臺灣人文及社會科學引文索引資料庫系統

:::

詳目顯示

回上一頁
第 1 筆 / 總合 1 筆   第一頁 上一頁 下一頁 最後一頁
/1頁
題名：基於深度學習之四面鉋床刀具安裝異音偵測
作者：薛凱藝
作者(外文)：HSUEH,KAI-YI
校院名稱：國立彰化師範大學
系所名稱：工業教育與技術學系
指導教授：盧建余
學位類別：博士
出版日期：2024
主題關鍵詞：人工智慧；異音偵測；卷積神經網路；梅爾頻率倒譜係數；梅爾倒頻譜；Artificial Intelligence；Anomalous Sound Detection；Convolutional Neural Network；Mel-Frequency Cepstral Coefficients；Mel Spectrogram
原始連結：連回原系統網址new window
相關次數：
  • 被引用次數被引用次數:期刊(0) 博士論文(0) 專書(0) 專書論文(0)
  • 排除自我引用排除自我引用:0
  • 共同引用共同引用:0
  • 點閱點閱:3
台灣木工機械近年來已將原有傳統產業轉型為與高科技結合的高科技產業，因全球科技的日新月異、疫情擴散、烏俄戰爭的影響及政府長期提供研發補助和稅收優惠等，台灣木工機械產業逐年將傳統機械產業往智慧製造邁進。機械產業中的人工智慧（Artificial Intelligence, AI）在應用面可增加實際效益並提高生產效率、品質控制、維護管理和人才培訓等。人工智慧的發展包括機器學習、深度學習、自然語言處理、專家系統等多個技術領域。但人工智慧的快速發展而被大量及廣泛應用，尤其以影像辨識和聲音辨識最為熱門領域。
臺灣目前的木工機械百分之八十以上為出口外銷，臺灣中部木工機械業者是全球木工機械供應重鎮，木工機械是用於將原木加工過程中的機檯設備，整個機檯中運作的核心是刀具。因此，本研究提出基於深度學習之四面鉋床刀具安裝異音偵測，將聲音分類運用於深度學習進行檢測，四面鉋床機檯刀具裝置後空載異音偵測模型訓練，並以預測木工機械刀具安裝是否異常取代過往人工經驗法則判斷應處方式。本研究使用C（Chroma）亮度、 S（Spectral Contrast）光譜對比與 T（Tonnetz）高低音合成CST、MFCC (Mel-Frequency Cepstral Coefficients)及Log-Mel ( Mel-frequency cepstrum )為基礎聲音特徵，「特徵」稱之為聲音頻譜圖，經由分類器(CNN)特徵訓練後準確度依序為CST為67.1% 、 MFCC為97.6%及Log-Mel為99.3%並再經模型驗證後，本研究選用MFCC與Log-Mel聲音特徵為使用模型訓練所需的數據。
本研究收集以木工刀具空載聲音正樣本與負樣本後進行模型訓練分類及驗證，MFCC空載正樣本聲及空載負樣本的分類準確率99.5%，Log-Mel空載正樣本聲及空載負樣本的分類準確率為99.89%，並透過混淆矩陣進行評估可以把聲音正確分類，經本研究進行模型訓練分類及驗證後，確認本研究所提出方法的可行性及有效性可達99.89%，顯示本研究四面鉋木機刀具架置後轉動之安裝正確與否，減少操作人員誤判和降低人員培訓成本。
In recent years, Taiwan's woodworking machinery has transformed its original traditional industry into a high-tech industry combined with high technology. Due to the rapid changes in global technology, the spread of the epidemic, the impact of the Ukraine-Russia war, and the government's long-term R&D subsidies and tax incentives, Taiwan's woodworking machinery The industry is moving the traditional machinery industry towards smart manufacturing year by year.
The application of Artificial Intelligence (AI) in the machinery industry can increase practical benefits and improve production efficiency, quality control, maintenance management and talent training in its application. The development of artificial intelligence includes many technical fields such as machine learning, deep learning, natural language processing, and expert systems. However, with the rapid development of artificial intelligence, it has been widely used in large numbers, especially in image recognition and sound recognition, which are the most popular fields.
