Fang-Rong Hsu - Academia.edu (original) (raw)

Papers by Fang-Rong Hsu

Lecture notes in electrical engineering, Dec 31, 2023

Biomedicines

We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation... more We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation models. We used an advanced semantic segmentation method and a deep convolutional neural network to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images. To improve the segmentation results, we used six models to analyse 309 patients, including 151 benign and 158 malignant tumour images. We compared the Unet3+ architecture with several other models, such as FCN, Unet, SegNet, DeeplabV3+ and pspNet. The Unet3+ model is a state-of-the-art, semantic segmentation architecture that showed optimal performance with an average accuracy of 82.53% and an average intersection over union (IU) of 52.57%. The weighted IU was found to be 89.14% with a global accuracy of 90.99%. The application of these types of segmentation models to the detection and diagnosis of breast cancer provides remarkable results. Our proposed method has the potential to provide...

Journal of Internet Technology, Sep 1, 2013

EST (Express Sequence Tag) is the fragment sequencing of human gene participation during transcri... more EST (Express Sequence Tag) is the fragment sequencing of human gene participation during transcription. In researches of bioinformatics, EST alignment can assist in studies of SNP, RNA editing, alternative splicing, etc. Different spliced alignment tools lead to different alignment results, therefore, the results of a single alignment tool seem to be arbitrary. Objective results can be obtained by analyzing the results of at least two alignment tools. However, if additional tools are adopted, increased computing time and storage capacities are required. This work deploys two different spliced alignment tools for sequencing, based on a grid computing environment, as constructed by globus, in order to solve the issues of numerous sequencing alignments and data storage. A grid environment can provide different service flows, recordings, and work monitoring states for two different splicing tools as a base of reference for node efficiency through load balance.

International MultiConference of Engineers and Computer Scientists, 2007

The process for reacting olefins with ozone in a carboxylic acid medium using pure oxygen or an o... more The process for reacting olefins with ozone in a carboxylic acid medium using pure oxygen or an oxygenated gas mixture for the ozone production, is improved by recycling the oxygen or the oxygenated gas mixture leaving the ozonizing stage. The oxygen containing gas leaving the ozonizing stage is: (a) washed with the carboxylic acid input of the ozonizing stage, (b) treated with an aqueous solution of an alkalinically reacting substance, and lastly, (c) dried and fed back to the ozonizer.

Canadian Conference on Computational Geometry, 1998

ABSTRACT Guarding in a simple polygon was motivated by art gallery problems. A guard capable of m... more ABSTRACT Guarding in a simple polygon was motivated by art gallery problems. A guard capable of moving along a line segment in a polygon is called a mobile guard. In this paper, we discuss about two different degrees of patrol freedom of mobile guards. First, a guard diagonal is an internal diagonal that a mobile guard moving along the diagonal in a polygon and every interior point of the polygon can be seen by the mobile guard. Second, a guard chord is an internal chord that a mobile guard moving along the chord in a polygon and every interior point of the polygon can be seen by the mobile guard. In this paper, we solve the problem of finding the longest guard diagonal in O(n) time, the shortest guard diagonal in O(n alpha(n)) and the longest guard chord in O(n) time of a simple polygon P with n vertices, where alpha(n) is the inverse of Ackermann's function.

To evaluate the learning performance of students, a final report is usually assigned. Students ar... more To evaluate the learning performance of students, a final report is usually assigned. Students are asked to form a group which includes several students and they are assigned a specific topic to prepare a report. The way of assignment greatly influences on the results. The purpose of this study is to present a novel optimization approach to final report assignment which considers the preferences of students to topics as well as their partners. Initially, students are asked to indicate their preferences to some specific topics and their preferred cooperative partners. After aggregating preference data, a scoring system is used to evaluate the assignment. Mathematical Programming (MP) is employed and an evolutionary method is used to find solutions. Results from this study show that the proposed approach presented in this study can get good solutions efficiently.

