cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
Jurnal Informatika
Published by Universitas Ahmad Dahlan
ISSN : 19780524     EISSN : 25286374     DOI : 10.26555
Core Subject : Science,
Computer Science & IT
Arjuna Subject : -
Articles 419 Documents
 38   39   40   41   42 
Hyper Parameter Tuning of Multilayer Convolutional Network and Augmentation Method for Classification Motive of Batik Agus Nursikuwagus; tono hartono; M A Nurwicaksono; M M Choir; M A Saputri
Jurnal Informatika Vol 17, No 1 (2023): January 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jifo.v17i1.a25823

Abstract

The purpose of this research is to create a batik motive image classification system to make it easier for the public to know the name of a type of batik motive. In carrying out this research, a quantitative method was used with seven kinds of batik motives that were augmented first, where 70% of the dataset was used for training and 30% for testing so that the accuracy and precision of the system were obtained. The result of this research is that the accuracy and precision of the system in classifying batik motive images is 0.985 or 98.5%. This high accuracy and precision were obtained because the quality of the previous dataset was improved by augmenting geometric and photometric. The machine learning method used was a Convolutional Neural Network which in previous studies also provided the highest accuracy and precision. The results of this study can be used for various purposes such as marketing, cultural reservation, and science.
A Hybrid Approch Tomato Diseases Detection At Early Stage Arif Ullah; Muhammad Azeem khalid; Dorsaf Sebai; Tanweer Alam
Jurnal Informatika Vol 17, No 1 (2023): January 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jifo.v17i1.a24759

Abstract

 In traditional farming practice, skilled people are hired to manually examine the land and detect the presence of diseases through visual inspection, but the visual inspection method is ineffective. High accuracy of disease detection is one of the most important factors in crop production and reducing crop losses. Meanwhile, the evolution of deep convolutional neural networks for image classification has rapidly improved the accuracy of object detection, classification and system recognition. Previous tomato detection methods based on faster region convolutional neural network (RCNN) are less efficient in terms of accuracy. Researchers have used many methods to detect tomato leaf diseases, but their accuracy is not optimal. This study presents a Faster RCNN-based deep learning model for the detection of three tomato leaf diseases (late blight, mosaic virus, and leaf septoria). The methodology presented in this paper consists of four main steps. The first step is pre-processing. At the second stage, segmentation was done using fuzzy C Means. In the third step, feature extraction was performed with ResNet 50. In the fourth step, classification was performed with Faster RCNN to detect tomato leaf diseases. Two evaluation parameters precision and accuracy are used to compare the proposed model with other existing approaches. The proposed model has the highest accuracy of 98.6% in detecting tomato leaf diseases. In addition, the work can be extended to train the model for other types of tomato diseases, such as leaf mold, spider mites, as well as to detect diseases of other crops, such as potatoes, peanuts, etc.
5G-Enabled Tactile Internet for smart cities: vision, recent developments, and challenges Alam, Tanweer
Jurnal Informatika Vol. 13 No. 2 (2019): July 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The Tactile Internet (TI) is an emerging technology next to the Internet of Things (IoT). It is a revolution to develop smart cities, communities, and cultures in the future. This technology will allow the real-time interaction between humans and machines as well as machine-to-machine with the 1ms challenge to achieve in round trip latency. The term TI is defined by the International Telecommunication Union (ITU) in August 2014. The TI provides a fast, reliable, secure and available internet network that is the requirements of the smart cities in 5G. Tactile internet can develop the part of the world where the machines are strong, and humans are weak. It increases the power of machines so that the value of human power will increase automatically. In this framework, we have presented the idea of tactile internet for the next generation of smart cities. This research will provide a high-performance reliable framework for the internet of smart devices to communicate with each other in a real-time (1ms round trip) using IEEE 1918.1 standard. The objective of this research is expected to bring a new dimension in the research of smart cities.
Crowd Level Monitoring System Using the R-CNN Mask Model rahadewan, rahadewan; Adhi Prahara
Jurnal Informatika Vol. 18 No. 3 (2024): September 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jifo.v18i3.a27275

