Developing a higher-level security system for iden- tification or authentication has long been an active research subject in many fields. Traditional security systems utilize a key or a password to secure a process or a product, whereas bio metric security systems use a person’s physical or behavioral attributes. Iris patterns play a significant role in a number of potential recognition or authentication applications because of their uniqueness, universality, dependability, and stability. The use of iris recognition techniques in bio metric identification and authentication systems has increased significantly. In this work, a novel approach for classification of iris is presented, making it simple for anybody to apply this technology. This model allows for the usage of any eye image and only selects photos that pass the model’s internal filters. Besides, this study provides iris identification model that starts with eye detection and ends with iris image recognition. In addition, a method for iris classification is presented in this study that combines Transfer learning and Convolutional Neural Networks (CNNs) algorithms using Ensemble learning. The automatic segmentation technique for iris detection uses Hough Transform and is capable of localizing the pupil and iris region, as well as obstructing eyelids, eyelashes, and reflections. To overcome the image irregularities, the iris region is extracted and then extracted iris is converted into rectangular block using Normalization. In this paper, a weighted ensemble technique is proposed that demonstrates iris classification which is made by combining the weighted average sum of the accuracy attained by various classifiers. This model is trained and tested on well- known iris datasets: Ubiris Version 2 (part1) and Ubiris Version 2 (part2), Casia Iris Interval. The paper resulted in the accuracy of the proposed system of Ensemble Learning on various epochs stating that the accuracy is directly dependent on the number of epochs as on Casia Iris Interval Dataset, the accuracy of the Ensemble model at epoch 10 (77.86%), epoch 30 (83.79%), epoch 50 (86.00%) and epoch 100 (87.24%) which is increasing as number of epochs increases. The paper also proves that the performance of the new system is better than the other base models. According to one of the dataset, Casia Iris Interval dataset, the proposed Ensemble Learning model’s accuracy on 100 epoch was 87.24%, which is significantly higher than the accuracy of the other base models, including DenseNet121 (70.88%), MobileNet (86.51%), InceptionV3 (63.61%), InceptionResNetV2 (34.09%), Xception (68.45%), and CNN (4.07%) respectively.
长期以来，开发更高层次的身份识别或认证安全系统一直是许多领域的活跃研究课题。传统的安全系统使用密钥或密码来保护过程或产品，而生物识别安全系统使用人的物理或行为属性。由于其唯一性、通用性、可靠性和稳定性，虹膜模式在许多潜在的识别或身份验证应用程序中发挥着重要作用。虹膜识别技术在生物识别和认证系统中的应用已经显著增加。本文提出了一种新颖的虹膜分类方法，使其易于应用。这个模型允许使用任何眼睛图像，并且只选择通过模型内部过滤器的照片。此外，本研究还提供了从眼部检测开始到虹膜图像识别结束的虹膜识别模型。此外，本研究提出了一种结合迁移学习和卷积神经网络(cnn)算法的虹膜分类方法。虹膜检测的自动分割技术采用霍夫变换，能够对瞳孔和虹膜区域进行定位，也能够遮挡眼睑、睫毛和反射。为了克服图像的不规则性，首先提取虹膜区域，然后用归一化方法将提取的虹膜转换为矩形块。本文提出了一种加权集成技术，该技术通过将各种分类器的分类精度加权平均相加来进行虹膜分类。该模型在著名的鸢尾数据集Ubiris Version 2 (part1)和Ubiris Version 2 (part2)， Casia iris Interval上进行了训练和测试。结果表明，在Casia Iris区间数据集上，集成学习系统在不同时期的准确率直接依赖于时期数，随着时期数的增加，集成模型在时期10(77.86%)、时期30(83.79%)、时期50(86.00%)和时期100(87.24%)的准确率呈上升趋势。本文还证明了新系统的性能优于其他基本模型。根据其中一个数据集Casia Iris Interval数据集，所提出的集成学习模型在100 epoch上的准确率为87.24%，显著高于其他基础模型，包括DenseNet121(70.88%)、MobileNet(86.51%)、InceptionV3(63.61%)、InceptionResNetV2(34.09%)、Xception(68.45%)和CNN(4.07%)。
