PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021最新文献
Şerafetdin Baloğlu, I. Saritas, A. Yasar, Adem Golcuk
Patients with chronic respiratory conditions such as Chronic Obstructive Pulmonary Disease (COPD) receive long- term oxygen therapy (USOT) to sustain their lives [1],[2]. With the development of oxygen concentrator (OC) devices that can produce the concentrated oxygen required for USOT, COPD patients are required to use these devices for more than 12 hours daily depending on the prescription [3],[4]. OC are medical devices that separate oxygen from the atmosphere using physical means to produce concentrated gas for medical purposes [5],[6]. The use of conventional motors based on the permanent magnetic rotary motor operating principle in OC devices increases the mass of the device and the operating noise disturbs the patients [3],[4],[7]. In this study, with the advances in magnet material, a tubular linear motor (TLM) structure with a strong, fixed coil moving permanent magnet, which is stronger than the linear motor used in many fields such as medical electronics, nanotechnology, defence industry, maglev trains, is designed and proposed for use in OK devices. It is difficult to optimise the TLM due to multiple design parameters and each parameter has a non- linear relationship with the static electromagnetic force. In this study, the thrust of the TLM is optimised by the finite element method (FEM) using the magnetic magnetostatic and transient solvers in Ansys Maxwell3D. Optimisation method based on FEM 3D model was used to optimise the design parameters. Comparing the pre- and post-optimisation of the TLM designed for use in the OC device, the thrust force was increased from 567.91 fN to 5.82 nN at the same working stroke distance.
{"title":"Design and optimisation of tubular linear motor (TLM) for oxygen concentrator device","authors":"Şerafetdin Baloğlu, I. Saritas, A. Yasar, Adem Golcuk","doi":"10.58190/icat.2023.10","DOIUrl":"https://doi.org/10.58190/icat.2023.10","url":null,"abstract":"Patients with chronic respiratory conditions such as Chronic Obstructive Pulmonary Disease (COPD) receive long- term oxygen therapy (USOT) to sustain their lives [1],[2]. With the development of oxygen concentrator (OC) devices that can produce the concentrated oxygen required for USOT, COPD patients are required to use these devices for more than 12 hours daily depending on the prescription [3],[4]. OC are medical devices that separate oxygen from the atmosphere using physical means to produce concentrated gas for medical purposes [5],[6]. The use of conventional motors based on the permanent magnetic rotary motor operating principle in OC devices increases the mass of the device and the operating noise disturbs the patients [3],[4],[7]. In this study, with the advances in magnet material, a tubular linear motor (TLM) structure with a strong, fixed coil moving permanent magnet, which is stronger than the linear motor used in many fields such as medical electronics, nanotechnology, defence industry, maglev trains, is designed and proposed for use in OK devices. It is difficult to optimise the TLM due to multiple design parameters and each parameter has a non- linear relationship with the static electromagnetic force. In this study, the thrust of the TLM is optimised by the finite element method (FEM) using the magnetic magnetostatic and transient solvers in Ansys Maxwell3D. Optimisation method based on FEM 3D model was used to optimise the design parameters. Comparing the pre- and post-optimisation of the TLM designed for use in the OC device, the thrust force was increased from 567.91 fN to 5.82 nN at the same working stroke distance.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"49 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80784459","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}
Thermal energy storage systems (TESS) are receiving attention because there are constant power cuts, major changes in electrical rate structures, increased maximum power demands, and incentive programmes sponsored by utilities. Household refrigerators were one of the main consumers of residential electricity, as they consume up to 26% and have an additional 17% greenhouse gas emissions. By incorporating TESS, this figure can be reduced. This study presents a low-cost potassium chloride saltwater phase change material (PCM) system to maintain a household refrigerator compartment below 5 ° C to preserve food and pharmaceutical products. After determining the 5-liter volume of PCM required, the experiments were carried out on a KIC KBF 525/1 ME refrigerator with an average daily power consumption of 0.567 kWh. With a heat transfer rate of 5 W and a total of 80 kJ of energy, the PCM took 2.5 days to fully solidify. It was then able to maintain the frigerated compartment at a temperature below 5 ° C for close to 25 hours, resulting in a 8W output power and a total of 90 kJ of energy being released. For power consumption analysis, 1.4175 kWh was used during the charging phase and 0.567 kWh was saved during the discharging phase. Heat transfer during the charging phase needs to be improved to better optimise the TESS.