Abstract

A crowd level detection system is a system that identifies crowds based on the number of visitors. This system makes it easy to calculate visitors automatically, and can provide information on crowd levels. In this research, we overcome the problem of inefficient manual supervision at Beringharjo Market by implementing human object detection technology. Using the Mask R-CNN method, this research aims to automatically identify and count the number of market visitors, improve monitoring and analysis of crowd levels. Mask R-CNN allows identifying people with high accuracy, precisely measuring crowds, and adding ROI lines to make calculations easier. Comparison with SSD shows Mask R-CNN has slightly lower accuracy with an accuracy of 0.8333 with SSD getting an accuracy of 0.927, but better object understanding. Mask R-CNN has a lower frame rate of 2 fps on average with SSD getting an average of 25 fps compared to SSD. The results of this research have the potential to increase the efficiency of crowd monitoring and analysis at Beringharjo Market, assisting market management in making strategic decisions and better planning.
Youtube Comment Sentiment Classification System With Naive Bayes TF-IDF Using Laravel IDX normawati, dwi; Rendy Saputra; Hendrik Fery Herdiatmoko
Jurnal Informatika Vol. 19 No. 1 (2025): January 2025
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jifo.v19i1.a30441

Abstract

The development of technology has enhanced social interactions through social media platforms like YouTube, making user comments a vital data source for sentiment analysis. One emerging issue is the lack of understanding regarding consumer perceptions of smartphone brands in Indonesia, which can be explored further through YouTube comments. This study aims to build a sentiment classification system for YouTube comments related to smartphone brands in Indonesia in 2024 using the Naïve Bayes Classifier algorithm with TF-IDF weighting and FastText features. Data was collected using the YouTube Data API, followed by preprocessing, labeling, and feature extraction stages. The model was optimized through GridSearchCV and evaluated with a Confusion Matrix, achieving an accuracy of up to 97%. The system was implemented as a Laravel-based web application, providing an interface for dataset management, model training, and sentiment visualization. This research also includes the integration of IDX Projects with Laravel, enabling more efficient data management and interactive presentation of sentiment analysis results. The findings demonstrate the effectiveness of this method in classifying positive and negative sentiments, which can help users understand consumer preferences for various smartphone brands.
A Hybrid Approch Tomato Diseases Detection At Early Stage Ullah, Arif; khalid, Muhammad Azeem; Sebai, Dorsaf; Alam, Tanweer
Jurnal Informatika Vol. 17 No. 1 (2023): January 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

 In traditional farming practice, skilled people are hired to manually examine the land and detect the presence of diseases through visual inspection, but the visual inspection method is ineffective. High accuracy of disease detection is one of the most important factors in crop production and reducing crop losses. Meanwhile, the evolution of deep convolutional neural networks for image classification has rapidly improved the accuracy of object detection, classification and system recognition. Previous tomato detection methods based on faster region convolutional neural network (RCNN) are less efficient in terms of accuracy. Researchers have used many methods to detect tomato leaf diseases, but their accuracy is not optimal. This study presents a Faster RCNN-based deep learning model for the detection of three tomato leaf diseases (late blight, mosaic virus, and leaf septoria). The methodology presented in this paper consists of four main steps. The first step is pre-processing. At the second stage, segmentation was done using fuzzy C Means. In the third step, feature extraction was performed with ResNet 50. In the fourth step, classification was performed with Faster RCNN to detect tomato leaf diseases. Two evaluation parameters precision and accuracy are used to compare the proposed model with other existing approaches. The proposed model has the highest accuracy of 98.6% in detecting tomato leaf diseases. In addition, the work can be extended to train the model for other types of tomato diseases, such as leaf mold, spider mites, as well as to detect diseases of other crops, such as potatoes, peanuts, etc.
Utilization of the PROMETHEE algorithm to determine the suitability of the atmospheric environment in traditional buildings Distia Diva, Ana; Winiarti, Sri; Miksa Mardhia, Murein
Jurnal Informatika Vol. 17 No. 1 (2023): January 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The village house is an example of a traditional building. The village house is currently used as a community residence. The life of the village house still protects and maintains ancestral customs, including in the form of house architecture. In the process of building a village house, there is one aspect that is used, such as an appropriate environmental atmosphere. Where the building must maintain the beauty of the environment. The importance of paying attention to the atmospheric environment is because the characteristics of these traditional buildings are not lost, especially in the atmospheric environment as historical evidence. Thus, to develop village house buildings, there is a lack of information related to the traditional buildings themselves, such as the past environmental conditions around traditional buildings, road conditions around buildings, beauty and distance between buildings, and building models around conventional houses, to achieve the goal, documentation of the necessary knowledge related to the atmospheric environment for traditional buildings that still maintains or provides an atmosphere like the old days. The research will be conducted using the Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE) algorithm. The research method is by conducting a literature study, observation, and documentation. Observations and documentation were carried out to collect data in the form of 300 photos of Kampung Rumah in Borobudur, from the data in the form of 300 photos, 9 (nine) were collected. System testing using System Usability Scale (SUS), Black-box, and Expert Judgment. The result of the research is a system for determining the suitability of the environmental atmosphere for village houses in Borobudur using the PROMETHEE algorithm. This research is expected to help determine the village house environment in Borobudur by displaying the final results in the form of outranking and the system test value of 85%.
Hyper Parameter Tuning of Multilayer Convolutional Network and Augmentation Method for Classification Motive of Batik Nursikuwagus, Agus; hartono, tono; Nurwicaksono, M A; Choir, M M; Saputri, M A
Jurnal Informatika Vol. 17 No. 1 (2023): January 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The purpose of this research is to create a batik motive image classification system to make it easier for the public to know the name of a type of batik motive. In carrying out this research, a quantitative method was used with seven kinds of batik motives that were augmented first, where 70% of the dataset was used for training and 30% for testing so that the accuracy and precision of the system were obtained. The result of this research is that the accuracy and precision of the system in classifying batik motive images is 0.985 or 98.5%. This high accuracy and precision were obtained because the quality of the previous dataset was improved by augmenting geometric and photometric. The machine learning method used was a Convolutional Neural Network which in previous studies also provided the highest accuracy and precision. The results of this study can be used for various purposes such as marketing, cultural reservation, and science.
Towards a Complete Kurdish NLP Pipeline: Challenges and Opportunities Jacksi, Karwan; Maulud, Dastan; Ali, Ismael
Jurnal Informatika Vol. 17 No. 1 (2023): January 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