{"title":"Smart Iris Classification Using Weighted Average Ensemble Learning","authors":"Aditi Arora, Aanchal Gupta, Bhavya Jindal, Gaurish Gupta","doi":"10.1109/ICDT57929.2023.10151036","DOIUrl":"https://doi.org/10.1109/ICDT57929.2023.10151036","url":null,"abstract":"Developing a higher-level security system for iden- tification or authentication has long been an active research subject in many fields. Traditional security systems utilize a key or a password to secure a process or a product, whereas bio metric security systems use a person’s physical or behavioral attributes. Iris patterns play a significant role in a number of potential recognition or authentication applications because of their uniqueness, universality, dependability, and stability. The use of iris recognition techniques in bio metric identification and authentication systems has increased significantly. In this work, a novel approach for classification of iris is presented, making it simple for anybody to apply this technology. This model allows for the usage of any eye image and only selects photos that pass the model’s internal filters. Besides, this study provides iris identification model that starts with eye detection and ends with iris image recognition. In addition, a method for iris classification is presented in this study that combines Transfer learning and Convolutional Neural Networks (CNNs) algorithms using Ensemble learning. The automatic segmentation technique for iris detection uses Hough Transform and is capable of localizing the pupil and iris region, as well as obstructing eyelids, eyelashes, and reflections. To overcome the image irregularities, the iris region is extracted and then extracted iris is converted into rectangular block using Normalization. In this paper, a weighted ensemble technique is proposed that demonstrates iris classification which is made by combining the weighted average sum of the accuracy attained by various classifiers. This model is trained and tested on well- known iris datasets: Ubiris Version 2 (part1) and Ubiris Version 2 (part2), Casia Iris Interval. The paper resulted in the accuracy of the proposed system of Ensemble Learning on various epochs stating that the accuracy is directly dependent on the number of epochs as on Casia Iris Interval Dataset, the accuracy of the Ensemble model at epoch 10 (77.86%), epoch 30 (83.79%), epoch 50 (86.00%) and epoch 100 (87.24%) which is increasing as number of epochs increases. The paper also proves that the performance of the new system is better than the other base models. According to one of the dataset, Casia Iris Interval dataset, the proposed Ensemble Learning model’s accuracy on 100 epoch was 87.24%, which is significantly higher than the accuracy of the other base models, including DenseNet121 (70.88%), MobileNet (86.51%), InceptionV3 (63.61%), InceptionResNetV2 (34.09%), Xception (68.45%), and CNN (4.07%) respectively.","PeriodicalId":266681,"journal":{"name":"2023 International Conference on Disruptive Technologies (ICDT)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123640054","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}
Pub Date : 2023-05-11DOI: 10.1109/ICDT57929.2023.10150897
Kesavan Nallaluthan, Jessnor Elmy Mat Jizat, S. Suhaimi, Normala S. Govindarajo, Dileep Kumar Mohanachandran, A. Ghouri
In the business programs of Universiti Pendidikan Sultan Idris (UPSI), the Three-Pronged teaching technique is implemented as a student-centered learning process. This approach combines elements of the game, problem, and challenge-based learning with the larger goal of preparing business students to handle complicated, unanticipated global or industrial problems. It promotes an interactive and dependable classroom that calls for students' innovative contributions, teamwork, and participation in the professional world. Micro credential platforms, artificial intelligence, and a new pedagogical strategy: that's the idea for UPSI's undergraduate business. Therefore, this kind of instruction is increasingly being used in business courses like Strategic Management. Undergraduate students benefit from this teaching method since they are exposed to industrial phenomena while developing 21st-century abilities (collaborative, creative, critical thinking, and communication).
