Pub Date : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127820
Al-Khowarizmi, S. Efendi, M. K. Nasution, Mawengkang Herman
Prediction is included in the data mining process to predict future data based on learning from past data. Various techniques are used in making predictions. The Regression method also includes techniques for making predictions. Various regressions such as Linear Regression, Ridge Regression, Lasso Regression, and Multivariate Adaptive Regression Splines (MARS) are regression techniques that are fond of being used in predicting data in business. Every prediction is always measured success with several formulations. As MAPE is a measuring tool in obtaining accuracy, so it is trying to be designed with the role of Detection Rate (DR) in order to get a smaller error value in obtaining accuracy. In this paper, the process of obtaining accuracy in Linear Regression is carried out to obtain a MAPE of 0.15874361801345002 % and the role of DR in MAPE is 0.1410249900632677 %. At Ridge Regression get a MAPE of 0.15820461185453846 % and the role of DR in MAPE is 0.14077739389387 %. On Lasso Regression get a MAPE of 0.14793925681569248 % and the role of DR in MAPE is 0.1370143839961479 %. On MARS get a MAPE of 0.16209808399129746 % and the role of DR in MAPE is 0.14528079908718253 %.
{"title":"The Role of Detection Rate in MAPE to Improve Measurement Accuracy for Predicting FinTech Data in Various Regressions","authors":"Al-Khowarizmi, S. Efendi, M. K. Nasution, Mawengkang Herman","doi":"10.1109/ICCoSITE57641.2023.10127820","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127820","url":null,"abstract":"Prediction is included in the data mining process to predict future data based on learning from past data. Various techniques are used in making predictions. The Regression method also includes techniques for making predictions. Various regressions such as Linear Regression, Ridge Regression, Lasso Regression, and Multivariate Adaptive Regression Splines (MARS) are regression techniques that are fond of being used in predicting data in business. Every prediction is always measured success with several formulations. As MAPE is a measuring tool in obtaining accuracy, so it is trying to be designed with the role of Detection Rate (DR) in order to get a smaller error value in obtaining accuracy. In this paper, the process of obtaining accuracy in Linear Regression is carried out to obtain a MAPE of 0.15874361801345002 % and the role of DR in MAPE is 0.1410249900632677 %. At Ridge Regression get a MAPE of 0.15820461185453846 % and the role of DR in MAPE is 0.14077739389387 %. On Lasso Regression get a MAPE of 0.14793925681569248 % and the role of DR in MAPE is 0.1370143839961479 %. On MARS get a MAPE of 0.16209808399129746 % and the role of DR in MAPE is 0.14528079908718253 %.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115868299","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127803
Muhammad Ibadurrahman Arrasyid Supriyanto, R. Sarno, C. Fatichah, Aziz Fajar
Higher image reconstruction with excellent structural detail allows experts to perform accurate analysis, especially on the smallest organ details. The interpolation method that approaches the problem of medical image reconstruction, especially 3D, still causes serious problems. The medical image produced by the interpolation method produces blurred or smooth lines on some parts of the organ. This can cause errors in the medical analysis that will be carried out if the reconstruction results are problematic. For this reason, a method is needed that can reconstruct images well without producing blur but does not require very large computer resources. This study aims to evaluate and compare the quality of 3D magnetic resonance imaging medical images reconstructed using interpolation methods and artificial neural network architectures in the DICOM data format. This study evaluates and compares the quality of 3D magnetic resonance imaging medical images reconstructed using interpolation methods and artificial neural network architectures. The test scenario was performed using images from the ADNI dataset and comparing the output results using a variational autoencoder and a multi-level densely connected super-resolution network on 3D data with existing interpolation methods. The evaluation was done using two metrics, i.e., SSIM and PSNR. The results showed that the variational autoencoder method has the highest SSIM and PSNR values, indicating it has the highest image quality among the three methods, while the mDCSRN method has the lowest SSIM and PSNR values, meaning it has the lowest image quality.
