• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.441-445
• /
• 2009

We have developed a real-time software tool to extract a speech feature vector whose time sequences consist of three groups of vector components; the phonetic/acoustic features such as formant frequencies, the phonemic features as outputs on neural networks, and some distances of Japanese phonemes. In those features, since the phoneme distances for Japanese five vowels are applicable to express vowel articulation, we have designed a switch, a volume control and a color representation which are operated by pronouncing vowel sounds. As examples of those vowel interface, we have developed some speech training tools to display a image character or a rolling color ball and to control a cursor's movement for aurally- or vocally-handicapped children. In this paper, we introduce the functions and the principle of those systems.

• Journal of Mechanical Science and Technology
• /
• 제19권2호
• /
• pp.505-519
• /
• 2005

In this paper, we develop an anti-sway control in proposed techniques for an ATC system. The developed algorithm is to build the optimal path of container motion and to calculate an anti-collision path for collision avoidance in its movement to the finial coordinate. Moreover, in order to show the effectiveness in this research, we compared NNP PID controller to be tuning parameters of controller using NN with 2 DOF PID controller. The simulation and experimental results show that the proposed control scheme guarantees performances, trolley position, sway angle and settling time in NNP PID controller than other controller. As the results in this paper, the application of NNP PID controller is analyzed to have robustness about disturbance which is wind of fixed pattern in the yard. Accordingly, the proposed algorithm in this study can be readily used for industrial applications.

• PNF and Movement
• /
• 제22권1호
• /
• pp.43-54
• /
• 2024

Purpose: Falls among persons older than 65 years are a significant concern due to their frequency and severity. This study aimed to develop a vest-type embedded artificial intelligence (AI) system capable of detecting and predicting falls in various scenarios. Methods: In this study, we established and developed a vest-type embedded AI system to judge and predict falls in various directions and situations. To train the AI, we collected data using acceleration and gyroscope values from a six-axis sensor attached to the seventh cervical and the second sacral vertebrae of the user, considering accurate motion analysis of the human body. The model was constructed using a neural network-based AI prediction algorithm to anticipate the direction of falls using the collected pedestrian data. Results: We focused on developing a lightweight and efficient fall prediction model for integration into an embedded AI algorithm system, ensuring real-time network optimization. Our results showed that the accuracy of fall occurrence and direction prediction using the trained fall prediction model was 89.0% and 78.8%, respectively. Furthermore, the fall occurrence and direction prediction accuracy of the model quantized for embedded porting was 87.0 % and 75.5 %, respectively. Conclusion: The developed fall detection and prediction system, designed as a vest-type with an embedded AI algorithm, offers the potential to provide real-time feedback to pedestrians in clinical settings and proactively prepare for accidents.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권1호
• /
• pp.10-17
• /
• 2017

We propose classification algorithms for human and dog movement. The proposed algorithms use micro-Doppler signals obtained from humans and dogs moving in four different directions. A two-stage classifier based on a support vector machine (SVM) is proposed, which uses a radial-based function (RBF) kernel and $16^{th}$-order linear predictive code (LPC) coefficients as feature vectors. With the proposed algorithms, we obtain the best classification results when a first-level SVM classifies the type of movement, and then, a second-level SVM classifies the moving object. We obtain the correct classification probability 95.54% of the time, on average. Next, to deal with the difficult classification problem of human and dog running, we propose a two-layer convolutional neural network (CNN). The proposed CNN is composed of six ($6{\times}6$) convolution filters at the first and second layers, with ($5{\times}5$) max pooling for the first layer and ($2{\times}2$) max pooling for the second layer. The proposed CNN-based classifier adopts an auto regressive spectrogram as the feature image obtained from the $16^{th}$-order LPC vectors for a specific time duration. The proposed CNN exhibits 100% classification accuracy and outperforms the SVM-based classifier. These results show that the proposed classifiers can be used for human and dog classification systems and also for classification problems using data obtained from an ultra-wideband (UWB) sensor.

• Journal of Korean Neurosurgical Society
• /
• 제65권5호
• /
• pp.665-679
• /
• 2022

Objective : Patients with mild ischemic stroke experience various sequela and residual symptoms, such as anxious behavior and deficits in movement. Few approaches have been proved to be effective and safe therapeutic approaches for patients with mild ischemic stroke by acute stroke. Sildenafil (SIL), a phosphodiesterase-5 inhibitor (PDE5i), is a known remedy for neurodegenerative disorders and vascular dementia through its angiogenesis and neurogenesis effects. In this study, we investigated the efficacy of PDE5i in the emotional and behavioral abnormalities in rats with mild ischemic stroke. Methods : We divided the rats into four groups as follows (n=20, respectively) : group 1, naïve; group 2, middle cerebral artery occlusion (MCAo30); group 3, MCAo30+SIL-pre; and group 4, MCAo30+SIL-post. In the case of drug administration groups, single dose of PDE5i (sildenafil citrate, 20 mg/kg) was given at 30-minute before and after reperfusion of MCAo in rats. After surgery, we investigated and confirmed the therapeutic effect of sildenafil on histology, immunofluorescence, behavioral assays and neural oscillations. Results : Sildenafil alleviated a neuronal loss and reduced the infarction volume. And results of behavior task and immunofluorescence shown possibility that anti-inflammation process and improve motor deficits sildenafil treatment after mild ischemic stroke. Furthermore, sildenafil treatment attenuated the alteration of theta-frequency rhythm in the CA1 region of the hippocampus, a known neural oscillatory marker for anxiety disorder in rodents, induced by mild ischemic stroke. Conclusion : PDE5i as effective therapeutic agents for anxiety and movement disorders and provide robust preclinical evidence to support the development and use of PDE5i for the treatment of mild ischemic stroke residual disorders.