More than 80% of Taiwan's current woodworking machinery is exported. The woodworking machinery industry in central Taiwan is a major global woodworking machinery supply chain. Woodworking machinery is a machine equipment used in the process of processing logs. The core of the entire machine operation is the cutting tool. Therefore, this study proposes deep learning-based detection of abnormal noise when installing cutter tools on a four-sided moulder. Sound classification is applied to deep learning for anomalous sound detection. The model is trained to detect no-load abnormal sound after the cutter tool is installed on the four-sided moulder, and is used to predict whether a woodworking machine cutter tool is mounted abnormally, replacing the previous manual rule of thumb.
In this study, CST was synthesized using C (Chroma) luminance, S (Spectral Contrast) spectral contrast and T (Tonnetz) treble and bass. Therefore, CST, MFCC (Mel-Frequency Cepstral Coefficients) and Log-Mel (Mel-frequency cepstrum) are the basic sound features which also known as sound spectrograms. After the model training process of the proposed model, the feature accuracies of the preliminary experiment results is 67.1% for CST, 97.6% for MFCC and 99.3% for Log-Mel. Therefore, both feature of MFCC and Log-Mel are selected to be the core features of the proposed model.
This study collected positive and negative samples of no-load sounds from woodworking cutter tools and conducted model training, classification, and verification. The classification accuracy for MFCC's no-load positive samples and no-load negative samples is 99.5%, while for Log-Mel, it is 99.89%. Through evaluation using the confusion matrix, the study confirmed the proposed model can output the correct classification of sound with lower error rate. After model training, classification, and verification in this study, it was confirmed that the proposed model's feasibility and effectiveness reached 99.89%. This demonstrates that the correct installation and rotation assessment of the four-sided wood planer, as proposed in this study, can reduce operator misjudgment and lower personnel training costs.
[1] P. C. Chang, C. P. Wang, B. J. C. Yuan and K. T. Chuang, “Forecast of development trends in Taiwan's machinery industry,” Technological Forecasting and Social Change., Vol. 69, pp. 781-802, 2002.
[2] L. R. LIN, “ Lean Smart Manufacturing in Taiwan? Focusing on the Bicycle Industry” Journal of Open Innovation: Technology, Market, and Complexity., Vol. 5, No. 4, pp. 79-91, 2019.
[3] I. Islam, K. M. Munim, M. N. Islam and M. M. Karim, “A Proposed Secure Mobile Money Transfer System for SME in Bangladesh: An Industry 4.0 Perspective,” 2019 International Conference on Sustainable Technologies for Industry 4.0 (STI), pp. 1-6, 2019.
[4] C. F. Chan and E. W. M. Yu, “An abnormal sound detection and classification system for surveillance applications, ” 2010 18th European Signal Processing Conference, Aalborg, Denmark, pp. 1851-1855, 2010.
[5] 許心俞，智慧製造環境下應用人工智慧、交互式三維輔助設計與機器人關鍵技術專利之趨勢與佈局分析，國立彰化師範大學財務金融技術學系，博士論文，2023。
[6] M. Bosovska, M. Boiko, L. Bovsh and A. Okhrimenko, “Models of the Industrial Revolution 5.0, ” 2022 IEEE 4th International Conference on Modern Electrical and Energy System (MEES), pp. 1-4 , 2022.
[7] S. M. Noble, M. Mende, D. Grewal, and A. Parasuraman, “The Fifth Industrial Revolution: How Harmonious Human–Machine Collaboration is Triggering a Retail and Service [R]evolution,” Journal of Retailing., Vol. 98, No. 2, pp. 199-208, 2022.
[8] Everything you need to know about the Fourth Industrial Revolution：https://www.cnbc.com/2019/01/16/fourth-industrial-revolution-explained-davos-2019.html(accessed March 2023)
[9] J. Buckberry and G. K. Gillian, “The dark satanic mills: Evaluating patterns of health in England during the industrial revolution,” International Journal of Paleopathology, Vol. 39, pp. 93-108, 2022.