{"title":"Low-Cost Potassium Chloride Saltwater Phase Change Material System for a Household Refrigerator","authors":"Thandiwe Bongani Radebe, Asasei Unarine Casey Ndanduleni, Zhongjie Huan","doi":"10.58190/icat.2023.32","DOIUrl":"https://doi.org/10.58190/icat.2023.32","url":null,"abstract":"Thermal energy storage systems (TESS) are receiving attention because there are constant power cuts, major changes in electrical rate structures, increased maximum power demands, and incentive programmes sponsored by utilities. Household refrigerators were one of the main consumers of residential electricity, as they consume up to 26% and have an additional 17% greenhouse gas emissions. By incorporating TESS, this figure can be reduced. This study presents a low-cost potassium chloride saltwater phase change material (PCM) system to maintain a household refrigerator compartment below 5 ° C to preserve food and pharmaceutical products. After determining the 5-liter volume of PCM required, the experiments were carried out on a KIC KBF 525/1 ME refrigerator with an average daily power consumption of 0.567 kWh. With a heat transfer rate of 5 W and a total of 80 kJ of energy, the PCM took 2.5 days to fully solidify. It was then able to maintain the frigerated compartment at a temperature below 5 ° C for close to 25 hours, resulting in a 8W output power and a total of 90 kJ of energy being released. For power consumption analysis, 1.4175 kWh was used during the charging phase and 0.567 kWh was saved during the discharging phase. Heat transfer during the charging phase needs to be improved to better optimise the TESS.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969378","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}
Vibration analysis is one of the most important aspects in the design of structures and mechanical systems, among others, subject to dynamic loads. As well as for the analysis of failures caused by vibratory aspects. A good performance of an industrial system is often associated with the availability of mathematical models of the dynamic behaviour of the system. In some situations, the complexity of the processes makes it difficult to have models that help us to analyse these processes. This paper proposes the use of knot theory, which is a topological tool, for vibration analysis. This topological tool, in this case, associates a topological invariant when there is a drastic change in vibrations. The present work is based on the fact that it is well known that the equations representing harmonic motion generate Lissajous figures. In knot theory, there are several classifications of knots, one of these classifications is known as Lissajous knots. The use of this tool is shown in the supposition that we have a system represented by three equations of the form f(t) = Acos(Bt + C) , where with the indicated parameters it generates a knot (being its nominal value). Making a change in the phase, which represents a fault, generates a different knot than the nominal knot. One of the advantages of this proposed method is that it is not necessary to have the model, and one of the disadvantages by nature of this method is that three signals are required to use this topological tool.
{"title":"TOWARD TO VIBRATION ANALYSIS BY KNOT THEORY","authors":"Daniel Enrique Rivas Cisneros","doi":"10.58190/icat.2023.30","DOIUrl":"https://doi.org/10.58190/icat.2023.30","url":null,"abstract":"Vibration analysis is one of the most important aspects in the design of structures and mechanical systems, among others, subject to dynamic loads. As well as for the analysis of failures caused by vibratory aspects. A good performance of an industrial system is often associated with the availability of mathematical models of the dynamic behaviour of the system. In some situations, the complexity of the processes makes it difficult to have models that help us to analyse these processes. This paper proposes the use of knot theory, which is a topological tool, for vibration analysis. This topological tool, in this case, associates a topological invariant when there is a drastic change in vibrations. The present work is based on the fact that it is well known that the equations representing harmonic motion generate Lissajous figures. In knot theory, there are several classifications of knots, one of these classifications is known as Lissajous knots. The use of this tool is shown in the supposition that we have a system represented by three equations of the form f(t) = Acos(Bt + C) , where with the indicated parameters it generates a knot (being its nominal value). Making a change in the phase, which represents a fault, generates a different knot than the nominal knot. One of the advantages of this proposed method is that it is not necessary to have the model, and one of the disadvantages by nature of this method is that three signals are required to use this topological tool.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969381","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}
Fisokuhle Hopewell Nyembe, John Andrew van der Poll, Hugo Hendrik Lotriet
Efficient, high-quality software systems embodying dependable methods are in high demand, which has led to a wide range of competitive market solutions. One effective technique that arguably has excelled above others is the Agile Software Development Methodology (ASDM). Agile approaches’ capacity to produce software in a way that is flexible to changes is the main factor that makes them preferable. Scrum, a recommended Agile methodology, prioritises feature coverage and project structure. Because iterative methodologies encourage engagement from cross-functional teams, including consumers, Agile provides flexibility in responding to change. However, achieving methodological efficiency is insufficient while developing software; high-quality software should be achieved with equal consideration. Formal Methods (FMs), which are mathematically based techniques, can offer highly dependable software but suffer from a steep learning curve in mastering the underlying discrete mathematics and logic. This research investigates the extent to which FMs may be embedded in traditional Agile as embodied by Scrum. Future work in this area would be the development of a framework for embedding FMs in Scrum, followed by a survey among software practitioners to establish the feasibility of our technique.
