跳到主要內容

臺灣博碩士論文加值系統

(18.97.14.86) 您好!臺灣時間:2025/02/09 00:39
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:Haobijam Basanta
研究生(外文):HAOBIJAM BASANTA
論文名稱:以深度學習演算法應用於資料分析與影像分類
論文名稱(外文):Deep Learning Algorithms in Data Analysis and Image Classification
指導教授:黃有評黃有評引用關係
指導教授(外文):HUANG,YO-PING
口試委員:黃有評練光佑李祖添蘇順豐林志民
口試委員(外文):HUANG,YO-PINGLIAN,KUANG-YOWLEE,TSU-TIANSU,SHUN-FENGLIN,CHIH-MIN
口試日期:2019-07-08
學位類別:博士
校院名稱:國立臺北科技大學
系所名稱:電資國際專班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2019
畢業學年度:107
語文別:英文
論文頁數:142
外文關鍵詞:Help to yousymptom checkervoice and gesture recognitiondeep learningdeep belief networkfuzzy analytical network processtransformed fuzzy neural networkconvolution neural networkbird classificationretinopathy of prematurity (ROP)
相關次數:
  • 被引用被引用:0
  • 點閱點閱:743
  • 評分評分:
  • 下載下載:6
  • 收藏至我的研究室書目清單書目收藏:0
Early recognition and diagnosis of disease are the best health practices in terms of minimizing health risks and limiting the dangers to well-being faced by each individual in their daily life. But most of the patients are daunted or neglected the preventive measures of health and safety challenges due to a lack of medical knowledge. They have under-recognized problems that can prompt conjunction with other health issues and exacerbate other diseases if not properly managed. Moreover, in the traditional healthcare, paper records are used to maintain the clinical history of the patients, which leads a greater risk of misplacement or lost and consequently hinder the treatment. So, it is vital to comprehend and recognize the preventive measures that can ensure proper care and improve or maintain quality of their daily life. To condense the risk for complications and assess the causes of unintended consequences of health risk this study aimed to validate the efficiency of constant monitoring and clinical data analysis of the patients from infants to elderly people by integrating diverse deep learning platforms in real time. The system includes Help-to-You (H2U) that can collect the Electronic Health Record (EHR) from the user through a mobile application. The collected clinical data can be monitored and managed seamlessly. Symptom checker which helps the user to define the type of ailments that they may have and suggests the right medical consultation. Voice and gesture recognition platform was used to control the user’s home appliances and gadgets. To ascertain and identify activities that are related to various health and self-care problems, a deep belief network (DBN) was used to monitor unsupervised, diverse daily life activities of patients or elderly people. Simulation results showed that the proposed system with DBN outperformed the support vector machines in terms of F1 score and accuracy in identifying daily activities. Uncertainty is an inherent problem of medical diagnosis due to the lack of sufficient evidences to assess a disease. A Fuzzy Analytical Network Process (FANP) with Transformed Fuzzy Neural Network (TFNN) was proposed to achieve best clinical judgement and precise treatment, especially applicable to enhance the classification accuracy. A benchmark dataset, diabetic retinopathy Debrecen was used to validate the model. Through the process, the model achieved 100% accuracy. A deep learning model using convolutional neural network (CNN) was designed to detect and classify the severity of ROP diseases which are especially observed in preterm infants with low birth weights. The model was applied to a group of patients at the early stages of the disease, i.e., stages 1 and 2. The inputs consisted 2205 annotated fundus images and validated by 441 test images with 10-fold cross validations. The preliminary result yielded a high accuracy rates for training and test datasets. Birdwatching is a recreational activity that can provide relaxation in daily life and promote resilience to face daily challenges. It can also offer health benefits and happiness derived from enjoying nature. Lastly, a CNN with skip connection was adopted to classify 3563 images of 27 endemic birds of Taiwan. The trained model was tested by 713 images, which achieved average sensitivity, specificity, and accuracy of 93.79%, 96.11%, and 95.37%, respectively. Timely recognition of health issues is mandatory and therefore the methods applied in this study might uplift a perspective on the treatment of patients. This process would impact immense benefit and improve the clinical data analysis with efficient classification of inherent problem of medical diagnosis.
