1 10 41 https://repository.horizon.ac.id/files/original/ae58de5584f71c74b556d0f37a627e61.pdf 32e1511700283c8220b11a9a170d7748 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource VOL. 19, NO. 3 2021 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource TELKOMNIKA Telecommunication, Computing, Electronics and Control A comparative analysis of automatic deep neural networks for image retrieval Subject The topic of the resource Content-based image retrieval Convolutional neural networks Image classification Image retrieval deep learning Description An account of the resource Feature descriptor and similarity measures are the two core components in content-based image retrieval and crucial issues due to “semantic gap” between human conceptual meaning and a machine low-level feature. Recently, deep learning techniques have shown a great interest in image recognition especially in extracting features information about the images. In this paper, we investigated, compared, and evaluated different deep convolutional neural networks and their applications for image classification and automatic image retrieval. The approaches are: simple convolutional neural network, AlexNet, GoogleNet, ResNet-50, Vgg-16, and Vgg-19. We compared the performance of the different approaches to prior works in this domain by using known accuracy metrics and analyzed the differences between the approaches. The performances of these approaches are investigated using public image datasets corel 1K, corel 10K, and Caltech 256. Hence, we deduced that GoogleNet approach yields the best overall results. In addition, we investigated and compared different similarity measures. Based on exhausted mentioned investigations, we developed a novel algorithm for image retrieval. Creator An entity primarily responsible for making the resource Hanan A. Al-Jubouri, Sawsan M. Mahmmod Source A related resource from which the described resource is derived http://journal.uad.ac.id/index.php/TELKOMNIKA Date A point or period of time associated with an event in the lifecycle of the resource Sep 20, 2020 Contributor An entity responsible for making contributions to the resource peri irawan Format The file format, physical medium, or dimensions of the resource pdf Language A language of the resource english Type The nature or genre of the resource text Content-based image retrieval convolutional neural networks Image classification Image retrieval deep learning Jurnal Nasional Informatika https://repository.horizon.ac.id/files/original/323bb46e2b5c1650d564d05391a14723.pdf fe51915ee8523665c8b197ea9c99267f Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource VOL. 19, NO. 3 2021 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource TELKOMNIKA Telecommunication, Computing, Electronics and Control A comprehensive review of vehicle detection using computer vision Subject The topic of the resource Computer vision GMM Intelligent transport system KDE Vehicle detection Description An account of the resource A crucial step in designing intelligent transport systems (ITS) is vehicle detection. The challenges of vehicle detection in urban roads arise because of camera position, background variations, occlusion, multiple foreground objects as well as vehicle pose. The current study provides a synopsis of state-of-the-art vehicle detection techniques, which are categorized according to motion and appearance-based techniques starting with frame differencing and background subtraction until feature extraction, a more complicated model in comparison. The advantages and disadvantages among the tech- niques are also highlighted with a conclusion as to the most accurate one for vehicle detection. Creator An entity primarily responsible for making the resource Aymen Fadhil Abbas, Usman Ullah Sheikh, Fahad Taha AL-Dhief, Mohd Norzali Haji Mohd Source A related resource from which the described resource is derived http://journal.uad.ac.id/index.php/TELKOMNIKA Date A point or period of time associated with an event in the lifecycle of the resource Dec 3, 2020 Contributor An entity responsible for making contributions to the resource peri irawan Format The file format, physical medium, or dimensions of the resource pdf Language A language of the resource english Type The nature or genre of the resource text Computer Vision GMM Intelligent transport system Jurnal Nasional Informatika KDE Vehicle detection https://repository.horizon.ac.id/files/original/c5ceae8484ea4dbe694122ef48fd68b0.pdf aaa0462f049005012fafe7d8fcfa1a6f Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource VOL. 19, NO. 3 2021 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource TELKOMNIKA Telecommunication, Computing, Electronics and Control An efficient method for stamps recognition using Haar wavelet sub-bands Subject The topic of the resource Energy Haar wavelet Low order moment Recognition rate Stamp recognition Description An account of the resource The problem facing certain organizations such as insurance companies and government institutions where a huge amount of documents is handled every day, hence an automated stamp recognition system is required. The image of the stamp may be on a different background, with different sizes, and suffers from rotating in different directions, also, the appearance of soft areas (patches) or small points as noise. Thus, the main objective of this paper is to extract and recognize the color stamp image. This paper proposed a method to recognize stamps, by using a technique named Haar wavelet sub-bands. The devised method has four stages: 1) extracts the stamp image; 