{"title":"A Comparison Between Interpolation Method and Neural Network Approach in 3D Digital Imaging and Communications in Medicine","authors":"Muhammad Ibadurrahman Arrasyid Supriyanto, R. Sarno, C. Fatichah, Aziz Fajar","doi":"10.1109/ICCoSITE57641.2023.10127803","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127803","url":null,"abstract":"Higher image reconstruction with excellent structural detail allows experts to perform accurate analysis, especially on the smallest organ details. The interpolation method that approaches the problem of medical image reconstruction, especially 3D, still causes serious problems. The medical image produced by the interpolation method produces blurred or smooth lines on some parts of the organ. This can cause errors in the medical analysis that will be carried out if the reconstruction results are problematic. For this reason, a method is needed that can reconstruct images well without producing blur but does not require very large computer resources. This study aims to evaluate and compare the quality of 3D magnetic resonance imaging medical images reconstructed using interpolation methods and artificial neural network architectures in the DICOM data format. This study evaluates and compares the quality of 3D magnetic resonance imaging medical images reconstructed using interpolation methods and artificial neural network architectures. The test scenario was performed using images from the ADNI dataset and comparing the output results using a variational autoencoder and a multi-level densely connected super-resolution network on 3D data with existing interpolation methods. The evaluation was done using two metrics, i.e., SSIM and PSNR. The results showed that the variational autoencoder method has the highest SSIM and PSNR values, indicating it has the highest image quality among the three methods, while the mDCSRN method has the lowest SSIM and PSNR values, meaning it has the lowest image quality.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116744136","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}
Citrus fruit is a fruit that has good vitamins and is popular with the public. This fruit also has various types with different benefits. Each type of orange also has a variety of colors. Types of oranges can be checked manually by looking directly at the color and texture of the fruit. This manual method is very simple but also very subjective because of the different understanding of each person about the types of oranges. Therefore, this research discusses and explains how to determine the type of fruit by comparing several methods, namely using the SVM method (Support Vector Machine), the CNN method (Convolutional Neural Network), the K-NN method (K-Nearest Neighbor), and the Naïve Bayes method by taking several samples of citrus fruit images consisting of sweet oranges, lemons and limes using a mobile phone camera. The total dataset used in this study is 90 datasets consisting of 30 sweet orange images, 30 lime images and 30 lemon images. Of the 90 datasets are divided into training data and test data. From the results of the study, it was obtained that the accuracy of compatibility with a percentage of 100% using the CNN method (Convolutional Neural Network).
{"title":"Classification of Orange Fruit Using Convolutional Neural Network, Support Vector Machine, K-Nearest Neighbor and Naive Bayes Methods Based on Color Analysis","authors":"Widhi Ersa Pratiwi, Mhd Arief Hasan, Gusyella Mustika, Siti Sarah, Dwi Suci Ramadhani, Fadli Julizar, Ferry","doi":"10.1109/ICCoSITE57641.2023.10127775","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127775","url":null,"abstract":"Citrus fruit is a fruit that has good vitamins and is popular with the public. This fruit also has various types with different benefits. Each type of orange also has a variety of colors. Types of oranges can be checked manually by looking directly at the color and texture of the fruit. This manual method is very simple but also very subjective because of the different understanding of each person about the types of oranges. Therefore, this research discusses and explains how to determine the type of fruit by comparing several methods, namely using the SVM method (Support Vector Machine), the CNN method (Convolutional Neural Network), the K-NN method (K-Nearest Neighbor), and the Naïve Bayes method by taking several samples of citrus fruit images consisting of sweet oranges, lemons and limes using a mobile phone camera. The total dataset used in this study is 90 datasets consisting of 30 sweet orange images, 30 lime images and 30 lemon images. Of the 90 datasets are divided into training data and test data. From the results of the study, it was obtained that the accuracy of compatibility with a percentage of 100% using the CNN method (Convolutional Neural Network).","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122811234","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}
Indoor positioning system determine the position of objects in a closed room or story building. This system can determine not only the position but also the orientation and direction of a person's movement. This research uses Wi-Fi (Wireless Fidelity) a network technology that utilizes wireless technology and can work at frequencies of 2.4 GHz and 5.8 GHz. The aims to produce a system that can monitor the presence of employees. This makes the supervisor's work more effective because it can unify based on the information displayed on the android application. Based on observation and testing that has been done, the proposed system can display BSSID as MAC address and SSID from user data by authentication by admin. The system can monitor the user's position in the faculty office area with the application of the K-Nearest Neighbor (KNN) algorithm and the calculation of Received Signal Strength Indication (RSSI) and using the Fingerprinting method with an average Euclidean distance accuracy of 2.37 meters and able to display the user's position with a 100% success percentage. Then, the system is able to read the value of RSSI with 2.08% error.