BMC Genomics, Dec 1, 2012

Background: The opportunistic enterobacterium, Morganella morganii, which can cause bacteraemia, ... more Background: The opportunistic enterobacterium, Morganella morganii, which can cause bacteraemia, is the ninth most prevalent cause of clinical infections in patients at Changhua Christian Hospital, Taiwan. The KT strain of M. morganii was isolated during postoperative care of a cancer patient with a gallbladder stone who developed sepsis caused by bacteraemia. M. morganii is sometimes encountered in nosocomial settings and has been causally linked to catheter-associated bacteriuria, complex infections of the urinary and/or hepatobiliary tracts, wound infection, and septicaemia. M. morganii infection is associated with a high mortality rate, although most patients respond well to appropriate antibiotic therapy. To obtain insights into the genome biology of M. morganii and the mechanisms underlying its pathogenicity, we used Illumina technology to sequence the genome of the KT strain and compared its sequence with the genome sequences of related bacteria. Results: The 3,826,919-bp sequence contained in 58 contigs has a GC content of 51.15% and includes 3,565 protein-coding sequences, 72 tRNA genes, and 10 rRNA genes. The pathogenicity-related genes encode determinants of drug resistance, fimbrial adhesins, an IgA protease, haemolysins, ureases, and insecticidal and apoptotic toxins as well as proteins found in flagellae, the iron acquisition system, a type-3 secretion system (T3SS), and several two-component systems. Comparison with 14 genome sequences from other members of Enterobacteriaceae revealed different degrees of similarity to several systems found in M. morganii. The most striking similarities were found in the IS4 family of transposases, insecticidal toxins, T3SS components, and proteins required for ethanolamine use (eut operon) and cobalamin (vitamin B 12) biosynthesis. The eut operon and the gene cluster for cobalamin biosynthesis are not present in the other Proteeae genomes analysed. Moreover, organisation of the 19 genes of the eut operon differs from that found in the other non-Proteeae enterobacterial genomes. Conclusions: This is the first genome sequence of M. morganii, which is a clinically relevant pathogen. Comparative genome analysis revealed several pathogenicity-related genes and novel genes not found in the genomes of other members of Proteeae. Thus, the genome sequence of M. morganii provides important information concerning virulence and determinants of fitness in this pathogen.

MATEC Web of Conferences, 2018

Monitoring of vibration in machine tools is becoming a very important application in industry to ... more Monitoring of vibration in machine tools is becoming a very important application in industry to reduce machine failures, maintenance costs, and dead time. In this paper, we propose a method to identify possible faults based on vibration data from which predictions about the working condition of the machine tools can be made. We used an accelerometer to collect the vibration data from which to analyse the health of machine tools by diagnosing whether they are in good or faulty condition for working. In our experiments, we introduced a machine called the Reliance Electric motor, which has a bearing running inside it. Our research analyses vibration data from components of the bearing including the outer bearing, inner bearing, and rolling element. The experimental results show that our method is highly accurate in diagnosing failures and significantly reduces the maintenance costs of machine tools.

Fuel, 1991

ABSTRACT The thermal conductivities of suspensions of particulate coals in water, in fuel oil and... more ABSTRACT The thermal conductivities of suspensions of particulate coals in water, in fuel oil and in other liquids, and of mixtures of different particulate solids in liquids were measured. The binary suspension data were used to determine the solid thermal conductivities of the particulate inclusions by various extrapolations, and to test the different extrapolation schemes. A general, second-order, effective conductivity formula for binary mixtures, valid for small differences between the conductivities of dispersed and continuous phases, was derived. For suspensions containing a mixture of N different solids, of solid to liquid conductivity ratios and volume fractions φi, the formulae and were derived for the suspension thermal conductivity k∗. The former was found to do a good job of prediction for binary and multi-solid suspensions. As the volume fraction weighted geometric mean of the constituent conductivities, this formula is known to lie between the harmonic and arithmetic means as lower and upper bounds, respectively. Furthermore, over the range of conductivity ratios βi where it works well, it either lies between tighter bounds based on variational principles, or when it falls outside it differs indistinguishably from these bounds, which in this case turn out to be quite close.

All in-text references underlined in blue are linked to publications on ResearchGate, letting you... more All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately.

Biomedicines

We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation... more We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation models. We used an advanced semantic segmentation method and a deep convolutional neural network to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images. To improve the segmentation results, we used six models to analyse 309 patients, including 151 benign and 158 malignant tumour images. We compared the Unet3+ architecture with several other models, such as FCN, Unet, SegNet, DeeplabV3+ and pspNet. The Unet3+ model is a state-of-the-art, semantic segmentation architecture that showed optimal performance with an average accuracy of 82.53% and an average intersection over union (IU) of 52.57%. The weighted IU was found to be 89.14% with a global accuracy of 90.99%. The application of these types of segmentation models to the detection and diagnosis of breast cancer provides remarkable results. Our proposed method has the potential to provide...