{"title":"Formal Methods for an Agile Scrum Software Development Methodology","authors":"Fisokuhle Hopewell Nyembe, John Andrew van der Poll, Hugo Hendrik Lotriet","doi":"10.58190/icat.2023.35","DOIUrl":"https://doi.org/10.58190/icat.2023.35","url":null,"abstract":"Efficient, high-quality software systems embodying dependable methods are in high demand, which has led to a wide range of competitive market solutions. One effective technique that arguably has excelled above others is the Agile Software Development Methodology (ASDM). Agile approaches’ capacity to produce software in a way that is flexible to changes is the main factor that makes them preferable. Scrum, a recommended Agile methodology, prioritises feature coverage and project structure. Because iterative methodologies encourage engagement from cross-functional teams, including consumers, Agile provides flexibility in responding to change. However, achieving methodological efficiency is insufficient while developing software; high-quality software should be achieved with equal consideration. Formal Methods (FMs), which are mathematically based techniques, can offer highly dependable software but suffer from a steep learning curve in mastering the underlying discrete mathematics and logic. This research investigates the extent to which FMs may be embedded in traditional Agile as embodied by Scrum. Future work in this area would be the development of a framework for embedding FMs in Scrum, followed by a survey among software practitioners to establish the feasibility of our technique.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"289 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969512","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}
Paria Sarzaeim, Aarya Mayurpalsingh Doshi, Qusay H. Mahmoud
The use of generative artificial intelligence is becoming increasingly prevalent in creating content in various formats such as text, video, and image. However, there is a need to distinguish between content that has been generated by humans and content that has been generated by AI as misuse of these technologies can raise scientific and social challenges. Moreover, there are concerns about the reliability and comprehensiveness of the content generated by AI without human validation. This paper presents a framework for AI-generated text. The prototype implementation of the proposed approach is to train a model using predefined datasets and deploy this model on a cloud-based service to predict whether a text was created by a human or AI. This approach is specifically focused on assessing the accuracy of scientific writings and research papers rather than general text. The proposed framework is compared with recently developed tools such as OpenAI Text Classifier, ZeroGPT, and Turnitin. The results show that training a text classifier can be highly useful in detecting whether a text is written by a human or AI. The source code and dataset are made open source so others can experiment with the prototype implementation and use it for future research.
{"title":"A Framework for Detecting AI-Generated Text in Research Publications","authors":"Paria Sarzaeim, Aarya Mayurpalsingh Doshi, Qusay H. Mahmoud","doi":"10.58190/icat.2023.28","DOIUrl":"https://doi.org/10.58190/icat.2023.28","url":null,"abstract":"The use of generative artificial intelligence is becoming increasingly prevalent in creating content in various formats such as text, video, and image. However, there is a need to distinguish between content that has been generated by humans and content that has been generated by AI as misuse of these technologies can raise scientific and social challenges. Moreover, there are concerns about the reliability and comprehensiveness of the content generated by AI without human validation. This paper presents a framework for AI-generated text. The prototype implementation of the proposed approach is to train a model using predefined datasets and deploy this model on a cloud-based service to predict whether a text was created by a human or AI. This approach is specifically focused on assessing the accuracy of scientific writings and research papers rather than general text. The proposed framework is compared with recently developed tools such as OpenAI Text Classifier, ZeroGPT, and Turnitin. The results show that training a text classifier can be highly useful in detecting whether a text is written by a human or AI. The source code and dataset are made open source so others can experiment with the prototype implementation and use it for future research.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969520","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}
Diagnosing heart disease is a challenging process for physicians. Insufficient number of experts, late diagnosis and misdiagnosis are the difficulties in this process. To overcome these difficulties, systems based on artificial intelligence are used today. Appropriate system selection and obtaining sufficient data sets are a challenge for researchers. In this study, a high-performance CAD architecture was proposed for the detection of heart disease. The proposed architecture has shown a higher performance than the studies carried out using the UCI dataset in the literature.
