Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
Perkembangan teknologi saat ini sudah mampu menunjang kegiatan belajar mengajar secara daring. Salah satu metode yang digunakan untuk melakukan kegiatan tersebut adalah secara asinkronus. Umumnya, materi yang disampaikan secara asinkronus menggunakan video pemelajaran. Pengajar mengunggah video pemelajaran pada sebuah layanan Learning Management System (LMS) dan siswa menggunakan video tersebut sebagai bahan belajar. Siswa tunarungu mengalami kesulitan mengikuti kegiatan pemelajaran dengan media tersebut karena kurangnya fitur aksesibilitas pada LMS yang digunakan. Fasilkom UI sebelumnya sudah mengembangkan modul pengubah suara menjadi teks dengan Automatic Speech Recognition (ASR) dan pengubah teks menjadi animasi bahasa isyarat (Text-to-Gesture). LMS yang digunakan adalah Moodle. Pada penelitian ini, dikembangkan suatu layanan yang bisa mengintegrasikan modul ASR dengan aplikasi Text-to-Gesture. Penelitian ini mengembangkan sebuah Application Programming Interface (API) yang bisa menerima hasil ASR dan mengirimkannya ke aplikasi Text-to-Gesture. Animasi dibangkitkan dengan aplikasi Text-to-Gesture yang di saat bersamaan direkam dan kemudian diproses menggunakan FFmpeg. Hasil prosesnya kemudian dikirimkan kembali ke Moodle untuk disajikan sebagai bahan ajar. Pada penelitian ini disimpulkan pengembang dapat membuat sebuah API yang bisa menghubungkan modul ASR pada Moodle dengan aplikasi Text-to-Gesture. API yang dibuat juga bisa dihubungkan dengan aplikasi lain selain Moodle selama mengikuti format yang sama dengan modul ASR. ......The current technology development has been able to support online learning activities. One of the methods used for such activities is asynchronous learning. Typically, asynchronous learning materials utilize instructional videos. Educators upload instructional videos to a Learning Management System (LMS), and students use these videos as learning materials. Deaf students face difficulties in following the learning activities with these media due to the lack of accessibility features in the LMS being used. Previously, Fasilkom UI has developed modules to convert speech into text using Automatic Speech Recognition (ASR) and to convert text into sign language animations (Text-to-Gesture). The LMS used in this research is Moodle. In this study, a service was developed to integrate the ASR module with the Text-to-Gesture application. An Application Programming Interface (API) was developed to receive ASR results and send them to the Text-to-Gesture application. The animations that are generated using the Text-to-Gesture application are recorded and then processed using FFmpeg. The processed results are then sent back to Moodle to be presented as teaching materials. This research concludes that developers can create an API to connect the ASR module in Moodle with the Text-to-Gesture application. The created API can also be connected to other applications as long as they follow the same format as the ASR module.

Abstrak :
Pandemi COVID-19 yang semakin mengkhawatirkan telah membatasi masyarakat dalam melakukan kontak fisik dengan benda-benda pada fasilitas umum. Berbagai sarana interaksi yang membutuhkan kontak fisik telah digantikan dengan alternatif yang mendukung interaksi secara contactless. Elevator merupakan salah satu fasilitas umum yang paling sering digunakan masyarakat, maka perlunya alternatif dari penggunaan tombol pada elevator untuk mengurangi kemungkinan tersebarnya virus. Perkembangan teknologi computer vision telah menghasilkan banyak implementasi yang bermanfaat, salah satu implementasi tersebut adalah pendeteksian objek. Pada penelitian ini, dilakukan perancangan dan implementasi dari deep learning untuk menghasilkan model pengenalan gestur tangan secara real-time yang ditujukan untuk diterapkan sebagai sarana interaksi dengan elevator. Metode transfer learning digunakan karena dapat menghasilkan model yang akurat tanpa perlu menggunakan dataset yang besar. Perancangan model dilakukan menggunakan Tensorflow Object Detection API dan SSD MobileNetV2 sebagai pre-trained model yang telah dilatih dengan dataset Microsoft COCO. Model yang telah dilatih dengan jumlah training steps sebesar 11000 menggunakan Dataset A pada nilai threshold 0.7 dapat mendeteksi 8 gestur tangan dengan nilai akurasi mencapai 90% berdasarkan uji coba real-time yang dilakukan. ......The increasingly worrying COVID-19 pandemic has limited people from making physical contact with objects in public facilities. Various means of interaction that require physical contact have been replaced with alternatives that support contactless interaction. Elevators are one of the public facilities that are most often used by the public, so there is a need for alternatives to using buttons on elevators to reduce the possibility of spreading the virus. The development of computer vision technology has resulted in many useful implementations, one of which is object detection. In this research, the design and implementation of deep learning and artificial neural network is carried out to produce a real-time hand gesture recognition model that is intended to be applied as a means of interaction with elevators. The transfer learning method is used because it can produce accurate models without the need to use large datasets. The model design is carried out using the Tensorflow Object Detection API and SSD MobileNetV2 as a pre-trained model that has been trained with the Microsoft COCO dataset. The model that has been trained with the number of training steps of 11000 using the Dataset A at a threshold value of 0.7 can detect 8 hand gestures with an accuracy reaching up to 90% based on real-time trials carried out.