Contents
ABSTRACT i
ACKNOWLEDGMENTS iv
List of Figures x
List of Tables xiii
Chapter 1 Introduction 1
1.1 Background 1
1.2 Problems Statement 2
1.2.1 Patient and Physical Safety 2
1.2.2 Decision Maker Concerns 3
1.3 Dissertation Development 3
Chapter 2 Literature Review 5
2.1 Introduction 5
2.2 Fuzzy Analytical Approach 6
2.2.1 Fuzzy Number 6
2.2.2 Computational Fuzzy Analytical Hierarchal Process 7
2.3 Convolution Neural Network 9
2.3.1 Batch Normalization (BN) 10
2.3.2 ReLU Activation 11
2.3.3 Pooling Layer 11
2.4 Restricted Boltzmann Machines (RBMs) 13
2.5 Deep Belief Network (DBN) 16
Chapter 3 Internet of Deep Healthcare 18
3.1 Introduction 18
3.2 Internet of Deep Healthcare Architecture 19
3.3 Internet of Deep Healthcare Amenities 20
3.3.1 Insurance 20
3.3.2 First Aid 21
3.3.3 Emergency Support System 22
3.3.4 Medical Record 22
3.3.5 Medication Reminder 23
3.3.6 Fall Detection 24
Chapter 4 Health Symptom Checking System for Elderly People Using Fuzzy Analytic Hierarchy Process 27
4.1 Introduction 27
4.2 MCDA Fuzzy AHP 28
4.3 Approach of Symptom Checker 29
4.4 Weight Determination for Various Diseases 31
4.5 Results 42
Chapter 5 Assistive Design for Elderly Living Ambient Using Voice and Gesture Recognition System 46
5.1 Introduction 46
5.2 Backbone Connection of Smart Environment 47
5.2.1 Voice Control 48
5.2.2 Gesture Control 51
5.2.3 Personal Monitoring System 58
5.3 Smart Interface 59
Chapter 6 Sensor-Based Detection of Abnormal Events in Daily Behavior of Elderly People by Using Deep Belief Network (DBN) 62
6.1 Introduction 62
6.2 Intelligent Home Environment 62
6.2.1 Data Acquisition by Sensors 62
6.2.2 Data Collection for Daily Activities 64
6.3 Network Architecture and Training 69
6.4 Results and Performance Evaluation 72
Chapter 7 A Fuzzy Approach to Determining Critical Factors of Diabetic Retinopathy and Enhancing Data Classification Accuracy 76
7.1 Introduction 76
7.2 Diabetic Retinopathy Dataset 77
7.3 Fuzzy Analytical Network Process (FANP) 78
7.4 Transformed Fuzzy Neural Network 81
7.5 Case Study 83
7.6 Experimental Results 95
7.6.1 Performance Evaluation 95
7.6.2 Association Rules 100
Chapter 8 Automated Detection of Early Stages Retinopathy of Prematurity with a Deep Convolution Neural Network 104
8.1 Introduction 104
8.2 Data Acquisition 105
8.3 Data Labelling 106
8.4 Data Generator 106
8.5 Network Architecture 107
8.6 Training of ROP Fundus Images 107
8.7 Experimental Results and Analysis 109
8.7.1 Statistics Analysis 109
8.7.2 Analysis of Misclassified Samples 110
Chapter 9 Bird Image Retrieval and Recognition Using Deep Learning Platform 112
9.1 Introduction 112
9.2 Data Acquisition 113
9.2.1 Internet of Bird (IoB) 113
9.2.2 Internet Bird Images 114
9.3 Proposed Deep Learning Model 115
9.3.1 CNN Architecture 115
9.3.2 Skip Connections 115
9.3.3 Training of the Bird Dataset 116
9.3.4 Feature Extraction 119
9.3.5 System Implementation 120
9.4 Experimental Results and Analysis 124
Chapter 10 Conclusions and Future Works 131
10.1 Conclusions 131
10.2 Future Works 132
References 133
References
[1]Mic.iii.org.tw (2009), “Impact on markets of the aging population in Taiwan, other Asian countries becoming increasingly evident,” [online]. https://mic.iii.org.tw/english/PressRelease_Detail.aspx?sqno=6742&type=Press&DataClass=Press%20Room, Accessed on May 30, 2017.
[2]L. Yang, A. M. MacEachren, P. Mitra, and T. Onorati, “Visually-enabled active deep learning for (geo) text and image classification: a review,” Int. Journal of Geo-Information, vol. 7, no. 2, pp.1-38, Feb. 2018.