[10] A. W. Colombo, S. Karnouskos, X. Yu, O. Kaynak, R. C. Luo, Y. Shi, P. Leitao, L. Ribeiro, and J. Haase, “A 70-Year Industrial Electronics Society Evolution Through Industrial Revolutions: The Rise and Flourishing of Information and Communication Technologies, ” in IEEE Industrial Electronics Magazine, Vol. 15, No. 1, pp. 115-126, 2021.
[11] A. Mathur, A. Dabas and N. Sharma, “Evolution From Industry 1.0 to Industry 5.0, ” 2022 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), pp. 1390-1394, 2022.
[12] S. Wicha, P. Temdee, C. Kamyod, R. Chaisricharoen, J. M. Thiriet and H. Yahoui, “Industrial requirements analysis for Excellence Center setting-up and curriculum design in Industry 4.0 context, ” 2023 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON, pp. 423-426 , 2023.
[13]工業4.0大全：從淺到深一篇搞懂它！台灣半導體協會: https://www.semi.org/zh/blogs/technology-trends/industry-4.0 (accessed June 2023)
[14] R. Hellebrand, M. Schulze and M. Becker, “A branching model for variability-affected cyber-physical systems, ” 2016 3rd International Workshop on Emerging Ideas and Trends in Engineering of Cyber-Physical Systems (EITEC), pp. 47-52, 2016.
[15] A. Y. Zalozhnev and V. N. Ginz, “Industry 4.0: Underlying Technologies. Industry 5.0: Human-Computer Interaction as a Tech Bridge from Industry 4.0 to Industry 5.0, ” 2023 9th International Conference on Web Research (ICWR), pp. 232-236, 2023.
[16] X. Xu, L. Lu, B. V. Heuser and L. Wang, “Industry 4.0 and Industry 5.0—Inception, conception and perception, ” Journal of Manufacturing Systems Vol. 61, pp. 530-535, 2021.
[17] Industry 5.0: Towards more sustainable, resilient and human-centric industry : https://research-and-innovation.ec.europa.eu/news/all-research-and-innovation-news/industry-50-towards-more-sustainable-resilient-and-human-centric-industry-2021-01-07_en (accessed June 2023)
[18] L. Gomathi, A. K. Mishra and A. K. Tyagi, “Industry 5.0 for Healthcare 5.0: Opportunities, Challenges and Future Research Possibilities, ” 2023 7th International Conference on Trends in Electronics and Informatics (ICOEI), pp. 204-213, 2023.
[19] S. D, B. A, K. TR, S. k. D, S. V and J. L. N, “A Multimodal AI Framework for Hyper Automation in Industry 5.0, ” 2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA), pp. 282-286, 2023.

[20] Y. Kwon, J. H. Han, Y. C. P. Cho, J.Y. Kim, J. Chung, J. Choi, S. Park, I. Kim, H. Kwon, J. Kim, H. Kim, W. Jeon, Y. Jeon, M. Cho and M. Choi, “Chiplet Heterogeneous-Integration AI Processor, ” 2023 International Conference on Electronics, Information, and Communication (ICEIC), pp. 1-2, 2023.
[21] B. Topuz and N. Ç. Alp, “Machine learning in architecture,” Automation in Construction, Vol. 154, pp. 105012-105026, 2023.
[22] Z. Zhang, C. Wang, D. Weng, Y. Liu and Y. Wang, “Symmetrical Reality: Toward a Unified Framework for Physical and Virtual Reality, ”2019 IEEE Conference on Virtual Reality and 3D User Interfaces (VR), pp. 1275-1276, 2019.
[23] T. Weissker, P. Bimberg, A. Kodanda and B. Froehlich, “Holding Hands for Short-Term Group Navigation in Social Virtual Reality, ”2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), pp. 728-729, 2022.