在Pendidikan Sultan Idris大学(UPSI)的商业课程中，三管齐下的教学技术被实施为以学生为中心的学习过程。这种方法结合了游戏、问题和基于挑战的学习元素，其更大的目标是让商科学生准备好处理复杂的、意想不到的全球或行业问题。它促进了一个互动和可靠的课堂，呼吁学生的创新贡献，团队合作和参与专业领域。微证书平台、人工智能和新的教学策略:这就是UPSI本科业务的理念。因此，在战略管理等商业课程中越来越多地使用这种教学方式。本科学生受益于这种教学方法，因为他们在接触工业现象的同时发展21世纪的能力(协作、创造性、批判性思维和沟通)。
{"title":"AI in Student as Manager Model-Future Directions of Business Studies","authors":"Kesavan Nallaluthan, Jessnor Elmy Mat Jizat, S. Suhaimi, Normala S. Govindarajo, Dileep Kumar Mohanachandran, A. Ghouri","doi":"10.1109/ICDT57929.2023.10150897","DOIUrl":"https://doi.org/10.1109/ICDT57929.2023.10150897","url":null,"abstract":"In the business programs of Universiti Pendidikan Sultan Idris (UPSI), the Three-Pronged teaching technique is implemented as a student-centered learning process. This approach combines elements of the game, problem, and challenge-based learning with the larger goal of preparing business students to handle complicated, unanticipated global or industrial problems. It promotes an interactive and dependable classroom that calls for students' innovative contributions, teamwork, and participation in the professional world. Micro credential platforms, artificial intelligence, and a new pedagogical strategy: that's the idea for UPSI's undergraduate business. Therefore, this kind of instruction is increasingly being used in business courses like Strategic Management. Undergraduate students benefit from this teaching method since they are exposed to industrial phenomena while developing 21st-century abilities (collaborative, creative, critical thinking, and communication).","PeriodicalId":266681,"journal":{"name":"2023 International Conference on Disruptive Technologies (ICDT)","volume":"240 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123002825","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}
When it comes to diagnosing patients’ illnesses, digital image modalities like X-ray, Ultrasound (US), Computer Tomography (CT), Magnetic resonance imaging (MRI), etc. play an essential part. Noise is a common problem in the pictures produced by these modalities, reducing image quality. An important factor in making correct diagnosis of illness is the quality of the medical pictures used. Poisson noise is a prevalent problem in X-ray pictures. Hairline fractures inside bones, chest coughs, and other similar conditions become more difficult to diagnose when this noise is present. These sounds need to be eliminated from the X-ray picture before it may be improved. In this study, we aimed to establish a method for effectively denoising X-ray pictures, hence reducing the amount of Poisson noise present in them. The suggested filter makes use of the Absolute Difference and Mean Filter (ADMF) to replace the processed pixel with the mean of its nearest neighbors within a 5x5 frame when the absolute difference between them is minimal. Using 75 X-rays of teeth from the Digital Dental X-ray Database, the proposed technique is compared to the state-of-the-art Region Classification and Response Median Filtering (RCRMF) method. Filter performance is measured by Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE) scores; the suggested approach improves PSNR by 5.41 percentage points and reduces MSE by 33.44 percentage points.
{"title":"Reduction of Noise in Medical Imaging Quality","authors":"Gandi Vivek Sai, Chekuri Seshank, Pothina Prudhvi Sai Krishna, Jagjit Singh Dhatterwal","doi":"10.1109/ICDT57929.2023.10150846","DOIUrl":"https://doi.org/10.1109/ICDT57929.2023.10150846","url":null,"abstract":"When it comes to diagnosing patients’ illnesses, digital image modalities like X-ray, Ultrasound (US), Computer Tomography (CT), Magnetic resonance imaging (MRI), etc. play an essential part. Noise is a common problem in the pictures produced by these modalities, reducing image quality. An important factor in making correct diagnosis of illness is the quality of the medical pictures used. Poisson noise is a prevalent problem in X-ray pictures. Hairline fractures inside bones, chest coughs, and other similar conditions become more difficult to diagnose when this noise is present. These sounds need to be eliminated from the X-ray picture before it may be improved. In this study, we aimed to establish a method for effectively denoising X-ray pictures, hence reducing the amount of Poisson noise present in them. The suggested filter makes use of the Absolute Difference and Mean Filter (ADMF) to replace the processed pixel with the mean of its nearest neighbors within a 5x5 frame when the absolute difference between them is minimal. Using 75 X-rays of teeth from the Digital Dental X-ray Database, the proposed technique is compared to the state-of-the-art Region Classification and Response Median Filtering (RCRMF) method. Filter performance is measured by Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE) scores; the suggested approach improves PSNR by 5.41 percentage points and reduces MSE by 33.44 percentage points.","PeriodicalId":266681,"journal":{"name":"2023 International Conference on Disruptive Technologies (ICDT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132874987","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}
Pub Date : 2023-05-11DOI: 10.1109/ICDT57929.2023.10150988
Kailash Sharma, Nagendra Kumar, Priyanka Datta, Jay Singh, Aditya Verma
Fire Fighting is considered one of the most dangerous Rescue operations that has caused many fire-fighters to lose their life. There were more than a thousand cases where the freighters lost their lives because they were made extra efforts to reach the places Inaccessible to the Human reach. Taking all these problems and the hindrance faced in the past few years we decided to bring technology to its best use and make the most of it. We will introduce you to the paper FROZONE- AUTONOMOUS FIRE FIGHTING ROBOT" which will make use of fire sensors and a controlled water splash to detect fire at the inaccessible places and do the work for the fire-fighters and make their work a little less risky.
