Articles
<![CDATA[Penerapan Deskriptor Warna Dominan untuk Temu Kembali Citra Busana pada Peranti Bergerak ]]>
<![CDATA[Yustina Dhyanti]]>;
<![CDATA[Khairul Munadi]]>;
<![CDATA[Fitri Arnia]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 12, No 3 (2016) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1062.094 KB)
|
DOI: 10.17529/jre.v12i3.5701
<![CDATA[Nowadays, clothes with various designs and color combinations are available for purchasing through an online shop, which is mostly equipped with keyword-based item retrieval. Here, the object in the online database is retrieved based on the keyword inputted by the potential buyers. The keyword-based search may bring potential customers on difficulties to describe the clothes they want to buy. This paper presents a new searching approach, using an image instead of text, as the query into an online shop. This method is known as content-based image retrieval (CBIR). Particularly, we focused on using color as the feature in our Muslimah clothes image retrieval. The dominant color descriptor (DCD) extracts the wardrobe's color. Then, image matching is accomplished by calculating the Euclidean distance between the query and image in the database, and the last step is to evaluate the performance of the DWD by calculating precision and recall. To determine the performance of the DCD in extracting color features, the DCD is compared with another color descriptor, that is dominant color correlogram descriptor (DCCD). The values of precision and recall of DCD ranged from 0.7 to 0.9 while the precision and recall of DCCD ranged from 0.7 to 0.8. These results showed that the DCD produce a superior performance compared to DCCD in retrieving a set of clothing image, either plain or patterned colored clothes.]]>
<![CDATA[Substraksi Latar Menggunakan Nilai Mean Untuk Klasifikasi Kendaraan Bergerak Berbasis Deep Learning ]]>
<![CDATA[Ilal Mahdi]]>;
<![CDATA[Kahlil Muchtar]]>;
<![CDATA[Fitri Arnia]]>;
<![CDATA[Tia Ernita]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 18, No 2 (2022) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1626.433 KB)
|
DOI: 10.17529/jre.v18i2.25224
<![CDATA[Moving object detection systems have been widely used in everyday life. Currently, research in the field of background subtraction is still being carried out to achieve maximum accuracy results. This study aims to model the background subtraction of an image using the mean value with the concept of non-overlapping block. Furthermore, the background abstraction results will be used in deep learning-based moving object detection. Specifically, the input image will be divided into several blocks, then the mean value of each block will be calculated to later produce a binary block (binary map). The binary blocks that have been generated will be used as input for background modeling. The background model aims to separate moving objects from the background in the input image. The resulting moving object (object localization) will be sent to the object classification stage using deep learning. The dataset used in this study is CDNet 2014. The results of the study were able to produce a more accurate moving object detection system. Quantitative tests carried out resulted in an accuracy of above 90%.]]>
<![CDATA[Fine Tuning CNN Pre-trained Model Based on Thermal Imaging for Obesity Early Detection ]]>
<![CDATA[Hendrik Leo]]>;
<![CDATA[Fitri Arnia]]>;
<![CDATA[Khairul Munadi]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 18, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1171.928 KB)
|
DOI: 10.17529/jre.v18i1.25100
<![CDATA[Obesity is a complex disease that causes serious impact health, such as diabetes mellitus, cardiovascular disease, cancer, and stroke. An early obesity diagnosis/ detection method is required to prevent the increasing number of obese people. This study aims to: (i) fine-tune the pre-trained Convolutional Neural Network (CNN) models to build an early detection of obesity and (ii) evaluate the model performance in terms of classifying performance, computation speed, and learning performance. The thermal images acquisition procedure was conducted with 18 normal subjects and 15 obese subjects to build a thermal images dataset of obesity. Pre-trained CNN models: VGG19, MobileNet, ResNet152V, and DenseNet201 were modified and trained using the acquired dataset as the input. The training results show that the DenseNet201 model outperformed other models regarding classifying accuracy: 83.33 % and learning performances. At the same time, the MobileNet model outperformed other models in terms of computation speed with training elapsed time: 12 seconds/epoch. The proposed DenseNet201 model was suitable for implementation as an early screening system of obesity for health workers or physicians. Meanwhile, the proposed MobileNet model was suitable for mobile applications' early detection/diagnosis of obesity.]]>
<![CDATA[Identifikasi Tingkat Kematangan Kelapa Sawit Berbasis Pencitraan Termal ]]>
<![CDATA[Khusnul Azima]]>;
<![CDATA[Khairul Munadi]]>;
<![CDATA[Fitri Arnia]]>;
<![CDATA[Maulisa Oktiana]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 15, No 1 (2019) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1469.872 KB)
|
DOI: 10.17529/jre.v15i1.12963