Lecture notes in electrical engineering, Dec 31, 2023

Biomedicines

We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation... more We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation models. We used an advanced semantic segmentation method and a deep convolutional neural network to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images. To improve the segmentation results, we used six models to analyse 309 patients, including 151 benign and 158 malignant tumour images. We compared the Unet3+ architecture with several other models, such as FCN, Unet, SegNet, DeeplabV3+ and pspNet. The Unet3+ model is a state-of-the-art, semantic segmentation architecture that showed optimal performance with an average accuracy of 82.53% and an average intersection over union (IU) of 52.57%. The weighted IU was found to be 89.14% with a global accuracy of 90.99%. The application of these types of segmentation models to the detection and diagnosis of breast cancer provides remarkable results. Our proposed method has the potential to provide...

Journal of Internet Technology, Sep 1, 2013

EST (Express Sequence Tag) is the fragment sequencing of human gene participation during transcri... more EST (Express Sequence Tag) is the fragment sequencing of human gene participation during transcription. In researches of bioinformatics, EST alignment can assist in studies of SNP, RNA editing, alternative splicing, etc. Different spliced alignment tools lead to different alignment results, therefore, the results of a single alignment tool seem to be arbitrary. Objective results can be obtained by analyzing the results of at least two alignment tools. However, if additional tools are adopted, increased computing time and storage capacities are required. This work deploys two different spliced alignment tools for sequencing, based on a grid computing environment, as constructed by globus, in order to solve the issues of numerous sequencing alignments and data storage. A grid environment can provide different service flows, recordings, and work monitoring states for two different splicing tools as a base of reference for node efficiency through load balance.

International MultiConference of Engineers and Computer Scientists, 2007

The process for reacting olefins with ozone in a carboxylic acid medium using pure oxygen or an o... more The process for reacting olefins with ozone in a carboxylic acid medium using pure oxygen or an oxygenated gas mixture for the ozone production, is improved by recycling the oxygen or the oxygenated gas mixture leaving the ozonizing stage. The oxygen containing gas leaving the ozonizing stage is: (a) washed with the carboxylic acid input of the ozonizing stage, (b) treated with an aqueous solution of an alkalinically reacting substance, and lastly, (c) dried and fed back to the ozonizer.

Canadian Conference on Computational Geometry, 1998

ABSTRACT Guarding in a simple polygon was motivated by art gallery problems. A guard capable of m... more ABSTRACT Guarding in a simple polygon was motivated by art gallery problems. A guard capable of moving along a line segment in a polygon is called a mobile guard. In this paper, we discuss about two different degrees of patrol freedom of mobile guards. First, a guard diagonal is an internal diagonal that a mobile guard moving along the diagonal in a polygon and every interior point of the polygon can be seen by the mobile guard. Second, a guard chord is an internal chord that a mobile guard moving along the chord in a polygon and every interior point of the polygon can be seen by the mobile guard. In this paper, we solve the problem of finding the longest guard diagonal in O(n) time, the shortest guard diagonal in O(n alpha(n)) and the longest guard chord in O(n) time of a simple polygon P with n vertices, where alpha(n) is the inverse of Ackermann's function.

To evaluate the learning performance of students, a final report is usually assigned. Students ar... more To evaluate the learning performance of students, a final report is usually assigned. Students are asked to form a group which includes several students and they are assigned a specific topic to prepare a report. The way of assignment greatly influences on the results. The purpose of this study is to present a novel optimization approach to final report assignment which considers the preferences of students to topics as well as their partners. Initially, students are asked to indicate their preferences to some specific topics and their preferred cooperative partners. After aggregating preference data, a scoring system is used to evaluate the assignment. Mathematical Programming (MP) is employed and an evolutionary method is used to find solutions. Results from this study show that the proposed approach presented in this study can get good solutions efficiently.

