Penerapan Convolutional Neural Networks untuk Mesin Penerjemah Bahasa Daerah Minangkabau Berbasis Gambar

One of efforts by the Indonesian people to defend the country is to preserve and to maintain the regional languages. The current era of modernity makes the regional language image become old-fashioned, so that most them are no longer spoken. If it is ignored, then there will be a cultural identity crisis that causes regional languages to be vulnerable to extinction. Technological developments can be used as a way to preserve regional languages. Digital image-based artificial intelligence technology using machine learning methods such as machine translation can be used to answer the problems. This research will use Deep Learning method, namely Convolutional Neural Networks (CNN). Data of this research were 1300 alphabetic images, 5000 text images and 200 vocabularies of Minangkabau regional language. Alphabetic image data is used for the formation of the CNN classification model. This model is used for text image recognition, the results of which will be translated into regional languages. The accuracy of the CNN model is 98.97%, while the accuracy for text image recognition (OCR) is 50.72%. This low accuracy is due to the failure of segmentation on the letters i and j. However, the translation accuracy increases after the implementation of the Leveinstan Distance algorithm which can correct text classification errors, with an accuracy value of 75.78%. Therefore, this research has succeeded in implementing the Convolutional Neural Networks (CNN) method in identifying text in text images and the Leveinstan Distance method in translating Indonesian text into regional language texts.

The E-Learning Design for Problem Based Learning in Dynamic Fluid Topic using Microsoft Sway

The development of information and communication technology (ICT) based on education can be an opportunity to improve the learning process. Learning in the pandemic era Covid-19 needs media that help teachers and students enthusiasm for learning. The lessons with e-learning are flexible and easy to use. Microsoft Sway 365 is one of the e-learning that can be used because of the features such as presentation, text, images, video, and sound. This study aims to produce e-learning using Microsoft Sway on Dynamic Fluid. This study uses an R&D method with the 4D model but only defines, designs, and develops stages. Media experts and material experts validated the e-learning. The validity test result from content experts showed that the e-learning using sway was feasible with 77.7% and from media experts was feasible with 77.5%. The study concludes that e-learning with Microsoft Sway is flexible, easy to use, can support physics learning with fun, and feasible to be used as a teaching medium that helps students in explanatory activities.

Reduced Annotation Based on Deep Active Learning for Arabic Text Detection in Natural Scene Images

<div>- A novel approach is presented to reduced annotation based on Deep Active Learning for Arabic text detection in Natural Scene Images.</div><div>- A new Arabic text images dataset (7k images) using the Google Street View service named TSVD.</div><div>- A new semi-automatic method for generating natural scene text images from the streets.</div><div>- Training samples is reduced to 1/5 of the original training size on average.</div><div>- Much less training data to achieve better dice index : 0.84</div>

Reduced Annotation Based on Deep Active Learning for Arabic Text Detection in Natural Scene Images

<div>- A novel approach is presented to reduced annotation based on Deep Active Learning for Arabic text detection in Natural Scene Images.</div><div>- A new Arabic text images dataset (7k images) using the Google Street View service named TSVD.</div><div>- A new semi-automatic method for generating natural scene text images from the streets.</div><div>- Training samples is reduced to 1/5 of the original training size on average.</div><div>- Much less training data to achieve better dice index : 0.84</div>

Kerentanan Perempuan dalam Surveillance Capitalism

Tulisan ini bertujuan untuk menganalisa kerentanan perempuan terhadap Kekerasan Gender Berbasis Online (KGBO) di dalam ruang digital. Studi ini menggunakan konsep kapitalisme pengawasan/surveillance capitalism dan symbolic violence sebagai dasar untuk memahami logika ekonomi dan juga kekerasan yang berlangsung dalam ruang digital. Ruang digital sebagai alat ekonomi tidak hanya menghasilkan “behavioral surplus” sebagai material baru tetapi juga menjadi ruang bagi terbentuknya “dominant habitus” tentang siapa itu perempuan dan bagaimana seharusnya perempuan merepresentasikan dirinya. Dominant habitus yang senantiasa direproduksi mampu menciptakan kebutuhan ekonomi bagi perempuan melalui komodifikasi dan bahkan eksploitasi terhadap tubuh perempuan yang terepresentasi dalam teks gambar, dan video di dalam platform digital. Melalui proses-proses ini, perempuan mengalami kekerasan simbolik yang terus-menerus direproduksi dalam dominant habitus. Dengan demikian, bekerjanya surveillance capitalism dan menguatnya dominant habitus di dalamnya menjadi kondisi yang membuka ruang bagi berlangsungya KGBO terhadap perempuan. Dengan menggunakan perspektif kritis dalam memandang KGBO tulisan ini hendak mendalami proses-proses yang mengkondisikan kerentanan perempuan di dalam ranah digital. Pemahaman akan hal-hal tersebut menjadi basis penting untuk memikirkan secara tepat posisi perempuan di dalam ruang digital yang saat ini secara luas diterima sebagai condition sine qua non yang di dalamnya berbagai bentuk relasi berlangsung. Dengan demikian, tulisan ini memberikan pijakan dasar untuk mendorong dan merumuskan beberapa agenda perubahan. === This paper aims to analyze women's vulnerability to Online-Based Gender Violence (KGBO) in the digital platform. This study uses the concept of surveillance capitalism and symbolic violence as a basis for understanding the economic logic and violence that takes place in today's digital platform. Digital platform as an economic tool not only produces a "behavioral surplus" as a new material, but also becomes a space for the formation of a "dominant habitus"; who is women are and how women should represent themselves. Dominant habitus which is always reproduced is able to create economic needs for women through commodification and even exploitation of women's bodies which are represented in text, images and videos on digital platforms. Throughout these processes, mostly women suffer from symbolic violence which persistently reproduced by the dominant habitus. It obviously reflects the vulnerability of woman as the victim of KGBO. By using a critical perspective in looking at KGBO, this paper intends to explore the process that put women’s vulnerability in the digital arena. Understanding of these matters becomes an important basis for thinking about the exact position of women in the digital space which is currently widely accepted as a condition sine qua non in which various forms of relations take place. Thus, this paper provides a basic basis for encouraging and formulating several agendas for change.

