Pub Date : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970072
Murie Dwiyaniti, Ajeng Bening Kusumaningtyas, Silawardono, S. L. Kusumastuti, Yoga Saefullah, Tohazen, Fairuza Qonitah Tireno, Daniswara Ramadhan
This article discusses the energy-saving efficiency of streetlights using two operating modes, namely timer mode and light intensity mode. Energy measurements are carried out in real time through an IoT-based smart streetlight monitoring system. The data used to compare the energy consumption in the two modes is the power and the length of time the streetlights are on. The results of this comparison will show the value of energy savings. Streetlights with timer mode usually operate from 6 pm to 6 am. Meanwhile, a streetlight with light intensity mode works according to the ambient lighting in light conditions below 10 lux. Implementation results show that streetlights with light intensity mode are 1.13 Wh more efficient than timer mode.
{"title":"Energy Saving of IoT-based Light Intensity on Smart Streetlight","authors":"Murie Dwiyaniti, Ajeng Bening Kusumaningtyas, Silawardono, S. L. Kusumastuti, Yoga Saefullah, Tohazen, Fairuza Qonitah Tireno, Daniswara Ramadhan","doi":"10.1109/IC2IE56416.2022.9970072","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970072","url":null,"abstract":"This article discusses the energy-saving efficiency of streetlights using two operating modes, namely timer mode and light intensity mode. Energy measurements are carried out in real time through an IoT-based smart streetlight monitoring system. The data used to compare the energy consumption in the two modes is the power and the length of time the streetlights are on. The results of this comparison will show the value of energy savings. Streetlights with timer mode usually operate from 6 pm to 6 am. Meanwhile, a streetlight with light intensity mode works according to the ambient lighting in light conditions below 10 lux. Implementation results show that streetlights with light intensity mode are 1.13 Wh more efficient than timer mode.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126927247","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970063
T. Mantoro, Muhammad Zamzami
From 10 random people in the world, there are at least 4 people who experience visual impairment such as blindness, cataracts, or the like due to an incident or congenital. Those who belong to this group need extra attention to carry out their activities as usual. However, in fact, there have been many devices or gadget inventions that can help with this problem. Unfortunately, existing devices are still difficult to reach for people with disabilities in terms of economy and ease of use. To overcome these two problems, this paper proposes a navigation device that has the main feature of direct-based navigation instruction and is supported by machine learning for people who have total or partial vision problems. The main hope of this study is to help people who have vision problems in the economic and practical fields to support their daily activities. In addition, this study is expected to contribute to other studies in the same field.
{"title":"Realtime Indoor Navigation System for Visually Impaired Person using Direct-based Navigation","authors":"T. Mantoro, Muhammad Zamzami","doi":"10.1109/IC2IE56416.2022.9970063","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970063","url":null,"abstract":"From 10 random people in the world, there are at least 4 people who experience visual impairment such as blindness, cataracts, or the like due to an incident or congenital. Those who belong to this group need extra attention to carry out their activities as usual. However, in fact, there have been many devices or gadget inventions that can help with this problem. Unfortunately, existing devices are still difficult to reach for people with disabilities in terms of economy and ease of use. To overcome these two problems, this paper proposes a navigation device that has the main feature of direct-based navigation instruction and is supported by machine learning for people who have total or partial vision problems. The main hope of this study is to help people who have vision problems in the economic and practical fields to support their daily activities. In addition, this study is expected to contribute to other studies in the same field.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116860716","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970073
Rehenuma Tabassum Meghla, Md. Ether Deowan, Ahsan Kabir Nuhel, Mir Mohibullah Sazid, Md. Nafiz Ekbal, Mohammad Hossain Mahamud
Health problems are getting worse day by day. Nowadays, most people undergo more than one disease irrespective of their age. This paper describes the development of the Smart Medication Dispenser (SMD) system employing a microcontroller, GSM module, and its associated hardware. In addition, an application has been created to provide basic prescriptions for common illnesses and notifications for various patient activities. The intelligent SMD will assist patients with the correct distribution of a predetermined number of tablets at a predetermined time. A patient who takes medicine according to SMD will give notification or an alert. It will also be able to give specific treatments for common diseases using the existing database. A gear mechanism will be employed to administer the pills. The Doctor or the caregiver can examine how the client uses the SMD. The networking firmware will avail the complete communication of the SMD device.