{"title":"A System Architecture Based on The RNN Classifier for Heart Disease Detection","authors":"Volkan Göreke","doi":"10.58190/icat.2023.14","DOIUrl":"https://doi.org/10.58190/icat.2023.14","url":null,"abstract":"Diagnosing heart disease is a challenging process for physicians. Insufficient number of experts, late diagnosis and misdiagnosis are the difficulties in this process. To overcome these difficulties, systems based on artificial intelligence are used today. Appropriate system selection and obtaining sufficient data sets are a challenge for researchers. In this study, a high-performance CAD architecture was proposed for the detection of heart disease. The proposed architecture has shown a higher performance than the studies carried out using the UCI dataset in the literature.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"289 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969526","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 escalating incidence of plant diseases presents considerable obstacles to the agricultural domain, resulting in substantial reductions in crop yield and posing a threat to food security. To address the pressing concern of Black Gram Plant Leaf Diseases (BPLD), this research endeavors to tackle disease classification through the application of a deep learning methodology. The approach leverages a comprehensive dataset that encompasses Anthracnose, Leaf Crinkle, Powdery Mildew, and Yellow Mosaic diseases, all of which affect the black gram crop. By employing this advanced technique, we aim to contribute valuable insights to combat BPLD effectively. Our research applies deep learning models, including Darknet-53, ResNet-101, GoogLeNet, and EfficientNet-B0, to classify plant diseases. Darknet-53 achieved 98.51% accuracy, followed by ResNet-101 (97.51%), GoogLeNet (96.52%), and EfficientNet-B0 (77.61%). These findings demonstrate the potential of deep learning for accurate disease identification, benefiting agriculture. The study provides a comparative analysis of deep learning models for Black Gram Plant Leaf Disease (BPLD) classification, revealing Darknet-53 and ResNet-101 as superior performers. Implementing these models in real-world agricultural scenarios holds promise for early disease detection and intervention, reducing potential crop losses. The high accuracy achieved signifies significant progress in automating disease recognition, benefiting the agricultural sector.
{"title":"Deep Learning-Based Classification of Black Gram Plant Leaf Diseases: A Comparative Study","authors":"Elham Tahsin Yasin, Ramazan Kursun, Murat Koklu","doi":"10.58190/icat.2023.9","DOIUrl":"https://doi.org/10.58190/icat.2023.9","url":null,"abstract":"The escalating incidence of plant diseases presents considerable obstacles to the agricultural domain, resulting in substantial reductions in crop yield and posing a threat to food security. To address the pressing concern of Black Gram Plant Leaf Diseases (BPLD), this research endeavors to tackle disease classification through the application of a deep learning methodology. The approach leverages a comprehensive dataset that encompasses Anthracnose, Leaf Crinkle, Powdery Mildew, and Yellow Mosaic diseases, all of which affect the black gram crop. By employing this advanced technique, we aim to contribute valuable insights to combat BPLD effectively. Our research applies deep learning models, including Darknet-53, ResNet-101, GoogLeNet, and EfficientNet-B0, to classify plant diseases. Darknet-53 achieved 98.51% accuracy, followed by ResNet-101 (97.51%), GoogLeNet (96.52%), and EfficientNet-B0 (77.61%). These findings demonstrate the potential of deep learning for accurate disease identification, benefiting agriculture. The study provides a comparative analysis of deep learning models for Black Gram Plant Leaf Disease (BPLD) classification, revealing Darknet-53 and ResNet-101 as superior performers. Implementing these models in real-world agricultural scenarios holds promise for early disease detection and intervention, reducing potential crop losses. The high accuracy achieved signifies significant progress in automating disease recognition, benefiting the agricultural sector.\u0000\u0000","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"39 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81364461","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}
Fatih Doğan KOCA, Haydar Matz Muhy, Mehmet Gökhan HALICI
First time in this study Tornabea scutellifera extract were used for synthesis of Platinium nanoparticles (Pt NPs). The DPPH scavenging activity of T. scutellifera-based Pt NPs was determined and its usability as antioxidant activity was evaluated. With characterization tests, it was observed that Pt NPs were in spherical structure and had an average diameter of 88.7 nm. Functional groups that play a role in the synthesis were determined by FT-IR analysis with the peaks determined at 1623 cm-1, 1146 cm-1, 1042 cm-1, 987 cm-1, 625 cm-1 ve 558 cm-1. Elemental structure (presence of Pt) was revealed by EDX analysis. It was determined that T. scutellifera-based Pt NPs exhibited anti-oxidant activity against DPPH (184.06 µg/ml, R2=0.8727). It is thought that the study can be used in nanotechnology-related multidisciplinary studies.
