Roman Kvуetnyy, Yu. Bunyak, Olga Sofina, Volodymyr Kotsiubynskyi, T. Piliavoz, Olena Stoliarenko, Saule Kumargazhanova
The investigation of the extraction of image objects features by filters based on tensor and vector data presentation is considered. The tensor data is obtained as a sum of rank-one tensors, given by the tensor product of the vector of lexicographic representation of image fragments pixels with itself. The accumulated tensor is approximated by one rank tensor obtained using singular values decomposition. It has been shown that the main vector of the decomposition can be considered as the object feature vector. The vector data is obtained by accumulating analogous vectors of image fragments pixels. The accumulated vector is also considered as an object feature. The filter banks of a set of objects are obtained by regularized inversion of the matrices compiled by object features vectors. Optimized regularization of the inversion is used to expand the regions of object features capture with minimal error. The object fragments and corresponding feature vectors are selected through a training iterative process. The tensor and vector approaches create two channels for recognition. High efficiency of object recognition can be achieved by choosing the filter capture band and creating filter branches according to the given bands. The filters create a convolutional network to recognize a set of objects. It has been shown that the obtained filters have an advantage over known correlation filters when recognizing objects with small fragments.
{"title":"TENSOR AND VECTOR APPROACHES TO OBJECTS RECOGNITION BY INVERSE FEATURE FILTERS","authors":"Roman Kvуetnyy, Yu. Bunyak, Olga Sofina, Volodymyr Kotsiubynskyi, T. Piliavoz, Olena Stoliarenko, Saule Kumargazhanova","doi":"10.35784/iapgos.5494","DOIUrl":"https://doi.org/10.35784/iapgos.5494","url":null,"abstract":"The investigation of the extraction of image objects features by filters based on tensor and vector data presentation is considered. The tensor data is obtained as a sum of rank-one tensors, given by the tensor product of the vector of lexicographic representation of image fragments pixels with itself. The accumulated tensor is approximated by one rank tensor obtained using singular values decomposition. It has been shown that the main vector of the decomposition can be considered as the object feature vector. The vector data is obtained by accumulating analogous vectors of image fragments pixels. The accumulated vector is also considered as an object feature. The filter banks of a set of objects are obtained by regularized inversion of the matrices compiled by object features vectors. Optimized regularization of the inversion is used to expand the regions of object features capture with minimal error. The object fragments and corresponding feature vectors are selected through a training iterative process. The tensor and vector approaches create two channels for recognition. High efficiency of object recognition can be achieved by choosing the filter capture band and creating filter branches according to the given bands. The filters create a convolutional network to recognize a set of objects. It has been shown that the obtained filters have an advantage over known correlation filters when recognizing objects with small fragments.","PeriodicalId":504633,"journal":{"name":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140358338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shanmukhaprasanthi Tammineni, Swaraiya Madhuri Rayavarapu, S. Gottapu, Raj Kumar Goswami
In contemporary times, the preservation of scientific and creative endeavours often relies on the utilization of film and image archives, hence emphasizing the significance of image processing as a critical undertaking. Image inpainting refers to the process of digitally altering an image in a manner that renders the adjustments imperceptible to a viewer lacking knowledge of the original image. Image inpainting is a technique mostly employed to restore damaged regions within an image by utilizing information obtained from matching characteristics in relevant images. This process involves filling in the damaged areas and removing undesired objects. The SURF (Speeded Up Robust Feature) algorithm under consideration is partitioned into three primary phases. Firstly, the essential characteristics of the impaired image and the pertinent image are identified. In the second stage, the relationship between the damaged image and the relevant image is determined in terms of translation, scaling, and rotation. Ultimately, the destroyed area is reconstructed through the application of the inverse transformation. The quality assessment of inpainted images can be evaluated using metrics such as Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), and Mean Squared Error (MSE). The experimental findings provide evidence that the suggested inpainting technique is effective in terms of both speed and quality.