[24] Novel Coronavirus (2019-nCoV) SITUATION REPORT - 1 : https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200121-sitrep-1-2019-ncov.pdf (accessed May 2023)
[25] Russia-Ukraine War：https://www.britannica.com/event/2022-Russian-invasion-of-Ukraine (accessed May 2023)
[26] E. M. Diaz, J.Cunado and F. P. d. Gracia, “Commodity price shocks, supply chain disruptions and U.S. inflation, ” Finance Research Letters., Vol. 58, Part C . 104495, 2023.
[27] T. Chen and G. Ji, “Study on supply chain disruption risk, ” 2009 6th International Conference on Service Systems and Service Management, pp. 404-409, 2009.
[28]台灣工具機產值全球排名第7位遜於陸日韓: https://today.line.me/tw/v2/article/fc25e352c27149b82b363898aedff22ec59b3e073d1bbc5231d79a59ccae9bf7 (accessed May 2023)
[29] 機械業是台灣第3個兆元產業持續支持發展：https://www.cna.com.tw/news/afe/202303060122.aspx (accessed May 2023)
[30]木工機產業聚落 拚出全球競爭力：https://www.trademag.org.tw/page/itemsd/?id=719345&no=54 (accessed May 2023)
[31] 鄭彥邦，以梅爾係數特徵值為基礎之木工機械刀具異音檢測，國立勤益科技大學資訊管理系研發科技與資訊管理碩士在職專班，碩士論文，2023。
[32] 林其德，鎳基合金端銑削切削溫度與刀具壽命研究，國立中正大學機械工程學系暨研究所碩士論文，博士論文，2011。
[33] 台達工業自動化。張開智慧之耳，台達自主研發的 AI 檢測一聽就知道哪裡故障。科技報橘2020年12月09日取自：https://buzzorange.com/techorange/2020/12/09/delta-mortar-ai-qc/(accessed May 2023)
[34] Y. Yan, Z. Li, H. Yu, D. Dang and Z. Liu, “An Online Leakage Current Monitoring System of MOV used in Series Capacitor Compensation, ” 2018 International Conference on Power System Technology (POWERCON), pp. 3541-3546, 2018.
[35] B. Samia, Z. Soraya and M. Malika, “Fashion Images Classification using Machine Learning, Deep Learning and Transfer Learning Models, ” 2022 7th International Conference on Image and Signal Processing and their Applications (ISPA), pp. 1-5, 2022.
[36] R. P. Vasava and H. A. Joshiara, “Different Respiratory Lung Sounds Prediction using Deep Learning, ” 2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC), pp. 1626-1630, 2023.
[37] O. M. Badreldine, N. A. Elbeheiry, A. N. M. Haroon, S. ElShehaby and E. M. Marzook, “Automatic Diagnosis of Asphyxia Infant Cry Signals Using Wavelet Based Mel Frequency Cepstrum Features, ” 2018 14th International Computer Engineering Conference (ICENCO), pp. 96-100, 2018.
[38]林佑錩，以梅爾倒頻譜係數特徵值為基礎之木工機刀具異音偵測，國立勤益科技大學資訊管理系研發科技與資訊管理碩士在職專班，碩士論文，2023。
[39] K. Ranipa, W. P. Zhu and M. N. S. Swamy, “ Multimodal CNN Fusion Architecture with Multi-Features for Heart Sound Classification, ”2021 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5, 2021.
[40] M. Mahyub, L. S. Souza, B. Batalo and K. Fukui, “Environmental Sound Classification Based on CNN Latent Subspaces, ” 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), pp. 1-5, 2022.
[41] T. Lin, P. Zhang, S. Wang, K. Zhou and X. Chen, “Mixed Chroma Sampling-Rate High Efficiency Video Coding for Full-Chroma Screen Content, ” in IEEE Transactions on Circuits and Systems for Video Technology, Vol. 23, No.1 , pp. 173-185, 2013.