{"title":"An Internet of Things (IoT)- based Smart Automatic Medication Dispenser with an Integrated Web Application for Patient Diagnosis","authors":"Rehenuma Tabassum Meghla, Md. Ether Deowan, Ahsan Kabir Nuhel, Mir Mohibullah Sazid, Md. Nafiz Ekbal, Mohammad Hossain Mahamud","doi":"10.1109/IC2IE56416.2022.9970073","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970073","url":null,"abstract":"Health problems are getting worse day by day. Nowadays, most people undergo more than one disease irrespective of their age. This paper describes the development of the Smart Medication Dispenser (SMD) system employing a microcontroller, GSM module, and its associated hardware. In addition, an application has been created to provide basic prescriptions for common illnesses and notifications for various patient activities. The intelligent SMD will assist patients with the correct distribution of a predetermined number of tablets at a predetermined time. A patient who takes medicine according to SMD will give notification or an alert. It will also be able to give specific treatments for common diseases using the existing database. A gear mechanism will be employed to administer the pills. The Doctor or the caregiver can examine how the client uses the SMD. The networking firmware will avail the complete communication of the SMD device.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128727954","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}
A Decision Support System (DSS) is a computer-based system that provides a selection of alternative options to assist management in making decision with structured or unstructured difficulties by employing the information. One of the DSS approaches used is the Elimination Et Choix Traduisant La Realité (Electre) methodology. The Electre method is a multi-criteria decision-making strategy that examines pairs of options based on each relevant criterion. The Electre approach can be used when alternatives that do not satisfy the requirements are eliminated and acceptable alternatives are generated. The Electre technique was employed in this study to achieve the selection of student data that had previously been processed using the Simple Additive Weighting (SAW) method. This study is helpful for studying the outcomes of a decision made using the Electre approach based on predefined criteria and alternatives. The results of these computations will be used in a prototype application. In addition, the results of the decision between the SAW technique and the Electre method will be examined for sensitivity in order to assess the sensitivity value of the two techniques.
决策支持系统(DSS)是一个以计算机为基础的系统，它提供了一系列可供选择的方案，以帮助管理人员利用这些信息，在遇到结构化或非结构化困难时作出决策。使用的决策支持系统方法之一是消除和选择Traduisant La realit (Electre)方法。Electre方法是一种多标准决策策略，它根据每个相关标准检查成对的选项。当不满足需求的替代方案被淘汰并产生可接受的替代方案时，可以使用Electre方法。在这项研究中，采用了电子技术来实现学生数据的选择，这些数据以前是用简单加性加权(SAW)方法处理的。本研究有助于研究基于预定义标准和备选方案的Electre方法做出的决策的结果。这些计算的结果将用于原型应用程序。此外，为了评估两种技术的灵敏度值，将对SAW技术和Electre方法之间的决策结果进行灵敏度检查。
{"title":"The Effect and Impact of the Electre Method for Sensitivity Testing Based on the Case Study Selection of Outstanding Students","authors":"Tonny Hidayat, Hendra - Kurniawan, Ika Asti Astuti, Rizka Pravitasari, Yudi Kristyawan, Litafira Syahadiyanti","doi":"10.1109/IC2IE56416.2022.9970134","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970134","url":null,"abstract":"A Decision Support System (DSS) is a computer-based system that provides a selection of alternative options to assist management in making decision with structured or unstructured difficulties by employing the information. One of the DSS approaches used is the Elimination Et Choix Traduisant La Realité (Electre) methodology. The Electre method is a multi-criteria decision-making strategy that examines pairs of options based on each relevant criterion. The Electre approach can be used when alternatives that do not satisfy the requirements are eliminated and acceptable alternatives are generated. The Electre technique was employed in this study to achieve the selection of student data that had previously been processed using the Simple Additive Weighting (SAW) method. This study is helpful for studying the outcomes of a decision made using the Electre approach based on predefined criteria and alternatives. The results of these computations will be used in a prototype application. In addition, the results of the decision between the SAW technique and the Electre method will be examined for sensitivity in order to assess the sensitivity value of the two techniques.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129701587","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970071
A. Fahrurozi, R. Kosasih
Wood types research usually regards species of wood images. This research focuses on the classification of wood types in Indonesia, coming from four wood species, with one species divided into two types based on their grade and morphological characteristics. The dataset in this research was also created with variations in scale and position, i.e., horizontal and vertical. The feature extraction method is regarded by its types, known as texture features and statistical features. Texture features were extracted using Gray Level Co-occurrence Matrix (GLCM), and statistical features were obtained using the Histogram method. This research aims to analyze the relationship between classifiers and feature types as their input to classification performance for our unique dataset. Support Vector Machine (SVM) and Random Forest are two classifiers used in this research. Generally, four scenarios of the classification system are considered. The output of this study is an image dataset consisting of 5 types of wood in Indonesia and a wood species classification model. The best model was given by statistical features that were used as input of SVM, with an accuracy of 89%, Weighted Average Precision at 94%, and Weighted Average Recall at 89%. This result leads to an exciting point that statistical features give better classification results than texture features in the case of wood types classification, which contains intra-species. It also found that two statistical features, deviation and smoothness, can be assumed as features that have theoretical implications that make intra-species classification more difficult.