{"title":"DIGITAL IMAGE RESTORATION USING SURF ALGORITHM","authors":"Shanmukhaprasanthi Tammineni, Swaraiya Madhuri Rayavarapu, S. Gottapu, Raj Kumar Goswami","doi":"10.35784/iapgos.5373","DOIUrl":"https://doi.org/10.35784/iapgos.5373","url":null,"abstract":"In contemporary times, the preservation of scientific and creative endeavours often relies on the utilization of film and image archives, hence emphasizing the significance of image processing as a critical undertaking. Image inpainting refers to the process of digitally altering an image in a manner that renders the adjustments imperceptible to a viewer lacking knowledge of the original image. Image inpainting is a technique mostly employed to restore damaged regions within an image by utilizing information obtained from matching characteristics in relevant images. This process involves filling in the damaged areas and removing undesired objects. The SURF (Speeded Up Robust Feature) algorithm under consideration is partitioned into three primary phases. Firstly, the essential characteristics of the impaired image and the pertinent image are identified. In the second stage, the relationship between the damaged image and the relevant image is determined in terms of translation, scaling, and rotation. Ultimately, the destroyed area is reconstructed through the application of the inverse transformation. The quality assessment of inpainted images can be evaluated using metrics such as Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), and Mean Squared Error (MSE). The experimental findings provide evidence that the suggested inpainting technique is effective in terms of both speed and quality.","PeriodicalId":504633,"journal":{"name":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140360120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
V. Lyshuk, Vasyl Tchaban, Anatolii Tkachuk, Valentyn Zablotskyi, Yosyp Selepyna
The paper proposes electromagnetic field equations from the point of view of their adaptation to numerical methods. Maxwell's equations with partial derivatives are used, written concerning field vectors, which most fully reproduce the picture of physical processes in electrical engineering devices. The values of these vectors provide comprehensive information about the field at any spatio-temporal point. The concept of creating mathematical models of electrical devices adequate to physical processes has been developed. Mathematical transformations are carried out according to the rules of differential calculus. Dynamic processes in the elements of electrotechnical devices were analyzed using the apparatus of mathematical modeling. An algorithm for implementing differential equations with partial derivative numerical methods using computer simulation was implemented. The obtained results made it possible to understand the nature of electromagnetic phenomena in nonlinear media. The paper provides calculations of the field parameters in a flat ferromagnetic plate and the groove of the rotor of an electric machine.
{"title":"RÓWNANIA POLA ELEKTROMAGNETYCZNEGO W ŚRODOWISKU NIELINIOWYM","authors":"V. Lyshuk, Vasyl Tchaban, Anatolii Tkachuk, Valentyn Zablotskyi, Yosyp Selepyna","doi":"10.35784/iapgos.5533","DOIUrl":"https://doi.org/10.35784/iapgos.5533","url":null,"abstract":"The paper proposes electromagnetic field equations from the point of view of their adaptation to numerical methods. Maxwell's equations with partial derivatives are used, written concerning field vectors, which most fully reproduce the picture of physical processes in electrical engineering devices. The values of these vectors provide comprehensive information about the field at any spatio-temporal point. The concept of creating mathematical models of electrical devices adequate to physical processes has been developed. Mathematical transformations are carried out according to the rules of differential calculus. Dynamic processes in the elements of electrotechnical devices were analyzed using the apparatus of mathematical modeling. An algorithm for implementing differential equations with partial derivative numerical methods using computer simulation was implemented. The obtained results made it possible to understand the nature of electromagnetic phenomena in nonlinear media. The paper provides calculations of the field parameters in a flat ferromagnetic plate and the groove of the rotor of an electric machine.","PeriodicalId":504633,"journal":{"name":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140360460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The article presents an energy analysis of a 3.5 kWp photovoltaic installation placed on a two-axis