BMC Genomics, Dec 1, 2012

Background: The opportunistic enterobacterium, Morganella morganii, which can cause bacteraemia, ... more Background: The opportunistic enterobacterium, Morganella morganii, which can cause bacteraemia, is the ninth most prevalent cause of clinical infections in patients at Changhua Christian Hospital, Taiwan. The KT strain of M. morganii was isolated during postoperative care of a cancer patient with a gallbladder stone who developed sepsis caused by bacteraemia. M. morganii is sometimes encountered in nosocomial settings and has been causally linked to catheter-associated bacteriuria, complex infections of the urinary and/or hepatobiliary tracts, wound infection, and septicaemia. M. morganii infection is associated with a high mortality rate, although most patients respond well to appropriate antibiotic therapy. To obtain insights into the genome biology of M. morganii and the mechanisms underlying its pathogenicity, we used Illumina technology to sequence the genome of the KT strain and compared its sequence with the genome sequences of related bacteria. Results: The 3,826,919-bp sequence contained in 58 contigs has a GC content of 51.15% and includes 3,565 protein-coding sequences, 72 tRNA genes, and 10 rRNA genes. The pathogenicity-related genes encode determinants of drug resistance, fimbrial adhesins, an IgA protease, haemolysins, ureases, and insecticidal and apoptotic toxins as well as proteins found in flagellae, the iron acquisition system, a type-3 secretion system (T3SS), and several two-component systems. Comparison with 14 genome sequences from other members of Enterobacteriaceae revealed different degrees of similarity to several systems found in M. morganii. The most striking similarities were found in the IS4 family of transposases, insecticidal toxins, T3SS components, and proteins required for ethanolamine use (eut operon) and cobalamin (vitamin B 12) biosynthesis. The eut operon and the gene cluster for cobalamin biosynthesis are not present in the other Proteeae genomes analysed. Moreover, organisation of the 19 genes of the eut operon differs from that found in the other non-Proteeae enterobacterial genomes. Conclusions: This is the first genome sequence of M. morganii, which is a clinically relevant pathogen. Comparative genome analysis revealed several pathogenicity-related genes and novel genes not found in the genomes of other members of Proteeae. Thus, the genome sequence of M. morganii provides important information concerning virulence and determinants of fitness in this pathogen.

MATEC Web of Conferences, 2018

Monitoring of vibration in machine tools is becoming a very important application in industry to ... more Monitoring of vibration in machine tools is becoming a very important application in industry to reduce machine failures, maintenance costs, and dead time. In this paper, we propose a method to identify possible faults based on vibration data from which predictions about the working condition of the machine tools can be made. We used an accelerometer to collect the vibration data from which to analyse the health of machine tools by diagnosing whether they are in good or faulty condition for working. In our experiments, we introduced a machine called the Reliance Electric motor, which has a bearing running inside it. Our research analyses vibration data from components of the bearing including the outer bearing, inner bearing, and rolling element. The experimental results show that our method is highly accurate in diagnosing failures and significantly reduces the maintenance costs of machine tools.

Fuel, 1991

ABSTRACT The thermal conductivities of suspensions of particulate coals in water, in fuel oil and... more ABSTRACT The thermal conductivities of suspensions of particulate coals in water, in fuel oil and in other liquids, and of mixtures of different particulate solids in liquids were measured. The binary suspension data were used to determine the solid thermal conductivities of the particulate inclusions by various extrapolations, and to test the different extrapolation schemes. A general, second-order, effective conductivity formula for binary mixtures, valid for small differences between the conductivities of dispersed and continuous phases, was derived. For suspensions containing a mixture of N different solids, of solid to liquid conductivity ratios and volume fractions φi, the formulae and were derived for the suspension thermal conductivity k∗. The former was found to do a good job of prediction for binary and multi-solid suspensions. As the volume fraction weighted geometric mean of the constituent conductivities, this formula is known to lie between the harmonic and arithmetic means as lower and upper bounds, respectively. Furthermore, over the range of conductivity ratios βi where it works well, it either lies between tighter bounds based on variational principles, or when it falls outside it differs indistinguishably from these bounds, which in this case turn out to be quite close.

All in-text references underlined in blue are linked to publications on ResearchGate, letting you... more All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately.

Biomedicines

We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation... more We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation models. We used an advanced semantic segmentation method and a deep convolutional neural network to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images. To improve the segmentation results, we used six models to analyse 309 patients, including 151 benign and 158 malignant tumour images. We compared the Unet3+ architecture with several other models, such as FCN, Unet, SegNet, DeeplabV3+ and pspNet. The Unet3+ model is a state-of-the-art, semantic segmentation architecture that showed optimal performance with an average accuracy of 82.53% and an average intersection over union (IU) of 52.57%. The weighted IU was found to be 89.14% with a global accuracy of 90.99%. The application of these types of segmentation models to the detection and diagnosis of breast cancer provides remarkable results. Our proposed method has the potential to provide...