2) preprocessing the image; 3) feature extraction; and 4) matching. This paper is implemented using C sharp (Microsoft Visual Studio 2012) programming language. The experiments conducted on a stamp dataset showed that the proposed method has a great capability to recognize stamps when using Haar wavelet transform with two sets of features (i.e., 100% recognition rate for energy features and 99.93% recognition rate for low order moment). Creator An entity primarily responsible for making the resource Maha A. Rajab, Loay E. George Source A related resource from which the described resource is derived http://journal.uad.ac.id/index.php/TELKOMNIKA Date A point or period of time associated with an event in the lifecycle of the resource Nov 25, 2020 Contributor An entity responsible for making contributions to the resource peri irawan Format The file format, physical medium, or dimensions of the resource pdf Language A language of the resource english Type The nature or genre of the resource text Energy Haar wavelet Jurnal Nasional Informatika Low order moment Recognition rate Stamp recognition https://repository.horizon.ac.id/files/original/63e7f87d59254ed803b4d0a3dcb7b6ae.pdf 38c90b2aae34024164a99ad49ca8e718 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource VOL. 19, NO. 3 2021 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource TELKOMNIKA Telecommunication, Computing, Electronics and Control Author identification in bibliographic data using deep neural networks Subject The topic of the resource Author name disambiguation Bibliographic data Deep neural networks Homonym Synonym Description An account of the resource Author name disambiguation (AND) is a challenging task for scholars who mine bibliographic information for scientific knowledge. A constructive approach for resolving name ambiguity is to use computer algorithms to identify author names. Some algorithm-based disambiguation methods have been developed by computer and data scientists. Among them, supervised machine learning has been stated to produce decent to very accurate disambiguation results. This paper presents a combination of principal component analysis (PCA) as a feature reduction and deep neural networks (DNNs), as a supervised algorithm for classifying AND problems. The raw data is grouped into four classes, i.e., synonyms, homonyms, homonyms- synonyms, and non-homonyms-synonyms classification. We have taken into account several hyperparameters tuning, such as learning rate, batch size, number of the neuron and hidden units, and analyzed their impact on the accuracy of results. To the best of our knowledge, there are no previous studies with such a scheme. The proposed DNNs are validated with other ML techniques such as Naïve Bayes, random forest (RF), and support vector machine (SVM) to produce a good classifier. By exploring the result in all data, our proposed DNNs classifier has an outperformed other ML technique, with accuracy, precision, recall, and F1-score, which is 99.98%, 97.98%, 97.86%, and 99.99%, respectively. In the future, this approach can be easily extended to any dataset and any bibliographic records provider. Creator An entity primarily responsible for making the resource Firdaus, Siti Nurmaini, Reza Firsandaya Malik, Annisa Darmawahyuni, Muhammad Naufal Rachmatullah, Andre Herviant Juliano, Tio Artha Nugraha, Varindo Ockta Keneddi Putra Source A related resource from which the described resource is derived http://journal.uad.ac.id/index.php/TELKOMNIKA Date A point or period of time associated with an event in the lifecycle of the resource Aug 31, 2020 Contributor An entity responsible for making contributions to the resource peri irawan Format The file format, physical medium, or dimensions of the resource pdf Language A language of the resource english Type The nature or genre of the resource text Author name disambiguation Bibliographic data Deep neural networks Homonym Jurnal Nasional Informatika Synonym https://repository.horizon.ac.id/files/original/55a022f19cc5f8967e0e6d2f4659adec.pdf ddbf47a43858c07b81cb150ff13ea485 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource VOL. 19, NO. 3 2021 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource TELKOMNIKA Telecommunication, Computing, Electronics and Control Bigram feature extraction and conditional random fields model to improve text classification clinical trial document Subject The topic of the resource Clinical trials Conditional random fields Deep learning Text classification Description An account of the resource In the field of health and medicine, there is a very important term known as clinical trials. Clinical trials are a type of activity that studies how the safest way to treat patients is. These clinical trials are usually written in unstructured free text which requires translation from a computer. The aim of this paper is to classify the texts of cancer clinical trial documents consisting of unstructured free texts taken from cancer clinical trial protocols. The proposed algorithm is conditional random Fields and bigram features. A new classification model from the cancer clinical trial document text is proposed to compete with other methods in terms of precision, recall, and f-1 score. The results of this study are better than the previous results, namely 88.07 precision, 88.05 recall and f-1 score 88.06. Creator An entity primarily responsible for making the resource Jasmir Jasmir, Siti Nurmaini, Reza Firsandaya Malik, Bambang Tutuko Source A related resource from which the described resource is derived http://journal.uad.ac.id/index.php/TELKOMNIKA