[42] N. Mu, X. Xu, L. Chen and J. Tian, “Block-Based Salient Region Detection Using a New Spatial-Spectral-Domain Contrast Measure, ” 2014 IEEE International Symposium on Multimedia, pp. 86-89, 2014.
[43] E. J. Humphrey, T. Cho and J. P. Bello, “Learning a robust Tonnetz-space transform for automatic chord recognition, ”2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 453-456, 2012.
[44] S. Seo, C. Kim and J. -H. Kim, “Convolutional Neural Networks Using Log Mel-Spectrogram Separation for Audio Event Classification with Unknown Devices, ” in Journal of Web Engineering, Vol. 21, No. 2, pp. 497-522, March, 2022.
[45] R. F. Rahmat, T. Ramadhani, D. Gunawan, S. Faza and R. Budiarto, “ Mel-frequency Cepstral Coefficient-Vector Quantization Implementation for Voice Detection of Rice-Eating Birds in The Rice Fields, ” 2018 Third International Conference on Informatics and Computing (ICIC), pp. 1-6, 2018.
[46] J. Chen, F. Zhang and Y. Li, “A Sound Event Recognition Method of Crop Shear Scrap Falling State Based on Log-Mel Spectrogram and MobileNetV2, ” 2023 42nd Chinese Control Conference (CCC), pp. 6946-6951, 2023.
[47] Ç. Candan, “Parameter Estimation For Bursty-Intermittent Observations, ” 2020 28th Signal Processing and Communications Applications Conference (SIU), pp. 1-4, 2020.
[48] Z. Zebing and H. Weidong, “Hyper parameter estimation in MRF-based SAR chip image segmentation, ” Proceedings of 2011 IEEE CIE International Conference on Radar, pp. 760-763, 2011.
[49] 木工機與塑膠機產業：https://www.digitimes.com.tw/seminar/dois_20141008/pdf/2014_%E6%9C%A8%E5%B7%A5%E6%A9%9F%E8%88%87%E5%A1%91%E8%86%A0%E6%A9%9F%E7%94%A2%E6%A5%AD%E8%AA%AA%E5%B8%96%E6%9B%B4%E6%96%B0(%E4%B8%AD).pdf(accessed May 2023)
[50] 張聰捷，木工機械產業發展策略研究，國立勤益科技大學資訊管理系，碩士論文， 2018。
[51] 王勝樑，少子化衝擊下兒童教育產業經營管理模式之個案研究，朝陽科技大學企業管理系台灣產業策略發展博士班，博士論文，2017。
[52] 沈步璠，應用規劃求解最佳化模式分析有限人力資源配置:以企業建廠為例，逢甲大學土木及水利工程博士學位學程，博士論文，2015。
[53] 陳映辰，以類神經網路學習及模糊滑動模式控制為基礎實現雙氣壓肌肉驅動手臂之快速追跡控制，國立臺灣科技大學機械工程系，博士論文，2018。
[54] 黃斌，面向視覺心率估計的時空神經網絡研究，國立中興大學電機工程學系所，博士論文，2022。
[55] D. Isogai, B. Liu, Y. Ishiguchi and S. Nakatake, “Analog Characterization Module with Data Converter-Coupled Signal Reconfiguration, ”2017 New Generation of CAS (NGCAS), pp. 149-152, 2017.
[56]臺灣木工機械工業同業公會：http://www.industry.org.tw/Company/show_data.asp?department_id=9385(accessed May 2023)
[57] 謝仁桂，創新製程應用於齒輪刀具製造之研究，國立交通大學機械工程系所，博士論文，2008。
[58] LEADERMAC MACHINERY CO., LTD.：https://www.leadermac.com/index.html(accessed September 2023)
[59] M. S. Carmeli, F. C. Dezza, M. Mauri and L. Piegari, “Energy recovery and efficiency optimisation in a wood cutting machines, ” 2013 International Conference on Clean Electrical Power (ICCEP), pp. 524-528, 2013.