{"title":"Indoor Positioning System Based on BSSID on Office Wi-Fi Network","authors":"Ratna Aisuwarya, Rian Ferdian, Indah Hestina Yulianti","doi":"10.1109/ICCoSITE57641.2023.10127734","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127734","url":null,"abstract":"Indoor positioning system determine the position of objects in a closed room or story building. This system can determine not only the position but also the orientation and direction of a person's movement. This research uses Wi-Fi (Wireless Fidelity) a network technology that utilizes wireless technology and can work at frequencies of 2.4 GHz and 5.8 GHz. The aims to produce a system that can monitor the presence of employees. This makes the supervisor's work more effective because it can unify based on the information displayed on the android application. Based on observation and testing that has been done, the proposed system can display BSSID as MAC address and SSID from user data by authentication by admin. The system can monitor the user's position in the faculty office area with the application of the K-Nearest Neighbor (KNN) algorithm and the calculation of Received Signal Strength Indication (RSSI) and using the Fingerprinting method with an average Euclidean distance accuracy of 2.37 meters and able to display the user's position with a 100% success percentage. Then, the system is able to read the value of RSSI with 2.08% error.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"70 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132570062","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127782
A. Suraji, A. Sudjianto, R. Riman, Candra Aditya, Aviv Yuniar Rahman, Rangga Pahlevi Putra
Identification of road surface infrastructure defects is a very important requirement and requires fast and accurate information. The purpose of this study is to identify road surface defects using recording technology with GPS video. The data collection method was carried out by surveying road defects using GPS video with moving car observation. Furthermore, the image data from the video recording is compiled to determine the condition of the road surface damage in accordance with the coordinates of the road segment. The method of analyzing the types of road damage used the Pavement Condition Index (PCI) method, then a roadmap of road damage conditions was made. The research results using GPS video obtained that the percentage of road surface defects for each type of damage is good 10 %, fair 45%, light poor 35% and heavy poor 10%. The results of the identification of road surface defects with GPS video are generally in accordance with the conditions in the field. From the results of this study, it can be recommended that a road defect survey using GPS video can be used as an alternative survey method and has the advantage of being faster.
{"title":"Moving Car Observation (MCO) for Road Surface Defect Identification Using GPS Video","authors":"A. Suraji, A. Sudjianto, R. Riman, Candra Aditya, Aviv Yuniar Rahman, Rangga Pahlevi Putra","doi":"10.1109/ICCoSITE57641.2023.10127782","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127782","url":null,"abstract":"Identification of road surface infrastructure defects is a very important requirement and requires fast and accurate information. The purpose of this study is to identify road surface defects using recording technology with GPS video. The data collection method was carried out by surveying road defects using GPS video with moving car observation. Furthermore, the image data from the video recording is compiled to determine the condition of the road surface damage in accordance with the coordinates of the road segment. The method of analyzing the types of road damage used the Pavement Condition Index (PCI) method, then a roadmap of road damage conditions was made. The research results using GPS video obtained that the percentage of road surface defects for each type of damage is good 10 %, fair 45%, light poor 35% and heavy poor 10%. The results of the identification of road surface defects with GPS video are generally in accordance with the conditions in the field. From the results of this study, it can be recommended that a road defect survey using GPS video can be used as an alternative survey method and has the advantage of being faster.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134313509","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127676
Jajang Taupik, Tossin Alamsyah, Asri Wulandari, Edmund Ucok Armin, A. Hikmaturokhman
Today, every airport manager in various countries has tightened runway security to avoid the entry of foreign objects that can endanger passengers and aircraft both when landing and taking off. Inspection and supervision of the runway must be carried out regularly. However, there are still many airports that carry out inspections and supervision by human labor without any technological support. Whereas inspection and supervision using human labor takes a relatively long time and is prone to errors, especially in bad weather and limited visibility. Technological developments in runway security using radar are one of the solutions. However, radar technology is relatively expensive, so many airport managers use computer vision because it is considered cheaper and more accurate. The use of computer vision has grown rapidly in monitoring FOD on aircraft runways. Our method is an impovement of the YOLOX architecture by moving output objects to branch classes. Our method got a MAP score of 0.832 which has an increase in score of 0.021 from the previous method in detecting FOD in classes of people, vehicles, birds, cats and dogs.
