Gabor Horvath
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Gabor Horvath has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
T. Szabo
6 shared publications- Istvan Engedy
Dept. of Meas. & Inf. Syst., Budapest Univ. of Technol. & Econ., Budapest, Hungary|c
4 shared publications - Balazs Scherer
Department of Measurement and Information Systems, Budapest University of Technology and Economics, Hungary
2 shared publications - Bela Feher
Department of Measurement and Information Systems, Budapest University of Technology and Economics, Budapest, Hungary
2 shared publications - Béla Pataki
Budapest University of Technology and Economics
2 shared publications G. Orbán
Budapest University of Technology and Economics
2 shared publications
Latest Publications
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1465-1470
Path reconstruction based on gyroscope bias estimation using GPS
This paper presents a method for path reconstruction from logged MEMS gyroscope and odometer measurements, through the estimation of the gyroscope bias from GPS data. The bias estimation is done by minimizing the distance between the reconstructed path and the external reference positions (GPS) by tuning the bias with common minimization methods. Both gradient based and quasi-Newton minimization methods are investigated. An efficient quaternion based mathematical model of the problem is presented. The path produced by the proposed method has higher spatial and temporal resolution than the GPS path, it is more accurate than a path from a purely inertial measurement unit and it is at least as accurate as the GPS path, according to real-life experiment.
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1465-1470
Path reconstruction based on gyroscope bias estimation using GPS
This paper presents a method for path reconstruction from logged MEMS gyroscope and odometer measurements, through the estimation of the gyroscope bias from GPS data. The bias estimation is done by minimizing the distance between the reconstructed path and the external reference positions (GPS) by tuning the bias with common minimization methods. Both gradient based and quasi-Newton minimization methods are investigated. An efficient quaternion based mathematical model of the problem is presented. The path produced by the proposed method has higher spatial and temporal resolution than the GPS path, it is more accurate than a path from a purely inertial measurement unit and it is at least as accurate as the GPS path, according to real-life experiment.
- 1 May 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 522-526
Microcontroller tracing in Hardware in the Loop tests integrating trace port measurement capability into NI VeriStand
Developing software for safety critical embedded systems requires extensive testing, and HIL (Hardware in the Loop) test has one of the most important roles in this testing process. Modern microcontrollers can provide opportunities to improve the efficiency and capability of traditional HIL testing. Many of these opportunities are connected to their internal so called Trace interfaces. This paper shortly introduces the capabilities of these Trace interfaces, and presents the way to integrate them into a professional HIL test development environment the NI VeriStand. The integration process starts with the acquisition of Trace signals, which requires a high speed FPGA based solution, and then a way to capture and process the data at the VeriStand engine level (usually runs on a real-time target), and at the Workspace level (Host PC) is described. The paper ends with the conclusion, which analyzes the throughput and capabilities of the integrated Trace interface and shows the possible application of the data captured by it.
- 1 May 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 522-526
Microcontroller tracing in Hardware in the Loop tests integrating trace port measurement capability into NI VeriStand
Developing software for safety critical embedded systems requires extensive testing, and HIL (Hardware in the Loop) test has one of the most important roles in this testing process. Modern microcontrollers can provide opportunities to improve the efficiency and capability of traditional HIL testing. Many of these opportunities are connected to their internal so called Trace interfaces. This paper shortly introduces the capabilities of these Trace interfaces, and presents the way to integrate them into a professional HIL test development environment the NI VeriStand. The integration process starts with the acquisition of Trace signals, which requires a high speed FPGA based solution, and then a way to capture and process the data at the VeriStand engine level (usually runs on a real-time target), and at the Workspace level (Host PC) is described. The paper ends with the conclusion, which analyzes the throughput and capabilities of the integrated Trace interface and shows the possible application of the data captured by it.