灭火被认为是最危险的救援行动之一，导致许多消防员丧生。有一千多个案例中，货轮失去了生命，因为他们在人类无法到达的地方付出了额外的努力。考虑到过去几年面临的所有这些问题和障碍，我们决定将技术发挥到最好，并充分利用它。我们将向您介绍一款名为“FROZONE- AUTONOMOUS FIRE FIGHTING ROBOT”的机器人，该机器人将利用火灾传感器和可控的水花在难以接近的地方探测火灾，并为消防员工作，降低他们的工作风险。
{"title":"A Research Paper on Frozone: An Autonomous Fire fighter","authors":"Kailash Sharma, Nagendra Kumar, Priyanka Datta, Jay Singh, Aditya Verma","doi":"10.1109/ICDT57929.2023.10150988","DOIUrl":"https://doi.org/10.1109/ICDT57929.2023.10150988","url":null,"abstract":"Fire Fighting is considered one of the most dangerous Rescue operations that has caused many fire-fighters to lose their life. There were more than a thousand cases where the freighters lost their lives because they were made extra efforts to reach the places Inaccessible to the Human reach. Taking all these problems and the hindrance faced in the past few years we decided to bring technology to its best use and make the most of it. We will introduce you to the paper FROZONE- AUTONOMOUS FIRE FIGHTING ROBOT\" which will make use of fire sensors and a controlled water splash to detect fire at the inaccessible places and do the work for the fire-fighters and make their work a little less risky.","PeriodicalId":266681,"journal":{"name":"2023 International Conference on Disruptive Technologies (ICDT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128697082","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}
Pub Date : 2023-05-11DOI: 10.1109/ICDT57929.2023.10150547
Brijendra Gupta, P. Sreelatha, M. Shanmathi, John Philip Bhimavarapu, P. John Augustine, K. Sathyarajasekaran
The Bio-Medical waste management system organizes everyday medical waste disposal in hospitals. Daily medical waste from hospitals is delivered through it. A separate system is in place for treating medical supplies, including needles, plastic, glassware, medical clothes, expired medications, and human waste. Based on that, they use the Biomedical Waste Management Centre to accept everyday medical waste from their hospitals and appropriately dispose of it. No hospital should ever dispose of medical trash. It is illegal, and the hospital responsible must appropriately separate the medical waste and deliver it to the biomedical waste treatment facility. In this paper, an intelligent machine learning model was proposed to handling the different bio medical wastages and segregate it based on the medical rules. Medical waste disposed of in hospitals is safely transported and incinerated. The proposed model helpful the disposal of such medical waste, which is usually contagious, takes place.