{"title":"Texture Features and Statistical Features for Wood Types Classification System","authors":"A. Fahrurozi, R. Kosasih","doi":"10.1109/IC2IE56416.2022.9970071","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970071","url":null,"abstract":"Wood types research usually regards species of wood images. This research focuses on the classification of wood types in Indonesia, coming from four wood species, with one species divided into two types based on their grade and morphological characteristics. The dataset in this research was also created with variations in scale and position, i.e., horizontal and vertical. The feature extraction method is regarded by its types, known as texture features and statistical features. Texture features were extracted using Gray Level Co-occurrence Matrix (GLCM), and statistical features were obtained using the Histogram method. This research aims to analyze the relationship between classifiers and feature types as their input to classification performance for our unique dataset. Support Vector Machine (SVM) and Random Forest are two classifiers used in this research. Generally, four scenarios of the classification system are considered. The output of this study is an image dataset consisting of 5 types of wood in Indonesia and a wood species classification model. The best model was given by statistical features that were used as input of SVM, with an accuracy of 89%, Weighted Average Precision at 94%, and Weighted Average Recall at 89%. This result leads to an exciting point that statistical features give better classification results than texture features in the case of wood types classification, which contains intra-species. It also found that two statistical features, deviation and smoothness, can be assumed as features that have theoretical implications that make intra-species classification more difficult.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129270264","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 : 2022-09-13DOI: 10.1109/ic2ie56416.2022.9970157
C. Chevauché, Christian P. Schindler, V. Boiten, Dirk Vantyghem
Catherine Chevauché chairs the international technical committee on circular economy (ISO TC323). This committee brings together many experts from 93 countries. It produces future ISO standards that will define circular economy and will support its practical implementation in organisations. Catherine worked for a water, waste and energy management company. She developed tools to assess environmental and economic performance for industry activities. More recently, she contributed to the implementation of a plan to reduce the company's greenhouse gas emissions as part of the 1.5 trajectory objective. She is now part of VEOLIA's Strategy and Innovation Department and is supervising a research project on the transition of linear business models towards circular economy for water, waste and energy resource management activities.
{"title":"Speakers Biography","authors":"C. Chevauché, Christian P. Schindler, V. Boiten, Dirk Vantyghem","doi":"10.1109/ic2ie56416.2022.9970157","DOIUrl":"https://doi.org/10.1109/ic2ie56416.2022.9970157","url":null,"abstract":"Catherine Chevauché chairs the international technical committee on circular economy (ISO TC323). This committee brings together many experts from 93 countries. It produces future ISO standards that will define circular economy and will support its practical implementation in organisations. Catherine worked for a water, waste and energy management company. She developed tools to assess environmental and economic performance for industry activities. More recently, she contributed to the implementation of a plan to reduce the company's greenhouse gas emissions as part of the 1.5 trajectory objective. She is now part of VEOLIA's Strategy and Innovation Department and is supervising a research project on the transition of linear business models towards circular economy for water, waste and energy resource management activities.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116478321","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970138
Hafid Kholidi Hadi, R. S. Dewi, Fresha Kharisma, Achmad Kautsar, Anita Safitri
The studies of software development risk continues to grow. One is the software development risk taxonomy released by Software Engineering Institute (SEI). Unfortunately, no risk management research has been explicitly combined with software size estimation. Therefore, this study aims to apply risk management over 13 technical and eight environmental factors in the Use Case Points (UCP) method. The dataset consists of 345 risk factors by any sources, then mapped and justified by three experts. This mapping generates the risk frequency, which is finally modified by adding it to the origin weight by UCP. The results of the application of risk to environmental factors dominate as much as 76.81 percent compared to technical factors. There are 2 objects that the most influencing risks, such skill and motivation for both the developer team and end-user. For further research, this study still challenges how risk management can be integrated to obtain better accuracy toward software effort estimation.
