Wijayanti Nurul Khotimah

Sitting to standing and walking therapy for post-stroke patients using virtual reality system

Generally, post-stroke patients suffer physical disorder or paralysis in various level. Common treatment to restore the functionality of the paralyzed limb is by doing motoric therapy. This therapy was done in hospital and was monitored by therapists. However, most of the post-stroke patients choose not to do therapy since their access to hospital is difficult or their motivation to do therapy is low. To overcome the limitations of traditional therapy methods some interactive game-based therapy systems were introduced i.e: AR-therapy and Wii-based movement therapy. Unfortunately, their performance is low due to user ergonomic factor problem. In this study, we proposed a virtual reality system for sitting to standing and walking therapy for post-stroke patients called KOMY. This application is integrated with Kinect technology. Four VR game-based training tasks were adopted from sitting to standing therapy and walking therapy that was done by therapist. These tasks are sitting-standing-sitting, moving leg aside, moving leg freely, and walking. Each task has tree difficulty level. From observation that involving post-stroke patient, elderly healthy people, and therapist, we find that all of them give positive comment to this application. They said that this application not only can be used for therapy of post-stroke patients but also can be used for exercise to elderly. Further, KOMY can be used as alternative for playing therapy and home education therapy.

Non-uniform decimation-free directional filter bank using histogram analysis for image enhancement

Directional Filter Banks (DFB) is a method for directional decomposition. It has been used in image enhancement procedure that involved image with many edges. The design of Decimation-Free Directional Filter Bank (DDFB) is made to give a better result for enhancement. However, the design cannot give an adaptive directional decomposition based on input image. In this paper, we proposed a Non-Uniform Decimation-Free Directional Filter Bank (NUDDFB) using Histogram Analysis for Image Enhancement. NUDDFB can build an adaptive directional filter depends on the input image. The result shows that NUDDFB can separate each directional image better than DDFB. The use of this method in image enhancement helps to retain the image from over enhancement.

Image thresholding based on index of fuzziness and fuzzy similarity measure

In this paper, we propose an automatic image thresholding method based on an index of fuzziness and a fuzzy similarity measure. This work aims at overcoming the limitation of the existing method which is semi-supervised. Using an index of fuzziness, two initial regions of gray levels located at the boundaries of the histogram are defined based on the fuzzy region. Then the threshold point is found by using a fuzzy similarity measure. No prior knowledge of the image is required. Experiments on practical images illustrate the effectiveness of the proposed method.

Classification and numbering on posterior dental radiography using support vector machine with mesiodistal neck detection

Dental radiography meets challenge to classify the dents into the proper class which useful for forensic and biomedical application. This paper proposed a novel method of classification and numbering on posterior dental radiography using support vector machine (SVM) with mesiodistal neck detection. In this method we developed SVM using a nouvelle feature with mesiodistal neck teeth. This feature was used to solve the problem in the dental image which suffered with completeness of whole part of teeth (crown-root). Preprocessing for enhancements included morphological operation, contrast adaptive, and tresholding. Every tooth has been assigned according to universal dental numbering and classified as their sequence order. Our system achieved classification precision of 90 %. This approach is robust and optimal for solving the problem of dental classification.

Pengenalan Bahasa Isyarat Indonesia dengan Metode Dynamic Time Warping (DTW) menggunakan Kinect 2.0

Bahasa isyarat merupakan media bagi penderita tuna rungu dan tuna wicara untuk saling berkomunikasi. Perkembangan teknologi untuk menerjemahkan bahasa isyarat Indonesia secara real-time bisa bermanfaat bagi komunitas tuna rungu. Pada penelitian sebelumnya, pengenalan bahasa isyarat menggunakan teknologi Kinect sudah berhasil dibuat. Namun dalam prosesnya, fitur bahasa isyarat yang digunakan hanya bahasa isyarat yang bersifat statis saja. Selain itu, terdapat pula penelitian sebelumnya yang menggunakan ekstraksi fitur untuk mengenali bahasa isyarat dinamis saja. Pada penelitian ini, dilakukan bahasa isyarat yang bersifat statis dan dinamis secara dengan metode Dynamic Time Warping (DTW), yang mampu mengenali secara real-time bahasa isyarat Indonesia dari 20 kata dan menerjemahkannya dalam gambar dan teks. Hasil pengujian menunjukkan bahwa persentase nilai akurasi rata-rata yang dihasilkan adalah 93%.

Virtual reality navigation system in virtual mall environment

The mall is a shopping center that contains a variety of retail stores and typically also restaurants or movie theater. Therefore, the building has large size and sometimes made people get confused to find a place or destination at the mall. The existing solution to this problem is to provide navigation in the mall such as directions, information boards, information center, or security guard who can help to guide people to their destination. This paper proposes the implementation of Virtual Reality (VR) to be one of the solutions. This research aims to provide an innovative application that can navigate people trying to find a certain place at the mall. The technology of VR is used to model the Virtual Environment of Mall. Google Cardboard is used as the additional device in VR. The navigation feature is implemented using NavMesh library. This library can be used to find the shortest path to reach the destination. The result of this research shows that Google Cardboard and NavMesh can be implemented to develop an innovative technology in the virtual navigation system and it can also give another experience for the user. This research also implements the feature to reach the destination quickly by using the shortest path algorithm.

Tuna fish classification using decision tree algorithm and image processing method

Fishery has contributed a lot to Indonesian economy development such as domestic industries, micro industries, and export industries. Tuna is one of the fishery product. To produce tuna fish product, an industry must separate tuna based on their type. Nowadays, the separation process is still done manually. As consequence, the process was slow and the error rate was high. This research proposed automatic tuna fish classification using decision tree algorithm and image processing method. Eight features, texture feature and shape feature, were extracted from tuna fish image using image processing method. The texture features are contrast, correlation, energy, homogeneity, inverse difference moment, and entropy. While the shape features are the circular rate of tunas head and the ratio of head area and circular area. These features are then used to create classification model using decision tree. Sixty tunas image from tree types tuna, Bigeye, Yellowfin, and Skipjack, were used in experiment. From experiment, it shows that the average accuracy of the classification is 88%.

Design and implementation of food nutrition information system using SURF and FatSecret API

People are constantly looking for ways to improve their health and one approach that could be taken in addition to exercising is managing daily nutrition intake. Even though to get fit and healthy we must manage our daily nutrition intake often we do not know what nutrients are present in food. Therefore, before eating we need to look for nutrition information of the food. The usual process of getting the foods nutrition information is by searching via the google or use some application such as Coach Noom, Calorie Counter, Lose It. In this paper we proposed to make this process smarter, faster, and more efficient by developing an android application that can shows the nutrition information by just taking the picture of the food. We develop an android augmented reality application to help users to get nutritional information in an easy and informative way. The information is displayed in the form of calorie, fat, carbohydrate, and protein per serving. Using this application, users can get the nutritional information simply by taking a picture of the food. From our experiments, the food recognitions accuracy level is 92%, while the average time required to identify the name and the nutrients is 9.295 seconds.