Feature Extraction Based on DBN-SVM for Tone Recognition

Chao, Hao,Song, Cheng,Lu, Bao-Yun,Liu, Yong-Li Korea Information Processing Society 2019 Journal of information processing systems Vol.15 No.1

An innovative tone modeling framework based on deep neural networks in tone recognition was proposed in this paper. In the framework, both the prosodic features and the articulatory features were firstly extracted as the raw input data. Then, a 5-layer-deep deep belief network was presented to obtain high-level tone features. Finally, support vector machine was trained to recognize tones. The 863-data corpus had been applied in experiments, and the results show that the proposed method helped improve the recognition accuracy significantly for all tone patterns. Meanwhile, the average tone recognition rate reached 83.03%, which is 8.61% higher than that of the original method.

Right-to-Left Displacement of an Airgun Lead Bullet after Transorbital Entry into the Skull Complicated by Posttraumatic Epilepsy : A Case Report

Chao-bin Wang,Hui Wang,Jun-shuang Zhao,Ze-jun Wu,Hao-dong Liu,Chao-jia Wang,An-rong Li,Dawei Wang,Juntao Hu 대한신경외과학회 2023 Journal of Korean neurosurgical society Vol.66 No.5

Penetrating head injury is a serious open cranial injury. In civilians, it is often caused by non-missile, low velocity flying objects that penetrate the skull through a weak cranial structure, forming intracranial foreign bodies. The intracranial foreign body can be displaced due to its special quality, shape, and location. In this paper, we report a rare case of right-to-left displacement of an airgun lead bullet after transorbital entry into the skull complicated by posttraumatic epilepsy, as a reminder to colleagues that intracranial metal foreign bodies maybe displaced intraoperatively. In addition, we have found that the presence of intracranial metallic foreign bodies may be a factor for the posttraumatic epilepsy, and their timely removal appears to be beneficial for epilepsy control.

Feature Extraction based on DBN-SVM for Tone Recognition

Hao Chao,Cheng Song,Bao-Yun Lu,Yongli Liu 한국정보처리학회 2019 Journal of information processing systems Vol.15 No.1

An innovative tone modeling framework based on deep neural networks in tone recognition was proposed inthis paper. In the framework, both the prosodic features and the articulatory features were firstly extracted asthe raw input data. Then, a 5-layer-deep deep belief network was presented to obtain high-level tone features. Finally, support vector machine was trained to recognize tones. The 863-data corpus had been applied inexperiments, and the results show that the proposed method helped improve the recognition accuracysignificantly for all tone patterns. Meanwhile, the average tone recognition rate reached 83.03%, which is 8.61%higher than that of the original method.

Landmark-Guided Segmental Speech Decoding for Continuous Mandarin Speech Recognition

( Hao Chao ),( Cheng Song ) 한국정보처리학회 2016 Journal of information processing systems Vol.12 No.3

In this paper, we propose a framework that attempts to incorporate landmarks into a segment-based Mandarin speech recognition system. In this method, landmarks provide boundary information and phonetic class information, and the information is used to direct the decoding process. To prove the validity of this method, two kinds of landmarks that can be reliably detected are used to direct the decoding process of a segment model (SM) based Mandarin LVCSR (large vocabulary continuous speech recognition) system. The results of our experiment show that about 30% decoding time can be saved without an obvious decrease in recognition accuracy. Thus, the potential of our method is demonstrated.

Landmark-Guided Segmental Speech Decoding for Continuous Mandarin Speech Recognition

Chao, Hao,Song, Cheng Korea Information Processing Society 2016 Journal of information processing systems Vol.12 No.3

In this paper, we propose a framework that attempts to incorporate landmarks into a segment-based Mandarin speech recognition system. In this method, landmarks provide boundary information and phonetic class information, and the information is used to direct the decoding process. To prove the validity of this method, two kinds of landmarks that can be reliably detected are used to direct the decoding process of a segment model (SM) based Mandarin LVCSR (large vocabulary continuous speech recognition) system. The results of our experiment show that about 30% decoding time can be saved without an obvious decrease in recognition accuracy. Thus, the potential of our method is demonstrated.