对软件开发风险的研究持续增长。一个是软件工程协会(software Engineering Institute, SEI)发布的软件开发风险分类法。不幸的是，没有风险管理研究明确地与软件规模评估结合起来。因此，本研究的目的是在用例点(UCP)方法中对13个技术因素和8个环境因素进行风险管理。该数据集由来自任何来源的345个风险因素组成，然后由三名专家绘制并证明。该映射生成风险频率，最后通过UCP将其添加到原始权重中进行修改。与技术因素相比，环境因素的风险应用结果占比高达76.81%。有两个对象最能影响风险，比如开发团队和最终用户的技能和动机。对于进一步的研究，本研究仍然挑战如何将风险管理集成到软件工作量评估中以获得更好的准确性。
{"title":"Applying Software Development Risk Taxonomy in Use Case Points Complexity Factor","authors":"Hafid Kholidi Hadi, R. S. Dewi, Fresha Kharisma, Achmad Kautsar, Anita Safitri","doi":"10.1109/IC2IE56416.2022.9970138","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970138","url":null,"abstract":"The studies of software development risk continues to grow. One is the software development risk taxonomy released by Software Engineering Institute (SEI). Unfortunately, no risk management research has been explicitly combined with software size estimation. Therefore, this study aims to apply risk management over 13 technical and eight environmental factors in the Use Case Points (UCP) method. The dataset consists of 345 risk factors by any sources, then mapped and justified by three experts. This mapping generates the risk frequency, which is finally modified by adding it to the origin weight by UCP. The results of the application of risk to environmental factors dominate as much as 76.81 percent compared to technical factors. There are 2 objects that the most influencing risks, such skill and motivation for both the developer team and end-user. For further research, this study still challenges how risk management can be integrated to obtain better accuracy toward software effort estimation.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116509488","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970008
A. Fathoni, H. Nuha
People use robots to facilitate an activity in everyday life. In everyday life there are many activities that can be done by humans, but in situations that cannot be handled by humans, a tool is needed that can alleviate or assist these activities. In this situation, one of the tools that can be used is a robot, especially a robot with a wireless sensor network so that it can be controlled remotely. Wireless Sensor Network (WSN) is an ad hoc and multihop network, this network also connects devices such as nodes, sink nodes, and routers. Wireless sensor networks can form a network without infrastructure and can transmit data in real-time which can make it easier for humans to do an activity. This paper uses the components of the relay robot itself using a microcontroller as a signal transmitter. This microcontroller has many types, one of which is NodeMCU ESP8266. This type has many features, one of which is the ESP8266 Wi-Fi module and can be programmed with the Arduino IDE. The experimental results show that the increase in time in sending messages in each condition is always increasing, this indicates that the interaction of distance and obstacles affects the signal strength in this system.
{"title":"Robot Relay Networks for Area Exploration","authors":"A. Fathoni, H. Nuha","doi":"10.1109/IC2IE56416.2022.9970008","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970008","url":null,"abstract":"People use robots to facilitate an activity in everyday life. In everyday life there are many activities that can be done by humans, but in situations that cannot be handled by humans, a tool is needed that can alleviate or assist these activities. In this situation, one of the tools that can be used is a robot, especially a robot with a wireless sensor network so that it can be controlled remotely. Wireless Sensor Network (WSN) is an ad hoc and multihop network, this network also connects devices such as nodes, sink nodes, and routers. Wireless sensor networks can form a network without infrastructure and can transmit data in real-time which can make it easier for humans to do an activity. This paper uses the components of the relay robot itself using a microcontroller as a signal transmitter. This microcontroller has many types, one of which is NodeMCU ESP8266. This type has many features, one of which is the ESP8266 Wi-Fi module and can be programmed with the Arduino IDE. The experimental results show that the increase in time in sending messages in each condition is always increasing, this indicates that the interaction of distance and obstacles affects the signal strength in this system.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134452735","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970126
M. A. Magboo, V. P. Magboo
There are more than 150 different brain tumors but can be grouped into two main types: primary and metastatic. Presently, magnetic resonance imaging (MRI) is the imaging of choice for the assessment of brain tumors. The objective of the study is to assess the diagnostic performance of convolutional neural networks in the evaluation of brain tumors from cranial MRI images. Different CNN models were applied to an anonymized publicly available MRI brain tumor dataset to assess the presence of brain tumors. Several pre-processing steps (image normalization, shuffling of images, image cropping, and geometric augmentation techniques) were applied to the MRI images. After a series of preliminary verification of various configurations, a base CNN model was developed with succeeding experiments being conducted to search for the optimum composition of neural network parameters. The best base CNN model configurations had very good performance results while the pre-trained architecture (VGG16 and ResN et50) generated excellent performance metrics. For complicated medical images such as cranial MRI, a deeper architecture is preferred over a shallower base model as the pre-trained models obtained much higher performance metrics. Nonetheless, the base model performed well particularly its sensitivity despite having a simpler though shallower architecture which indicates lower false negative results leading to fewer missed cases of patients with brain tumors. This indicates the base model's capability as a valid and reliable decision support tool. Hence, any of these CNN models can be incorporated routinely by physicians in their clinical practice to further augment their decision-making capability.