[3]J. Dean, G. S. Corrado, R. Monga, K. Chen, M. Devin, Q. V. Le, M. Mao, M. Ranzato, A. Senior, P. Tucker, K. Yang, and A. Y. Ng, “Large-scale distributed deep networks,” in Proc. of 25th Int. Conf. of the Advance in Neural Information Processing Systems, Lake Tahoe, NV, USA, pp.1223-1231, Dec. 2012.
[4]M. I. Razzak, S. Naz, and A. Zaib. “Deep learning for medical image processing: overview, challenges and the future. In: Dey N, Ashour AS, Borra S, editors. Classification in bioApps,” Switzerland: Springer, Cham, pp.323-350, Nov. 2017.
[5]M. L. Giger, “Machine learning in medical imaging,” Journal of the American College of Radiology, vol. 15, no. 3, pp.512-520. Mar. 2018.
[6]A. Z. Lotfi, “Fuzzy sets,” Information and Control, vol. 8, no. 3, pp.338-353, Jun. 1965.
[7]F. Liu, Y. Peng, W. Zhang, and W. Pedrycz, “On consistency in AHP and Fuzzy AHP,” Journal of Systems Science and Information, vol. 5. no. 2. pp.127-148, Apr. 2017.
[8]A.Voulodimos, N. Doulamis, A. Doulamis, and E. Protopapadakis, “Deep learning for computer vision: A brief review,” Computational Intelligence and Neuroscience, vol. 2018, pp.1-13, Feb. 2018.
[9]S. Ioffe and C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift,” in Proc. of the 32nd Int. Conf. on Machine Learning, vol. 37, pp.448-456, Mar. 2015.
[10]X. Zhang, H. Xiong, W. Zhou, W. Lin, and Q. Tian, “Picking deep filter responses for fine-grained image recognition,” in Proc. of Int. Conf. on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp.1134-1142, Dec. 2016.
[11]Y. Bengio, “Learning deep architectures for AI,” Foundations and Trends in Machine Learning, vol. 2, vo. 1, pp.1-127, Jan. 2009.
[12]G. Montufar and N. Ay, “Refinements of universal approximation results for deep belief networks and restricted Boltzmann machines,” Journal of Neural Computation, vol. 23, no. 5, pp.1306-1319, Jul. 2011.
[13]G. E. Hinton, S. Osindero, and Y. W. The, “A fast learning algorithm for deep belief nets,” Neural Computation, vol. 18, no. 7, pp.1527-1554, Jul. 2006.
[14]G. E. Hinton, “Deep belief networks,” Scholarpedia, 4(5947) [online] http://www.scholarpedia.org/article/Deep_belief_networks, Accessed on Jun. 15, 2017.
[15]T. L. Saaty, “Decision making with the analytic hierarchy process,” Int. Journal Service Science, vol. 1, no. 1, pp.83-97, Mar. 2008.
[16]S. Kanugantia, R. Agarwalab, B. Dutta, P. Bhanegaonkard, A. P. Singh, and A. K. Sakar, “Road safety analysis using multi criteria approach: A case study in India,” Transportation Research Procedia, vol. 25, pp.4649-4661, Jul. 2017.
[17]C. Bahler, C. A. Huber, B. Brüngger, and O. Reich, “Multimorbidity, health care utilization and costs in an elderly community-dwelling population: A claims data based observational study,” BMC Health Services Research, vol. 15, no. 23, pp.15-23, Jan. 2015.
[18]S. M. McPhail, “Multimorbidity in chronic disease: Impact on health care resources and costs,” Risk Management Healthcare Policy, vol. 9, pp.143-156, Jul. 2016.
[19]Z. Tyack, K. A. Frakes, A. Barnett, P. Cornwell, S. Kuys, and S. McPhail, “Predictors of health-related quality of life in people with a complex chronic disease including multimorbidity: A longitudinal cohort study,” Quality of Life Research, vol. 25, no. 10, pp.2579-2592, Oct. 2016.
[20]A. Afsordegan, M. Sanchez, N. Agell, S. Zahedi, and L. V. Cremades, “Decision making under uncertainty using a qualitative TOPSIS method for selecting sustainable energy alternatives,” Int. Journal Environmental Science Technology, vol. 13, no. 6, pp.1419-1432, Jun. 2016.
[21]K. Burnuamkaew, How to do AHP analysis in excel. In Division of Spatial Information Science, Graduate School of Life and Environmental Sciences, University of Tsukuba: Tsukuba, Japan, Mar. 2012.
[22]S. A. Khoubrouy and J. H. L. Hansen, “Microphone array processing strategies for distant-based automatic speech recognition,” IEEE Signal Processing Letters, vol. 23, no. 10, pp.1344-1348, Oct. 2016.
