A Versatile Fruit and Vegetable Image Recognition Method based on Deep Convolutional Neural Networks

( Yi-hsuan Huang ),( Ta-te Lin ) 한국농업기계학회 2018 한국농업기계학회 학술발표논문집 Vol.23 No.1

Due to the increasing labor costs and shortage of labor in the agricultural industry, automation in agriculture has become ever more important. This paper proposes a versatile and automatic fruit and vegetable recognition method through the use of computer vision and deep neural networks. The proposed method allows for detection, recognition, and localization of selected fruits and vegetables via images or video streams. Therefore, the method can be used in various applications in agriculture such as robotic harvest, greenhouse management, or crop phenotyping. To detect fruits or vegetables in images, traditional image processing algorithms have some limitations due to occlusions and background variations. Different fruits or vegetables may require different algorithms. However, deep convolutional neural networks have brought about a breakthrough in dealing with this problem. The significance of deep neural networks in imaging processing is that features are no longer extracted by image processing algorithms. Instead, the network will learn by itself from the input data and extract the important features, called deep features. Therefore, we apply deep convolutional neural networks with You Only Look Once (YOLO), a real-time object detection algorithm, to build a versatile image recognition model for selected fruits and vegetables. Using YOLO, the models are trained with five kinds of fruits and vegetables: apple, tomato, cucumber, orange and strawberry. There are two kinds of models developed: ‘one vs. all’ and ‘one vs. one’ models. These models are compared to obtain the ensemble model. In addition, the effects of different phenotype between training data sets and testing data sets are also evaluated. Finally, the optimized model is applied in the recognition system and multiple kinds of fruits are recognized. We also tested the method with images and video streams acquired from greenhouses to evaluate the performance of the method.

Bostrycin production by agro-industrial residues and its potential for food processing

Yi-Hsuan Huang,Wen-Jen Yang,Chih-Yu Cheng,Huang-Mo Sung,Shuen-Fuh Lin 한국식품과학회 2017 Food Science and Biotechnology Vol.26 No.3

Bostrycin, a red antibacterial agent produced by Nigrospora sp. no. 407, is considered for meat processing. To optimize production, the culture conditions of submerged fermentation (SmF) and solid-state fermentation (SSF) were investigated. The optimal SmF conditions were a medium containing 1.0% cane molasses and incubation at 30 C and 150 rpm for 6 days. In SSF, other than bostrycin, less pigment was produced and the optimal ratio of bagasse to water was 1:2 for 10 days. The production and recovery rate of bostrycin by SmF were 120 mg/L and 40%, respectively. Bostrycin exhibited thermostable, pHdependent color change and dose-dependent antibacterial activity against Clostridium botulinum. Bostrycin-modified meat turned strong red for at least 24 h and could not be removed by washing; bostrycin maintained its antibacterial activity with a bacteriostasis rate of 91% on Staphylcoccus aureus. This is an easy and inexpensive means of acquiring bostrycin from molasses and sugarcane.

Taiwan Neurosurgical Spine Society: The New Shining Star

Yi-Hsuan Kuo,Jau-Ching Wu,Wen-Cheng Huang,Ming-Chao Huang,E-Jian Lee,Henrich Cheng 대한척추신경외과학회 2018 Neurospine Vol.15 No.4

As spine surgery flourished in Taiwan and neurosurgeons became more involved in spine surgery towards the end of the 20th century, the Taiwan Neurosurgical Spine Society (TNSS), earlier named the Taiwan Neurospinal Society, was established on March 11, 2001. As its main founder, Dr. Chun-I Huang was elected as the first president of the TNSS. The goals of the TNSS were to promote research, to hold academic seminars, to participate in international conferences, and to exchange clinical experiences. The mission of the TNSS was successful, and the profession of spine surgery in Taiwan advanced during the first decade of the 21st century, culminating in the TNSS joining ASIA SPINE in 2010. Since its establishment, the TNSS has always been supportive of collaboration and communication with the Korean Spinal Neurosurgery Society and the Neurospinal Society of Japan. Through periodical meetings, supported by the TNSS, surgeons worldwide have enjoyed a platform of sharing and mutual learning. To further promote academic research, the TNSS has officially supported the journal Neurospine since 2018. With extensive efforts from local and international surgeons, the TNSS will continue to adhere to its mission and to advance the profession of spine surgery.

