• Journal of the Korea Society of Computer and Information
• /
• v.18 no.12
• /
• pp.197-205
• /
• 2013

In this study, we developed a program of optimizing stand-level carbon stock using a stand-level yield model and the Simulated Annealing (SA) heuristic method to derive a optimized forest treatment solution. The SA is one of the heuristic algorithms that can provide a desirable management solution when dealing with various management purposes. The SA heuristic algorithm applied 'thermal equilibrium test', a thresholds approach to solve the phenomenon that does not find an optimum solution and stays at a local optimum value during the process. We conducted a sensitivity test for the temperature reduction rate, the major parameter of the thermal equilibrium test, to analyze its influence on the objective function value and the total iteration of the optimization process. Using the developed program, three scenarios were compared: a common treatment in forestry (baseline), the optimized solution of maximizing the amount of harvest(alternative 1), and the optimized solution of maximizing the amount of carbon stocks(alternative 2). As the results, we found that the alternative 1 showed provide acceptable solutions for the objectives. From the sensitivity test, we found that the objective function value and the total iteration of the process can be significantly influenced by the temperature reduction rate. The developed program will be practically used for optimizing stand-level carbon stock and developing optimized treatment solutions.

• Phonetics and Speech Sciences
• /
• v.12 no.4
• /
• pp.81-90
• /
• 2020

This paper describes a method of building Korean conversational speech data in the emergency medical domain and proposes an annotation method for the collected data in order to improve speech recognition performance. To suggest future research directions, baseline speech recognition experiments were conducted by using partial data that were collected and annotated. All voices were recorded at 16-bit resolution at 16 kHz sampling rate. A total of 166 conversations were collected, amounting to 8 hours and 35 minutes. Various information was manually transcribed such as orthography, pronunciation, dialect, noise, and medical information using Praat. Baseline speech recognition experiments were used to depict problems related to speech recognition in the emergency medical domain. The Korean conversational speech data presented in this paper are first-stage data in the emergency medical domain and are expected to be used as training data for developing conversational systems for emergency medical applications.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.13-23
• /
• 2022

In this study we leveraged a probing method to evaluate how a pre-trained L2 LSTM language model represents sentences with relative and coordinate clauses. The probing experiment employed adapted models based on the pre-trained L2 language models to trace the syntactic properties of sentence embedding vector representations. The dataset for probing was automatically generated using several templates related to different sentence structures. To classify the syntactic properties of sentences for each probing task, we measured the adaptation effects of the language models using syntactic priming. We performed linear mixed-effects model analyses to analyze the relation between adaptation effects in a complex statistical manner and reveal how the L2 language models represent syntactic features for English sentences. When the L2 language models were compared with the baseline L1 Gulordava language models, the analogous results were found for each probing task. In addition, it was confirmed that the L2 language models contain syntactic features of relative and coordinate clauses hierarchically in the sentence embedding representations.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.319-325
• /
• 2022

The variation of utterance lengths is a representative factor that can degrade the performance of speaker verification systems. To handle this issue, previous studies had attempted to extract speaker features from various branches or to use convolution layers with different receptive fields. Combining the advantages of the previous two approaches for variable-length input, this paper proposes integrated receptive field diversification that extracts speaker features through more diverse receptive field. The proposed method processes the input features by convolutional layers with different receptive fields at multiple time-axis branches, and extracts speaker embedding by dynamically aggregating the processed features according to the lengths of input utterances. The deep neural networks in this study were trained on the VoxCeleb2 dataset and tested on the VoxCeleb1 evaluation dataset that divided into 1 s, 2 s, 5 s, and full-length. Experimental results demonstrated that the proposed method reduces the equal error rate by 19.7 % compared to the baseline.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.536-543
• /
• 2023

Speaker diarization, which labels for "who spoken when?" in speech with multiple speakers, has been studied on a deep neural network-based end-to-end method for labeling on speech overlap and optimization of speaker diarization models. Most deep neural network-based end-to-end speaker diarization systems perform multi-label classification problem that predicts the labels of all speakers spoken in each frame of speech. However, the performance of the multi-label-based model varies greatly depending on what the threshold is set to. In this paper, it is studied a speaker diarization system using single-label classification so that speaker diarization can be performed without thresholds. The proposed model estimate labels from the output of the model by converting speaker labels into a single label. To consider speaker label permutations in the training, the proposed model is used a combination of Permutation Invariant Training (PIT) loss and cross-entropy loss. In addition, how to add the residual connection structures to model is studied for effective learning of speaker diarization models with deep structures. The experiment used the Librispech database to generate and use simulated noise data for two speakers. When compared with the proposed method and baseline model using the Diarization Error Rate (DER) performance the proposed method can be labeling without threshold, and it has improved performance by about 20.7 %.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.11-20
• /
• 2024

In this paper, we propose the BAG (Bit-width Aware Generator) and the Intermediate Layer Knowledge Distillation using Channel-wise Attention to reduce the knowledge gap between a quantized network, a full-precision network, and a generator in GDFQ (Generative Data-Free Quantization). Since the generator in GDFQ is only trained by the feedback from the full-precision network, the gap resulting in decreased capability due to low bit-width of the quantized network has no effect on training the generator. To alleviate this problem, BAG is quantized with same bit-width of the quantized network, and it can generate synthetic images, which are effectively used for training the quantized network. Typically, the knowledge gap between the quantized network and the full-precision network is also important. To resolve this, we compute channel-wise attention of outputs of convolutional layers, and minimize the loss function as the distance of them. As the result, the quantized network can learn which channels to focus on more from mimicking the full-precision network. To prove the efficiency of proposed methods, we quantize the network trained on CIFAR-100 with 3 bit-width weights and activations, and train it and the generator with our method. As the result, we achieve 56.14% Top-1 Accuracy and increase 3.4% higher accuracy compared to our baseline AdaDFQ.

