Papers by Lodoiravsal Choimaa
Predicting and forecasting air quality is the one of the most essential activity in the Smart Cit... more Predicting and forecasting air quality is the one of the most essential activity in the Smart City. Recently, there are many study to use the machine learning approaches for evaluating and predicting air quality using big data. The aim of this study is to obtain machine learning model for air quality forecasting using previous air quality station data and the weather data. The air quality depends on multi-dimensional factors including location, time, weather parameters, such as temperature, humidity, wind direction and force, air pressure, etc. There are many machine learning approaches, but artificial neural Network model tries to simulate the structures and networks within human brain. It is convenient for working to find relation between multi parameters. If the neural network could determine the relation of the air quality using the weather and air quality data of last year, it is possible to predict approximately air quality of Ulaanbaatar city. We used features including parameters of temperature, humidity, wind direction, air pressure, PM2.5 and PM10, NO2, CO, SO2 and measuring time to build recurrent neural network model that is the class of artificial neural network. In this work we did machine learning test of neural network algorithm for the air quality prediction using LSTM /long short term memory/ model and discussed machine learning test results. * Speaker PoS(ISGC2021)012 Air quality predictions of Ulaanbaatar using machine learning approach Otgonsuvd Badrakh
Nowadays any recognition algorithms need to work more faster and use less resources for mobile de... more Nowadays any recognition algorithms need to work more faster and use less resources for mobile device applications. Therefore, in this paper we propose a new algorithm for the limitations in the case of traditional Mongolian script recognition. The proposed method based on a line profile in view point of the specific feature of the traditional Mongolian script. Our experimental results have shown that the proposed method is proper to printed Mongolian script.
Journal of Infection, May 1, 2019
Frontiers in Bioengineering and Biotechnology, May 22, 2018
International Journal of Software Engineering and its Applications, Jun 30, 2017
Recently, the digitizing of historical and ancient books written in thousand year old Traditional... more Recently, the digitizing of historical and ancient books written in thousand year old Traditional Mongolian Script has emerged to facilitate access and preservation. Unique writing style and multi-fonttype variations of Traditional Mongolian script brings challenges to recognize. Recognition of woodblock printed documents is one of the largest problems of digitizing a huge number of ancient Mongolian books such as the Kanjur (it consists of 108 volumes). In this paper we propose a method for feature extraction in a 'Modonbar' case which is printed by woodblock printing technology. In general, Mongolian traditional script has several special properties: an agglutinative language, horizontal written style up to down, column order is from left to right, different shapes dependent on their position in current word, for example a letter has 3 kinds of shapes in the beginning, middle and end of the word. In this work, we use two feature extraction methods with localization of the characters. First method focuses on the bounding box size and the second method uses the percentage of the black pixels within thecandidate region. Our experimental results have shown that the competitive recognition rates well compared to state-of-the-art methods and uses fewer features than those methods in the 'Modonbar' case.
IEEE Access, 2022
Grasping and manipulating transparent objects with a robot is a challenge in robot vision. To suc... more Grasping and manipulating transparent objects with a robot is a challenge in robot vision. To successfully perform robotic grasping, 6D object pose estimation is needed. However, transparent objects are difficult to recognize because their appearance varies depending on the background, and modern 3D sensors cannot collect reliable depth data on transparent object surfaces due to the translucent, refractive, and specular surfaces. To address these challenges, we proposed a 6D pose estimation of transparent objects for manipulation. Given a single RGB image of transparent objects, the 2D keypoints are estimated using a deep neural network. Then, the PnP algorithm takes camera intrinsics, object model size, and keypoints as inputs to estimate the 6D pose of the object. Finally, the predicted poses of the transparent object were used for grasp planning. Our experiments demonstrated that our picking system is capable of grasping transparent objects from different backgrounds. To the best of our knowledge, this is the first time a robot has grasped transparent objects from a single RGB image. Furthermore, the experiments show that our method is better than the 6D pose estimation baselines and can be generalized to real-world images. INDEX TERMS Pose estimation, synthetic data, robot picking, transparent object.