- 1 April 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 141-144
Lung nodule detection on digital tomosynthesis images: A preliminary study
In this paper, we address the problem of small pulmonary nodule detection on digital tomosynthesis (DT) scans. We propose efficient, domain-specific filters for the enhancement and classification of bright, rounded structures in three-dimensional volumes. First, 61 DT slices per scan are reconstructed from the DT projections by filtered backprojection (FBP). Next, nodule candidates are searched slice-wise calculating the determinant of the Hessian (DoH). Then a large number of false candidates are removed by a supervised classifier. The features for classification include coordinates, image correlation and overlap with vessels. For the segmentation of the vascular tree, a modification of the Frangi filter is employed. The system is evaluated on simulated DT scans generated from a computed tomography database. A subset of the LIDC/IDRI database of 37 scans was used. 42% of nodules could be detected while producing on average 100 false positives per scan. Sensitivity increased to 77% when restricting the search to nodules marked as visible.
- 1 April 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 141-144
Lung nodule detection on digital tomosynthesis images: A preliminary study
In this paper, we address the problem of small pulmonary nodule detection on digital tomosynthesis (DT) scans. We propose efficient, domain-specific filters for the enhancement and classification of bright, rounded structures in three-dimensional volumes. First, 61 DT slices per scan are reconstructed from the DT projections by filtered backprojection (FBP). Next, nodule candidates are searched slice-wise calculating the determinant of the Hessian (DoH). Then a large number of false candidates are removed by a supervised classifier. The features for classification include coordinates, image correlation and overlap with vessels. For the segmentation of the vascular tree, a modification of the Frangi filter is employed. The system is evaluated on simulated DT scans generated from a computed tomography database. A subset of the LIDC/IDRI database of 37 scans was used. 42% of nodules could be detected while producing on average 100 false positives per scan. Sensitivity increased to 77% when restricting the search to nodules marked as visible.
- Open Access
- 1 January 2013
- Published by Periodica Polytechnica Budapest University of Technology and Economics in Periodica Polytechnica Electrical Engineering
- Vol. 57 (1) , 19
An X-ray CAD system with ribcage suppression for improved detection of lung lesions
An X-ray CAD system with ribcage suppression for improved detection of lung lesions
- 1 January 2013
- Published by Periodica Polytechnica Budapest University of Technology and Economics in Periodica Polytechnica Electrical Engineering
- Vol. 57 (1) , 19
Open AccessAn X-ray CAD system with ribcage suppression for improved detection of lung lesions
An X-ray CAD system with ribcage suppression for improved detection of lung lesions
- 1 June 2012
- Published by Akademiai Kiado Zrt. in Orvosi Hetilap
- Vol. 153 (23) , 899-903
Pulmonary infections following solid organ transplantation
Solid organ transplantation is the standard of care for selected patients with severe vital organ dysfunction. The need for immunosuppression to prevent organ rejection is a common characteristic of recipients. Immunosuppression increases the risk of infections, especially with low virulence opportunistic pathogens. Infections following solid organ transplantation mainly affect the lungs and the airways. Establishing the diagnosis includes a wide spectrum of pulmonary diagnostics, high standard microbiological analysis and various imaging methods. With the improvement of treatment options, the number of kidney, liver, heart and lung transplant recipients is increasing and, therefore, more and more physicians may meet pulmonary complications in these patients. Orv. Hetil., 2012, 153, 899–903.
- 1 June 2012
- Published by Akademiai Kiado Zrt. in Orvosi Hetilap
- Vol. 153 (23) , 899-903
Pulmonary infections following solid organ transplantation
Solid organ transplantation is the standard of care for selected patients with severe vital organ dysfunction. The need for immunosuppression to prevent organ rejection is a common characteristic of recipients. Immunosuppression increases the risk of infections, especially with low virulence opportunistic pathogens. Infections following solid organ transplantation mainly affect the lungs and the airways. Establishing the diagnosis includes a wide spectrum of pulmonary diagnostics, high standard microbiological analysis and various imaging methods. With the improvement of treatment options, the number of kidney, liver, heart and lung transplant recipients is increasing and, therefore, more and more physicians may meet pulmonary complications in these patients. Orv. Hetil., 2012, 153, 899–903.