{"title":"Antioxidant Activity of Green Synthesized Platinum Nanoparticles by Using Tornabea scutellifera Extract","authors":"Fatih Doğan KOCA, Haydar Matz Muhy, Mehmet Gökhan HALICI","doi":"10.58190/icat.2023.25","DOIUrl":"https://doi.org/10.58190/icat.2023.25","url":null,"abstract":"First time in this study Tornabea scutellifera extract were used for synthesis of Platinium nanoparticles (Pt NPs). The DPPH scavenging activity of T. scutellifera-based Pt NPs was determined and its usability as antioxidant activity was evaluated. With characterization tests, it was observed that Pt NPs were in spherical structure and had an average diameter of 88.7 nm. Functional groups that play a role in the synthesis were determined by FT-IR analysis with the peaks determined at 1623 cm-1, 1146 cm-1, 1042 cm-1, 987 cm-1, 625 cm-1 ve 558 cm-1. Elemental structure (presence of Pt) was revealed by EDX analysis. It was determined that T. scutellifera-based Pt NPs exhibited anti-oxidant activity against DPPH (184.06 µg/ml, R2=0.8727). It is thought that the study can be used in nanotechnology-related multidisciplinary studies.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969517","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}
Early detection of plant diseases in the agricultural sector is considered an important goal to increase productivity and minimize damage. This study deals with the use of deep learning methods to realize the automatic detection of leaf diseases in peanut plants and the explicability of the model with heatmap visualizations formed during the detection of diseases. In the study, a dataset containing 3058 images with 5 classes enriched with diseased and healthy samples of peanut leaves was used. The explainability property has also been studied to understand why the models detect a particular disease. The decision processes of deep learning models, which are usually described as the "magic box", were visualized with the heatmap method in this study. By highlighting the pixels that are effective in detecting diseased leaves with heatmap visualization, the decision-making process of the model has been tried to be made understandable. The results show that deep learning models have high performance in detecting peanut leaf diseases, and the explainability obtained by heatmap visualization is a reliable tool for agricultural specialists and producers. Thanks to the visual explanations provided by the model, the level of confidence in the detection of diseases has been increased and confidence in the decision processes of the model has been provided. This study constitutes an important step towards increasing efficiency in agricultural applications and providing a more efficient approach to disease management by investigating the impact and explicability of deep learning methods in the field of disease detection in peanut plants.