{"title":"Airport Runway Foreign Object Debris (FOD) Detection Based on YOLOX Architecture","authors":"Jajang Taupik, Tossin Alamsyah, Asri Wulandari, Edmund Ucok Armin, A. Hikmaturokhman","doi":"10.1109/ICCoSITE57641.2023.10127676","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127676","url":null,"abstract":"Today, every airport manager in various countries has tightened runway security to avoid the entry of foreign objects that can endanger passengers and aircraft both when landing and taking off. Inspection and supervision of the runway must be carried out regularly. However, there are still many airports that carry out inspections and supervision by human labor without any technological support. Whereas inspection and supervision using human labor takes a relatively long time and is prone to errors, especially in bad weather and limited visibility. Technological developments in runway security using radar are one of the solutions. However, radar technology is relatively expensive, so many airport managers use computer vision because it is considered cheaper and more accurate. The use of computer vision has grown rapidly in monitoring FOD on aircraft runways. Our method is an impovement of the YOLOX architecture by moving output objects to branch classes. Our method got a MAP score of 0.832 which has an increase in score of 0.021 from the previous method in detecting FOD in classes of people, vehicles, birds, cats and dogs.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125594548","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127683
Muhammad Fikri Hasani, Y. Heryadi, Yulyani Arifin, Lukas, W. Suparta
Task oriented chatbots are a sub-topic related to chatbots, where chatbots will perform certain tasks with specific goals. One part of creating a task-oriented chatbot is doing intent classification. Intent classification is a task of text classification. As in general text classification, the required dataset requires a label to carry out the classification process. To speed up and help the utterance analysis process, there is already a method, namely clustering, and Density-based clustering is a part of clustering that can determine cluster patterns based on arbitrary data, with DBScan as one of its algorithms. This research used 10000 client utterance data of awhatsapp based e-commerce conversation. SentenceBert also used as a state of art sentence embedding. This research yield silhouette score of 0.327 as the best result from eps of 0.1 and MinPts of 95. However, based on the cluster result, sentences labelled as noise can be further clustered. Text Preprocessing, text augmentation and sentence embedding techniques can be explored to increase the cluster performance.
