TY - CHAP AU - Knyihár, Gábor AU - Csorba, Kristóf ED - Vajk, István ED - Dunaev, Dmitriy TI - In vitro Dissolution Prediction using Deep Convolutional Neural Networks T2 - Proceedings of the Automation and Applied Computer Science Workshop 2023 (AACS'23) PB - Budapesti Műszaki Egyetem, Automatizálási és Alkalmazott Informatikai Tanszék CY - Budapest SN - 9789634219262 PY - 2023 SP - 27 EP - 38 PG - 12 UR - https://m2.mtmt.hu/api/publication/34567948 ID - 34567948 LA - English DB - MTMT ER - TY - CHAP AU - Mrad, Mohamed Azouz AU - Csorba, Kristóf AU - Galata, Dorián László AU - Nagy, Zsombor Kristóf AU - Nagy, Brigitta ED - Vajk, István ED - Dunaev, Dmitriy TI - Droplet Based Prediction of Viscosity of Water-PVP Solutions Using Convolutional Neural Networks T2 - Proceedings of the Automation and Applied Computer Science Workshop 2023 (AACS'23) PB - Budapesti Műszaki Egyetem, Automatizálási és Alkalmazott Informatikai Tanszék CY - Budapest SN - 9789634219262 PY - 2023 SP - 1 EP - 15 PG - 15 UR - https://m2.mtmt.hu/api/publication/34476285 ID - 34476285 AB - The viscosity of a liquid is the property that measures the liquid internal resistance to flow. Monitoring viscosity is a vital component of quality control in several industrial fields including chemical, pharmaceutical, food, and energy-related industries. The most commonly used instrument for measuring viscosity is capillary viscometers, but their cost and complexity pose challenges for industries where accurate and real-time viscosity information is vital. In this work, we prepared thirteen solutions with different water and PVP (Polyvinylpyrrolidone) ratios, measured their different viscosity values, and produced videos of their droplets. We extracted the images of the fully developed droplets from the videos and we used the images to train a Convolutional neural network model to estimate the viscosity values of the WaterPVP solutions. The proposed model was able to predict the viscosity values of the samples using images of their droplets with a high accuracy on the test dataset. LA - English DB - MTMT ER - TY - JOUR AU - Mrad, Mohamed Azouz AU - Csorba, Kristóf AU - Galata, Dorián László AU - Nagy, Zsombor Kristóf AU - Charaf, Hassan TI - Droplet Based Estimation of Viscosity of Water–PVP Solutions Using Convolutional Neural Networks JF - PROCESSES J2 - PROCESSES VL - 11 PY - 2023 IS - 7 PG - 13 SN - 2227-9717 DO - 10.3390/pr11071917 UR - https://m2.mtmt.hu/api/publication/34045465 ID - 34045465 N1 - Department of Automation and Applied Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Műegyetem rkp.3, Budapest, H-1111, Hungary Department of Organic Chemistry and Technology, Faculty of Chemical Technology and Biotechnology, Budapest University of Technology and Economics, Budafoki út 8., F. II, Budapest, H-1111, Hungary Export Date: 14 August 2023 Correspondence Address: Mrad, M.A.; Department of Automation and Applied Informatics, Műegyetem rkp.3, Hungary; email: mmrad@edu.bme.hu AB - The viscosity of a liquid is the property that measures the liquid’s internal resistance to flow. Monitoring viscosity is a vital component of quality control in several industrial fields, including chemical, pharmaceutical, food, and energy-related industries. In many industries, the most commonly used instrument for measuring viscosity is capillary viscometers, but their cost and complexity pose challenges for these industries where accurate and real-time viscosity information is vital. In this work, we prepared fourteen solutions with different water and PVP (Polyvinylpyrrolidone) ratios, measured their different viscosity values, and produced videos of their droplets. We extracted the images of the fully developed droplets from the videos and we used the images to train a convolutional neural network model to estimate the viscosity values of the water–PVP solutions. The proposed model was able to accurately estimate the viscosity values of samples of unseen chemical formulations with the same composition with a low MSE score of 0.0243 and R2 score of 0.9576. The proposed method has potential applications in scenarios where real-time monitoring of liquid viscosity is required. LA - English DB - MTMT ER - TY - CHAP AU - Mrad, Mohamed Azouz AU - Csorba, Kristóf AU - Galata, Dorián László AU - Nagy, Zsombor Kristóf AU - Nagy, Brigitta ED - Zurada, Jacek M. ED - Tadeusiewicz, Ryszard ED - Pedrycz, Witold ED - Korytkowski, Marcin ED - Scherer, Rafał ED - Rutkowski, Leszek TI - Viscosity Estimation of Water-PVP Solutions from Droplets using Artificial Neural Networks and Image Processing T2 - Artificial Intelligence and