With the rapid growth of Kurdish language content on the web, there is a high demand for making this information readable and processable by machines. In order to accomplish this, the Kurdish Natural Language Processing (KNLP) pipeline is required. Computers that can process human language use the field of Natural Language Processing (NLP). In its efforts to bridge the communication gap between humans and computers, NLP draws from a wide range of fields, including computer science and computational linguistics. There have been some notable efforts made toward creating the KNLP pipeline. However, it does not support the complete NLP tasks needed to enable semantic web and text mining applications. This paper surveys the work done in the field of NLP for the Kurdish language, its applications, and linguistic challenges.

Page 42 of 42 | Total Record : 419

 38   39   40   41   42 

Filter by Year

2008 2025


Reset
Filter By Issues
All Issue Vol. 19 No. 1 (2025): January 2025 Vol. 18 No. 3 (2024): September 2024 Vol. 17 No. 1 (2023): January 2023 Vol 17, No 1 (2023): January 2023 Vol 16, No 3 (2022): September 2022 Vol 16, No 2 (2022): May 2022 Vol 16, No 1 (2022): January 2022 Vol 15, No 3 (2021): September 2021 Vol 15, No 2 (2021): May 2021 Vol 15, No 1 (2021): January 2021 Vol 14, No 3 (2020): September 2020 Vol 14, No 2 (2020): May 2020 Vol 14, No 1 (2020): January 2020 Vol. 13 No. 2 (2019): July 2019 Vol 13, No 2 (2019): July 2019 Vol 13, No 1 (2019): January 2019 Vol 12, No 2: July 2018 Vol 12, No 1: January 2018 Vol 11, No 2 (2017): Juli Vol 11, No 2 (2017): Juli Vol 11, No 1 (2017): Januari Vol 11, No 1 (2017): Januari Vol 10, No 2 (2016): Juli Vol 10, No 2 (2016): Juli Vol 10, No 1 (2016): Januari Vol 10, No 1 (2016): Januari Vol 9, No 2 (2015): Juli Vol 9, No 2 (2015): Juli Vol 9, No 1 (2015): Januari Vol 9, No 1 (2015): Januari Vol 8, No 2 (2014): Juli Vol 8, No 2 (2014): Juli Vol 8, No 1 (2014): Januari Vol 8, No 1 (2014): Januari Vol 7, No 2: Juli 2013 Vol 7, No 2: Juli 2013 Vol 7, No 1: Januari 2013 Vol 7, No 1: Januari 2013 Vol 6, No 2: Juli 2012 Vol 6, No 2: Juli 2012 Vol 6, No 1: Januari 2012 Vol 6, No 1: Januari 2012 Vol 5, No 2: Juli 2011 Vol 5, No 2: Juli 2011 Vol 5, No 1: January 2011 Vol 5, No 1: January 2011 Vol 4, No 2: July 2010 Vol 4, No 2: July 2010 Vol 4, No 1: January 2010 Vol 4, No 1: January 2010 Vol 3, No 2: July 2009 Vol 3, No 2: July 2009 Vol 3, No 1: January 2009 Vol 3, No 1: January 2009 Vol 2, No 2: July 2008 Vol 2, No 2: July 2008 Vol 2, No 1: January 2008 Vol 2, No 1: January 2008 More Issue