• 방송공학회논문지
• /
• 제25권1호
• /
• pp.83-93
• /
• 2020

최근 급격한 도시화 및 인구 집중으로 다양한 교통 문제가 빈번히 발생하고 있다. 따라서, 이를 효과적으로 해결하기 위한 교통 흐름 분석 관련 연구들이 활발히 진행되고 있다. 교통 흐름 정보는 도시 교통 관리의 핵심 요소로 차량 통행량 분석을 통해 수집된다. 본 논문에서는 도로 CCTV 영상에서 교통 흐름 정보를 정밀하게 추정하기 위해 차로 중앙 지점을 기반으로 한 고정밀 차량 통행량 측정 방법을 제안한다. 제안하는 방법은 심층 신경망(Deep Neural Network) 기반 객체 검출 방법을 이용하여 차량을 검출한 후, 누적 이동량을 바탕으로 각 차로의 중앙 지점을 검출한다. 또한, 객체 추적 기술을 통해 동일 차량의 궤적을 추정하여 검출된 각 차로 중앙 지점과의 거리를 비교함으로써 정밀하게 차량 통행량을 측정한다. 다양한 실험 결과들을 통해 본 논문에서 제안하는 방법이 차량 통행량 측정에 효과적임을 보인다.

• PNF and Movement
• /
• 제6권2호
• /
• pp.39-50
• /
• 2008

Purpose : This article reviewed the advances in the understanding of the effect of motor rehabilitation and brain plasticity on functional recovery after CNS damage. Methods : This is literature study with Pubmed, Medline and Science journal. Results : The inability of CNS neurons to regenerate is largely associated with nonneuronal aspects of the CNS environment. Especially, this neuronal growth inhibition is mediated by myelin associated glycoprotein, olygodendrocyte-myelin glycoprotein, and NOGO. Enriched environment, motor learning, forced limb use have been utilized in scientific studies to promote functional reorganization and brain plasticity. Especially, enriched environment and motor enrichment may prime the brain to respond more adaptively to injury, in part by expressed neurotrophic factors. Conclusions : These reviews suggest that activity-induced neural plasticity occur in damaged brain areas in order to functional reorganization, where it could contribute to motor recovery, and represent a target for stroke rehabilitation.

• Biomolecules & Therapeutics
• /
• 제25권4호
• /
• pp.390-395
• /
• 2017

The present study investigated the sedative effects of Sophora flavescens (SF) and its bioactive compound, matrine through performing locomotor activity test and the electroencephalography (EEG) analysis in the rat. The underlying neural mechanism of their beneficial effects was determined by assessing c-Fos immunoreactivity and serotonin (5-HT) in the brain utilizing immunohistochemical method and enzyme-linked immunosorbent assay. The results showed that SF and matrine administration had an effect on normalization of caffeine-induced hyperactivity and promoting a shift toward non-rapid eye movement (NREM) sleep. c-Fos-immunoreactivity and 5-HT level in the ventrolateral preoptic nucleus (VLPO), a sleep promoting region, were increased in the both SF and matrine-injected groups. In conclusion, SF and its bioactive compound, matrine alleviated caffeine-induced hyperactivity and promoted NREM sleep by activating VLPO neurons and modulating serotonergic transmission. It is suggested that SF might be a useful natural alternatives for hypnotic medicine.

• 한국컴퓨터정보학회논문지
• /
• 제28권10호
• /
• pp.9-16
• /
• 2023

태권도 겨루기의 전자호구, 축구의 VAR 등 스포츠에서 기술 발전이 고도화되고 있다. 하지만 태권도 품새는 사람이 직접 자세를 눈으로 보고 판단하며 지도하기 때문에 때로는 대회의 현장에서 판정시비가 일어난다. 본 연구는 인공지능을 이용하여 태권도 동작을 더 정확하게 판단하고 평가할 수 있는 인공지능 모델을 제안한다. 본 연구에서는 촬영 및 수집한 데이터를 전처리한 후 학습, 테스트, 검증 세트로 분리한다. 분리한 데이터를 각 모델과 조건을 적용하여 학습한 후 비교하여 가장 좋은 성능의 모델을 제시한다. 각 조건의 모델은 정확도, Precision, Recall, F1-Score, 학습 소요 시간, Top-n error의 값을 비교하였고 그 결과 ResNet50과 Adam을 사용한 조건에서 학습한 모델의 성능이 가장 우수한 것으로 나타났다. 본 연구에서 제시한 모델을 활용하여 교육 현장이나 대회 등 다양한 방면에서 활용할 수 있을 것으로 기대한다.

• PNF and Movement
• /
• 제5권1호
• /
• pp.29-35
• /
• 2007

Purpose : The purpose of this study was investigated to find the approach in the PNF and TC for frail elder Method : This is a literature study with books, articles, seminal note and books for PNF and TC international course. Result : Neural mechanisms contribute significantly to the gains that occur in the range of motion about a joint with stretching exercises. The participation in a stretch-training program decreases tonic reflex activity and increases flexibility and decreases in force production and muscle activation. Also the stretching-induced decreases may be due to a central nervous system inhibitory mechanism. PNF stretch techniques can increase ROM in older adults. These results may differ from those of studies performed with younger populations because of age-related physiologic changes. TC exercise improves balance control and muscle strength and were associated with reorganized lower extremity neuromuscular patterns. Conclusions : The stretch training program of the PNF and TC contribute to increase the balance and coordination for frail elder. Therefore, The frail elder prevent falling. Further study, The PNF and TC be introduced as the new therapeutic intervention for frail elder.