International Journal on Advanced Science, Engineering and Information Technology
Not a member yet
2006 research outputs found
Sort by
Mapping Climate Change Vulnerability of the Java Sea Ecosystem
Get PDFThis present study aims to investigate climate change trends in the Java Sea and integrate these trends with the distribution of the lower trophic level of marine ecosystem parameters and the distribution of coastal ecosystems into a climate change vulnerability map using data products of wind, rainfall, sea surface temperature (SST), satellite imagery of Landsat TM and a coupled hydrodynamic-biogeochemical model output. Climate change vulnerability mapping was conducted using a Geographic Information System (GIS), with a vulnerability equation from IPCC. This study shows that the high vulnerability is located in the southern coast of Kalimantan, Jakarta Bay, Semarang waters, and Madura Strait because of riverine inputs from human activities in the land and possible future worse conditions due to the positive rainfall trends in those regions. The low vulnerability is found in the northwestern and southeastern parts of the Java Sea associated with the negative trends of rainfall and SST. In general, the moderate vulnerability covers almost the entire Java Sea. This study suggests strengthening the coastal ecosystem through protection and rehabilitation in the future to enhance adaptive capacity. In addition, the organic and inorganic riverine inputs have to minimize, related to the positive trend of rainfall in the future, particularly those regions with high vulnerability. Integration of the spatial land model, the ocean model, and climate forcing are expected to improve our understandings of climate change vulnerability, which is relevant for climate adaptation action plans
Developing Big Data Analytics Course for Non-ICT Major University Students
Get PDFIn the fourth industrial revolution's education era, there is no boundary between majors or subjects, and it is common for university students to enrol in information and communication technology (ICT)-related courses as convergence education blends different disciplines. Today's job market is getting more competitive and requiring higher skills in ICT and computational thinking. Since non-ICT major students rarely have programming experiences and knowledge in regular classes, teaching a big data analytics course for non-ICT major university students is not easy. Thus, it is vital to develop a curriculum that comprises easy-to-follow and easy-to-understand modules. In this paper, we develop a big data analytics course for non-ICT major university students. The proposed big data analytics course for non-ICT major students comprises two parts: (1) basic programming skill modules with step-by-step guidelines and (2) extension to big data analytics modules with laboratory exercises, with the five principal programming modules based on the Python programming language. First, our investigation discusses the suggestions and limitations of the big data analytics course for non-ICT major university students. Then, we recommend programming languages, integrated development environments (IDEs), and useful tools that help learners perform programming exercises and milestone projects. The learning objectives and course design models are carefully selected based on Bloom's taxonomy with six thinking levels and five
KERO-Playable Robotic Platform to Contribute to Non-verbal Communication Teaching in Children with Autism Spectrum Disorder
Get PDFThis work presents the design and construction of a recreational platform named KERO, which is oriented to the development of non-verbal communication skills in children with autism spectrum disorder (ASD) levels 1 and 2, between ages of 4 and 7 years old. The development of a friendly-looking robot with head and upper limbs movement is presented, which can perform 8 gestures such as: Cry, happy, Affirm, Deny, Say Hello, Exclaim, Quiet, Aim. KERO is a social robot that interacts with children with ASD through the usage of an intuitive interface. This interface allows proper interaction with the robot. In this interface, two games were developed to complement the robot-children interaction and increase their cognitive abilities by observing improvements in his/her attention, perception, memory, and problem-solving. The tests were validated under two different scenarios, preliminary and field tests, involving psychopedagogues, initial education students, therapists and children with ASD. Tests were carried out in a different number of sessions for each child. Each patient with ASD showed a different degree of social interaction with the KERO playable kit; their therapists evaluated this interaction during all sessions. At the end of the sessions with the patients, an improvement of 45% in recognition of gestures and 23.06% in the execution time of the memory game could be observed
G-OFDM Variants Evaluation for Transmitter and Receiver Implementation