tracking system, depending on resolution of step tracking system, that tracks apparent position of the Sun on the celestial sphere. Measurements were taken during July and August, months with similar solar radiation intensity. During the first month, the tracking system changed the spatial orientation of the photovoltaic panels with a frequency of 20 minutes, while in the second month the resolution of the tracking step was 120 minutes. The total energy production by the photovoltaic installation cooperating with the tracking system was 589.5 kWh and 579.85 kWh, for a tracking step resolution of 20 and 120 minutes, respectively. The monthly difference between the two analysed periods does not exceed 1.7%. However, when analysing the days with the highest energy production – exceeding 28 kWh/day, the photovoltaic installation which changed its spatial orientation with greater frequency produced 309.83 kWh, and with a smaller one 259.88 kWh. In the case of sunny, cloudless days, the difference in the efficiency of both solutions is equal to 19%. During days with lower solar radiation, the efficiency of the photovoltaic installations was similar. It can be concluded that increasing the step resolution of the tracking system increases energy production on sunny, cloudless days. It should be taken into account that increasing the frequency of changing the position of photovoltaic panels increased energy consumption by tracker motors from 2.48 kWh to 3.75 kWh, which constitutes 13.2% of the energy gain obtained over the entire tested period, but less than 1% during days with the highest amount of solar radiation.
{"title":"ENERGY EFFICIENCY OF PHOTOVOLTAIC PANELS DEPENDING ON THE STEP RESOLUTION OF TRACKING SYSTEM","authors":"K. Płachta","doi":"10.35784/iapgos.5777","DOIUrl":"https://doi.org/10.35784/iapgos.5777","url":null,"abstract":"The article presents an energy analysis of a 3.5 kWp photovoltaic installation placed on a two-axis tracking system, depending on resolution of step tracking system, that tracks apparent position of the Sun on the celestial sphere. Measurements were taken during July and August, months with similar solar radiation intensity. During the first month, the tracking system changed the spatial orientation of the photovoltaic panels with a frequency of 20 minutes, while in the second month the resolution of the tracking step was 120 minutes. The total energy production by the photovoltaic installation cooperating with the tracking system was 589.5 kWh and 579.85 kWh, for a tracking step resolution of 20 and 120 minutes, respectively. The monthly difference between the two analysed periods does not exceed 1.7%. However, when analysing the days with the highest energy production – exceeding 28 kWh/day, the photovoltaic installation which changed its spatial orientation with greater frequency produced 309.83 kWh, and with a smaller one 259.88 kWh. In the case of sunny, cloudless days, the difference in the efficiency of both solutions is equal to 19%. During days with lower solar radiation, the efficiency of the photovoltaic installations was similar. It can be concluded that increasing the step resolution of the tracking system increases energy production on sunny, cloudless days. It should be taken into account that increasing the frequency of changing the position of photovoltaic panels increased energy consumption by tracker motors from 2.48 kWh to 3.75 kWh, which constitutes 13.2% of the energy gain obtained over the entire tested period, but less than 1% during days with the highest amount of solar radiation.","PeriodicalId":504633,"journal":{"name":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140358918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Les Hotra, Oksana Boyko, Igor Helzhynskyy, H. Barylo, Pylyp Skoropad, Alla Ivanyshyn, Olena Basalkevych
Prolonged exposure to elevated temperatures exceeding 47°C, which can occur during root canal obturation, can cause damage of both dental and bone tissues. In order to study the temperature distribution on the surface of the tooth root a temperature measuring device with cold-junction compensation is proposed. For in vitro measurement of the temperature distribution on the surface of the tooth, 8 thermocouples placed in direct contact with the cementum of the tooth were used. In order to eliminate the cold-junction temperature variations, the temperature equilibration device and RTD were used. The suggested linear approximation for the thermocouples' conversion function provides a nonlinearity relative error of less than 0.05% for K-type thermocouples and 0.07% for J-type thermocouples over the temperature range from 20 to 60°C.