[23]S. Schall, S. J. Kiebel, B. Maess and K. von Kriegstein, “Voice identity recognition: functional division of the right STS and its behavioral relevance,” Journal of Cognitive Neuroscience, vol. 27, no. 2, pp.280-291, Feb. 2014.
[24]R. Xie, X. Sun, X. Xia and J. Cao, “Similarity matching-based extensible hand gesture recognition,” IEEE Sensors Journal, vol. 15, no. 6, pp.3475-3483, Jun. 2015.
[25]S. Y. Kim, H. G. Han, J. W. Kim, S. Lee and T. W. Kim, “A hand gesture recognition sensor using reflected impulses,” IEEE Sensors Journal, vol. 17, no. 10, pp.2975-2976, May 2017.
[26]C. Wang, Z. Liu, and S.-C. Chan, “Superpixel-based hand gesture recognition with Kinect depth camera,” IEEE Trans. on Multimedia, vol. 17, no. 1, pp.29-39, Jan. 2015.
[27]H. P. Gupta, H. S. Chudgar, S. Mukherjee, T. Dutta and K. Sharma, “A continuous hand gestures recognition technique for human-machine interaction using accelerometer and gyroscope sensors,” IEEE Sensors Journal, vol. 16, no. 16, pp.6425-6432, Aug. 2016.
[28]R. Chen and Y. Tong, “A two-stage method for solving multi-resident activity recognition in smart environments,” Journal of Entropy, vol. 16, no. 4, pp.2184-2203, Apr. 2014.
[29]H. Rezaie, and M. Ghassemian, “An adaptive algorithm to improve energy efficiency in wearable activity recognition systems,” IEEE Sensors Journal, vol. 17, no. 16, pp.5315-5323, Jun. 2017.
[30]A. Benmansour, A. Bouchachia, and M. Feham, “Multi-occupant activity recognition in pervasive smart home environments,” Journal of ACM Computing Surveys, vol. 48, no. 3, pp.34-36, Feb. 2016.
[31]L. Wang, T. Gu, X. Tao, H. Chen, and J. Lu, “Recognizing multi-user activities using wearable sensors in a smart home,” Pervasive Mobile Computation, vol. 7, no. 3, pp.287-298, Jun. 2011.
[32]O. D. Lara, and M. A. Labrador “A survey on human activity recognition using wearable sensors,” IEEE Communications Surveys and Tutorials, vol. 15, no. 3, pp.1192-1209, Jun. 2011.
[33]L. Chen, C. D. Nugent, J. Biswas, and J. Hoey, “Activity recognition in pervasive intelligent environments,” Atlantis Ambient and Pervasive Intelligence, vol. 4, pp.165-186, May 2011.
[34]H. Martín, A. M. Bernardos, J. Iglesias, and J. R. Casar, “Activity logging using lightweight classification techniques in mobile devices,” Journal of Personal and Ubiquitous Computing, vol. 17, no. 4, pp.675-695, Apr. 2013.
[35]Deeplearning.net Deep belief networks. [online] http://deeplearning.net/tutorial/DBN.html. Accessed on Jun. 15, 2017.
[36]WHO, “Diabetes,” [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/diabetes, Accessed on Oct. 20, 2018.
[37]Healthline, “The effects of diabetes on your body,” [Online]. Available: https://www.healthline.com/health/diabetes/effects-on-body#1, Accessed on Oct. 22, 2018.
[38]E. Decencière, X. Zhang, G. Cazuguel, B. Lay, B. Cochener, C. Trone, P. Gain, R. Ordonez, P. Massin, A. Erginay, B. Charton, and J.-C. Klein “Feedback on a publicly distributed image database: the messidor database,” Image Analysis and Stereology, vol. 33, no. 3, pp.123-234, Dec. 2014.
[39]J. J. Huang, “A matrix method for the fuzzy analytic network process,” Int. Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, vol. 16, no. 6, pp.863-878, May 2008.
[40]S. N. Isfahani, A. A. Haddad, E. Roghanian, and M. Rezayi, “Customer relationship management performance measurement using balanced scorecard and fuzzy analytic network process,” Journal of Intelligent & Fuzzy Systems, vol. 27, no. 1, pp.377-389, 2014.
[41]T. L. Saaty, “The Analytic Hierarchy Process,” McGraw-Hill, New York, USA, 1980.