{"title":"Detection of Brain Tumors from MRI Images using Convolutional Neural Networks","authors":"M. A. Magboo, V. P. Magboo","doi":"10.1109/IC2IE56416.2022.9970126","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970126","url":null,"abstract":"There are more than 150 different brain tumors but can be grouped into two main types: primary and metastatic. Presently, magnetic resonance imaging (MRI) is the imaging of choice for the assessment of brain tumors. The objective of the study is to assess the diagnostic performance of convolutional neural networks in the evaluation of brain tumors from cranial MRI images. Different CNN models were applied to an anonymized publicly available MRI brain tumor dataset to assess the presence of brain tumors. Several pre-processing steps (image normalization, shuffling of images, image cropping, and geometric augmentation techniques) were applied to the MRI images. After a series of preliminary verification of various configurations, a base CNN model was developed with succeeding experiments being conducted to search for the optimum composition of neural network parameters. The best base CNN model configurations had very good performance results while the pre-trained architecture (VGG16 and ResN et50) generated excellent performance metrics. For complicated medical images such as cranial MRI, a deeper architecture is preferred over a shallower base model as the pre-trained models obtained much higher performance metrics. Nonetheless, the base model performed well particularly its sensitivity despite having a simpler though shallower architecture which indicates lower false negative results leading to fewer missed cases of patients with brain tumors. This indicates the base model's capability as a valid and reliable decision support tool. Hence, any of these CNN models can be incorporated routinely by physicians in their clinical practice to further augment their decision-making capability.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130761220","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 : 2022-09-13DOI: 10.1109/IC2IE56416.2022.9970086
Muhammad Rafid Ediputra, Anna Agus Amalyah
The purpose of this study is to analyze the factors that influence consumer preference when using QRIS (Quick Response Code Indonesian Standard) in Indonesian mobile payment systems in-store. With the advent of QRIS mobile payments, transactions in many areas of the business scene, especially in stores, have been disrupted. From cash and EDC (Electronic Data Capture) payments, it has become common in Indonesia to use QR payments with QRIS. A comprehensive review of the scientific literature shows the development of a behavioral model that explains the preference for using QRIS. This study uses a sample of 17–30 years old classified as active mobile payment users who regularly use QRIS in their business. This research aims to seek relationships between two variables by analyzing a quantitative type with a conclusive and descriptive research design. This study uses the technology acceptance model (TAM) to form different behaviors depending on the user's usage of each payment method offered. Insights and impacts on management provide an alternative to operating a business. This research uses SmartPLS since the focus of the research is to analyze the relationship between constructs, not analyzing a model. Empirical results show that the recognized convenience and speed constitute an important barrier to the payment process, along with the behavioral intention of users towards the QRIS payment. Other potential obstacles include an in-store selection of mobile payments, consumer ignorance of QRIS, old habits, image, and personal innovativeness of users' socially acceptable services and needs.
{"title":"Analysis Factors Affecting Consumer Preferences in using Qris Payment In-Store","authors":"Muhammad Rafid Ediputra, Anna Agus Amalyah","doi":"10.1109/IC2IE56416.2022.9970086","DOIUrl":"https://doi.org/10.1109/IC2IE56416.2022.9970086","url":null,"abstract":"The purpose of this study is to analyze the factors that influence consumer preference when using QRIS (Quick Response Code Indonesian Standard) in Indonesian mobile payment systems in-store. With the advent of QRIS mobile payments, transactions in many areas of the business scene, especially in stores, have been disrupted. From cash and EDC (Electronic Data Capture) payments, it has become common in Indonesia to use QR payments with QRIS. A comprehensive review of the scientific literature shows the development of a behavioral model that explains the preference for using QRIS. This study uses a sample of 17–30 years old classified as active mobile payment users who regularly use QRIS in their business. This research aims to seek relationships between two variables by analyzing a quantitative type with a conclusive and descriptive research design. This study uses the technology acceptance model (TAM) to form different behaviors depending on the user's usage of each payment method offered. Insights and impacts on management provide an alternative to operating a business. This research uses SmartPLS since the focus of the research is to analyze the relationship between constructs, not analyzing a model. Empirical results show that the recognized convenience and speed constitute an important barrier to the payment process, along with the behavioral intention of users towards the QRIS payment. Other potential obstacles include an in-store selection of mobile payments, consumer ignorance of QRIS, old habits, image, and personal innovativeness of users' socially acceptable services and needs.","PeriodicalId":151165,"journal":{"name":"2022 5th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114720602","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：