Abstrak :
Artikel ini membahas feminitas dalam majalah ELLE RUSSIA. Pada artikel ini, pembahasan difokuskan pada enam iklan parfum yakni Dior Addict Eau de Toilette, GIORGIO ARMANI ACQUA di GIOIA, DOLCE & GABBANA – LIGHT BLUE, GUCCI Flora Gardenia the Floral Fragrances, PRADA CANDY FLORALE The New Eau de Toilette, GIVENCHY Very Irresistible L’eau en rose yang dimuat dalam halaman majalah ELLE RUSSIA edisi Juli 2014. Analisis dilakukan menggunakan teori Semiotika Roland Barthes. Metode yang digunakan adalah metode deskriptif analisis. Hasil analisis artikel ini menyatakan bahwa majalah ELLE RUSSIA memuat konten perempuan dan feminitas dalam bentuk fashion, make up, skincare, parfum memberikan dampak secara tersirat melalui tampilan feminitas yang dipromosikan pada tampilan fisik yang sensual, kebebasan, serta perpaduan warna sesuai konsep. ......This article discusses femininity in ELLE Russia Magazine. In this article, the discussion focused on six perfume ads, namely Dior Addict Eau de Toilette, Giorgio Armani Acqua di Gioia, Dolce & Gabbana Light Blue, Gucci Flora Gardenia the Floral Fragrances, Prada Candy Florale the New Eau de Toilette, and Givenchy Very Irresistible L'eau en Rose, which were published on the pages of the July 2014 issue of ELLE Russia Magazine. The analysis was carried out using Roland Barthes' semiotics theory. The method used is the descriptive method of analysis. The results of the analysis of this article stated that ELLE Russia Magazine contains women's and femininity content in the form of fashion, makeup, skincare, and perfume, giving an implicit impact through the appearance of femininity that is promoted through a sensual physical appearance, freedom, and a combination of colors according to the concept.

Abstrak :
This book constitutes revised selected papers from the 9th International Gesture Workshop, GW 2011, held in Athens, Greece, in May 2011. The 24 papers presented were carefully reviewed and selected from 35 submissions. They are ordered in five sections named: human computer interaction; cognitive processes; notation systems and animation; gestures and signs: linguistic analysis and tools; and gestures and speech.

Abstrak :
A technique is presented here for directional gesture recognition by robots. The usual technique employed now is using camera vision and image processing. One major disadvantage with that is the environmental constrain. The machine vision system has a lot of lighting constrains. It is therefore only possible to use that technique in a conditioned environment, where the lighting is compatible with camera system used. The technique presented here is designed to work in any environment. It does not employ machine vision. It utilizes a set of sensors fixed on the hands of a human to identify the direction in which the hand is pointing. This technique uses cylindrical coordinate system to precisely find the direction. A programmed computing block in the robot identifies the direction accurately within the given range.

Sebuah teknik yang disajikan di sini untuk arah pengenalan gestur oleh robot. Teknik yang biasa digunakan saat ini menggunakan camera vision dan pengolahan citra. Salah satu kelemahan utama dengan teknik itu adalah keterbatasan lingkungan. Sistem machine vision memiliki banyak kendala pencahayaan. Oleh karena itu, teknik tersebut hanya mungkin digunakan dalam lingkungan yang telah dikondisikan sebelumnya, di mana pencahayaan cocok dengan sistem kamera yang digunakan. Teknik yang disajikan di makalah ini dirancang untuk bekerja dalam lingkungan apapun dan tidak menggunakan machine vision. Sistem yang diusulkan ini menggunakan satu set sensor tetap di tangan manusia untuk mengidentifikasi arah di mana tangan menunjuk. Teknik ini menggunakan sistem koordinat silinder untuk secara tepat menemukan arah. Sebuah blok komputasi diprogram pada robot mengidentifikasi arah secara akurat dalam kisaran yang diberikan.