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
An improved wavelet-based contralateral subtraction algorithm
Contralateral subtraction is an image processing technique aimed to enhance asymmetries in chest radiographs. Since malignant processes often result in asymmetrical lesions, a computer aided diagnostic system capable of enhancing asymmetries on these images could support the diagnostic procedure. The technique itself consists of registration of the two lung areas, and subtraction of the registered images. Contralateral subtraction is therefore essentially a registration problem, a field that has been widely researched offering various solutions to the problem at hand. One of these solutions is wavelet transformation, a multiresolution method that has a potential not fully unlocked by previous methods. We propose a contralateral subtraction scheme based on an elastic registration algorithm in the wavelet domain, using dual tree complex wavelet transform. By registering only the low frequency components of the images, the resulting transformation will be inherently regular, without relying on conventional regularization methods. We demonstrate the effectiveness of this concept by applying it to a contralateral subtraction problem, verifying the algorithm with synthetic tests as well as chest radiographs from the JSRT public database. These results show an increased sensitivity of nodule detection, indicating that the proposed method is a valid alternative to other known registration methods.
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
An improved wavelet-based contralateral subtraction algorithm
Contralateral subtraction is an image processing technique aimed to enhance asymmetries in chest radiographs. Since malignant processes often result in asymmetrical lesions, a computer aided diagnostic system capable of enhancing asymmetries on these images could support the diagnostic procedure. The technique itself consists of registration of the two lung areas, and subtraction of the registered images. Contralateral subtraction is therefore essentially a registration problem, a field that has been widely researched offering various solutions to the problem at hand. One of these solutions is wavelet transformation, a multiresolution method that has a potential not fully unlocked by previous methods. We propose a contralateral subtraction scheme based on an elastic registration algorithm in the wavelet domain, using dual tree complex wavelet transform. By registering only the low frequency components of the images, the resulting transformation will be inherently regular, without relying on conventional regularization methods. We demonstrate the effectiveness of this concept by applying it to a contralateral subtraction problem, verifying the algorithm with synthetic tests as well as chest radiographs from the JSRT public database. These results show an increased sensitivity of nodule detection, indicating that the proposed method is a valid alternative to other known registration methods.
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10915281,p. 488-491
Trace and debug port based watchdog processor
Novel architectures and processors are designed to satisfy the needs specified by functional safety standards, like IEC 61508 and ISO 26262. An example for this devices is the TMS570 from Texas Instruments, which is a SIL3 (Safety Integrity Level 3) capable microcontroller. The question is whether a specialized hardware alone, like the TMS570 is enough for reaching safety goals or additional efforts should be done. This paper presents our novel idea of trace and debug port based watchdog processor that increase the safety for systems designed with traditional microcontrollers or with modern dual core safe ones. The approach presented is using the debug and trace hardware blocks (present in nearly every 32-bit microcontrollers introduced into the market in the last 5 years) to see inside the guarded system and to make statements of its healthiness. The paper shows the benefits and capability of such debug and trace hardware based watchdog control. We also introduce the bottlenecks of this approach and make suggestions to eliminate these, by making minor modifications to the existing trace blocks of the ARM CoreSight architecture.
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10915281,p. 488-491
Trace and debug port based watchdog processor
Novel architectures and processors are designed to satisfy the needs specified by functional safety standards, like IEC 61508 and ISO 26262. An example for this devices is the TMS570 from Texas Instruments, which is a SIL3 (Safety Integrity Level 3) capable microcontroller. The question is whether a specialized hardware alone, like the TMS570 is enough for reaching safety goals or additional efforts should be done. This paper presents our novel idea of trace and debug port based watchdog processor that increase the safety for systems designed with traditional microcontrollers or with modern dual core safe ones. The approach presented is using the debug and trace hardware blocks (present in nearly every 32-bit microcontrollers introduced into the market in the last 5 years) to see inside the guarded system and to make statements of its healthiness. The paper shows the benefits and capability of such debug and trace hardware based watchdog control. We also introduce the bottlenecks of this approach and make suggestions to eliminate these, by making minor modifications to the existing trace blocks of the ARM CoreSight architecture.