Multimodal Data Evaluation for Classification Problems

Social media data is currently the main input to a wide variety of research works in many knowledge fields. This kind of data is generally multimodal, i.e., it contains different modalities of information such as text, images, video or audio, mainly. To deal with multimodal data to tackle a specific task could be very difficult. One of the main challenges is to find useful representations of the data, capable of capturing the subtle information that the users who generate that information provided, or even the way they use it. In this paper, we analysed the usage of two modalities of data, images, and text, both in a separate way and by combining them to address two classification problems: meme's classification and user profiling. For images, we use a textual semantic representation by using a pre-trained model of image captioning. Later, a text classifier based on optimal lexical representations was used to build a classification model. Interesting findings were found in the usage of these two modalities of data, and the pros and cons of using them to solve the two classification problems are also discussed.

Photometric Ligature Extraction Technique for Urdu Optical Character Recognition

Urdu Optical Character Recognition (OCR) based on character level recognition (analytical approach) is less popular as compared to ligature level recognition (holistic approach) due to its added complexity, characters and strokes overlapping. This paper presents a holistic approach Urdu ligature extraction technique. The proposed Photometric Ligature Extraction (PLE) technique is independent of font size and column layout and is capable to handle non-overlapping and all inter and intra overlapping ligatures. It uses a customized photometric filter along with the application of X-shearing and padding with connected component analysis, to extract complete ligatures instead of extracting primary and secondary ligatures separately. A total of ~ 2,67,800 ligatures were extracted from scanned Urdu Nastaliq printed text images with an accuracy of 99.4%. Thus, the proposed framework outperforms the existing Urdu Nastaliq text extraction and segmentation algorithms. The proposed PLE framework can also be applied to other languages using the Nastaliq script style, languages such as Arabic, Persian, Pashto, and Sindhi.

ANALISIS KELAYAKAN BUKU AJAR KELAS 5 SD/MI TEMA 7 PERISTIWA DALAM KEHIDUPAN

<p><strong>Abstract</strong>: <em>The study aimed to analyze the feasibility of textbook for fifth grade of elementary school in theme ‘Events in Life’. The research was qualitative with an analytical-descriptive approach. Data collection techniques were documentation and interviews. The results showed that: (1) on the feasibility of content, textbook for fifth grade of elementary school in theme ‘Events in Life’ met 100% on the indicator of material completeness, the material components, the choice of discourse, text, images, and illustrations, met 97.53% on the indicator of conformity of concepts and material descriptions on scientific systematics, and met 95.06% on the indicator of example selection; (2) on the feasibility of acceptability and readability, textbook for fifth grade of elementary school in theme ‘Events in Life’ met 100% on the indicator of language suitability, the layout designs, supporting elements, and letters. It concludes that textbook for fifth grade of elementary school in theme ‘Events in Life’ is appropriate to be used in teaching and learning activities.</em></p><p><strong><em>Keywords:</em></strong><em> feasibility analysis, textbooks, feasibility of content, feasibility of acceptability, feasibility of readability</em></p><p><strong> </strong></p><p><strong>Abstrak</strong>: Tujuan penelitian ini adalah menganalisis kelayakan buku ajar kelas V tema 7 “Peristiwa dalam Kehidupan”. Penelitian ini merupakan penelitian kualitatif dengan menggunakan metode analisis-deskriptif. Subjek penelitian ini adalah guru kelas V dan Siswa Kelas V pada SD Negeri 1 Purwantoro, SD Negeri 2 Bangsri, MI Al Barokah di Kecamatan Purwantoro. Hasil dari penelitian yang dilakukan, diketahui bahwa: (1) Pada aspek kelayakan isi pada buku ajar kelas V tema 7 “Peristiwa dalam Kehidupan” memiliki persentase sebesar 100% pada indikator kelengkapan materi, 100% pada indikator kedalaman materi, 100% pada indikator keakuratan pemilihan wacana, teks, gambar, dan ilustrasi, 97,53% pada indikator kesesuaian konsep dan uraian materi dengan sistematika keilmuan, 95,06% pada indikator pemilihan contoh; (2) Pada aspek kelayakan bahasa serta keterbacaan buku pada buku ajar kelas V tema 7 “Peristiwa dalam Kehidupan” memiliki persentase sebesar 100% pada indikator kesesuaian bahasa, 100% pada kesesuaian unsur tata letak konten buku, 100% pada kesesuaian unsur pendukung, dan 100% pada indikator kesesuaian huruf yang digunakan. Implikasi dari penelitian ini adalah buku ajar kelas V tema 7 “Peristiwa dalam Kehidupan” layak untuk dipergunakan dalam kegiatan belajar mengajar.</p>Keyword: Analisis Kelayakan, Buku Ajar, Kelayakan isi, Kelayakan Bahasa serta Keterbacaan Buku.