Application of Convolution Neural Network Analysis on Intra-row Weeding System for Vegetables

( I-chen Liu ),( Suming Chen ),( Chao-yin Tsai ),( Yung-huei Chang ) 한국농업기계학회 2018 한국농업기계학회 학술발표논문집 Vol.23 No.1

Weeds play an important, non-negligible role in crop cultivation because their competition for sunlight, moisture, nutrients, space and other resources directly affects the growth of crops. Application of chemical treatment on weed control will pollute the environment and agricultural products, while physical treatments is time-consuming and laborious, which leads to low efficiency. This research intends to develop an intelligent vegetable intra-row weeding system using image positioning technology to conduct physical weeding. Total of 474 cabbage images with weeds were captured in the field with camera, in which 379 of these images were used as training data, and the other 95 images were used as testing data. Through the image processing method of Convolutional Neural Network (CNN), the features were extracted and classified between identify cabbages and weeds. There were 381 cabbages in the verified images in total, only 3 of which were unidentified, with a success rate of 99.2%. No weed was identified as cabbage, and the positions of cabbages were also obtained. Field tests were conducted using this built model to identify cabbage and had good recognition rates even when weeds were more than training samples.

Political Feasibility Analysis of the New Financing Scheme for the National Health Insurance Reform in Taiwan: An Application of Stakeholder Analysis

Chao-Yin Lin,Don-Yun Chen,I-Chun Liu,Naiyi Hsiao 한국사회복지학회 2010 Asian Social Work and Policy Review Vol.4 No.3

This study carries out in-depth political feasibility analysis of the prospective health financingreform currently taking place in Taiwan. The National Health Insurance (NHI) Program, whichwas established in Taiwan in 1995, covers virtually all of the island’s citizens. Between the years2001 and 2004, the Taiwanese Government organized a taskforce to carry out the wholesale reformof the NHI program into the so-called ‘Second Generation NHI Program’. This study is part of thecomprehensive review, focusing on the preferences and positions of key policy stakeholders withregard to the financial reform proposals, as well as their network relationships. The approach ofstakeholder analysis was employed to conduct this empirical study. The results reveal that the newfinancing scheme has a certain degree of support from the policy stakeholders participating in thisstudy, and that in particular, the measures concerning equity and sustainability were most welcome. However, controversy remains with regard to the issue of the equitable sharing of contributions. It is clear that there is much strong support for the new scheme amongst the administrativeand legislative elite, although the same level of support is not evident amongst the social eliteaffiliated with employees’ associations and welfare groups.

The tyrosine kinase inhibitor nintedanib activates SHP-1 and induces apoptosis in triple-negative breast cancer cells

Chun-Yu Liu,Tzu-Ting Huang,Pei-Yi Chu,Chun-Teng Huang,Chia-Han Lee,Wan-Lun Wang,Ka-Yi Lau,Wen-Chun Tsai,Tzu-I Chao,Jung-Chen Su,Ming-Huang Chen,Chung-Wai Shiau,Ling-Ming Tseng,Kuen-Feng Chen 생화학분자생물학회 2017 Experimental and molecular medicine Vol.49 No.-

Triple-negative breast cancer (TNBC) remains difficult to treat and urgently needs new therapeutic options. Nintedanib, a multikinase inhibitor, has exhibited efficacy in early clinical trials for HER2-negative breast cancer. In this study, we examined a new molecular mechanism of nintedanib in TNBC. The results demonstrated that nintedanib enhanced TNBC cell apoptosis, which was accompanied by a reduction of p-STAT3 and its downstream proteins. STAT3 overexpression suppressed nintedanib-mediated apoptosis and further increased the activity of purified SHP-1 protein. Moreover, treatment with either a specific inhibitor of SHP-1 or SHP-1-targeted siRNA reduced the apoptotic effects of nintedanib, which validates the role of SHP-1 in nintedanib-mediated apoptosis. Furthermore, nintedanib-induced apoptosis was attenuated in TNBC cells expressing SHP-1 mutants with constantly open conformations, suggesting that the autoinhibitory mechanism of SHP-1 attenuated the effects of nintedanib. Importantly, nintedanib significantly inhibited tumor growth via the SHP-1/p-STAT3 pathway. Clinically, SHP-1 levels were downregulated, whereas p-STAT3 was upregulated in tumor tissues, and SHP-1 transcripts were associated with improved disease-free survival in TNBC patients. Our findings revealed that nintedanib induces TNBC apoptosis by acting as a SHP-1 agonist, suggesting that targeting STAT3 by enhancing SHP-1 expression could be a viable therapeutic strategy against TNBC.