{"title":"The Effectiveness of Deep Learning Methods on Groundnut Disease Detection","authors":"Ramazan Kursun, Elham Tahsin Yasin, Murat Koklu","doi":"10.58190/icat.2023.11","DOIUrl":"https://doi.org/10.58190/icat.2023.11","url":null,"abstract":"Early detection of plant diseases in the agricultural sector is considered an important goal to increase productivity and minimize damage. This study deals with the use of deep learning methods to realize the automatic detection of leaf diseases in peanut plants and the explicability of the model with heatmap visualizations formed during the detection of diseases. In the study, a dataset containing 3058 images with 5 classes enriched with diseased and healthy samples of peanut leaves was used. The explainability property has also been studied to understand why the models detect a particular disease. The decision processes of deep learning models, which are usually described as the \"magic box\", were visualized with the heatmap method in this study. By highlighting the pixels that are effective in detecting diseased leaves with heatmap visualization, the decision-making process of the model has been tried to be made understandable. The results show that deep learning models have high performance in detecting peanut leaf diseases, and the explainability obtained by heatmap visualization is a reliable tool for agricultural specialists and producers. Thanks to the visual explanations provided by the model, the level of confidence in the detection of diseases has been increased and confidence in the decision processes of the model has been provided. This study constitutes an important step towards increasing efficiency in agricultural applications and providing a more efficient approach to disease management by investigating the impact and explicability of deep learning methods in the field of disease detection in peanut plants.","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"32 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78791794","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 double-wall façades (or “double skin façades”) are deter-mined as building mechanical and engineered systems realized by the cavity between the inner curtain and the outer screen, for thermal and acoustic insulation, for ventilation and for the inser-tion of functional devices (such as sunscreens) and, also, plant ducts. The cavity between the two enclosures constitutes a venti-lated cavity that can be used according to certain modes of func-tioning (passive or active type) aimed at controlling external cli-matic and environmental stresses in order to regulate the condi-tions of the interior spaces. The double envelope system is real-ized as an apparatus of mediation and reaction towards envi-ronmental loads, according to the needs of well-being and reduc-tion of energy consumption. In general, the system offers the functioning in the form of a passive solar system, assuming the use and accumulation of solar radiation for the regulation of indoor thermal comfort conditions, and the functioning for the capture and input of air flows. The calibration of solar radiation is integrated with the use of shading devices in order to achieve diffuse lighting conditions in interior spaces. In addition, the application of the double glass surface reduces thermal losses from the interior spaces by reducing the speed of the airflow in contact with the inner curtain, increasing thermal insulation. The system foresees that the ventilated cavity performs various inte-grated functions (for the definition of complex mechanisms of dynamic interaction with the external climatic conditions), both permanent (e.g. for the increase of thermal inertia and acoustic insulation relative to the internal curtain) and temporary (e.g. for the cooling of the same spaces during periods of high tempera-ture).
{"title":"Double Skin Façade Mechanical Systems as Ad-vanced Building Technologies","authors":"Massimiliano NASTRI","doi":"10.58190/icat.2023.21","DOIUrl":"https://doi.org/10.58190/icat.2023.21","url":null,"abstract":"The double-wall façades (or “double skin façades”) are deter-mined as building mechanical and engineered systems realized by the cavity between the inner curtain and the outer screen, for thermal and acoustic insulation, for ventilation and for the inser-tion of functional devices (such as sunscreens) and, also, plant ducts. The cavity between the two enclosures constitutes a venti-lated cavity that can be used according to certain modes of func-tioning (passive or active type) aimed at controlling external cli-matic and environmental stresses in order to regulate the condi-tions of the interior spaces. The double envelope system is real-ized as an apparatus of mediation and reaction towards envi-ronmental loads, according to the needs of well-being and reduc-tion of energy consumption. In general, the system offers the functioning in the form of a passive solar system, assuming the use and accumulation of solar radiation for the regulation of indoor thermal comfort conditions, and the functioning for the capture and input of air flows. The calibration of solar radiation is integrated with the use of shading devices in order to achieve diffuse lighting conditions in interior spaces. In addition, the application of the double glass surface reduces thermal losses from the interior spaces by reducing the speed of the airflow in contact with the inner curtain, increasing thermal insulation. The system foresees that the ventilated cavity performs various inte-grated functions (for the definition of complex mechanisms of dynamic interaction with the external climatic conditions), both permanent (e.g. for the increase of thermal inertia and acoustic insulation relative to the internal curtain) and temporary (e.g. for the cooling of the same spaces during periods of high tempera-ture).","PeriodicalId":20592,"journal":{"name":"PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135969377","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}
PROCEEDINGS OF THE III INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES IN MATERIALS SCIENCE, MECHANICAL AND AUTOMATION ENGINEERING: MIP: Engineering-III – 2021
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：