[60] 張家豪，結合機台防碰撞與切削力模擬之新型擺線路徑研究，國立中正大學機械工程系研究所，博士論文，2022。
[61] X. Zhao, J. Ji and C.Lv, “Primary investigation of machine tool's appearance modeling design, ”2009 IEEE 10th International Conference on Computer-Aided Industrial Design & Conceptual Design, pp. 120-125, 2009.
[62] S. Chen, X. Xie and P. Cong, “A measurement system based on virtual instrumentation for field dynamic balancing of rotors, ” 2009 International Conference on Information and Automation, pp. 768-772, 2009.
[63] 張富惇，預估微小徑鑽頭加工壽命之智能感測系統，國立雲林科技大學機械工程系，博士論文，2022。
[64] 王教燊，基於深度學習之智慧型馬達系統設計及螺帽品質檢測，國立中山大學機械與機電工程學系研究所，博士論文，2022。
[65] F. Ye, H. Zhang, J. Ouyang, J. Zhou and L. Hu, “Power Plant Production Equipment Abnormal Sound Perception Method Research based on Machine Hearing, ” 2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS), pp. 179-184, 2022.
[66] L. Zhenzhen, W. Xiaoming and D. Minghui, “A novel method for feature extraction of crackles in lung sound, ” 2012 5th International Conference on BioMedical Engineering and Informatics, pp.399-402, 2012.
[67] M. Mishra, A. Singh, M. K. Dutta, R. Burget and J. Masek, “Classification of normal and abnormal heart sounds for automatic diagnosis, ” 2017 40th International Conference on Telecommunications and Signal Processing (TSP), pp. 753-757, 2017.
[68] S. A. H. Tabatabaei, P. Fischer, H. Schneider, U. Koehler, V. Gross and K. Sohrabi, “Methods for Adventitious Respiratory Sound Analyzing Applications Based on Smartphones: A Survey, ” in IEEE Reviews in Biomedical Engineering, Vol. 14, pp. 98-115, 2021.
[69] S. Prusty, S. Patnaik and S. K. Dash, “Differentiating S1, S2 Noises from Abnormal Heart Sounds Generated in Closure of Atrioventricular and Semilunar Valves using MFCC and LSTM, ” 2022 1st IEEE International Conference on Industrial Electronics: Developments & Applications (ICIDeA), pp. 208-213, 2022.
[70] Y. Ye, J. Zhang and H. Liang, “An Acoustic-Based Recognition Algorithm for the Unreleased Braking of Railway Wagons in Marshalling Yards, ” in IEEE Access, Vol. 8, pp. 120295-120308, 2020.
[71] Y. Peng, X. Zhong, X. Yang and L. Hu, “Detection of Abnormal Sound of Power Plant Equipment Fault based on Self-supervised Learning, ” 2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS), pp. 174-178, 2022.
[72] R. Tanabe, H. Purohit, K. Dohi, T. Endo, Y. Nikaido, T. Nakamura and Y Kawaguchi, “MIMII Due: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection with Domain Shifts Due to Changes in Operational and Environmental Conditions, ” 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 21-25, 2021.
[73] G. Kim and Y. Choo, “Bi-Sphere Anomaly Detection With Learnable Centroid for Active Sonar Classification, ” in IEEE Access, Vol. 10, pp. 128590-128603, 2022.
[74] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-Based Learning Applied to Document Recognition, ” PROC. OF THE IEEE, NOVEMBER,1998.
[75] E. Buluş, “Gender Determination from Pictures with CNN Models, ” 2021 6th International Conference on Computer Science and Engineering (UBMK), pp. 310-313, 2021.
[76] L. Koshy, A. S, A. Paul, H. V and A. Basheer, “Video Forgery Detection using CNN, ” 2021 Smart Technologies, Communication and Robotics (STCR), pp. 1-6, 2021.
[77] A. Krizhevsky, I. Sutskever and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks, ” Advances in Neural Information Processing Systems 25, (NIPS 2012).
[78] M. D. Zeiler and R. Fergus, “ Visualizing and Understanding Convolutional Networks, ” Computer Science, Computer Vision and Pattern Recognition, arXiv:1311.2901, 2013.