{"title":"ROOT SURFACE TEMPERATURE MEASUREMENT DURING ROOT CANAL OBTURATION","authors":"Les Hotra, Oksana Boyko, Igor Helzhynskyy, H. Barylo, Pylyp Skoropad, Alla Ivanyshyn, Olena Basalkevych","doi":"10.35784/iapgos.5895","DOIUrl":"https://doi.org/10.35784/iapgos.5895","url":null,"abstract":"Prolonged exposure to elevated temperatures exceeding 47°C, which can occur during root canal obturation, can cause damage of both dental and bone tissues. In order to study the temperature distribution on the surface of the tooth root a temperature measuring device with cold-junction compensation is proposed. For in vitro measurement of the temperature distribution on the surface of the tooth, 8 thermocouples placed in direct contact with the cementum of the tooth were used. In order to eliminate the cold-junction temperature variations, the temperature equilibration device and RTD were used. The suggested linear approximation for the thermocouples' conversion function provides a nonlinearity relative error of less than 0.05% for K-type thermocouples and 0.07% for J-type thermocouples over the temperature range from 20 to 60°C.","PeriodicalId":504633,"journal":{"name":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140359421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Kuzlo, V. Moshynskyi, Nataliya Zhukovska, V. Zhukovskyy
Significant changes in the stress-strain state cause a change in the soil profile of the massif, which is affected by various physical and chemical factors. In particular, groundwater filtration, mass transfer, heat transfer, dissolution and leaching of soil masses. This can lead to various types of accidents. Therefore, the study of the stress-strain state of the soil massif is an important topic. Nonlinear dependences in the form of polynomials of the modulus of deformation and Lame coefficients on the concentration of salt solutions and their temperature have been received in this research based on experimental research and their statistical processing. This allowed improving the mathematical model of the stress-strain state of the soil taking into account the nonlinear deformation processes occurring in the soil masses under the presence and filtration of saline solutions in non-isothermal conditions.
{"title":"DEFORMATIONS OF SOIL MASSES UNDER THE ACTION OF HUMAN-INDUCED FACTORS","authors":"M. Kuzlo, V. Moshynskyi, Nataliya Zhukovska, V. Zhukovskyy","doi":"10.35784/iapgos.5824","DOIUrl":"https://doi.org/10.35784/iapgos.5824","url":null,"abstract":"Significant changes in the stress-strain state cause a change in the soil profile of the massif, which is affected by various physical and chemical factors. In particular, groundwater filtration, mass transfer, heat transfer, dissolution and leaching of soil masses. This can lead to various types of accidents. Therefore, the study of the stress-strain state of the soil massif is an important topic. Nonlinear dependences in the form of polynomials of the modulus of deformation and Lame coefficients on the concentration of salt solutions and their temperature have been received in this research based on experimental research and their statistical processing. This allowed improving the mathematical model of the stress-strain state of the soil taking into account the nonlinear deformation processes occurring in the soil masses under the presence and filtration of saline solutions in non-isothermal conditions.","PeriodicalId":504633,"journal":{"name":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140360511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Digital Twins is a digital replica of a physical object to observe its real-time performance, gather data, and recommend corrective actions if required to enhance its performance. This fascinating technological idea is now reaching the agriculture fields to transform farming, by creating digital twins of entire farms. This initiative presents an innovative strategy to enhance crop health and yield by creating a digital twin for paddy fields. The aim is to enable early detection of nutrient deficiencies and leaf blast disease, leading to a transformation in agriculture. Creating virtual replicas of plants and fields, the digital twin harnesses real-time data and advanced analytics to transform the way agricultural systems are managed. By integrating remote sensing, data analytics, and various Internet of Things devices like pH, nitrous, potassium, and phosphorus sensors, coupled with a gateway system, the digital twin provides real-time monitoring and analysis of crop health and nutrient levels. Employing advanced machine learning algorithms, notably Convolutional Neural Networks ensures precise and early detection of nutrient deficiencies and crop diseases. This ground-breaking technology provides timely alerts and actionable insights to farmers, enabling proactive decision-making for optimal crop management. This farmland digital twin represents a transformative approach towards agricultural sustainability and enhancing productivity.