Vocal Effort Detection Based on Spectral Information Entropy Feature and Model Fusion

Chao, Hao,Lu, Bao-Yun,Liu, Yong-Li,Zhi, Hui-Lai Korea Information Processing Society 2018 Journal of information processing systems Vol.14 No.1

Vocal effort detection is important for both robust speech recognition and speaker recognition. In this paper, the spectral information entropy feature which contains more salient information regarding the vocal effort level is firstly proposed. Then, the model fusion method based on complementary model is presented to recognize vocal effort level. Experiments are conducted on isolated words test set, and the results show the spectral information entropy has the best performance among the three kinds of features. Meanwhile, the recognition accuracy of all vocal effort levels reaches 81.6%. Thus, potential of the proposed method is demonstrated.

Vocal Effort Detection Based on Spectral Information Entropy Feature and Model Fusion

( Hao Chao ),( Bao-yun Lu ),( Yong-li Liu ),( Hui-lai Zhi ) 한국정보처리학회 2018 Journal of information processing systems Vol.14 No.1

Vocal effort detection is important for both robust speech recognition and speaker recognition. In this paper, the spectral information entropy feature which contains more salient information regarding the vocal effort level is firstly proposed. Then, the model fusion method based on complementary model is presented to recognize vocal effort level. Experiments are conducted on isolated words test set, and the results show the spectral information entropy has the best performance among the three kinds of features. Meanwhile, the recognition accuracy of all vocal effort levels reaches 81.6%. Thus, potential of the proposed method is demonstrated.

Exosomes Derived from Mouse Breast Carcinoma Cells Facilitate Diabetic Wound Healing

Zhang Chao,Xiao Wenchi,Wang Hao,Li Linxiao,Yang Yan,Hao Yongwei,Xu Zhihao,Chen Hongli,Nan Wenbin 한국조직공학과 재생의학회 2024 조직공학과 재생의학 Vol.21 No.4

BACKGROUND: Exosomes derived from breast cancer have been reported to play a role in promoting cell proliferation, migration, and angiogenesis, which has the potential to accelerate the healing process of diabetic wounds. The aim of this investigation was to examine the function of exosomes originating from 4T1 mouse breast carcinoma cells (TEXs) in the process of diabetic wound healing. METHODS: The assessment of primary mouse skin fibroblasts cell proliferation and migration was conducted through the utilization of CCK-8 and wound healing assays, while the tube formation of HUVECs was evaluated by tube formation assay. High-throughput sequencing, RT-qPCR and cell experiments were used to detect the roles of miR-126a-3p in HUVECs functions in vitro. The in vivo study employed a model of full-thickness excisional wounds in diabetic subjects to explore the potential therapeutic benefits of TEXs. Immunohistochemical and immunofluorescent techniques were utilized to evaluate histological changes in skin tissues. RESULTS: The findings suggested that TEXs facilitate diabetic wound healing through the activation of cell migration, proliferation, and angiogenesis. An upregulation of miR-126a-3p has been observed in TEXs, and it has demonstrated efficient transferability from 4T1 cells to HUVEC cells. The activation of the PI3K/Akt pathway has been attributed to miR-126a-3p derived from TEXs. CONCLUSIONS: The promotion of chronic wound healing can be facilitated by TEXs through the activation of cellular migration, proliferation, and angiogenesis. The activation of the PI3K/Akt pathway by miR-126a-3p originating from TEXs has been discovered, indicating a potential avenue for enhancing the regenerative capabilities of wounds treated with TEXs. BACKGROUND: Exosomes derived from breast cancer have been reported to play a role in promoting cell proliferation, migration, and angiogenesis, which has the potential to accelerate the healing process of diabetic wounds. The aim of this investigation was to examine the function of exosomes originating from 4T1 mouse breast carcinoma cells (TEXs) in the process of diabetic wound healing. METHODS: The assessment of primary mouse skin fibroblasts cell proliferation and migration was conducted through the utilization of CCK-8 and wound healing assays, while the tube formation of HUVECs was evaluated by tube formation assay. High-throughput sequencing, RT-qPCR and cell experiments were used to detect the roles of miR-126a-3p in HUVECs functions in vitro. The in vivo study employed a model of full-thickness excisional wounds in diabetic subjects to explore the potential therapeutic benefits of TEXs. Immunohistochemical and immunofluorescent techniques were utilized to evaluate histological changes in skin tissues. RESULTS: The findings suggested that TEXs facilitate diabetic wound healing through the activation of cell migration, proliferation, and angiogenesis. An upregulation of miR-126a-3p has been observed in TEXs, and it has demonstrated efficient transferability from 4T1 cells to HUVEC cells. The activation of the PI3K/Akt pathway has been attributed to miR-126a-3p derived from TEXs. CONCLUSIONS: The promotion of chronic wound healing can be facilitated by TEXs through the activation of cellular migration, proliferation, and angiogenesis. The activation of the PI3K/Akt pathway by miR-126a-3p originating from TEXs has been discovered, indicating a potential avenue for enhancing the regenerative capabilities of wounds treated with TEXs.