[79] C. Szegedy , W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A Rabinovich, “Going deeper with convolutions,”2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-9, 2015.
[80] K. Simonyan and A. Zisserman, “ Very Deep Convolutional Networks for Large-Scale Image Recognition, ” Published as a conference paper at ICLR 2015, 2015.
[81] K. He, X. Zhang, S. Ren and Jian Sun, “Deep Residual Learning for Image Recognition, ” https://arxiv.org/abs/1512.03385
[82] A. G. Howard, M. Zhu, Bo Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto and H. Adam. “ MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” https://arxiv.org/abs/1704.04861
[83] M. Tan and Q. V. Le , “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” International Conference on Machine Learning, Vol. 5, 2019, arXiv:1905.11946
[84] K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition, ” Published as a conference paper at ICLR , 2015, arXiv:1409.1556v6
[85] URBANSOUND8K DATASET：https://urbansounddataset.weebly.com/urbansound8k.html (accessed September 2023)
[86] C. Zhang, M. D. Frye, W. Sun, A. Sharma, S. Manohar, R. Salvi and B. Hu, “New insights on repeated acoustic injury: Augmentation of cochlear susceptibility and inflammatory reaction resultant of prior acoustic injury, ” Vol. 393, August 2020.
[87] P. Ruan, X. Zheng,Y. Qiu and Z. Hao, “A Binaural MFCC-CNN Sound Quality Model of High-Speed Train, ” Applied Sciences, Vol. 12,No.23: 12151, 2022.
[88] Á. Oliveira, D. Cavaleiro, R. Branco, H. Hadla and S. Cruz, “An encoderless high-performance synchronous reluctance motor drive, ” 2015 IEEE International Conference on Industrial Technology (ICIT), Seville, pp. 2048-2055, 2015.
[89] P. Singh, A. Prakash and S. K. Parida, “Neural network based pattern recognition for classification of the forced and natural oscillation, ” Electric Power Systems Research, Vol. 224, 109706, 2023.
[90] L. Muda, M. Begam and I. Elamvazuthi, “Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques,” arXiv:1003.4083v1
[91] J. Xiang, Q. Zhou, S. Yi, and Y. Qu, “Fluorescence Spectral Imaging Based on Computational Spectral Sensing,” 2023 American Physical Society, Vol. 19, 024022, Published 8, 2023.
[92] H. Kui , J. Pan , R. Zong , H. Yang and W. Wang, “Heart sound classification based on log Mel-frequency spectral coefficients features and convolutional neural networks,” Biomedical Signal Processing and Control, Vol. 69, 2021.
[93] C. Wiwatcharakoses and D. Berrar, “A self-organizing incremental neural network for continual supervised learning,” Expert Systems with Applications, Vol. 185, 2021.
[94] E. Sivari, M. S. Güzel. E. Bostanci and A. Mishra, “A Novel Hybrid Machine Learning Based System to Classify Shoulder Implant Manufacturers,” Healthcare, Vol. 10, 580, 2022.
[95] E. Sivari, Z. Civelek and S. Sahin,“Determination and classification of fetal sex on ultrasound images with deep learning,”Expert Systems with Applications, Vol. 240, 122508, 2024.
[96] Z. H. Hoo, J. Candlish and D. Teare “What is an ROC curve? ” Emerg Med J, Vol. 34, pp. 357-359. 2017.

 
 
 
 
第一頁 上一頁 下一頁 最後一頁 top
QR Code
QRCODE

臺灣人文及社會科學引文索引資料庫

目前上線人數：761（臺灣：737，外國：24） ／ 本年度總使用人次：2541260 ／ 訪客人次（自102年09月）：68346136
國家圖書館著作權聲明 Copyright © 2013 All rights reserved.
本館地址: 100201臺北市中山南路20號． 本館地圖及交通資訊．
總機：(02)23619132．最佳瀏覽解析度為1024x768以上