selection techniques to reduce the data dimension and extract important features as well as remove noisy features to increase the accuracy of the model. We conducted several different experimental models based on different subsets of modalities on the MovieLens and Amazon sub-category datasets. According to the experimental results, the proposed model significantly enhances the accuracy of recommendations when compared to SVD, which is acknowledged as one of the most effective models for recommender systems. Specifically, the proposed model reduces the RMSE by a range of 4.8% to 21.43% and increases the Precision by a range of 2.07% to 26.49% for the Amazon datasets. Similarly, for the MovieLens dataset, the proposed model reduces the RMSE by 45.61% and increases the Precision by 14.06%. Additionally, the experimental results on both datasets demonstrate that combining information from multiple modalities in the proposed model leads to superior outcomes compared to relying on a single type of information.

• ETRI Journal
• /
• 제36권3호
• /
• pp.385-395
• /
• 2014

In this paper, we consider a resource allocation scheme for millimeter wave-based wireless personal area networks using directional antennas. This scheme involves scheduling the reservation period of medium access control for IEEE 802.15.3c. Objective functions are considered to minimize the average delay and maximize throughput; and two scheduling algorithms-namely, MInMax concurrent transmission and MAxMin concurrent transmission-are proposed to provide a suboptimal solution to each objective function. These are based on an exclusive region and two decision rules that determine the length of reservation times and the transmission order of groups. Each group consists of flows that are concurrently transmittable via spatial reuse. The algorithms appropriately apply two decision rules according to their objectives. A real video trace is used for the numerical results, which show that the proposed algorithms satisfy their objectives. They outperform other schemes on a range of measures, showing the effect of using a directional antenna. The proposed scheme efficiently supports variable bit rate traffic during the reservation period, reducing resource waste.