[42]R. E. Bellman and L. A. Zadeh, “Decision-making in a fuzzy environment,” Management Science, vol. 17, no. 4, pp.141-164, Dec. 1970.
[43]O. U. Akaa, A. Abu, M. Spearpoint, and S. Giovinazzi “A group-AHP decision analysis for the selection of applied fire protection to steel structures,” Fire Safety Journal, vol. 86, pp.95-105, Nov. 2016.
[44]U. Asan, A. Soyer, and S, Serdarasan, “A fuzzy analytic network process approach,” Computational Intelligence Systems in Industrial Engineering, vol. 6, no. 2, pp.155-179, Nov. 2012.
[45]X. Q. Feng, C. Wei, and Q. Liu, “EDAS method for extended hesitant fuzzy linguistic multicriteria decision making,” Int. Journal of Fuzzy Systems, vol. 20, no. 6, pp.1-14, Jun. 2018.
[46]R. Chutia, S. Mahanta, and D. Datta, “Arithmetic of triangular fuzzy variable from credibility theory,” Int. Journal of Energy, Information and Communications, vol. 2, no. 3, pp.73-80, Aug. 2011.
[47]H. K. Sharma, “A fuzzy logic multi-criteria decision approach for vendor selection manufacturing system,” IEEE Trans. on Modern Engineering Research, vol. 2, no. 6, pp.4189-4194, Dec. 2012.
[48]L. Abdullah and L. Najib, “A new preference scale MCDM method based on interval-valued intuitionistic fuzzy sets and the analytic hierarchy process,” Soft Computing, vol. 20, no. 2, pp.511-523, Feb. 2016.
[49]K. Sehra, Y. S. Brar, and N. Kaur, “Multi criteria decision making approach for selecting effort estimation model,” Int. Journal of Computer Applications, vol. 39, no. 1, pp.10-17, Jan. 2012.
[50]T. C. Chu and R. Varma, “Evaluating suppliers via a multiple levels multiple criteria decision making method under fuzzy environment,” IEEE Trans. on Computers and Industrial Engineering, vol. 62, no. 2, pp.653-660, Mar. 2012.
[51]C.-M. Huang, Y. Ghafoor, Y.-P. Huang, and S.-I. Liu, “A dolphin herding inspired fuzzy data clustering model and its applications,” Int. Journal of Fuzzy Systems, vol. 18, no. 2, pp.299-311, Apr. 2016.
[52]Y. Ma and X. Wu, “A new approach for deriving fuzzy global priorities in fuzzy analytic network process,” Journal of Intelligent & Fuzzy Systems, vol. 30, no. 2, pp.1249-1261, Feb. 2016.
[53]J. A. Quinn, F. M. Munoz, B. Gonik B, L. Frau, C. Cutland, T. Mallett-Moore, A. Kissou, F. Wittke, M. Das, T. Nunes, S. Pye, W. Watson, A. A. Ramos, J. F. Cordero, W. T. Huang, S. Kochhar, and J. Buttery, “Preterm birth: Case definition & guidelines for data collection, analysis, and presentation of the immunisation safety data,” Vaccince. vol. 39, no. 49, pp.6047-6056, Dec. 2016.
[54]H. Blencowe, S. Cousens, M. Z. Oestergaard, D. Chou, A. B. Moller, R. Narwal, A. Adler, C. V. Garcia, S. Rohde, L. Say, and J. E. Lawn, “National, regional and worldwide estimates of preterm birth,” Lancet. vol. 379, no. 9832, pp. 162-2172, Jun. 2012.
[55]L. Liu, S. Oza, D. Hogan, Y. Chu, J. Perin, J. Zhu, J. E. Lawn, S. Cousens, Colin Mathers, and R. E. Black, “Global, regional, and national causes of under-5 mortality in 2000-15: an updated systematic analysis with implications for the sustainable development goals,” Lancet. vol. 388, no. 10063, pp.3027-3035, Dec. 2016.
[56]C. Gilbert, A. Fielder, L. Gordillo, G. Quinn, R. Semiglia, P. Visintin, and A. Zin, “Characteristics of infants with severe retinopathy of prematurity in countries with low, moderate, and high levels of development: implications for screening programs,” Pediatrics. vol. 115, no.5, pp.e518-e525, May 2005.
[57]J. S. Mora, C. Waite, C. E. Gilbert, B. Breidenstein, and J. J. Sloper, “A worldwide survey of retinopathy prematurity screening,” British Journal of Ophthalmology. vol.102, no. 1, pp.9-13, Jan. 2018.