Does Labor Market Rigidity Matter for Economic Performance? Evidence from the Four Asian Tigers

Li-Hsuan Huang,Julia Hsin-Yi Huang 한국학술연구원 2013 Korea Observer Vol.44 No.3

With the increments of labor market institutions, the potential problem caused by labor market rigidity is emerging within the four Asian tigers, namely, Hong Kong, South Korea, Singapore and Taiwan. This study emphasizes the impact of labor market rigidity on economic performance in the four Asian tigers over the 1980-2010 period. Through the estimation of the aggregate production function, we find that labor market rigidity has a negative impact on output and economic growth. On the other hand, without imposing any labor market institutional adjustment that would lower the standard of labor conditions, the rises in country’s competitiveness can serve as a balancing force to mitigate the negative impacts of labor market rigidity. A crucial insight for policymakers is to determine the most efficient method for giving labor effective protection without hurting economic performance.

Anterior Cervical Discectomy and Fusion for Hirayama Disease: A Case Report and Literature Review

Yi-Hsuan Kuo,Chao-Hung Kuo,Wen-Cheng Huang,Jau-Ching Wu 대한척추신경외과학회 2019 Neurospine Vol.16 No.3

Hirayama disease, a juvenile muscular atrophy of the distal upper extremity, is a rare form of cervical flexion myelopathy characterized by insidiously progressive weakness of the hands and forearm muscles (i.e., painless amyotrophy). The pathognomonic finding is a markedly forward-shifted spinal cord during neck flexion, demonstrated by dynamic magnetic resonance imaging (MRI), as in a young man with muscle atrophy in the bilateral distal upper extremities. In this report, the authors describe a 31-year-old man who had the classic radiological and clinical presentations of Hirayama disease. Since prior medical treatment had been ineffective for years, he underwent multilevel instrumented anterior cervical discectomy and fusion (ACDF) to keep his subaxial cervical spine slightly-lordotic (nonflexion). His motor evoked potential amplitude improved immediately during the operation, and there were improvements of myelopathy and a modest reversal of muscle wasting at 1 year postoperatively. Postoperative dynamic cervical spine MRI also demonstrated minimal cord compression and elimination of the venous plexus engorgement dorsal to the thecal sac. Although Hirayama disease is benign in nature and frequently self-limiting, multilevel instrumented ACDF could be a reasonable management option.

Identification of differential DNA methylated regions between different development of entomopathogenic fungi, Beauveria bassiana NCHU-157, by Nanopore sequencing

Yi-Hsuan Li,Ju-Chun Chang,Ming-Ren Yen,Yu-Feng Huang,Tzu-Han Chen,Yu-Shin Nai 한국응용곤충학회 2022 한국응용곤충학회 학술대회논문집 Vol.2022 No.10

Exploration of Oligotrophic Bacteria from Soils in Taiwan

Yi-Ying Kao,Yu-Hsuan Huang,Fo-Ting Shen,Chiu-Chung Young 한국토양비료학회 2014 한국토양비료학회 학술발표회 초록집 Vol.2014 No.6

The Robotic Arm Velocity Planning Based on Reinforcement Learning

Hao-Hsuan Huang,Chih‑Kai Cheng,Yi‑Hung Chen,Hung‑Yin Tsai 한국정밀공학회 2023 International Journal of Precision Engineering and Vol.24 No.9

In order to improve the performance of the robotic arm effectively, this study established a robotic arm velocity planning model developed by artificial intelligence in the simulation system. The model not only considered the dynamic factors of the robotic arm but was also able to set different customized conditions such as machining accuracy and rotation angle. The study could be divided into three parts. First, the simulation environment was constructed with the ABB IRB140 six axes multipurpose industrial robot. To be consistent with real-world situations, a Vortex physics engine was applied to the simulation supplying varying locomotion parameters. In this research, friction, kinematics, and inertia were considered. Second, artificial intelligence was imported into the robotic arm through the establishment of connecting V-rep and Python. The proposed model was developed in the Python environment by deep deterministic policy gradients. Eventually, a design of the appropriate reward function governing the ultimate results was presented. Compared with traditional velocity planning, the proposed method can decline moving error by 0.05 degrees under the considerations involving dynamic factors in a robotic arm. Besides, the proposed velocity planning strategy could be obtained after taking the training time of one hour which can meet the demand for the time cost of the industry.

The Clinical Outcomes of Different First-Line EGFR-TKIs Plus Bevacizumab in Advanced EGFR-Mutant Lung Adenocarcinoma

Yen-Hsiang Huang,Kuo-Hsuan Hsu,Chun-Shih Chin,Jeng-Sen Tseng,Tsung-Ying Yang,Kun-Chieh Chen,Kang-Yi Su,Sung-Liang Yu,Jeremy J.W. Chen,Gee-Chen Chang 대한암학회 2022 Cancer Research and Treatment Vol.54 No.2