Abstrak :
Anak dengan Down Syndrome (DS) memiliki kemampuan delay of gratification yang rendah. Mereka mengalami kesulitan saat harus menunggu dan menunda kepuasan. Sementara kemampuan delay of gratification diperlukan agar dapat menyesuaikan dengan tuntutan lingkungan. Penelitian ini bertujuan untuk menelaah tentang peran scaffolding dalam interaksi ibu-anak, kemampuan bahasa reseptif, atensi, working memory terhadap kemampuan delay of gratification anak dengan DS. Penelitian ini terdiri dari dua tahap penelitian dimana masing-masing tahap menggunakan rancangan penelitian explanatory sequential mixed methods. Penelitian kuantitatif tahap pertama bertujuan untuk membuktikan (1) korelasi waiting time saat anak menjalankan tugas delay dan kemampuan delay of gratification domain makanan, interaksi sosial, dan physical pleasure menurut persepsi ibu (2) hubungan dimensi dan tipe scaffolding dalam interaksi ibu-anak dan kemampuan delay of gratification. Penelitian kualitatif bertujuan untuk mendapatkan gambaran kemampuan delay of gratification anak dari ibu dengan skor scaffolding tinggi dan rendah saat bermain lego. Analisis data kuantitatif menggunakan uji korelasi Spearman Rho. Hasil penelitian menunjukkan bahwa tidak terdapat korelasi yang signifikan antara waiting time saat anak menjalankan tugas delay dengan kemampuan delay of gratification domain makanan, interaksi sosial dan physical pleasure yang dipersepsi ibu. Dimensi scaffolding yang berkorelasi dengan waiting time anak adalah direction maintenance dan frustration control. Tipe scaffolding yang berkorelasi dengan waiting time adalah speech disertai gesture. Hasil penelitian kualitatif terhadap tiga orang ibu dengan skor scaffolding tinggi dan empat ibu dengan skor scaffolding rendah saat bermain lego menggambarkan bahwa ibu dengan skor scaffolding tinggi memiliki anak dengan waiting time yang lebih lama saat menjalankan tugas delay dibandingkan anak dari ibu dengan skor scaffolding rendah. Penelitian tahap kedua bertujuan untuk membuktikan (1) perbedaan waiting time saat bersama ibu, bersama ibu dan orang asing, bersama orang asing dan ketika anak berada sendirian (2) hubungan dimensi scaffolding dengan kemampuan delay of gratification (3) kesesuaian antara model dinamika hubungan antar variabel scaffolding dalam interaksi ibu-anak, kemampuan bahasa reseptif, atensi, working memory dan kemampuan delay of gratification dengan data (model fit). Hasil penelitian menunjukkan bahwa terdapat perbedaan waiting time secara signifikan antara saat bersama ibu, bersama ibu dan orang asing, bersama orang asing dan saat anak berada sendirian. Dimensi scaffolding yang berkorelasi dengan kemampuan delay of gratification adalah direction maintenance, reduction in degrees of freedom, demonstration. Tipe scaffolding speech disertai gesture berkorelasi positif dengan kemampuan delay of gratification. Model teoritis yang diusulkan fit dengan data. Penelitian kualitatif tahap kedua menggambarkan bahwa ibu dengan skor scaffolding tinggi saat menjalankan tugas delay memiliki anak dengan waiting time yang lebih lama dibandingkan anak dari ibu dengan skor scaffolding rendah. Implikasinya adalah ibu disarankan memberikan scaffolding berupa direction maintenance, reduction in degrees of freedom, demonstration dan frustration control, yang diberikan melalui speech disertai gesture. ......Children with Down Syndrome (DS) have a low delay of gratification ability. They have difficulty waiting and delaying gratification. Meanwhile, the delay of gratification capability is needed in order to adapt to environment demands. This study aims to examine the role of scaffolding in mother-child interactions, receptive language skills, attention, working memory and the delay of gratification ability of children with DS. This study consisted of two stages of research where each stage used an explanatory sequential mixed methods research design. The first stage of quantitative research aims to prove (1) the correlation of waiting time when children perform delay tasks and the ability of delay gratification in the food, social interaction, and physical pleasure domain according to mother's perception (2) the relationnship between dimensions and types of scaffolding in mother-child interactions and the delay of gratification ability. The qualitative research aims to get a description of the delay of gratification ability of children from mothers with high and low scaffolding scores when playing lego. Quantitative data analysis used the Spearman Rho correlation test. The results showed that there was no significant correlation between waiting time when the child performed a delay task with the delay of gratification ability in the food, social interactions and physical pleasure domain perceived by mothers. The scaffolding dimensions which correlate with children's waiting time are direction maintenance and frustration control. The type of scaffolding that correlates with waiting time is speech accompanied by gesture. The results of a qualitative study of three mothers with high scaffolding scores and four mothers with low scaffolding scores while playing lego illustrate that mothers with high scaffolding scores have children with a longer waiting time while carrying out delay tasks than mothers with low scaffolding scores. The second stage of research aims to prove (1) the difference in waiting time when with mother, with mother and strangers, with strangers and when the child is alone (2) the relationship between the scaffolding dimension and the delay of gratification ability (3) the suitability dynamic models of the relationship between scaffolding in mother-child interactions, receptive language skills, attention, working memory and delay of gratification ability with data (model fit). The results showed that there was a significant difference in waiting time between with the mother, with the mother and strangers, with strangers and when the child was alone. The dimensions of scaffolding that correlate with the delay of gratification ability are direction maintenance, reduction in degrees of freedom, demonstration. The type of scaffolding speech accompanied by gesture has a positive correlation with the ability to delay gratification. The proposed theoretical model is fit with the data. The second stage of qualitative research illustrates that mothers with high scaffolding scores while carrying out delay tasks have children with a longer waiting time than mothers with low scaffolding scores. The implication is that mothers are suggested to provide scaffolding in the form of direction maintenance, reduction in degrees of freedom, demonstration and frustration control, which is given through speech accompanied by gestures.