Get PDFOrthogonal Frequency Division Multiplexing (OFDM) is chosen as a multiplexing technique and broadly used in today’s radiocommunication environments to overcome spectrum insufficiency. In current OFDM applications, the IDFT/DFT algorithms are used for modulation and demodulation, efficiently implemented using the IFFT/FTT. The IFFT and FFT are some of the main components of OFDM systems, requiring intensive computation, especially for a high number of sub-channels. Reducing the computational burden of the IFFT/FFT would offer an advantage in reducing the total OFDM system complexity.  In this proposed system, the idea of implementing the very fast Fourier transform (VFFT) in OFDM (later, it is called G-OFDM) is based on a trade-off between performance and complexity. The implementation complexity of G-OFDM is lower than OFDM. However, there is a performance cost. G-OFDM has been studied both analytically and in simulation over the AWGN channel. In particular, performance is marred by the non-uniformity of SNR among sub-carriers. In this study, it was proposed two G-OFDM variants called G1-OFDM and G2-OFDM. G1-OFM is the least complex among all G-OFDM scenarios but gives the worst performance, while G2-OFDM gives the best performance but is the most complex. The results show that the performance of G-OFDM and its variants can be improved through the application of different values of n-quantization levels. In other words, using n-quantization levels, we can decrease the processing loss of the G system
Tool Sorting Algorithm Using Faster R-CNN and Haar Classifiers
Get PDFThe following paper presents an algorithm for sorting up to 5 different tools based on deep learning and specifically in a convolutional neural network, according to the top in pattern recognition found in state of the art and compared by a Haar classifier in object recognition tasks. A Faster R-CNN is used to detect and classify tools located randomly on a table and a Haar classifier to detect other tools delivered by the user. The Faster R-CNN allows recognizing the existing tools on the table and where they are located in the physical space. The Haar classifier detects and tracks, in real-time, a tool delivered by the user's hand to sort it on the table, together with the other elements. Both the training of the convolutional network and the design of the Haar classifier are exposed. The algorithm detects and classifies the tools found on a table, then orders them side by side, and finally waits for the user to deliver some of the five missing tools on the table, take it from his hand, and locate it at the end of the row of objects. A Faster R-CNN was used with an accuracy of 70.8% and a Haar classifier with a 96% recognition, managing to order the five tools in a physical environment. The average time in comparison demonstrates that the Haar classifier presents a lower computational cost
Visual Commands for Control of Food Assistance Robot
Get PDFAssistance robots improve people's quality of life in residential and office tasks, especially for people with physical limitations. In the case of the elderly or people with upper limb motor disabilities, an assistance robot for food support is necessary. This development is based on a mixed environment, a real and virtual environment working interactively. A camera located in front of the user is used, at a distance of 60 cm, so that it has an excellent visual range to capture the user's hand gestures for the commands. Pattern recognition based on a deep learning algorithm is made with convolutional neural networks to identify the user's hand gestures. This work exposes the network's training and the results of the robot command's execution. A virtual environment is presented in which a robotic arm with a spoon-like effector is used in a machine vision system that allows eight different types of commands to be recognized for the robot by training a faster R-CNN network for which a database of 640 images is used, achieving a degree of system performance of over 95%. The average time in the execution of a cycle from detecting and identify the command gesture to move the robot towards the food and return in front of the user is 21 seconds, making the development useful for real-time applications
Tech Tools for Anticipating Human Trafficking in Archipelago State
Get PDFThe current mitigation efforts of human trafficking fail to combat cross-border trafficking in the sea. Â On the other hand, most of the studies in human trafficking have not dealt with the context of transporting victims via seaport. This paper attempts to critically discuss the process and consequences of transporting victims of human trafficking via illegal seaport. Part of the objective is to propose compatible tech tools to anticipate potential victims. A qualitative approach was employed since investigating human trafficking in Riau Islands' seaports needs a robust research method. Thus, a case study is selected to focus on a single exit point phenomenon for sending migrant workers who have been identified as a group at high risk of human trafficking. Riau Islands, specifically Bintan Island and Batam Island, were selected as samples of case studies because these are critical locations for sending and repatriating victims. The current study found that an archipelago country like Indonesia deals with multifaceted challenges in combating human trafficking. Moreover, there is a significant shift in human trafficking crime from recruiting to executing due to the cyber world's invention. One unanticipated finding is that social networks and cybercrime have expanded the possibilities for supplying victims. This study contributes to research on human trafficking by introducing tech tools that may help overcome the problems.Â