[58]S. H. L. Chang, Y. S. Lee, S. C. Wu, L. C. See, C. C. Chung, M. L. Yang, C. C. Lai, and W. C. Wu, “Anterior chamber angle and anterior segment structure of eyes in children with early stages of retinopathy of prematurity,” American Journal of Ophthalmology, vol. 179, pp.46-54, Jul. 2017.
[59]The international classification of retinopathy of prematurity, “International Committee for the Classification of Retinopathy of Prematurity Revisited,” Archive Ophthalmology. vol. 123, no. 7, pp.991-999, Jul. 2005.
[60]R. Richa, R. Linhares, E. Comunello, A. V. Wangenheim, J.-Y. Schnitzler, B. Wassmer, C. Guillemot, G. Thuret, P. Gain, G. Hager, and R. Taylor, “Fundus image mosaicking for information augmentation in computer-assisted slit-lamp imaging,” IEEE Trans. on Medical Imaging, vol. 33, no. 6, pp.1304-1312, Jun. 2014.
[61]J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, “How transferable are features in deep neural networks,” in Proc. of Int. Conf. of the Advance in Neural Information Processing Systems, Montréal, Canada, pp.1-5, Dec. 2014.
[62]K. He, X. Zhang, S. Ren and J. Sun, “Deep residual learning for image recognition,” in Proc. of the Int. Conf. on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp.770-778, Dec. 2016.
[63]H. Yao, D. Zhang, J. Li, J. Zhou, S. Zhang, and Y. Zhang, “DSP: discriminative spatial part modeling for fine-grained visual categorization,” Journal of Image and Vision Computing, vol. 63, pp.24-37, Jul. 2017.
[64]Stanford, CS231n.2017: Convolutional Neural Networks for Visual Recognition. [Online]. Available: http://cs231n.github.io/convolutional-networks/, Accessed on Oct. 25, 2017.
[65]N. Zhang, J. Donahue, R. Girshick, and T. Darrell, “Part-based R-CNN for fine-grained category detection,” in Proc. of the Int. Conf. of European Conference on Computer Vision, Cham, Switzerland, pp.834-849, Jul. 2014.
[66]L. Xie, J. Wang, B. Zhang, and Q. Tian, “Fine-grained image search,” IEEE Trans. on Multimedia, vol. 17, no. 5, pp.636-647, May 2015.
[67]C. Huang, Z. He, G. Cao, and W. Cao, “Task-driven progressive part localization for fine-grained object recognition,” IEEE Trans. on Multimedia, vol. 18, no. 12, pp.2372-2383, Dec. 2016.
[68]D. Lin, X. Shen, C. Lu, and J. Jia, “Deep LAC: deep localization, alignment and classification for fine-grained recognition,” in Proc. of the Int. Conf. on Computer Vision and Pattern Recognition, Boston, MA, USA, pp.1666-1674, Oct. 2015.
[69]Y.-P. Huang and T. Tsai, “A fuzzy semantic approach to retrieving bird information using handheld devices,” IEEE Intelligent Systems, vol. 20, no. 1, pp.16-23, Jan.-Feb. 2005.
[70]TensorFlow, “Building TensorFlow on Android,” [Online], Available: https://www.tensorflow.org/mobile/android_build, Accessed on Sep. 20, 2017.
[71]Keras, “Keras: The Python Deep Learning library,” [Online], Available: https://keras.io/, Accessed on Sep. 25, 2017.
[72]J. R. Uijlings, K. E. V. D. Sande, T. Gevers, and A. W. Smeulders, “Selective search for object recognition,” Int. Journal of Computer Vision, vol. 104, no. 2, pp.154-171, Feb. 2013.
[73]H. Zheng, Y. Huang, H. Ling, Q. Zou, and H. Yang, “Accurate segmentation for infrared flying bird tracking,” Chinese Journal of Electronics, vol. 25, no. 4, pp.625-631, Jul. 2016.
[74]Y. Wei, W. Xia, M. Lin, J. Huang, B. Ni, J. Dong, Y. Zhao, and S. Yan, “HCP: a flexible CNN framework for multi-label image classification,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 38, no. 9, pp.1901-1907, Sep. 2016.
[75]K.-J. Hsu, Y.-Y. Lin, and Y.-Y. Chuang, “Augmented multiple instance regression for inferring object contours in bounding boxes,” IEEE Trans. on Image Processing, vol. 23, no. 4, pp.1722-1736, Apr. 2014.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