Soft Computing PB - Springer Nature Switzerland AG CY - Cham SN - 9783031425059 T3 - Lecture Notes in Computer Science, ISSN 0302-9743 ; 14125. PY - 2023 SP - 157 EP - 166 PG - 10 DO - 10.1007/978-3-031-42505-9_14 UR - https://m2.mtmt.hu/api/publication/33605280 ID - 33605280 N1 - Export Date: 6 October 2023 Correspondence Address: Mrad, M.A.; Budapest University of Technology and Economics, Budapest Muegyetem rkp. 3, Hungary; email: mmrad@edu.bme.hu LA - English DB - MTMT ER - TY - JOUR AU - Knyihár, Gábor AU - Csorba, Kristóf AU - Charaf, Hassan TI - Evaluating the Accuracy of a Linear Regression Model in Predicting the Dissolution of Tablets based on Raman Maps JF - SIGNAL & IMAGE PROCESSING: AN INTERNATIONAL JOURNAL J2 - SIPIJ VL - 14 PY - 2023 IS - 1 SP - 23 EP - 33 PG - 11 SN - 2229-3922 DO - 10.5121/sipij.2023.14102 UR - https://m2.mtmt.hu/api/publication/33604474 ID - 33604474 AB - Investigation of the dissolution of tablets is an important area of pharmaceutical research. Such research aims to predict the dissolution process as accurately as possible without destroying the tablets. Several methods have been published that can estimate dissolution with approximate accuracy, but they are primarily complex learning algorithms that are time-consuming and require many samples to train. This article seeks to answer whether these complex models are necessary or whether a similar result can be achieved with the help of more straightforward methods. Therefore, during this work, a simpler linear regression model was created and analysed its effectiveness in estimating the dissolution curves. The investigation concluded that the results are not as accurate as in the case of more complex methods, but the model is more robust and can be used in the case of fewer samples. Thus, by further developing these and combining the methods, we can achieve better results in the future. LA - English DB - MTMT ER - TY - CHAP AU - Knyihár, Gábor AU - Csorba, Kristóf AU - Charaf, Hassan TI - Tabletták kioldódásának előrejelzése Raman térképek alapján lineáris regressziós modell segítségével T2 - Hungarian Association for Image Analysis and Pattern Recognition - 14th Conference PB - Képfeldolgozók és Alakfelismerők Társasága CY - Gyula PY - 2023 PG - 11 UR - https://m2.mtmt.hu/api/publication/33604424 ID - 33604424 AB - A tabletták oldódásának vizsgálata a gyógyszerészeti kutatások egyik fontos területe. Az ilyen kutatások célja az oldódás folyamatának előrejelzése a lehető legpontosabban a tabletták roncsolása nélkül. Számos olyan módszert publikáltak már, ami közelítő pontossággal meg tudja becsülni a kioldódást, de ezek többnyire olyan összetett tanuló algoritmusok, amelyek időigényesek és betanításukhoz nagy számú mintára van szükség. Ez a cikk arra a kérdésre keresi a választ, hogy szükségeseke ezek az összetett modellek, vagy egyszerűbb módszerek segítségével is elérhető hasonló eredmény. A munka során ezért egy egyszerűbb lineáris regressziós modellt készítettünk, és ennek hatékonyságát mértük a kioldódási görbék becslésében. A vizsgálattal arra a következtetésre jutottunk, hogy az eredmények ugyan nem annyira pontosak, mint a komplexebb módszerek esetében, ellenben a modell robosztusabb és kevesebb minta esetében is használható. Így a jövőben ezek továbbfejlesztésével és a módszerek kombinálásával akár jobb eredményeket is elérhetünk. LA - Hungarian DB - MTMT ER - TY - CHAP AU - Mrad, Mohamed Azouz AU - Csorba, Kristóf AU - Galata, Dorián László AU - Nagy, Zsombor Kristóf AU - Nagy, Brigitta ED - Zurada, Jacek M. ED - Tadeusiewicz, Ryszard ED - Pedrycz, Witold ED - Korytkowski, Marcin ED - Scherer, Rafał ED - Rutkowski, Leszek TI - Spectroscopy-Based Prediction of In Vitro Dissolution Profile Using Random Decision Forests T2 - Artificial Intelligence and Soft Computing PB - Springer Netherlands CY - Cham SN - 9783031234927 T3 - Lecture Notes in Computer Science, ISSN 0302-9743 ; 13588. PY - 2023 SP - 411 EP - 422 PG - 12 DO - 10.1007/978-3-031-23492-7_35 UR - https://m2.mtmt.hu/api/publication/33595245 ID - 33595245 LA - English DB - MTMT ER - TY - CHAP AU - Knyihár, Gábor AU - Csorba, Kristóf AU - Charaf, Hassan TI - Predicting the Dissolution of Tablets based on Raman Maps using a Linear Regression Model T2 - Computer Science and Machine Learning Trends 2023 PB - Academy and Industry Research Collaboration Center (AIRCC) SN - 9781925953848 PY - 2023 SP - 79 EP - 85 PG - 7 DO - 10.5121/csit.2023.130107 UR - https://m2.mtmt.hu/api/publication/33543170 ID - 33543170 AB - Investigation of the dissolution of tablets is an important area of pharmaceutical research. Such