{"title":"A Smart Handling of Bio-Medical Waste and its Segregation with Intelligant Machine Learning Model","authors":"Brijendra Gupta, P. Sreelatha, M. Shanmathi, John Philip Bhimavarapu, P. John Augustine, K. Sathyarajasekaran","doi":"10.1109/ICDT57929.2023.10150547","DOIUrl":"https://doi.org/10.1109/ICDT57929.2023.10150547","url":null,"abstract":"The Bio-Medical waste management system organizes everyday medical waste disposal in hospitals. Daily medical waste from hospitals is delivered through it. A separate system is in place for treating medical supplies, including needles, plastic, glassware, medical clothes, expired medications, and human waste. Based on that, they use the Biomedical Waste Management Centre to accept everyday medical waste from their hospitals and appropriately dispose of it. No hospital should ever dispose of medical trash. It is illegal, and the hospital responsible must appropriately separate the medical waste and deliver it to the biomedical waste treatment facility. In this paper, an intelligent machine learning model was proposed to handling the different bio medical wastages and segregate it based on the medical rules. Medical waste disposed of in hospitals is safely transported and incinerated. The proposed model helpful the disposal of such medical waste, which is usually contagious, takes place.","PeriodicalId":266681,"journal":{"name":"2023 International Conference on Disruptive Technologies (ICDT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115839799","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 deaf and dumb community’s primary mode of communication is signs. It is the only source through which deaf and dumb people can communicate with others. The goal of this paper is to invent a model for translating signs into text format. With assistance of machine learning algorithms, we will scan the signs and then convert them to understandable text. KNN (k-nearest neighbour) algorithm will be used to do so. User will get an interface where it can train the system according to their signs and meanings with respect to it, which can later be used for interaction between deaf and dumb people and common people and vice versa. The assessment of this model is conducted with 3 students using various training examples. The accuracy obtained is approximately 97%.
{"title":"An Improved Sign Language Translation approach using KNN in Deep Learning Environment","authors":"Neeraj Kumar Pandey, Aakanchha Dwivedi, Mukul Sharma, Arpit Bansal, A. Mishra","doi":"10.1109/ICDT57929.2023.10150934","DOIUrl":"https://doi.org/10.1109/ICDT57929.2023.10150934","url":null,"abstract":"The deaf and dumb community’s primary mode of communication is signs. It is the only source through which deaf and dumb people can communicate with others. The goal of this paper is to invent a model for translating signs into text format. With assistance of machine learning algorithms, we will scan the signs and then convert them to understandable text. KNN (k-nearest neighbour) algorithm will be used to do so. User will get an interface where it can train the system according to their signs and meanings with respect to it, which can later be used for interaction between deaf and dumb people and common people and vice versa. The assessment of this model is conducted with 3 students using various training examples. The accuracy obtained is approximately 97%.","PeriodicalId":266681,"journal":{"name":"2023 International Conference on Disruptive Technologies (ICDT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115313285","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}
Image processing is a process to identify the differ- ent patterns in multiple scale. This research explains the funda- mentals of digital image processing and this study provides the significant area of research in image enhancement and deal with multiple parameters on spatial and transform domain. On the other side Image processing which aims to enhance the visibility of input images and extract useful data from them. The most common image transformation is the Fourier transform. There are many applications for the Fourier Transform. Examining photos to identify items and determine their relevance is known as "image processing." A picture analyst examines the distant detected data and makes an effort to find, name, categorise, quantify, and the importance of tangible and cultural items, their through logical processes, patterns and spatial relationships are created.
{"title":"Image Resolution on Multiple Parameters using Spatial and Transform Domain: A Systematic Analysis","authors":"Kapil Joshi, Ajesh F, V. Singh, Sunil Ghildiyal, Prashant Chaudhary, Gunjan Chhabra","doi":"10.1109/ICDT57929.2023.10150817","DOIUrl":"https://doi.org/10.1109/ICDT57929.2023.10150817","url":null,"abstract":"Image processing is a process to identify the differ- ent patterns in multiple scale. This research explains the funda- mentals of digital image processing and this study provides the significant area of research in image enhancement and deal with multiple parameters on spatial and transform domain. On the other side Image processing which aims to enhance the visibility of input images and extract useful data from them. The most common image transformation is the Fourier transform. There are many applications for the Fourier Transform. Examining photos to identify items and determine their relevance is known as \"image processing.\" A picture analyst examines the distant detected data and makes an effort to find, name, categorise, quantify, and the importance of tangible and cultural items, their through logical processes, patterns and spatial relationships are created.","PeriodicalId":266681,"journal":{"name":"2023 International Conference on Disruptive Technologies (ICDT)","volume":"30 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125968277","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}