• Journal of the Society of Disaster Information
• /
• v.20 no.1
• /
• pp.199-205
• /
• 2024

Purpose: This study aims to improve the recognition rate of Auto People Counting (APC) in accurately identifying and providing information on remaining evacuees in disaster-vulnerable facilities such as nursing homes to firefighting and other response agencies in the event of a disaster. Methods: In this study, a baseline model was established using CNN (Convolutional Neural Network) models to improve the algorithm for recognizing images of incoming and outgoing individuals through cameras installed in actual disaster-vulnerable facilities operating APC systems. Various algorithms were analyzed, and the top seven candidates were selected. The research was conducted by utilizing transfer learning models to select the optimal algorithm with the best performance. Results: Experiment results confirmed the precision and recall of Densenet201 and Resnet152v2 models, which exhibited the best performance in terms of time and accuracy. It was observed that both models demonstrated 100% accuracy for all labels, with Densenet201 model showing superior performance. Conclusion: The optimal algorithm applicable to APC among various artificial intelligence algorithms was selected. Further research on algorithm analysis and learning is required to accurately identify the incoming and outgoing individuals in disaster-vulnerable facilities in various disaster situations such as emergencies in the future.

• The Journal of the Korea Contents Association
• /
• v.5 no.4
• /
• pp.141-149
• /
• 2005

The paper's suggestion is Web based Tele-Medicine System will be open to public, low-budget featuring high quality of extensive medical services. It will keep a log of personal medical history to allow doctors to share information on patients and their families. This will result in the reduction of erroneous diagnosis and ensure successful e-business. On top of this, the new system will provide a solution for membership (client) management. It will combine online and offline medical services and be available 24 hours a day to anywhere users have Internet access, setting itself apart from the existing distance medical services system. Specially, The paper's suggestion is sharing medical treatment information between family members is suggested. This approach makes possible understanding physical constitution and environment between family members, and can result in bringing a faster treatment effect if some family member suffers from a similar disease.

• Electronics and Telecommunications Trends
• /
• v.10 no.4 s.38
• /
• pp.1-12
• /
• 1995

현재 통신망 서비스는 과거의 한 지역에 국한된 서비스 수준을 넘어 전세계 지역을 대상으로 발전되고 있으며, 그에따라 통신 설비와 그 서비스의 종류도 다양화 및 고도화 되어 가고 있다. 그러나, 각 지역의 통신 노드들은 서로 다른 형태의 정보와 시스템으로 구성되어 있기 때문에 전체 통신 노드들의 통합시 발생할 수 있는 이기종 시스템간의 상호운용(interoperability) 및 관리 문제, 분산 환경하에서의 처리 문제 및 무관성(transparency) 충족문제 등을 표준화 작업을 통하여 해결해 나가고 있다. 또한, 초기의 통신망 출현 시에는 망 자체적인 특성으로 인하여 정보의 수준이 단순하였으나, 요사이 통신망은 엄청난 수의 노드 분산화, 구성 노드의 이질화 및 복잡화는 물론이고 이러한 특성을 갖는 망 자체의 빠른 진화로 인하여 망에서 다루어야 할 정보의 종류와 가지수는 천문학적으로 증가하고 있는 실정이다. 이와 같은 현실로 인하여 정보 관리 서비스 구조에 대한 연구가 꾸준히 진행되어 1988년 국제전신전화자문회(Consultative Committee for International Telegraph and Telephone: CCITT, 이하 CCITT라 함, CCITT는 현재 ITU로 개명)에서는 전체 통신망에 존재하는 통신 관련 정보를 효율적으로 관리할 수 있는 강력한 정보 제공 시스템인 전역(global) 디렉토리 서비스에 대한 국제 표준으로 X.500 시리즈를 발표하기에 이르렀으며, 계속적인 보완작업을 통하여 1992년판 표준안이 완료되었다. 이에 본 고에서는 1992년 판 X.500 디렉토리 표준에 명시된 내용 중 정보 모델링 관점의 내용들을 발췌 분석하므로써 향후 디렉토리 정보 베이스 구축시에 가이드라인으로 사용할 수 있도록 하고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04a
• /
• pp.856-858
• /
• 2001

지적 재산권 보호 중에서 디지털 저작물 보호는 근래에 활발히 연구되고 있으며 법 과학 분야는 지문감식, 치아감정, DNA 등 많은 분야가 있다. 법과학 분야 중 법적용 컴퓨팅(Forensic Computing)에 관한 응용은 새로운 연구 과제이다. 그 중에서도 디지털 저작물에 대하여 증거를 보전 하고자 많은 연구가 진행되고 있지만 디지털 저작물에 관하여 네트워크를 통한 능동적 저작물 보호는 미약하다. 현재의 데이터 추출(Extraction), 발굴(Exploitation), 복구, 암호 해독, 패스워스 풀기(Defeat), 미러 이미징 등의 방법 가지고 해결 못하는 경우와 인터넷 상에서 온라인으로 이루어지는 불법 복제에서 결정적 기여(smoking gun)를 찾아내려고 하는 것이 본 논문에서 해결 하고자 하는 부분이다. 오프라인일 경우도 가능하며 분석된 결과는 변호사/대리인, 법인, 보험회사, 법집행관 등에게 온라인으로 제공한다. 진행 과정은 서버에서 파견시킨, 미션을 부여받은 에이전트가 저작물 불법 복제 상황을 트래킹 한 후, 네트워크를 통하여 정해진 시간별로 서버에 전달하면, 법 조항과 매핑시켜서 분석한 다음 서버의 지식베이스에 저장되어 사용자의 요구에 응하는 능동형 디지털 저작물 보호 관리 시스템이다.