Date A point or period of time associated with an event in the lifecycle of the resource Oct 29, 2020 Contributor An entity responsible for making contributions to the resource peri irawan Format The file format, physical medium, or dimensions of the resource pdf Language A language of the resource english Type The nature or genre of the resource text Clinical trials Conditional random fields deep learning Jurnal Nasional Informatika text classification https://repository.horizon.ac.id/files/original/d30deb0f04684c5e81323c52074a982b.pdf 1c3f0b48d370836963754adfc4c39c5d Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource VOL. 19, NO. 3 2021 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource TELKOMNIKA Telecommunication, Computing, Electronics and Control Biomass estimation model for peat swamp forest ecosystem using light detection and ranging Subject The topic of the resource Allometry Biomass Canopy cover LiDAR Peat Swamp forest Description An account of the resource Peat swamp forest plays a very important role in absorbing and storing large amounts of terrestrial carbon, both above ground and in the soil. There has been a lot of research on the estimation of the amount of biomass above the ground, but a little on peat swamp ecosystems using light detection and ranging (LiDAR) technology, especially in Indonesia. The purpose of this study is to build a biomass estimation model based on LiDAR data. This technology can obtain information about the structure and characteristics of any vegetation in detail and in real time. Data was obtained from the East Kotawaringin Regency, Central Kalimantan. Biomass field was generated from the available allometry, and Point cloud of LiDAR was extracted into canopy cover (CC), and data on tree height, using the FRCI and local maxima (LM) method, respectively. The CC and tree height data were then used as independent variables in building the regression model. The best-fitted model was obtained after the scoring and ranking of several regression forms such as linear, quadratic, power, exponential and logarithmic. This research concluded that the quadratic regression model, with R2 of 72.16% and root mean square error (RMSE) of 0.0003% is the best-fitted estimation model (BK). Finally, the biomass value from the models was 244.510 tons/ha. Creator An entity primarily responsible for making the resource Muhamad Rizal, M. Buce Saleh, Lilik Budi Prasetyo Source A related resource from which the described resource is derived http://journal.uad.ac.id/index.php/TELKOMNIKA Date A point or period of time associated with an event in the lifecycle of the resource Nov 25, 2020 Contributor An entity responsible for making contributions to the resource peri irawan Format The file format, physical medium, or dimensions of the resource pdf Language A language of the resource english Type The nature or genre of the resource text Allometry Biomass Canopy cover Jurnal Nasional Informatika LiDAR Peat Swamp forest https://repository.horizon.ac.id/files/original/fc8a00648139873dd621c8fa4e5216c9.pdf 9259d981de739f34dfcc1b35d8b6e497 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource VOL. 19, NO. 3 2021 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource TELKOMNIKA Telecommunication, Computing, Electronics and Control Comparison of two methods on vector space model for trust in social commerce Subject The topic of the resource Data mining Improved TF-IDF method Information retrieval Online social commerce TF-IDF method Web mining Description An account of the resource The study of dealing with searching information in documents within web pages is information retrieval (IR). The user needs to describe information with comments or reviews that consists of a number of words. Discovering weight of an inquiry term is helpful to decide the significance of a question. Estimation of term significance is a basic piece of most information retrieval approaches and it is commonly chosen through term frequency-inverse document frequency (TF-IDF). Also, improved TF-IDF method used to retrieve information in web documents. This paper presents comparison of TF-IDF method and improved TF-IDF method for information retrieval. Cosine similarity method calculated on both methods. The results of cosine similarity method on both methods compared on the desired threshold value. The relevance documents of TF-IDF method are more extracted than improved TF-IDF method. Creator An entity primarily responsible for making the resource Hla Sann Sint, Khine Khine Oo Source A related resource from which the described resource is derived http://journal.uad.ac.id/index.php/TELKOMNIKA Date A point or period of time associated with an event in the lifecycle of the resource Nov 25, 2020 Contributor An entity responsible for making contributions to the resource peri irawan Format The file format, physical medium, or dimensions of the resource pdf Language A language of the resource english Type The nature or genre of the resource text data mining Improved TF-IDF method Information retrieval Jurnal Nasional Informatika Online social commerce TF-IDF method Web mining https://repository.horizon.ac.id/files/original/3b9d5444d7f7659fac107701ac5b0158.pdf ef2642e2336613671ebd0bbaf8361df6 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource VOL. 19, NO. 3 2021 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource TELKOMNIKA Telecommunication, Computing, Electronics and Control Customer application protocol for data transfer between embedded processor and microcontroller systems Subject The topic of the resource