<![CDATA[Indonesia is the biggest producer of palm oil (Elaeis guineenis jacq). The palm tree is a primary commodity that posses a high economic value. Palm oil must be considered in terms of quality to produce optimal and high-quality oil. Previously, the stipulation of the palm tree characterization used manual and visual image utilization method; it may have weaknesses due to the dependency of individual sorting and coruscation factor. Therefore, this research is aimed to improve the performance of the previous method in identifying the ripeness of palm tree based on thermal imaging. The excess of thermal imaging was not related to the coruscation since the level of ripeness was both determined by the temperature and colour. The detection method of this research deployed the colour-based features that are Dominant Colour Descriptor and Color Moment. The DCD and Color Moment was the input to the K-Nearest Neighbor (KNN) method. The percentage of identification rate was 89%, and the identification of oil palm maturity level using thermal imaging is more efficient because it is done without human intervention and does not depend on lighting assistance compared to manual method and method of using RGB visual images.]]>
<![CDATA[Sistem Multi-Sensor Nirkabel Berbasis RFID Untuk Pemantauan Keaktifan Siswa ]]>
<![CDATA[Zakiah Zakiah]]>;
<![CDATA[Yuwaldi Away]]>;
<![CDATA[Fitri Arnia]]>;
<![CDATA[Andri Novandri]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 15, No 3 (2019) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (909.052 KB)
|
DOI: 10.17529/jre.v15i3.14107
<![CDATA[This study aims to design a multisensor observation system, develop a microcontroller-based prototype with ESP8266 and RFID modules, and analyze the performance of the prototype. From the testing carried out by tagging each time students do activities, the client tag data will be sent to the server, and the results are displayed PLX-DAQ. With the 50 tag cards that have registered the IDs of each student, it shows that those who attend the schedule will be given the logic "1" (otherwise logic "0"), and attendance data will be obtained by calculating the number of attendance of students in four types of activities in four locations. The data is transmitted to Data-loggers through two configurations, namely Data-logger as the client (indirect), and Data-logger as a server (direct). From the two configurations, it was found that the configuration of Data-logger as a server had a performance of 19.08% better than Data-logger as a client. From the data processing, it was found that the highest activity of students was the interest in the activities of language institutions (95.92%), followed by religious activities (95.83%), teaching and earning activities (93.88%), and reading (79.59 %)]]>
<![CDATA[Penerapan Deskriptor Warna Dominan untuk Temu Kembali Citra Busana pada Peranti Bergerak ]]>
<![CDATA[Yustina Dhyanti]]>;
<![CDATA[Khairul Munadi]]>;
<![CDATA[Fitri Arnia]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 12, No 3 (2016) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.17529/jre.v12i3.5701
<![CDATA[Nowadays, clothes with various designs and color combinations are available for purchasing through an online shop, which is mostly equipped with keyword-based item retrieval. Here, the object in the online database is retrieved based on the keyword inputted by the potential buyers. The keyword-based search may bring potential customers on difficulties to describe the clothes they want to buy. This paper presents a new searching approach, using an image instead of text, as the query into an online shop. This method is known as content-based image retrieval (CBIR). Particularly, we focused on using color as the feature in our Muslimah clothes image retrieval. The dominant color descriptor (DCD) extracts the wardrobe's color. Then, image matching is accomplished by calculating the Euclidean distance between the query and image in the database, and the last step is to evaluate the performance of the DWD by calculating precision and recall. To determine the performance of the DCD in extracting color features, the DCD is compared with another color descriptor, that is dominant color correlogram descriptor (DCCD). The values of precision and recall of DCD ranged from 0.7 to 0.9 while the precision and recall of DCCD ranged from 0.7 to 0.8. These results showed that the DCD produce a superior performance compared to DCCD in retrieving a set of clothing image, either plain or patterned colored clothes.]]>
<![CDATA[Substraksi Latar Menggunakan Nilai Mean Untuk Klasifikasi Kendaraan Bergerak Berbasis Deep Learning ]]>
<![CDATA[Ilal Mahdi]]>;
<![CDATA[Kahlil Muchtar]]>;
<![CDATA[Fitri Arnia]]>;
<![CDATA[Tia Ernita]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 18, No 2 (2022) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.17529/jre.v18i2.25224