Frontiers in Physiology
Background: To conduct a rapid preliminary COVID-19 screening prior to polymerase chain reaction ... more Background: To conduct a rapid preliminary COVID-19 screening prior to polymerase chain reaction (PCR) test under clinical settings, including patient’s body moving conditions in a non-contact manner, we developed a mobile and vital-signs-based infection screening composite-type camera (VISC-Camera) with truncus motion removal algorithm (TMRA) to screen for possibly infected patients.Methods: The VISC-Camera incorporates a stereo depth camera for respiratory rate (RR) determination, a red–green–blue (RGB) camera for heart rate (HR) estimation, and a thermal camera for body temperature (BT) measurement. In addition to the body motion removal algorithm based on the region of interest (ROI) tracking for RR, HR, and BT determination, we adopted TMRA for RR estimation. TMRA is a reduction algorithm of RR count error induced by truncus non-respiratory front-back motion measured using depth-camera-determined neck movement. The VISC-Camera is designed for mobile use and is compact (22 cm × ...
Proceedings of International Symposium on Grids & Clouds 2021 — PoS(ISGC2021), 2021
Predicting and forecasting air quality is the one of the most essential activity in the Smart Cit... more Predicting and forecasting air quality is the one of the most essential activity in the Smart City. Recently, there are many study to use the machine learning approaches for evaluating and predicting air quality using big data. The aim of this study is to obtain machine learning model for air quality forecasting using previous air quality station data and the weather data. The air quality depends on multi-dimensional factors including location, time, weather parameters, such as temperature, humidity, wind direction and force, air pressure, etc. There are many machine learning approaches, but artificial neural Network model tries to simulate the structures and networks within human brain. It is convenient for working to find relation between multi parameters. If the neural network could determine the relation of the air quality using the weather and air quality data of last year, it is possible to predict approximately air quality of Ulaanbaatar city. We used features including parameters of temperature, humidity, wind direction, air pressure, PM2.5 and PM10, NO2, CO, SO2 and measuring time to build recurrent neural network model that is the class of artificial neural network. In this work we did machine learning test of neural network algorithm for the air quality prediction using LSTM /long short term memory/ model and discussed machine learning test results. * Speaker PoS(ISGC2021)012 Air quality predictions of Ulaanbaatar using machine learning approach Otgonsuvd Badrakh
Journal of Infection, 2019
Frontiers in bioengineering and biotechnology, 2018
Over 350 million people across the world suffer from major depressive disorder (MDD). More than 1... more Over 350 million people across the world suffer from major depressive disorder (MDD). More than 10% of MDD patients have suicide intent, while it has been reported that more than 40% patients did not consult their doctors for MDD. In order to increase consultation rate of potential MDD patients, we developed a novel MDD screening system which can be used at home without help of health-care professionals. Using a fingertip photoplethysmograph (PPG) sensor as a substitute of electrocardiograph (ECG), the system discriminates MDD patients from healthy subjects using autonomic nerve transient responses induced by a mental task (random number generation) via logistic regression analysis. The nine logistic regression variables are averages of heart rate (HR), high frequency (HF) component of heart rate variability (HRV), and the low frequency (LF)/HF ratio of HRV before, during, and after the mental task. We conducted a clinical test of the proposed system. Participants were 6 MDD patient...
International Journal of Software Engineering and Its Applications, 2017
Recently, the digitizing of historical and ancient books written in thousand year old Traditional... more Recently, the digitizing of historical and ancient books written in thousand year old Traditional Mongolian Script has emerged to facilitate access and preservation. Unique writing style and multi-fonttype variations of Traditional Mongolian script brings challenges to recognize. Recognition of woodblock printed documents is one of the largest problems of digitizing a huge number of ancient Mongolian books such as the Kanjur (it consists of 108 volumes). In this paper we propose a method for feature extraction in a 'Modonbar' case which is printed by woodblock printing technology. In general, Mongolian traditional script has several special properties: an agglutinative language, horizontal written style up to down, column order is from left to right, different shapes dependent on their position in current word, for example a letter has 3 kinds of shapes in the beginning, middle and end of the word. In this work, we use two feature extraction methods with localization of the characters. First method focuses on the bounding box size and the second method uses the percentage of the black pixels within thecandidate region. Our experimental results have shown that the competitive recognition rates well compared to state-of-the-art methods and uses fewer features than those methods in the 'Modonbar' case.