Customer application protocol Embedded processor system Ethernet Lightweight IP Description An account of the resource This paper develops a new customer application protocol (CAP) to improve the efficiency of transferring data between embedded processor and microcontroller systems. The established protocol is characterized by its fidelity and simplicity for using a small header to control and monitor the data flow between the two systems. This is achieved by constructing an embedded processor system with an Ethernet intellectual property (IP) core featured by lightweight IP (lwIP) to settle a connection with a microcontroller device. The embedded system is configured on spartan6E FPGAs slice. The system performance is tested by transferring audio samples and displaying them on chipscope media. The performance test of the designed embedded system with the developed customer application protocol showed fast, efficient and high precision data exchange between the processor and microcontroller systems. Creator An entity primarily responsible for making the resource Mazin R. Khalil, Laith A. Mohammed, Omar N. Yousif Source A related resource from which the described resource is derived http://journal.uad.ac.id/index.php/TELKOMNIKA Date A point or period of time associated with an event in the lifecycle of the resource Nov 25, 2020 Contributor An entity responsible for making contributions to the resource peri irawan Format The file format, physical medium, or dimensions of the resource pdf Language A language of the resource english Type The nature or genre of the resource text Customer application protocol Embedded processor system Ethernet Jurnal Nasional Informatika Lightweight IP https://repository.horizon.ac.id/files/original/132135abc547f0739ae748216c4c37ca.pdf 74fc94202c2967bb20261202ea202309 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource VOL. 19, NO. 3 2021 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource TELKOMNIKA Telecommunication, Computing, Electronics and Control Deep fingerprint classification network Subject The topic of the resource Classification Deep learning Fingerprint Description An account of the resource Fingerprint is one of the most well-known biometrics that has been used for personal recognition. However, faked fingerprints have become the major enemy where they threat the security of this biometric. This paper proposes an efficient deep fingerprint classification network (DFCN) model to achieve accurate performances of classifying between real and fake fingerprints. This model has extensively evaluated or examined parameters. Total of 512 images from the ATVS-FFp_DB dataset are employed. The proposed DFCN achieved high classification performance of 99.22%, where fingerprint images are successfully classified into their two categories. Moreover, comparisons with state-of-art approaches are provided. Creator An entity primarily responsible for making the resource Abdulsattar M. Ibrahim, Abdulrahman K. Eesee, Raid Rafi Omar Al-Nima Source A related resource from which the described resource is derived http://journal.uad.ac.id/index.php/TELKOMNIKA Date A point or period of time associated with an event in the lifecycle of the resource Nov 25, 2020 Contributor An entity responsible for making contributions to the resource peri irawan Format The file format, physical medium, or dimensions of the resource pdf Language A language of the resource english Type The nature or genre of the resource text classification deep learning Fingerprint Jurnal Nasional Informatika https://repository.horizon.ac.id/files/original/c779e6eb1d69225beb70e4fcf759f1b6.pdf 760076f181ee555d9421f36ac0e22592 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource VOL. 19, NO. 3 2021 Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource TELKOMNIKA Telecommunication, Computing, Electronics and Control Design a compact CPW monopole antenna on rubber substrate for ISM band application Subject The topic of the resource CPW-fed monopole antenna CST microwave studio ISM band Rubber substrate Description An account of the resource One of the most challenging works on compact antenna design is to maintain the flexibility orientation. This paper demonstrates a coplanar waveguide (CPW) fed monopole antenna with rubber substrate at 2.45 GHz center frequency for ISM band application. The proposed antenna attained the realized gain at 4.06 dB with the radiation efficiency around 90% at peak value and the bandwidth of 541.5 MHz. The antenna was designed using the CPW structure. CST microwave studio applied to design the proposed antenna simulation. The main purposed of this study is to improve the antenna performances specially the bandwidth, gain, and radiation efficiency. Moreover, another aim of that antenna design is to reduce the antenna size and thickness upon the existing related design with rubber substrate. Creator An entity primarily responsible for making the resource Nazmus Sakib, S. Noorjannah Ibrahim, M. M. Hasan Mahfuz , S. Yasmin Mohamad Source A related resource from which the described resource is derived http://journal.uad.ac.id/index.php/TELKOMNIKA Date A point or period of time associated with an event in the lifecycle of the resource Nov 25, 2020 Contributor An entity responsible for making contributions to the resource peri irawan Format The file format, physical medium, or dimensions of the resource pdf Language A language of the resource english Type The nature or genre of the resource text CPW-fed monopole antenna CST microwave studio ISM band Jurnal Nasional Informatika Rubber substrate