Purpose The aim of this study was to investigate the efficacy of various epidermal growth factor receptor (EGFR)–tyrosine kinase inhibitors (TKIs) plus bevacizumab in advanced EGFR-mutant lung adenocarcinoma patients. Materials and Methods From August 2016 to October 2020, we enrolled advanced lung adenocarcinoma patients harboring exon 19 deletion or L858R receiving gefitinib, erlotinib and afatinib plus bevacizumab as the first-line treatment for the purposes of analysis. Results A total of 36 patients were included in the final analysis. Three patients received gefitinib, 17 received erlotinib, and 16 received afatinib combined with bevacizumab as the first-line treatment. The objective response rate was 77.8%, and disease control rate was 94.4%. The overall median progression-free survival (PFS) was 16.4 months, while the median PFS was 17.1 months in patients with exon 19 deletion, and 16.2 months in patients with L858R mutation (p=0.311). Regarding the use of different EGFR-TKIs, the median PFS was 17.1 months in the erlotinib group and 21.6 months in the afatinib group (p=0.617). In patients with brain metastasis at baseline, the median PFS was 18.9 months in the erlotinib group and 16.4 months in the afatinib group (p=0.747). Amongst patients harboring exon 19 deletion, the median PFS was 16.2 months in the erlotinib group and not-reached in the afatinib group (p=0.141). In patients with L858R mutation, the median PFS was 18.9 months in the erlotinib group and 16.2 months in the afatinib group (p=0.481). Conclusion Our research demonstrates that not only erlotinib combined with bevacizumab, but also afatinib plus bevacizumab as first-line treatment, provides solid clinical efficacy in advanced EGFR-mutant lung adenocarcinoma patients. PurposeThe aim of this study was to investigate the efficacy of various epidermal growth factor receptor (EGFR)–tyrosine kinase inhibitors (TKIs) plus bevacizumab in advanced <i>EGFR</i>-mutant lung adenocarcinoma patients.Materials and MethodsFrom August 2016 to October 2020, we enrolled advanced lung adenocarcinoma patients harboring exon 19 deletion or L858R receiving gefitinib, erlotinib and afatinib plus bevacizumab as the first-line treatment for the purposes of analysis.ResultsA total of 36 patients were included in the final analysis. Three patients received gefitinib, 17 received erlotinib, and 16 received afatinib combined with bevacizumab as the first-line treatment. The objective response rate was 77.8%, and disease control rate was 94.4%. The overall median progression-free survival (PFS) was 16.4 months, while the median PFS was 17.1 months in patients with exon 19 deletion, and 16.2 months in patients with L858R mutation (p=0.311). Regarding the use of different EGFR-TKIs, the median PFS was 17.1 months in the erlotinib group and 21.6 months in the afatinib group (p=0.617). In patients with brain metastasis at baseline, the median PFS was 18.9 months in the erlotinib group and 16.4 months in the afatinib group (p=0.747). Amongst patients harboring exon 19 deletion, the median PFS was 16.2 months in the erlotinib group and not-reached in the afatinib group (p=0.141). In patients with L858R mutation, the median PFS was 18.9 months in the erlotinib group and 16.2 months in the afatinib group (p=0.481).ConclusionOur research demonstrates that not only erlotinib combined with bevacizumab, but also afatinib plus bevacizumab as first-line treatment, provides solid clinical efficacy in advanced <i>EGFR</i>-mutant lung adenocarcinoma patients.

Health Care Utilization and Expenditures of Patients with Diabetes Comorbid with Depression Disorder: A National Population-Based Cohort Study

Chun-Jen Huang,Hui-Min Hsieh,Herng-Chia Chiu,Peng-Wei Wang,Mei-Hsuan Lee,Chih-Yi Li,Ching-Hua Lin 대한신경정신의학회 2017 PSYCHIATRY INVESTIGATION Vol.14 No.6

Objective: The study investigated to compare health care utilization and expenditures between diabetic patients with and without depression in Taiwan. Methods: Health care utilization and expenditure among diabetic patients with and without depression disorder during 2000 and 2004 were examined using Taiwan’s population-based National Health Insurance claims database. Health care utilization included outpatient visits and the use of inpatient services, and health expenditures were outpatient, inpatient, and total medical expenditures. Moreover, general estimation equation models were used for analyzing the factors associated with outpatient visits and expenditures. Multiple logistic regression analysis was applied for identifying the factors associated with hospitalization. Results: The average annual outpatient visits and annual total medical expenditures in the study period were 44.23–52.20; NT$87,496–133,077 and 30.75–32.92; NT$64,411–80,955 for diabetic patients with and without depression. After adjustment for covariates, our results revealed that gender and complication were associated with out-patient visits. Moreover, the time factor was associated with the total medical expenditure, and residential urbanization and complication factors were associated with hospitalization. Conclusion: Health care utilization and expenditures for diabetic patients with depression were significantly higher than those without depression. Sex, complications, time, and urbanization are the factors associated with health care utilization and expenditures.