Abstrak :
Perkembangan Human Computer Interaction (HCI) dalam dunia medis dapat membantu pasien untuk berkomunikasi dengan keluarga atau perawat agar kebutuhan mereka dapat terpenuhi dengan baik. Pada penelitian ini akan digunakan salah satu aplikasi HCI yaitu pengenalan isyarat tangan melalui web camera sebagai sistem penyampaian pesan. Akuisisi citra dilakukan pada 12 subjek dengan berbagai jenis kelamin dan usia yang memperagakan lima isyarat tangan. Isyarat tangan yang diperagakan berdasarkan pada kebutuhan dasar pasien: makan, minum, ingin ke toilet, butuh bantuan, dan butuh obat-obatan. Citra yang telah dikumpulkan lalu dilakukan pengolahan seperti labelling kelas hingga akhirnya dilatih menggunakan algoritma Single Shot Detector (SSD) MobileNet V2. SSD MobileNet V2 dipilih karena memiliki kemampuan deteksi yang baik dan komputasi yang cukup ringan sehingga cocok diaplikasikan untuk real-time. Pada penelitian ini, didapatkan mean Accuracy Precision (mAP) sebesar 44.7% serta dapat mendeteksi dan mengenali 85 dari 100 citra dengan baik ketika dijalankan pada komputer personal. Hasil mAP yang didapatkan lebih baik dari penelitian sebelumnya. Frame Rate per Second (FPS) yang dihasilkan saat diaplikasikan real-time sebesar ±2 FPS. Model hasil pelatihan kemudian juga diaplikasikan pada Raspberry Pi Model 3 dan 4 untuk mengetahui perbandingannya. ......The development of Human Computer Interaction (HCI) in medical side can help dissabled patient to communicate well with their relatives and medical helpers. This can help to maintain their needs to be well-fullfilled. In this research study, one of HCI aplication has been used. It is hand gesture recognition using web camera as a notification system. Image acquisition has been done on 12 subjects with various gender and ages. They demonstrated the five gestures: need to eat, need to drink, need to go to the toilet, need help and need medicines. These gestures are based on human’s basic daily needs. The collected images were processed like labelling the images and tarined using Single Shot Detector (SSD) MobileNet V2 algorithm.We chosed SSD because it has good ability in object detection and needs low computation. Therefore, it is suitable to be applied on real-time detection. In this study, we yielded mean Accuracy Precision (mAP) 44.7% and 85 out of 100 images were well-detected when they were run on personal computer (PC). The result provided in this study is considered better than previous study. Frame rate per second (FPS) provided in this study was ±2 FPS. The trained model also was run on Raspberry Pi 3 and 4 to compare their results.

Abstrak :
Ian Waterman lost touch and movement/position sense (proprioception) below the neck over 40 years ago, though pain and temperature perception and his peripheral movement nerves were unaffected. Without proprioceptive feedback he was completely unable to move and felt both disembodied and frightened. Then, slowly, he taught himself to dress, eat, and walk by thinking about each movement and with visual supervision. Through his experiences we can better understand proprioception. The narrative moves between biography and the scientific research he has been involved in. He has been married three times and built up successful careers in disability access audit, using his impairment to his advantage, and in rare turkey breeding and journalism. The neuroscience has led to data on movement without feedback, the pleasantness of touch, gesture, pain, and orientation of the body in space. This account shows how the science was actually done but also reveals Ians journey from passive subject to informed critic of science and scientists. His unique response to such a rare condition has also led to a BBC documentary, theatrical portrayals, and a weightless flight with NASA. As a young man Ian sought triumph over his impairment; now, nearly 65, he has more mature reflections on living with such an extraordinary loss, the limits it has imposed, and the opportunities it has enabled. He gives his views on scientists and on others he has met including Oliver Sacks and Peter Brook. In an Afterword those from science, the arts, and philosophy give an appreciation of his contribution.