{"title":"POPRAWA ZDROWIA UPRAW DZIĘKI CYFROWEMU BLIŹNIAKOWI DO MONITOROWANIA CHORÓB I RÓWNOWAGI SKŁADNIKÓW ODŻYWCZYCH","authors":"Sobhana Mummaneni, Tribhuvana Sree Sappa, Venkata Gayathri Devi Katakam","doi":"10.35784/iapgos.5626","DOIUrl":"https://doi.org/10.35784/iapgos.5626","url":null,"abstract":"Digital Twins is a digital replica of a physical object to observe its real-time performance, gather data, and recommend corrective actions if required to enhance its performance. This fascinating technological idea is now reaching the agriculture fields to transform farming, by creating digital twins of entire farms. This initiative presents an innovative strategy to enhance crop health and yield by creating a digital twin for paddy fields. The aim is to enable early detection of nutrient deficiencies and leaf blast disease, leading to a transformation in agriculture. Creating virtual replicas of plants and fields, the digital twin harnesses real-time data and advanced analytics to transform the way agricultural systems are managed. By integrating remote sensing, data analytics, and various Internet of Things devices like pH, nitrous, potassium, and phosphorus sensors, coupled with a gateway system, the digital twin provides real-time monitoring and analysis of crop health and nutrient levels. Employing advanced machine learning algorithms, notably Convolutional Neural Networks ensures precise and early detection of nutrient deficiencies and crop diseases. This ground-breaking technology provides timely alerts and actionable insights to farmers, enabling proactive decision-making for optimal crop management. This farmland digital twin represents a transformative approach towards agricultural sustainability and enhancing productivity.","PeriodicalId":504633,"journal":{"name":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140359539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The electrical network is the set of elements where loads are connected to the generation plants by transmission lines. They can be either overhead or underground cables. A new technology has been introduced to replace these transmission lines with underground cables gas insulated line “GIL”. The latest has many advantages over underground cables and overhead transmission lines, such as low transmission losses, less capacitive load, reliability, personal safety, same operation as overhead lines and negligible electrical aging. GIL can handle much more power than overhead lines due to its large conductive area. GIL is the best for high voltage. In this paper, the simulation of lightning strike effects on a 400 kV hybrid transmission line located in the Wilaya of Setif in northern Algeria is presented in the absence and presence of line arresters and GIL arresters. The results of this paper can provide a rich and valuable theoretical reference for GIL simulation modeling and evaluation of lightning strike impact on hybrid overhead – GIL lines.