{"title":"Density Based Spatial Clustering of Applications with Noise and Sentence Bert Embedding for Indonesian Utterance Clustering","authors":"Muhammad Fikri Hasani, Y. Heryadi, Yulyani Arifin, Lukas, W. Suparta","doi":"10.1109/ICCoSITE57641.2023.10127683","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127683","url":null,"abstract":"Task oriented chatbots are a sub-topic related to chatbots, where chatbots will perform certain tasks with specific goals. One part of creating a task-oriented chatbot is doing intent classification. Intent classification is a task of text classification. As in general text classification, the required dataset requires a label to carry out the classification process. To speed up and help the utterance analysis process, there is already a method, namely clustering, and Density-based clustering is a part of clustering that can determine cluster patterns based on arbitrary data, with DBScan as one of its algorithms. This research used 10000 client utterance data of awhatsapp based e-commerce conversation. SentenceBert also used as a state of art sentence embedding. This research yield silhouette score of 0.327 as the best result from eps of 0.1 and MinPts of 95. However, based on the cluster result, sentences labelled as noise can be further clustered. Text Preprocessing, text augmentation and sentence embedding techniques can be explored to increase the cluster performance.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124795779","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127770
B. Wijanarko, Dina Fitria Murad, Y. Heryadi, C. Tho, Kiyota Hashimoto
Automated language translation involving low-resource language has gained wide interest from many research communities in the past decade. One lesson learned from the past COVID-19 pandemic, particularly in Indonesia, is that many local Governments have to release regular public announcements to keep people following health protocol especially when they are in public areas. Many studies showed some evidence that rural people in Indonesia which covers a large proportion of Indonesia’s population, feel more convenience receiving official announcements in their local language. However, translating official announcement from the national language to many local languages in Indonesia require many experienced bilingual translators and time. This paper presents exploration results in developing an automated language translator model to translate texts in Bahasa Indonesia to the Sundanese language. In particular, this study aims to explore the effect of ReLU, Sigmoid, and Tanh activation functions of the Vanilla Transformer Model on its translation performance. The experiment results showed that the activation function under study gives similar training accuracy (0.98). However, ReLU achieves better performance than Tanh in terms of validation accuracy, training loss, and validation loss.
{"title":"Exploring the Effect of Activation Function on Transformer Model Performance for Official Announcement Translator from Indonesian to Sundanese Languages","authors":"B. Wijanarko, Dina Fitria Murad, Y. Heryadi, C. Tho, Kiyota Hashimoto","doi":"10.1109/ICCoSITE57641.2023.10127770","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127770","url":null,"abstract":"Automated language translation involving low-resource language has gained wide interest from many research communities in the past decade. One lesson learned from the past COVID-19 pandemic, particularly in Indonesia, is that many local Governments have to release regular public announcements to keep people following health protocol especially when they are in public areas. Many studies showed some evidence that rural people in Indonesia which covers a large proportion of Indonesia’s population, feel more convenience receiving official announcements in their local language. However, translating official announcement from the national language to many local languages in Indonesia require many experienced bilingual translators and time. This paper presents exploration results in developing an automated language translator model to translate texts in Bahasa Indonesia to the Sundanese language. In particular, this study aims to explore the effect of ReLU, Sigmoid, and Tanh activation functions of the Vanilla Transformer Model on its translation performance. The experiment results showed that the activation function under study gives similar training accuracy (0.98). However, ReLU achieves better performance than Tanh in terms of validation accuracy, training loss, and validation loss.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132240644","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127835
Muhammad Yusuf Kardawi, R. Sarno
Mammography offers the most efficient approach for detecting breast illnesses early. Nevertheless, Image enhancement to improve breast cancer detection is required since mammograms are low-contrast and noisy images, and typical diagnostic markers such as microcalcifications and masses are challenging to identify. Due to this issue, this paper evaluates the impact of image enhancement on the performance of the deep learning approach and conducts qualitative and quantitative testing of various deep learning models in breast cancer classification. This study uses Mini Digital Database for Screening Mammography (Mini-DDSM) breast dataset containing cancer and normal images. The mammography images are then improved using morphological erosion and enhanced using two image enhancement algorithms which are Unsharp Masking (UM) and High-Frequency Emphasis Filtering (HEF). Deep learning classification algorithms such as ResNet, DenseNet, and EfficientNet are employed to classify breast cancer. Each architecture is compared and analyzed regarding the effect of the image enhancement techniques and achieves the highest 76.08% accuracy score on breast cancer classification in the mammography dataset using the HEF technique.
