• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제35권3A호
• /
• pp.287-295
• /
• 2010

In wireless sensor networks(WSNs), the studies that support sink mobility without global position information exploit a Backbone-based Virtual Infrastructure (BVI) which considers one-hop clusters and a backbone-based tree. Since the clusters of a sink and a source node are connected via flooding into the infrastructure, it causes high routing cost. Although the network could reduce the number of clusters via multi-level clusters, if the source nodes exist at nearest clusters from the cluster attached by the sink and they are in different branches of the tree, the data should be delivered via detour paths on the tree. Therefore, to reduce the number of clusters, we propose a novel multi-hop cluster based communication protocol supporting sink mobility without global position information. We exploit a rendezvous cluster head for sink location service and data dissemination but the proposed protocol effectively reduces data detour via comparing cluster hops from the source. Simulation shows that the proposed protocol is superior to the existing protocols in terms of the data delivery hop counts.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.150-156
• /
• 2023

For a doctor, diagnosing a patient's heart disease is not easy. It takes the ability and experience with high flying hours to be able to accurately diagnose the type of patient's heart disease based on the existing factors in the patient. Several studies have been carried out to develop tools to identify types of heart disease in patients. However, most only focus on the results of patient answers and lab results, the rest use only echocardiography data or electrocardiogram results. This research was conducted to test how accurate the results of the classification of heart disease by using two medical data, namely echocardiography and electrocardiogram. Three treatments were applied to the two medical data and analyzed using the decision tree approach. The first treatment was to build a classification model for types of heart disease based on echocardiography and electrocardiogram data, the second treatment only used echocardiography data and the third treatment only used electrocardiogram data. The results showed that the classification of types of heart disease in the first treatment had a higher level of accuracy than the second and third treatments. The accuracy level for the first, second and third treatment were 78.95%, 73.69% and 50%, respectively. This shows that in order to diagnose the type of patient's heart disease, it is advisable to look at the records of both the patient's medical data (echocardiography and electrocardiogram) to get an accurate level of diagnosis results that can be accounted for.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.587-590
• /
• 2019

This paper is about to improve the network life's reduction due to the deviation of sensor node and frequently change of network, the main problem of sensor network. The existing Scalable Topology Organization(STO)-based ZigBee Tree Topology Control Algorithm did not consider ways to consume power so the network lifetime is too short. Accordingly, per each round, electing a new parent node and consisting of the new network topology technique, The Cluster Header Selection, extending the network's overall lifetime. The OMNet++ Simulator yielded results from the existing STO Algorithm and the proposed Cluster Header Selection Technique in the same experimental environment, which resulted in an increase in overall network life by about 40% and an improvement of about 10% in performance in the remaining portion of the battery.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제11권1호
• /
• pp.92-97
• /
• 2012

This paper suggests a data gathering scheme using dynamic branch tree in wireless sensor networks. A mobile sink gathers data from each sensor node using a dynamic data gathering tree rooted at the mobile sink node. As the sink moves, a tree that has multiple branch is formed and changed dynamically as with the position of the sink node. A hop-based scope filter and a restricted flooding scheme of the tree are also suggested. Simulation results show that the proposed data gathering scheme has better results in data arrival rate, the end-to-end delay and energy saving characteristics compared with the previous scheme.

• The Journal of Society for e-Business Studies
• /
• 제9권1호
• /
• pp.83-104
• /
• 2004

Recently, information systems that require storage and retrieval of huge amount of data are becoming used widely. Accordingly, research efforts have been made to develop Linux cluster file systems in the SAN environment in which clients themselves can manage metadata and access data directly. Also a semi-flat directory structure based on extendible hashing has been proposed to support fast retrieval of files[1]. In this research, we have designed and implemented the semi-flat extendible hash directory under the Linux system. In order to evaluate the practicality of the directory, we have also implemented the B+-tree based directory and experimented the performance. According to the performance comparisons, the extendible hash directory has the better performance at insert, delete, and search operations. On the other hand, the B+-tree directory is better at sorting files.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권2호
• /
• pp.629-648
• /
• 2012