research aims to predict the dissolution process as accurately as possible without destroying the tablets. Several methods have been published that can estimate dissolution with approximate accuracy, but they are mostly complex and time-consuming. This article seeks to answer whether these complex models are necessary or whether a similar result can be achieved with the help of more straightforward methods. Therefore, during this work, a simpler linear regression model was created and analysed its effectiveness in estimating the dissolution curves. The investigation concluded that the results are not as accurate as in the case of more complex methods, but they are not far behind. Thus, even similar results may be achieved by fine-tuning and possibly developing these methods. LA - English DB - MTMT ER - TY - CHAP AU - Mrad, Mohamed Azouz AU - Csorba, Kristóf AU - Galata, Dorián László AU - Nagy, Zsombor Kristóf AU - Nagy, Brigitta ED - Dunaev, Dmitriy ED - Vajk, István TI - Comparing Measurements in the Prediction of In Vitro Dissolution Profile Using Artificial Neural Networks T2 - Proceedings of the Automation and Applied Computer Science Workshop 2022 (AACS'22) PB - Budapesti Műszaki Egyetem, Automatizálási és Alkalmazott Informatikai Tanszék CY - Budapest SN - 9789634218753 PY - 2022 SP - 1 EP - 11 PG - 11 UR - https://m2.mtmt.hu/api/publication/34476278 ID - 34476278 AB - In the pharmaceutical industry, dissolution testing is part of the target product quality that are essentials in the approval of new products. The prediction of the dissolution profile based on spectroscopic data is an alternative to the current destructive and time-consuming method. Raman and near infrared (NIR) spectroscopies are two complementary methods, that provide information on the physical and chemical properties of the tablets and can help in predicting their dissolution profiles. This work aims to compare the information collected by these methods to support the decision of which measurements should be used so that the accuracy requirement of the industry is met . Artificial neural network models were created, in which the spectroscopy data and the measured compression curves were used as an input individually and in different combinations in order to estimate the dissolution profiles. It was found that , using only the NIR transmission method along with the compression force data or the Raman and NIR reflection methods , the dissolution profile was estimated within the acceptance limits of the f2 similarity factor. Adding further spectroscopy methods increased the prediction accuracy. LA - English DB - MTMT ER - TY - CHAP AU - Krammer, Olivér AU - Varga, Arpad AU - Géczy, Attila AU - Csorba, Kristóf TI - Image Processing Methods for Detecting Voids in the Solder Joints of Surface-Mounted Components T2 - 2022 45th International Spring Seminar on Electronics Technology (ISSE) PB - IEEE CY - Piscataway (NJ) SN - 9781665465908 T3 - International Spring Seminar on Electronics Technology ISSE, ISSN 2161-2536 PY - 2022 SP - 1 EP - 4 PG - 4 DO - 10.1109/ISSE54558.2022.9812775 UR - https://m2.mtmt.hu/api/publication/33127355 ID - 33127355 N1 - Funding Agency and Grant Number: National Research, Development and Innovation Office -NKFIH [FK 132186] Funding text: The research reported in this paper has been supported by the National Research, Development and Innovation Office -NKFIH, FK 132186 AB - Void formation in the lead-free solder joints of electrical components can significantly affect their mechanical properties and thermal performance. Void-detection methods have been investigated in this paper, which are able to identify and measure voids in meniscus-shaped solder joints of surface mounted components automatically. In the experiment, 0603 size resistors (1.5 x 0.75 mm) were soldered onto a testboard, and X-ray images were acquired about the samples then. The image processing methods for the void detection were implemented in OpenCV-Python. At first, the properties of the images were analyzed (for example, calculating the histogram), and then the area, including the resistor and solder pads, was extracted by masking. Several methods were investigated for identifying voids in the images; Canny edge detection, global- and adaptive thresholding, and blob detection algorithm. The accuracy of the extraction methods was evaluated by identifying voids on a test image manually and comparing the results to that provided by the different methods. Canny edge detection was the best in our case, but global thresholding and blob detection are also promising solutions. LA - English DB - MTMT ER -