Pub Date : 2023-05-11DOI: 10.1109/ICDT57929.2023.10150866
L. Maguluri, S. K, M. K, Muhammad Ahtesham Farooqui, H. P. Sultana, S. V.
In general, treatments and medications for diabetics are usually prescribed based on the level of glucose-level in the human-blood. Blood glucose-level was calculated by performing two separate tests: before meals and after meals. The practical functions present in this test enable physicians to carry out appropriate treatment modalities. This paper introduces an improved method of running a machine learning system. Its main task is to accurately analyze the given input data and calculate the correct point of blood-glucose in the blood of diabetics. It was designed to do so and then list the appropriate control methods and drugs and share that data with the user in a paperless digital manner. Thus it is enough for patients to go to laboratories and do tests. Only their results will be calculated and sent to them for treatment.
{"title":"An Artificial Intelligence based Machine Learning Approach for Automatic Blood Glucose Level Identification of Diabetes Patients","authors":"L. Maguluri, S. K, M. K, Muhammad Ahtesham Farooqui, H. P. Sultana, S. V.","doi":"10.1109/ICDT57929.2023.10150866","DOIUrl":"https://doi.org/10.1109/ICDT57929.2023.10150866","url":null,"abstract":"In general, treatments and medications for diabetics are usually prescribed based on the level of glucose-level in the human-blood. Blood glucose-level was calculated by performing two separate tests: before meals and after meals. The practical functions present in this test enable physicians to carry out appropriate treatment modalities. This paper introduces an improved method of running a machine learning system. Its main task is to accurately analyze the given input data and calculate the correct point of blood-glucose in the blood of diabetics. It was designed to do so and then list the appropriate control methods and drugs and share that data with the user in a paperless digital manner. Thus it is enough for patients to go to laboratories and do tests. Only their results will be calculated and sent to them for treatment.","PeriodicalId":266681,"journal":{"name":"2023 International Conference on Disruptive Technologies (ICDT)","volume":"434 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126100751","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}
Pub Date : 2023-05-11DOI: 10.1109/ICDT57929.2023.10151137
R. Chaturvedi, Udayan Ghose
Object detection had gained importance in previous decade due to large amount of data that is being generated throughout the world by cameras, mobile phones, satellite imaginary, medical image, social media, UAV etc. As hardware cost to render these images had been reduced significantly and we have access to plethora of algorithms, framework to detect the object and use this information to solve day to day problems. The object detection is most researched area but it still fails to detect and recognize small objects as detecting large objects had got more focus. But small object detection had got less attention and the algorithms and methodology developed for detecting large object does not yield the desired results and accuracy. In this paper we attempt to detect small objects by using state of art algorithm yolov7 and roboflow and try to evaluate the robustness of object detection with scarcity of data in dataset.
{"title":"Evaluation of Small Object Detection in Scarcity of Data in the Dataset Using Yolov7","authors":"R. Chaturvedi, Udayan Ghose","doi":"10.1109/ICDT57929.2023.10151137","DOIUrl":"https://doi.org/10.1109/ICDT57929.2023.10151137","url":null,"abstract":"Object detection had gained importance in previous decade due to large amount of data that is being generated throughout the world by cameras, mobile phones, satellite imaginary, medical image, social media, UAV etc. As hardware cost to render these images had been reduced significantly and we have access to plethora of algorithms, framework to detect the object and use this information to solve day to day problems. The object detection is most researched area but it still fails to detect and recognize small objects as detecting large objects had got more focus. But small object detection had got less attention and the algorithms and methodology developed for detecting large object does not yield the desired results and accuracy. In this paper we attempt to detect small objects by using state of art algorithm yolov7 and roboflow and try to evaluate the robustness of object detection with scarcity of data in dataset.","PeriodicalId":266681,"journal":{"name":"2023 International Conference on Disruptive Technologies (ICDT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121615895","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：