World Technopolis Review, 2015
Innovation system is a framework concept that can be classified in many ways, namely-national, re... more Innovation system is a framework concept that can be classified in many ways, namely-national, regional, sectoral and technological. Regardless of classification, all these systems have some common features and characteristics as a system. Before the innovation system concept, Mongolia developed and implemented a system to maintain nation's capacity to acquire, absorb and disseminate technologies like other countries. There were two important practices in the system development. Firstly, Mongolia modified and implemented a system "ShBOS" (meant "Invention and Innovative Idea System") that met its unique features to create innovative culture in the nation. Secondly, newly emerged ICT sector was quickly scaled up to be able to export technological products. The main objective of this article is to study modern experience of developing the national innovation system in Mongolia, assess current state of the system, innovation awareness and readiness, and carry out recommendations on its improvement with particular focus on the capacity of ICT sector as a pilot sector. The paper suggests that the above mentioned two achievements can be applied for developing the national innovation system through technological innovation system approach.
SPIE Proceedings, 2015
Integral imaging (InIm) is an interesting research area in the three-dimensional (3-D) display te... more Integral imaging (InIm) is an interesting research area in the three-dimensional (3-D) display technology. While it is simple in structure, it shows full color and full parallax 3-D images without the necessity of special glasses. InIm display usually uses the simplest lens array, and hence displayed 3-D image suffers from distortions. A dominating distortion is a Petzval curvature. To the authors' best knowledge, we have firstly analyzed an effect of the Petzval curvature in InIm display. The immediate consequence of Petzval curvature is that the depth plane of InIm display becomes a curved plane array. Using simulation, the effect of Petzval curvature is found to reduce the depth range, change the viewing direction, and increase the black stripe. The result indicates that the lens array in the InIm display should be customized to reduce these undesirable effects.
2014 7th International Conference on Ubi-Media Computing and Workshops, 2014
Nowadays any recognition algorithms need to work more faster and use less resources for mobile de... more Nowadays any recognition algorithms need to work more faster and use less resources for mobile device applications. Therefore, in this paper we propose a new algorithm for the limitations in the case of traditional Mongolian script recognition. The proposed method based on a line profile in view point of the specific feature of the traditional Mongolian script. Our experimental results have shown that the proposed method is proper to printed Mongolian script.
IEEE Access
Grasping and manipulating transparent objects with a robot is a challenge in robot vision. To suc... more Grasping and manipulating transparent objects with a robot is a challenge in robot vision. To successfully perform robotic grasping, 6D object pose estimation is needed. However, transparent objects are difficult to recognize because their appearance varies depending on the background, and modern 3D sensors cannot collect reliable depth data on transparent object surfaces due to the translucent, refractive, and specular surfaces. To address these challenges, we proposed a 6D pose estimation of transparent objects for manipulation. Given a single RGB image of transparent objects, the 2D keypoints are estimated using a deep neural network. Then, the PnP algorithm takes camera intrinsics, object model size, and keypoints as inputs to estimate the 6D pose of the object. Finally, the predicted poses of the transparent object were used for grasp planning. Our experiments demonstrated that our picking system is capable of grasping transparent objects from different backgrounds. To the best of our knowledge, this is the first time a robot has grasped transparent objects from a single RGB image. Furthermore, the experiments show that our method is better than the 6D pose estimation baselines and can be generalized to real-world images. INDEX TERMS Pose estimation, synthetic data, robot picking, transparent object.
2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2018
Fever is one significant sign of infection. Hence, infrared thermography systems are important fo... more Fever is one significant sign of infection. Hence, infrared thermography systems are important for detecting infected suspects in public places. Reliable temperature measurements by thermography are influenced by several factors, including environmental conditions. This paper proposes a linear regression analysis-based facial temperature optimization method to improve the accuracy of multiple vital signs-based infection screening at various ambient temperatures. To obtain the relationship between ambient temperature and thermography measurements, 20 instances of axillary temperature, thermography measurements of facial temperature, and five different ambient temperature values at the time of measurement were used as a training set for a linear regression model. Temperatures from a total of 30 subjects were recalculated by the model. The screening system was evaluated using the temperature both before and after optimization to demonstrate the accuracy of the optimization method. A k-...
Uploads
Papers by Lodoiravsal Choimaa