Implementation of Three Phase Axial Flux Disc Permanent Magnet Generator for Low-Speed Horizontal Axis Wind Turbine
Get PDFThe wind speed characteristic in Indonesia requires a low-speed generator for a wind turbine generator system. One type of generator suitable for a low-speed wind turbine is the Axial Flux Disc Permanent Magnet Synchronous Generator (AFDPMSG). This type of generator uses permanent magnets to produce axial flux in the rotor disk, making it easier to implement for wind power generation. This paper discusses the design of three-phase AFDPMSG compatible with low-speed Horizontal Axis Wind Turbine (HAWT) in the single coreless stator and single rotor configuration. The AFDPMSG stator is designed using 15 coils coated with fiberglass, while the rotor is designed using 18 poles of Neodymium N52 type permanent magnet. To drive low-speed AFDPMSG with large mechanical torque, the HAWT is designed using six blades made of fiberglass with NACA6412 type airfoils. The magnetic characteristics of AFDPMSG were analyzed using SolidWorks software based on the finite element method. Then the electrical characteristics were verified through simulations using Matlab software and experiments using horizontal axis wind turbines. Both simulation and experimental results show that AFDPMSG has produced voltage and power for a low-speed wind turbine as expected. HAWT has been able to drive the AFDPMSG with a speed of 263 rpm at a wind speed 9 m/sec so that the AFDPMSG can produce the output voltage 14 volts with the output power of 580 Watts. These results are close to the AFDPMSG rating design
Cloud Detection for Pleiades and SPOT 6/7 Imageries Using Modified K-means and Deep Learning
Get PDFCloud detection is one of the important stages in optical remote sensing activities as the cloud's existence interferes with the works. Many methods have been developed to detect the cloud, but it is still a few methods for high-resolution images, which mostly have limited multispectral bands. In this paper, a novel method of cloud detection for the images is proposed by integrating an unsupervised algorithm and deep learning. This method has three main steps: (1) pre-processing; (2) segmentation using modified K-means; and (3) cloud detection using CNN. In the segmentation step, an unsupervised algorithm, K-means is modified and used to divide pixels values into k clusters. Our modified K-means method can separate thin clouds from relative bright objects in gray clusters that will be grouped into potential cloud pixels. Afterward, a design of convolutional neural network (CNN) is used to extract the multi-scale features from each cluster and classify them into two classes: (1) cloud, which consists of thin cloud and thick cloud, and (2) non-cloud. The potential cloud area from the first step is used for guiding the result of CNN to provide accurate cloud areas. Several Pleiades and SPOT 6/7 images were used to test the reliability of the proposed method. As a result, our modified K-means has an improvement to increase the accuracy of the results. The results showed that the proposed method could detect cloud and non-cloud accurately and has the highest accuracy of the results compared to the other methods. Â
Roasted Pearl Millet Flour (RoPMF) Improved the Mineral Composition of Beef Sausages
Get PDFMeat products which are cheaper and have better nutritional composition are crucial for reducing hunger and promoting good health and wellbeing of humans. This study investigated the nutritional, physicochemical, sensory, and formulation cost of beef sausages prepared using roasted pearl millet flour (RoPMF). A complete randomized design was used to assign roasted pearl millet flour (0% RoPMF, 5% RoPMF, 10% RoPMF and 15% RoPMF) to meats. Other ingredients were added in equal amounts. The official methods of analysis of the Association of Official Analytical Chemists and British Standard Institute procedures were used for mineral and sensory analysis, respectively. There were significant differences (P<0.05) in the mineral composition of the beef sausages. The iron, magnesium and calcium contents of the RoPMF sausages were generally higher than the control (0% RoPMF) sausages. The potassium contents of 5% RoPMF and 15% RoPMF sausages were similar (P>0.05) to the control. The 5% RoPMF sausages had the highest zinc content of 35.29±0.18 mg/kg. There were no significant differences (P>0.05) in the sensory (color, flavor intensity, flavor liking, texture, tenderness, juiciness) scores and overall acceptability of the beef sausages. The ash, fat, carbohydrate, water holding capacity, and peroxide value of the beef sausages were not affected (P>0.05) when RoPMF was used for the formulation. In general, the protein content of the RoPMF beef sausages was not affected negatively. The cost of producing a kilogram of beef sausages was GHS 31.50 (5.40), GHS 30.70 (5.26) for 0% RoPMF, 5% RoPMF, 10% RoPMF, and 15% RoPMF beef sausages, respectively. It is concluded that the formulation of beef sausages with roasted pearl millet flour did not negatively affect the sensory characteristics of the sausages, but improved it mineral composition and reduced production cost