电网是通过输电线路将负载与发电厂连接起来的一组元件。它们可以是架空电缆，也可以是地下电缆。一种新技术已经问世，即用地下电缆气体绝缘线 "GIL "取代这些输电线路。与地下电缆和架空输电线路相比，最新技术具有许多优点，如传输损耗低、电容负荷小、可靠性高、人身安全、与架空线路操作相同以及电气老化可忽略不计。由于导电面积大，GIL 比架空线路能承受更大的功率。GIL 最适用于高电压。本文模拟了位于阿尔及利亚北部塞提夫省的一条 400 千伏混合输电线路在没有和有线路避雷器和 GIL 避雷器的情况下遭受雷击的影响。本文的结果可为 GIL 仿真建模和评估雷击对架空-GIL 混合线路的影响提供丰富而有价值的理论参考。
{"title":"THE IMPACT OF LIGHTNING STRIKE ON HYBRID HIGH VOLTAGE OVERHEAD TRANSMISSION LINE – INSULATED GAS LINE","authors":"S. Boumous, Z. Boumous, Y. Djeghader","doi":"10.35784/iapgos.5445","DOIUrl":"https://doi.org/10.35784/iapgos.5445","url":null,"abstract":"The electrical network is the set of elements where loads are connected to the generation plants by transmission lines. They can be either overhead or underground cables. A new technology has been introduced to replace these transmission lines with underground cables gas insulated line “GIL”. The latest has many advantages over underground cables and overhead transmission lines, such as low transmission losses, less capacitive load, reliability, personal safety, same operation as overhead lines and negligible electrical aging. GIL can handle much more power than overhead lines due to its large conductive area. GIL is the best for high voltage. In this paper, the simulation of lightning strike effects on a 400 kV hybrid transmission line located in the Wilaya of Setif in northern Algeria is presented in the absence and presence of line arresters and GIL arresters. The results of this paper can provide a rich and valuable theoretical reference for GIL simulation modeling and evaluation of lightning strike impact on hybrid overhead – GIL lines.","PeriodicalId":504633,"journal":{"name":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140360118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zakaryae Khomsi, Mohamed El Fezazi, Achraf Elouerghi, L. Bellarbi
Early-stage and advanced breast cancer represent distinct disease processes. Thus, identifying the stage of tumor is a crucial procedure for optimizing treatment efficiency. Breast thermography has demonstrated significant advancements in non-invasive tumor detection. However, the accurate determination of tumor stage based on temperature distribution represents a challenging task, primarily due to the scarcity of thermal images labeled with the stage of tumor. This work proposes a transfer learning approach based on Deep Convolutional Neural Network (DCNN) with thermal images for predicting breast tumor stage. Various tumor stage scenarios including early and advanced tumors are embedded in a 3D breast model using the Finite Element Method (FEM) available on COMSOL Multiphysics software. This allows the generation of the thermal image dataset for training the DCNN model. A detailed investigation of the hyperparameters tuning process has been conducted to select the optimal predictive model. Thus, various evaluation metrics, including accuracy, sensitivity, and specificity, are computed using the confusion matrix. The results demonstrate the DCNN model's ability to accurately predict breast tumor stage from thermographic images, with an accuracy of 98.2%, a sensitivity of 98.8%, and a specificity of 97.7%. This study indicates the promising potential of thermographic images in enhancing deep learning algorithms for the non-invasive prediction of breast tumor stage.
{"title":"EVALUATING THE FEASIBILITY OF THERMOGRAPHIC IMAGES FOR PREDICTING BREAST TUMOR STAGE USING DCNN","authors":"Zakaryae Khomsi, Mohamed El Fezazi, Achraf Elouerghi, L. Bellarbi","doi":"10.35784/iapgos.5555","DOIUrl":"https://doi.org/10.35784/iapgos.5555","url":null,"abstract":"Early-stage and advanced breast cancer represent distinct disease processes. Thus, identifying the stage of tumor is a crucial procedure for optimizing treatment efficiency. Breast thermography has demonstrated significant advancements in non-invasive tumor detection. However, the accurate determination of tumor stage based on temperature distribution represents a challenging task, primarily due to the scarcity of thermal images labeled with the stage of tumor. This work proposes a transfer learning approach based on Deep Convolutional Neural Network (DCNN) with thermal images for predicting breast tumor stage. Various tumor stage scenarios including early and advanced tumors are embedded in a 3D breast model using the Finite Element Method (FEM) available on COMSOL Multiphysics software. This allows the generation of the thermal image dataset for training the DCNN model. A detailed investigation of the hyperparameters tuning process has been conducted to select the optimal predictive model. Thus, various evaluation metrics, including