Multidisciplinary Perspectives in Understanding Slow-moving Landslide

( Wei-an Chao ),( Ming-chien Chung ),( Keng-hao Kang ),( Chih-pin Lin ),( Tung-lin Tai ),( Hao-wen Yang ) 대한지질공학회 2019 대한지질공학회 학술발표회논문집 Vol.2019 No.2

Landslides have caused extensive infrastructure damage and threatened the human fatalities through the centuries. Among all triggered factors, massive precipitation and large earthquakes are considered to be the two key activators for pushing landslide moving, particularly for catastrophic landslides. The most acceptable mechanism resulting the landslide movement is liquefaction due to increasing water pore pressure. In this study, a landslide site has been well understood by hydrological, geophysical, geological, geodetic, geotechnical and seismological (H4GS) perspectives. Our seismic monitoring of daily relative velocity changes (dv/v) in sliding material decreased coinciding with first-half rainy period yet increased observing in post-half raining event. Geodetic survey (real-time kinematic, RTK; total station) before and after rainy period presents the vertical subsidence without any horizontal movement. The results from multidisciplinary investigation allow us to draw the conceptual model of landslide healing process caused by the water loading. Under the stability condition (F > 1.0) for each sliding materials, unconsolidated landslide colluvium and impermeable sliding surface could trap the seepage water to be as water pool, provided compact force acting on the materials below the sliding boundary. The vertical force of compaction facilitates to increasing the cohesion and strength of materials, tending the landslide material to be much stability. We demonstrated that healing process is periodically occurred but only for prolonged and intense precipitation combined with stability condition.

Blood-Blister Aneurysms of the Internal Carotid Artery in Tibetan and Han Populations : A Retrospective Observational Study

Bowen Huang,Yanming Ren,Hao Liu,Anqi Xiao,Lunxin Liu,Hong Sun,Yi Liu,Hao Liu,Lu Ma,Chang-Wei Zhang,Chao-Hua Wang,Min He,Yuekang Zhang,Chao You,Jin Li 대한신경외과학회 2024 Journal of Korean neurosurgical society Vol.67 No.3

Objective : Blood-blister aneurysms (BBAs) of the internal carotid artery (ICA) are challenging lesions with high morbidity and mortality rates. Although research on BBAs is well documented in different populations, the study of BBAs in the Tibetan population is extremely rare. This study aimed to evaluate the characteristics of BBAs and analyze the treatment modalities and long-term outcomes in the Tibetan population in comparison with the Han population. Methods : The characteristics of patients with BBAs of the ICA from January 2009 to January 2021 at our institution were reviewed. The features of aneurysms, treatment modalities, complications, and follow-up outcomes were retrospectively analyzed. Results : A total of 130 patients (41 Tibetan and 89 Han patients) with BBAs of the ICA who underwent treatment were enrolled. Compared with the Han group, the Tibetan group significantly demonstrated a high ratio of BBAs among ICAs (8.6%, 41/477 vs. 1.6%, 89/5563; p<0.05), a high ratio of vasospasm (34.1%, 14/41 vs. 6.7%, 6/89; p=0.001), a high risk of ischemic events (43.9%, 18/41 vs. 22.5%, 20/89; p<0.05), and a low ratio of good outcomes (modified Rankin scale, 0–2) at the 1-year follow-up (51.2%, 21/41 vs. 74.2%, 66/89; p<0.05). The multivariate regression model showed that ischemic events significantly contributed to the prediction of outcomes at 1 year. Further analysis revealed that microsurgery and vasospasm were associated with ischemic events. Conclusion : In comparison with Han patients, the Tibetan population had a high ratio of BBA occurrence, a high incidence of ischemic events, and a high ratio of poor outcomes. The endovascular approach showed more benefits in BBA patients.