- 23 March 2012
- Published by Emerald Publishing in International Journal of Intelligent Computing and Cybernetics
- Vol. 5 (1) , 111-144
Algorithm fusion to improve detection of lung cancer on chest radiographs
Purpose: The purpose of this paper is to show an efficient method for the detection of signs of early lung cancer. Various image processing algorithms are presented for different types of lesions, and a scheme is proposed for the combination of results.Design/methodology/approach: A computer aided detection (CAD) scheme was developed for detection of lung cancer. It enables different lesion enhancer algorithms, sensitive to specific lesion subtypes, to be used simultaneously. Three image processing algorithms are presented for the detection of small nodules, large ones, and infiltrated areas. The outputs are merged, the false detection rate is reduced with four separated support vector machine (SVM) classifiers. The classifier input comes from a feature selection algorithm selecting from various textural and geometric features. A total of 761 images were used for testing, including the database of the Japanese Society of Radiological Technology (JSRT).Findings: The fusion of algorithms reduced false positives on average by 0.6 per image, while the sensitivity remained 80 per cent. On the JSRT database the system managed to find 60.2 per cent of lesions at an average of 2.0 false positives per image. The effect of using different result evaluation criteria was tested and a difference as high as 4 percentage points in sensitivity was measured. The system was compared to other published methods.Originality/value: The study described in the paper proves the usefulness of lesion enhancement decomposition, while proposing a scheme for the fusion of algorithms. Furthermore, a new algorithm is introduced for the detection of infiltrated areas, possible signs of lung cancer, neglected by previous solutions.
- 23 March 2012
- Published by Emerald Publishing in International Journal of Intelligent Computing and Cybernetics
- Vol. 5 (1) , 111-144
Algorithm fusion to improve detection of lung cancer on chest radiographs
Purpose: The purpose of this paper is to show an efficient method for the detection of signs of early lung cancer. Various image processing algorithms are presented for different types of lesions, and a scheme is proposed for the combination of results.Design/methodology/approach: A computer aided detection (CAD) scheme was developed for detection of lung cancer. It enables different lesion enhancer algorithms, sensitive to specific lesion subtypes, to be used simultaneously. Three image processing algorithms are presented for the detection of small nodules, large ones, and infiltrated areas. The outputs are merged, the false detection rate is reduced with four separated support vector machine (SVM) classifiers. The classifier input comes from a feature selection algorithm selecting from various textural and geometric features. A total of 761 images were used for testing, including the database of the Japanese Society of Radiological Technology (JSRT).Findings: The fusion of algorithms reduced false positives on average by 0.6 per image, while the sensitivity remained 80 per cent. On the JSRT database the system managed to find 60.2 per cent of lesions at an average of 2.0 false positives per image. The effect of using different result evaluation criteria was tested and a difference as high as 4 percentage points in sensitivity was measured. The system was compared to other published methods.Originality/value: The study described in the paper proves the usefulness of lesion enhancement decomposition, while proposing a scheme for the fusion of algorithms. Furthermore, a new algorithm is introduced for the detection of infiltrated areas, possible signs of lung cancer, neglected by previous solutions.
- 1 November 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 177-182
Neural models for an intelligent greenhouse - A CMAC global greenhouse model
The effectiveness of greenhouse control can be raised by the application of model based intelligent control. The large complexity of the thermal system in the greenhouse calls for a decomposed model. The key element of such model decomposition is the global greenhouse model creating predictions for all important parts of the greenhouse. A Cerebellar Model Articulation Controller (CMAC) model was built and trained to learn the thermal dynamics in the greenhouse and to provide forecasts for the future state of the house for 20 minutes ahead. The CMAC model was tested with 2 actuator configuration settings of the greenhouse, representing more than 57% of the operating time of the house.
- 1 November 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 177-182
Neural models for an intelligent greenhouse - A CMAC global greenhouse model
The effectiveness of greenhouse control can be raised by the application of model based intelligent control. The large complexity of the thermal system in the greenhouse calls for a decomposed model. The key element of such model decomposition is the global greenhouse model creating predictions for all important parts of the greenhouse. A Cerebellar Model Articulation Controller (CMAC) model was built and trained to learn the thermal dynamics in the greenhouse and to provide forecasts for the future state of the house for 20 minutes ahead. The CMAC model was tested with 2 actuator configuration settings of the greenhouse, representing more than 57% of the operating time of the house.
- 1 June 2011
- Published by Elsevier in Discrete Mathematics
- Vol. 311 (12) , 1034-1039
A lower bound for the number of blocks of designs with odd- 1 June 2011
- Published by Elsevier in Discrete Mathematics
- Vol. 311 (12) , 1034-1039
A lower bound for the number of blocks of designs with odd