{"title":"Image Enhancement for Breast Cancer Detection on Screening Mammography Using Deep Learning","authors":"Muhammad Yusuf Kardawi, R. Sarno","doi":"10.1109/ICCoSITE57641.2023.10127835","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127835","url":null,"abstract":"Mammography offers the most efficient approach for detecting breast illnesses early. Nevertheless, Image enhancement to improve breast cancer detection is required since mammograms are low-contrast and noisy images, and typical diagnostic markers such as microcalcifications and masses are challenging to identify. Due to this issue, this paper evaluates the impact of image enhancement on the performance of the deep learning approach and conducts qualitative and quantitative testing of various deep learning models in breast cancer classification. This study uses Mini Digital Database for Screening Mammography (Mini-DDSM) breast dataset containing cancer and normal images. The mammography images are then improved using morphological erosion and enhanced using two image enhancement algorithms which are Unsharp Masking (UM) and High-Frequency Emphasis Filtering (HEF). Deep learning classification algorithms such as ResNet, DenseNet, and EfficientNet are employed to classify breast cancer. Each architecture is compared and analyzed regarding the effect of the image enhancement techniques and achieves the highest 76.08% accuracy score on breast cancer classification in the mammography dataset using the HEF technique.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132766821","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127689
Md Musfiq Us Saleheen, Md Rabbul Fahad, R. Khan
Robotic arms are highly effective for industries that demand quick and reliable performance. These efficient devices are essentially automated systems that, unlike humans, do not get tired or need a rest. These machines have been used for many years but have recently progressed significantly with the advancement of complex sensors. Robotic arms of today come with various sensors that let them move around and react quickly in their working areas. This paper introduces a human hand gesture-controlled automatic low-cost robotic arm. In this proposed system, an Arduino Mega microcontroller gets the information from all the sensors and correctly manages the servomotor with the help of the value of sensors. All the sensors required to control the various servos on the robotic arm are placed into a hand glove. The robotic arm is operated in this system by two flex sensors. One flex sensor is linked to the glove’s forefinger section to manage the arm’s claw, and another is attached to the middle finger section of the glove to regulate the arm’s wrist. A gyroscope is also pinned to the glove to track the movement of the forearm and base. As a result, the base servo moves clockwise or counterclockwise depending on whether the hand glove is angled right or left. However, if the hand glove is angled upward or downward, the gyroscope data will cause the forearm servo to rotate either clockwise or counterclockwise. The sensors’ values are converted to the servo motors’ rotational degrees. The sensors’ values are converted to the servo motors’ rotational degrees. The claw, wrist, forearm servos and base of the proposed robotic device can rotate up to 900, 450, 1200 and 1800 degrees, respectively.
{"title":"Gesture-Controlled Robotic Arm","authors":"Md Musfiq Us Saleheen, Md Rabbul Fahad, R. Khan","doi":"10.1109/ICCoSITE57641.2023.10127689","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127689","url":null,"abstract":"Robotic arms are highly effective for industries that demand quick and reliable performance. These efficient devices are essentially automated systems that, unlike humans, do not get tired or need a rest. These machines have been used for many years but have recently progressed significantly with the advancement of complex sensors. Robotic arms of today come with various sensors that let them move around and react quickly in their working areas. This paper introduces a human hand gesture-controlled automatic low-cost robotic arm. In this proposed system, an Arduino Mega microcontroller gets the information from all the sensors and correctly manages the servomotor with the help of the value of sensors. All the sensors required to control the various servos on the robotic arm are placed into a hand glove. The robotic arm is operated in this system by two flex sensors. One flex sensor is linked to the glove’s forefinger section to manage the arm’s claw, and another is attached to the middle finger section of the glove to regulate the arm’s wrist. A gyroscope is also pinned to the glove to track the movement of the forearm and base. As a result, the base servo moves clockwise or counterclockwise depending on whether the hand glove is angled right or left. However, if the hand glove is angled upward or downward, the gyroscope data will cause the forearm servo to rotate either clockwise or counterclockwise. The sensors’ values are converted to the servo motors’ rotational degrees. The sensors’ values are converted to the servo motors’ rotational degrees. The claw, wrist, forearm servos and base of the proposed robotic device can rotate up to 900, 450, 1200 and 1800 degrees, respectively.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132988696","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：