The Javanese Letters Classifier with Mobile Client-Server Architecture and Convolution Neural Network Method

Harjoseputro, Yulius; Handarkho, Yonathan Dri; Adie, Heronimus Tresy Renata

doi:10.3991/ijim.v13i12.11492

Cited by 6 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The size of model is another factor considered apart from the accuracy and loss rate. As addressed in [17,24,67], flexibility, computation ability, and capacity are important factors when applying deep learning networks on mobile platforms or portable devices [68]. Huge computation and millions of parameters are needed in large models [69], while mobile phones are constrained by memory size [17], and not recommended to use a large model with complex computation [68], the comparison regarding the size of model is also presented in the right column in Tab.…”

Section: Comparison Of Model Sizementioning

confidence: 99%

An Improved Transfer-Learning for Image-Based Species Classification of Protected Indonesians Birds

Yang¹,

Harjoseputro²,

Hu³

et al. 2022

Computers, Materials &Amp; Continua

Self Cite

View full text Add to dashboard Cite

This research proposed an improved transfer-learning bird classification framework to achieve a more precise classification of Protected Indonesia Birds (PIB) which have been identified as the endangered bird species. The framework takes advantage of using the proposed sequence of Batch Normalization Dropout Fully-Connected (BNDFC) layers to enhance the baseline model of transfer learning. The main contribution of this work is the proposed sequence of BNDFC that can be applied to any Convolutional Neural Network (CNN) based model to improve the classification accuracy, especially for image-based species classification problems. The experiment results show that the proposed sequence of BNDFC layers outperform other combination of BNDFC. The addition of BNDFC can improve the model's performance across ten different CNN-based models. On average, BNDFC can improve by approximately 19.88% in Accuracy, 24.43% in F-measure, 17.93% in G-mean, 23.41% in Sensitivity, and 18.76% in Precision. Moreover, applying fine-tuning (FT) is able to enhance the accuracy by 0.85% with a smaller validation loss of 18.33% improvement. In addition, MobileNetV2 was observed to be the best baseline model with the lightest size of 35.9 MB and the highest accuracy of 88.07% in the validation set.

show abstract

Section: Comparison Of Model Sizementioning

confidence: 99%

An Improved Transfer-Learning for Image-Based Species Classification of Protected Indonesians Birds

Yang¹,

Harjoseputro²,

Hu³

et al. 2022

Computers, Materials &Amp; Continua

Self Cite

View full text Add to dashboard Cite

show abstract

“…The testing is functionality, performance test and usability test. Therefore, Harjoseputro, Handrarkho and Adie [11] according, the performance on mobile devices and problems resulting from the limitation of computation resource on the platform that proposed a 2-tier architecture by placing the mobile app as a client that invokes a Javanese letters classifier service, which is based on CNN, and implemented in the webserver through the Application Program Interface (API).…”

Section: Literature Reviewmentioning

confidence: 99%

Readability Evaluation of Variable Handwritten Fonts on Different Screen Sizes Using Fuzzy Logic

Bratić

Loknar

Ivančević

2022

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

According to the OpenType standard, variable font is a single font file which contains all style versions of one typeface family, as opposed to standard font families that use different files for each style version. Therefore, they are suitable for use on web because one file with all the necessary typeface styles is significantly smaller in size than classic families with multiple files. This shortens the font loading time, which enables wide range of typographical use on various devices. This paper investigates the readability of handwritten variable fonts in a responsible web environment on four screen sizes: extra small, small, medium, and large. Seven letter cuts were made from basic monoline handwritten font: thin, ultra-light, light, regular, semi-bold, bold, and ultra-bold. This paper presents model of readability evaluation using the fuzzy logic based postprocessing method for segmentation values related to evaluation criteria. Linguistic variable’s values are used to rate readability level against each of the criteria i.e., attributes. Prototype of a variable handwritten fonts are tested in responsive web environment, using CSS technology. The results show that readability evaluation has measurable output because the score combine various numeral factors affecting the readability of particular letter cut. Also, the results indicate that this type of font is not suitable for displays on extra small and medium screens such as mobile phones and tablets. That knowledge opens advanced possibilities to designers when designing for web because variable handwritten fonts are relatively simple, uniform and easily manageable. Using of proposed model in short time can show readability level of some font type on a new web.

show abstract

“…Dalam hal ini, Sandbox juga sering digunakan untuk mengeksekusi kode yang belum teruji [4]. Sistem Sandbox dibuat menjadi sebuah web service berbasis REST API agar dapat melakukan komunikasi antar aplikasi [5] [6]. Tentunya hal ini digunakan untuk membantu tahap pengembangan maupun pengujian pengujian, sehingga segala bentuk pemanggilan terhadap pihak ketiga dapat dialihkan ke sistem Sandbox.…”

Section: Pendahuluanunclassified

Golang and NSG Implementation in REST API Based Third-Party Sandbox System

Kristanto

Harjoseputro

Samodra

2020

RESTI

Self Cite

View full text Add to dashboard Cite

A good application development requires a testing phase to ensure there are no errors before it’s released to public. But testing phase becomes difficult if the application development involves features from third parties. The idea to resolve the problem for Dhanapala application under the auspices of PT. Semangat Gotong Royong is to make the Sandbox system which is a system designed to resemble the characteristics of a third party. The Sandbox system will be developed into a REST API and written using the Golang programming language. In conducting communications with other systems New Simple Queue (NSQ) is also used that can support concurrency and prevent data transmission failures. As a result, the Sandbox system can receive requests and will process responses that are similar to functions from third parties. All forms of feature calls to third parties can be transferred to the Sandbox system so that all the data needs on some functions involving third parties can be fulfilled and the Dhanapala application can be run without its dependence on third parties

show abstract

The Javanese Letters Classifier with Mobile Client-Server Architecture and Convolution Neural Network Method

Cited by 6 publications

References 23 publications

An Improved Transfer-Learning for Image-Based Species Classification of Protected Indonesians Birds

An Improved Transfer-Learning for Image-Based Species Classification of Protected Indonesians Birds

Readability Evaluation of Variable Handwritten Fonts on Different Screen Sizes Using Fuzzy Logic

Golang and NSG Implementation in REST API Based Third-Party Sandbox System

Contact Info

Product

Resources

About