An Application of Machine Vision on Identification of Sugarcane Nodes

( Shao-yuan Zhao ),( Suming Chen ),( Chao-yin Tsai ),( I-chen Liu ) 한국농업기계학회 2018 한국농업기계학회 학술발표논문집 Vol.23 No.1

Due to labor shortage, modern agriculture goes up on automation gradually, the planting of sugarcane is no exception. If the automatic planting machine is used, sugarcane seedlings should be prepared in advance. A sugarcane node is the main place where bud is grown from. The existing sugarcane node cutting machines rely on human judgement to determine the node locations. There are time-consuming and laborious to collect the sugarcane nodes. This study intends to use machine vision to identify sugarcane nodes for developing automatic machine. The two algorithms of R-CNN and FASTER R-CNN were used to identify sugarcane node and to compare their performance. The R-CNN algorithm is usually used for the identification of multiple targets, and its accuracy is less than FASTER R-CNN, but the processing speed is faster. In this study, 530 sugarcane photos (1300 nodes) were analyzed, 400 and 130 sugarcane photos were selected as the calibration and validation groups, respectively. The experimental results show that the processing time of the R-CNN can be completed within 0.02 sec with the identification rate of 97.9%, and the processing time and identification rate of the FASTER R-CNN are similar to those of the R-CNN. The both algorithms have good results, and can be applied to the development of automated sugarcane node cutting machines.

A Systemic Review and Experts’ Consensus for Long-acting Injectable Antipsychotics in Bipolar Disorder

Yuan-Hwa Chou,Po-Chung Chu,Szu-Wei Wu,Jen-Chin Lee,Yi-Hsuan Lee,I-Wen Sun,Chen-Lin Chang,Chien-Liang Huang,I-Chao Liu,Chia-Fen Tsai,Yung-Chieh Yen 대한정신약물학회 2015 CLINICAL PSYCHOPHARMACOLOGY AND NEUROSCIENCE Vol.13 No.2

Bipolar disorder (BD) is a major psychiatric disorder that is easily misdiagnosed. Patient adherence to a treatment regimen is of utmost importance for successful outcomes in BD. Several trials of antipsychotics suggested that depot antipsychotics, including long-acting first- and second-generation agents, are effective in preventing non-adherence, partial adherence, and in reducing relapse in BD. Various long-acting injectable (LAI) antipsychotics are available, including fluphenazine decanoate, haloperidol decanoate, olanzapine pamoate, risperidone microspheres, paliperidone palmitate, and aripiprazole monohydrate. Due to the increasing number of BD patients receiving LAI antipsychotics, treatment guidelines have been developed. However, the clinical applicability of LAI antipsychotics remains a global cause for concern, particularly in Asian countries. Expert physicians from Taiwan participated in a consensus meeting, which was held to review key areas based on both current literature and clinical practice. The purpose of this meeting was to generate a practical and implementable set of recommendations for LAI antipsychotic use to treat BD; target patient groups, dosage, administration, and adverse effects were considered. Experts recommended using LAI antipsychotics in patients with schizophrenia, rapid cycling BD, BD I, and bipolar-type schizoaffective disorder. LAI antipsychotic use was recommended in BD patients with the following characteristics: multiple episodes and low adherence; seldom yet serious episodes; low adherence potential per a physician’s clinical judgment; preference for injectable agents over oral agents; and multiple oral agent users still experiencing residual symptoms.