<![CDATA[Moving object detection systems have been widely used in everyday life. Currently, research in the field of background subtraction is still being carried out to achieve maximum accuracy results. This study aims to model the background subtraction of an image using the mean value with the concept of non-overlapping block. Furthermore, the background abstraction results will be used in deep learning-based moving object detection. Specifically, the input image will be divided into several blocks, then the mean value of each block will be calculated to later produce a binary block (binary map). The binary blocks that have been generated will be used as input for background modeling. The background model aims to separate moving objects from the background in the input image. The resulting moving object (object localization) will be sent to the object classification stage using deep learning. The dataset used in this study is CDNet 2014. The results of the study were able to produce a more accurate moving object detection system. Quantitative tests carried out resulted in an accuracy of above 90%.]]>
<![CDATA[Fine Tuning CNN Pre-trained Model Based on Thermal Imaging for Obesity Early Detection ]]>
<![CDATA[Hendrik Leo]]>;
<![CDATA[Fitri Arnia]]>;
<![CDATA[Khairul Munadi]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 18, No 1 (2022) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.17529/jre.v18i1.25100
<![CDATA[Obesity is a complex disease that causes serious impact health, such as diabetes mellitus, cardiovascular disease, cancer, and stroke. An early obesity diagnosis/ detection method is required to prevent the increasing number of obese people. This study aims to: (i) fine-tune the pre-trained Convolutional Neural Network (CNN) models to build an early detection of obesity and (ii) evaluate the model performance in terms of classifying performance, computation speed, and learning performance. The thermal images acquisition procedure was conducted with 18 normal subjects and 15 obese subjects to build a thermal images dataset of obesity. Pre-trained CNN models: VGG19, MobileNet, ResNet152V, and DenseNet201 were modified and trained using the acquired dataset as the input. The training results show that the DenseNet201 model outperformed other models regarding classifying accuracy: 83.33 % and learning performances. At the same time, the MobileNet model outperformed other models in terms of computation speed with training elapsed time: 12 seconds/epoch. The proposed DenseNet201 model was suitable for implementation as an early screening system of obesity for health workers or physicians. Meanwhile, the proposed MobileNet model was suitable for mobile applications' early detection/diagnosis of obesity.]]>
<![CDATA[Identifikasi Tingkat Kematangan Kelapa Sawit Berbasis Pencitraan Termal ]]>
<![CDATA[Khusnul Azima]]>;
<![CDATA[Khairul Munadi]]>;
<![CDATA[Fitri Arnia]]>;
<![CDATA[Maulisa Oktiana]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 15, No 1 (2019) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.17529/jre.v15i1.12963
<![CDATA[Indonesia is the biggest producer of palm oil (Elaeis guineenis jacq). The palm tree is a primary commodity that posses a high economic value. Palm oil must be considered in terms of quality to produce optimal and high-quality oil. Previously, the stipulation of the palm tree characterization used manual and visual image utilization method; it may have weaknesses due to the dependency of individual sorting and coruscation factor. Therefore, this research is aimed to improve the performance of the previous method in identifying the ripeness of palm tree based on thermal imaging. The excess of thermal imaging was not related to the coruscation since the level of ripeness was both determined by the temperature and colour. The detection method of this research deployed the colour-based features that are Dominant Colour Descriptor and Color Moment. The DCD and Color Moment was the input to the K-Nearest Neighbor (KNN) method. The percentage of identification rate was 89%, and the identification of oil palm maturity level using thermal imaging is more efficient because it is done without human intervention and does not depend on lighting assistance compared to manual method and method of using RGB visual images.]]>
<![CDATA[Sistem Multi-Sensor Nirkabel Berbasis RFID Untuk Pemantauan Keaktifan Siswa ]]>
<![CDATA[Zakiah Zakiah]]>;
<![CDATA[Yuwaldi Away]]>;
<![CDATA[Fitri Arnia]]>;
<![CDATA[Andri Novandri]]>
<![CDATA[ Jurnal Rekayasa Elektrika Vol 15, No 3 (2019) ]]>
Publisher : <![CDATA[Universitas Syiah Kuala ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.17529/jre.v15i3.14107
<![CDATA[This study aims to design a multisensor observation system, develop a microcontroller-based prototype with ESP8266 and RFID modules, and analyze the performance of the prototype. From the testing carried out by tagging each time students do activities, the client tag data will be sent to the server, and the results are displayed PLX-DAQ. With the 50 tag cards that have registered the IDs of each student, it shows that those who attend the schedule will be given the logic "1" (otherwise logic "0"), and attendance data will be obtained by calculating the number of attendance of students in four types of activities in four locations. The data is transmitted to Data-loggers through two configurations, namely Data-logger as the client (indirect), and Data-logger as a server (direct). From the two configurations, it was found that the configuration of Data-logger as a server had a performance of 19.08% better than Data-logger as a client. From the data processing, it was found that the highest activity of students was the interest in the activities of language institutions (95.92%), followed by religious activities (95.83%), teaching and earning activities (93.88%), and reading (79.59 %)]]>