Given a video stream delivering system deployed on a multicast tree, which is embedded in a multi-channel multi-radio wireless mesh network, our problem is concerned about how to allocate interference-free channels to tree links and maximize the number of serviced mesh clients at the same time. In this paper, we propose a channel allocation heuristic algorithm based on best-first search and backtracking techniques. The experimental results show that our BFB based CA algorithm outperforms previous methods such as DFS and BFS based CA methods. This superiority is due to the backtracking technique used in BFB approach. It allows previous channel-allocated links to have feasibility to select the other eligible channels when no conflict-free channel can be found for the current link during the CA process. In addition to that, we also propose a tree refinement method to enhance the quality of channel-allocated trees by adding uncovered destinations at the cost of deletion of some covered destinations. Our aim of this refinement is to increase the number of serviced mesh clients. According to our simulation results, it is proved to be an effective method for improving multicast trees produced by BFB, BFS and DFS CA algorithms.

• ETRI Journal
• /
• 제44권3호
• /
• pp.462-475
• /
• 2022

Although researchers have proposed numerous techniques for speech emotion recognition, its performance remains unsatisfactory in many application scenarios. In this study, we propose a speech emotion recognition model based on a genetic algorithm (GA)-decision tree (DT) fusion of deep and acoustic features. To more comprehensively express speech emotional information, first, frame-level deep and acoustic features are extracted from a speech signal. Next, five kinds of statistic variables of these features are calculated to obtain utterance-level features. The Fisher feature selection criterion is employed to select high-performance features, removing redundant information. In the feature fusion stage, the GA is is used to adaptively search for the best feature fusion weight. Finally, using the fused feature, the proposed speech emotion recognition model based on a DT support vector machine model is realized. Experimental results on the Berlin speech emotion database and the Chinese emotion speech database indicate that the proposed model outperforms an average weight fusion method.

• International journal of advanced smart convergence
• /
• 제13권1호
• /
• pp.212-220
• /
• 2024

When a typhoon or natural disaster occurs, a significant number of orchard fruits fall. This has a great impact on the income of farmers. In this paper, we introduce an AI-based method to enhance low-quality raw images. Specifically, we focus on apple images, which are being used as AI training data. In this paper, we utilize both a basic program and an artificial intelligence model to conduct a general image process that determines the number of apples in an apple tree image. Our objective is to evaluate high and low performance based on the close proximity of the result to the actual number. The artificial intelligence models utilized in this study include the Convolutional Neural Network (CNN), VGG16, and RandomForest models, as well as a model utilizing traditional image processing techniques. The study found that 49 red apple fruits out of a total of 87 were identified in the apple tree image, resulting in a 62% hit rate after the general image process. The VGG16 model identified 61, corresponding to 88%, while the RandomForest model identified 32, corresponding to 83%. The CNN model identified 54, resulting in a 95% confirmation rate. Therefore, we aim to select an artificial intelligence model with outstanding performance and use a real-time object separation method employing artificial function and image processing techniques to identify orchard fruits. This application can notably enhance the income and convenience of orchard farmers.

• Journal of Korea Society of Industrial Information Systems
• /
• 제8권3호
• /
• pp.99-104
• /
• 2003

Ad-hoc is the wireless network and consists of moving Hosts in environments which don't have a network-based Frame. Because ad-hoc is considered as broadcast network and network which has useful benefits, multicast muting protocols have been studied on ad-hoc network For this work we scrutinized ad-hoc and multicast routing protocols presented in previous works. And we presents a protocol for Ad-hoc network.

• The Transactions of the Korea Information Processing Society
• /
• 제7권6호
• /
• pp.1949-1955
• /
• 2000

This paper proposes a multistage interconnection ATM switching network without internal blocking. The first is recirculating shuffle-exchange network improved on hardware complexity. The next is connected to Rank network with tree structure. In this network, after the packets transferred to the same output ports are given each priority, only a packet with highest priority is sent to the next, an the others are recirculated to the first. Rearrangeability through decomposition and composition algorithm is applied for the transferred packets in hanyan network and all they arrive at a final destinations. To analyze throughput, waiting time and packet loss ratio according tothe size of buffer, the probabilities are modeled by a binomial distribution of packet arrival.