accuracy, sensitivity, and specificity, are computed using the confusion matrix. The results demonstrate the DCNN model's ability to accurately predict breast tumor stage from thermographic images, with an accuracy of 98.2%, a sensitivity of 98.8%, and a specificity of 97.7%. This study indicates the promising potential of thermographic images in enhancing deep learning algorithms for the non-invasive prediction of breast tumor stage.","PeriodicalId":504633,"journal":{"name":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140360875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Parallel hierarchical memory (PI memory) is a new type of memory that is designed to improve the performance of parallel computing systems. PI memory is composed of two blocks: a mask RAM and a tail element RAM. The mask RAM stores the masks that are used to encode the information, while the tail element RAM stores the actual information. The address block of the PI memory is responsible for generating the physical addresses of the cells where the tail elements and their masks are stored. The address block also stores the field of addresses where the array was written and associates this field of addresses with the corresponding external address used to write the array. The proposed address block structure is able to efficiently generate the physical addresses of the cells where the tail elements and their masks are stored. The address block is also able to store the field of addresses where the array was written and associate this field of addresses with the corresponding external address used to write the array. The proposed address block structure has been implemented in a prototype PI memory. The prototype PI memory has been shown to be able to achieve significant performance improvements over traditional memory architectures. The paper will present a detailed description of the PI transformation algorithm, a description of the different modes of addressing organization that can be used in PI memory, an analysis of the efficiency of parallel-hierarchical memory structures, and a discussion of the challenges and future research directions in the field of PI memory.
并行分层内存（PI 内存）是一种新型内存，旨在提高并行计算系统的性能。PI 内存由两个区块组成：掩码 RAM 和尾部元素 RAM。掩码 RAM 存储用于编码信息的掩码，而尾部元素 RAM 存储实际信息。PI 存储器的地址块负责生成存储尾部元素及其掩码的单元的物理地址。地址块还存储写入阵列的地址字段，并将该地址字段与用于写入阵列的相应外部地址相关联。建议的地址块结构能够有效地生成存储尾元素及其掩码的单元的物理地址。地址块还能存储写入数组的地址字段，并将该地址字段与用于写入数组的相应外部地址相关联。拟议的地址块结构已在 PI 存储器原型中实现。事实证明，原型 PI 存储器的性能比传统存储器架构有显著提高。本文将详细介绍 PI 变换算法，描述 PI 存储器中可使用的不同寻址组织模式，分析并行分层存储器结构的效率，并讨论 PI 存储器领域的挑战和未来研究方向。
{"title":"ARCHITEKTONICZNE, STRUKTURALNE I FUNKCJONALNE CECHY RÓWNOLEGŁO-HIERARCHICZNEJ ORGANIZACJI PAMIĘCI","authors":"Leonid Timchenko, Natalia Kokriatska, Volodymyr Tverdomed, Iryna Yepifanova, Yurii Didenko, Dmytro Zhuk, Maksym Kozyr, Iryna Shakhina","doi":"10.35784/iapgos.5615","DOIUrl":"https://doi.org/10.35784/iapgos.5615","url":null,"abstract":"Parallel hierarchical memory (PI memory) is a new type of memory that is designed to improve the performance of parallel computing systems. PI memory is composed of two blocks: a mask RAM and a tail element RAM. The mask RAM stores the masks that are used to encode the information, while the tail element RAM stores the actual information. The address block of the PI memory is responsible for generating the physical addresses of the cells where the tail elements and their masks are stored. The address block also stores the field of addresses where the array was written and associates this field of addresses with the corresponding external address used to write the array. The proposed address block structure is able to efficiently generate the physical addresses of the cells where the tail elements and their masks are stored. The address block is also able to store the field of addresses where the array was written and associate this field of addresses with the corresponding external address used to write the array. The proposed address block structure has been implemented in a prototype PI memory. The prototype PI memory has been shown to be able to achieve significant performance improvements over traditional memory architectures. The paper will present a detailed description of the PI transformation algorithm, a description of the different modes of addressing organization that can be used in PI memory, an analysis of the efficiency of parallel-hierarchical memory structures, and a discussion of the challenges and future research directions in the field of PI memory.","PeriodicalId":504633,"journal":{"name":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140361316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：