International Journal on Advanced Science, Engineering and Information Technology
Not a member yet
2006 research outputs found
Sort by
Performance of ShuffleNet and VGG-19 Architectural Classification Models for Face Recognition in Autistic Children
Full text linkThis study discusses the face recognition of children with special needs, especially those with autism. Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder that affects social skills, ways of interacting, and communication disorders. Facial recognition in autistic children is needed to help detect autism quickly to minimize the risk of further complications. There is extraordinarily little research on facial recognition of autistic children, and the resulting system is not fully accurate. This research proposes using the Convolution Neural Network (CNN) model using two architectures: ShuffleNet, which uses randomization channels, and Visual Geometry Group (VGG)-19, which has 19 layers for the classification process. The research object used in the face recognition system is secondary data obtained through the Kaggle site with a total of 2,940 image data consisting of images of autism and non-autism. The faces of autistic children are visually difficult to distinguish from those of normal children. Therefore, this system was built to recognize the faces of people with autism. The method used in this research is applying the CNN model to autism face recognition through images by comparing two architectures to see their best performance. Autism and non-autism data are grouped into training data, 2,540, and test data, as much as 300. In the training stage, the data was validated using validation data consisting of 50 autism image data and 50 non-autism image data. The experimental results show that the VGG-19 has high accuracy at 98%, while ShuffleNet is 88%
Investigation of Mechanical Properties and Thermal Analysis of Bagasse Fiber Reinforced Composite Polymer Foam
Full text linkBagasse is a waste used as a new material for foam polymer composites as reinforcement. This waste is quite a lot and has not been processed properly to become new material. This waste is adopted as ordinary organic fertilizer, incinerated, or disposed of. For that reason, it needs further research investigation. Due to its advantages, further investigation into the best composition is needed to achieve a tough composite material. It is a lightweight material with high economic value and can be used to overcome environmental problems. Therefore, this research obtains the mechanical properties and thermal analysis of the composite polymer foam reinforced with bagasse fibers. Part of the matrix is a thermoset polymer polyurethane (BQTN 157), and the reinforcement part is bagasse fiber. Bagasse was local waste from traders around Langsa City in Indonesia. The bagasse waste was processed into the fiber. The bagasse composition on a percentage weight ratio. They were mixed with resin and foam ingredients, blowing agent, and catalyst and poured into casting pattern composite material. A mesh of bagasse fiber was the size of 80. Thermogravimetric Analysis has made All specimens that need a tensile test to obtain the material’s strength and thermal stability. The result has found that the specimen of polymeric foam composite material with 5% bagasse fiber was obtained based on the results. The tensile strength values are 19.5 MPa. A thermal stability condition changes temperature between 39.95°C – 516.55°C
Blockchain Technology in Malaysian Context: Bibliometric Analysis and Systematic Review
Full text linkBlockchain technology has attracted widespread attention due to its compelling features, such as decentralization, transparency, and smart contracts, which can address significant issues in various industries in developing countries such as Malaysia. However, although several studies have arisen from diverse academic backgrounds addressing blockchain in Malaysia, no studies provide a comprehensive review and classification of the research in this field. The main goal of this research is to conduct a bibliometric analysis and systematic review of all blockchain papers published in Malaysia to understand the evolution of knowledge and present state and identify prospective future research fields. Web of Science and Scopus databases searched for existing literature on blockchain in Malaysia, and 76 papers were reviewed and categorized based on study purpose/focus, domain/sectors, the methodology employed, theories applied, and level of analysis. The findings show that blockchain is under-explored in Malaysia, and most current studies focus on Blockchain adoption in specific industries such as finance and supply chain management. However, in other areas, such as healthcare and education, Blockchain conceptual progress is still in its infancy. These findings are being utilized to suggest future research paths in this discipline, such as the need for methodological improvements and a theoretical basis to study blockchain in different sectors
Smart Machine Learning-based IoT Health and Cough Monitoring System
Full text linkCoronavirus 2019, more commonly known as COVID-19, was declared a global pandemic by the World Health Organization (WHO) on March 11, 2020. The β coronavirus culpable for the disease, SARS CoV-2, is known to be highly contagious with a relatively long incubation period of up to 14 days and is transmittable through small droplets, especially among people who are in close face-to-face contact. The Ministry of Health of Malaysia has recommended five days of quarantine for people who are positive for COVID-19 to avoid further disease transmission. Many resources are used to monitor patients throughout the quarantine period. Therefore, this project would like to present an IoT-enabled wearable device capable of monitoring COVID-19 quarantine patients by utilizing sensors to monitor the necessary health parameters and facilitate home quarantine. The low-cost ESP32 and Arduino Nano 33 BLE Sense microcontrollers are used in this device. They are connected to various IoT sensors to collect temperature, humidity, and sound data. The data obtained will then be uploaded to an IoT platform for doctors to analyze and monitor remotely via the health log throughout the 5-day quarantine period. An alert system is also devised to inform the medical staff if the patient is experiencing abnormal symptoms. The medical staff can then bring their attention to the patient and take the necessary actions to combat COVID-19
An Extensive Analysis of Digital Image Compression Techniques Using Different Image Files and Color Formats
Full text linkData storage on the device can affect the access speed of the device used; for example, files, images, and data will affect the performance of the device, become slow to access, difficult to open, download, and save images, files, because the available storage capacity is limited, with the problems that arise, an image compression technique is needed to minimize storage space and speed up the access. The compression technique can reduce a file, image, and data size but does not reduce the existing image's quality or lower the threshold during the sending or receiving. This research aims to reduce the size, speed up the process of accessing data on devices, and, more importantly, minimize memory space. It can also affect the bandwidth used when sending and receiving files and can speed up the process of sending from source to destination. The method used in this study is Lossy Compression, lose less Compression by comparing RLE, Huffman, and LZW using different image file types. For the Lossless Technique, the best quality reduction ratio is in binary image types, whether using a background or not using a background. The best results obtained are 99.10% (PNG Compression). Using the BMP file extension type, the recommended reduced ratio is lossy compression with format image BMP (JPG compression) for binary image using Lossless Compression has a good reduced ratio compression with an average of 99%
Assessing the Accuracy of Land Use Classification Using Multi-spectral Camera From LAPAN-A3, Landsat-8 and Sentinel-2 Satellite: A Case Study in Probolinggo-East Java
Full text linkThe LAPAN-A3 is the third microsatellite generation developed by the Research Center for Satellite Technology. The satellite can be used for land classification, agriculture monitoring, drought monitoring, and land use change. This study aims to classify land use and land cover in the research area. The main image used is LAPAN-A3; the compared images are Landsat-8 and Sentinel-2. Three images were taken on the same day and selected on cloud-free terms. The classification process starts with determining the region of interest (ROI) and the class. The classification is divided into six classes: water, forests, rice fields, settlements, open land, and coastal areas. The classification technique uses supervised learning with the maximum likelihood method. This study used Landsat 8 and Sentinel-2 data to compare the results obtained from LAPAN-A3. The accuracy test results for the LAPAN-A3 and Landsat-8 are 84.7042% and 0.783, respectively. While the accuracy test of LAPAN-A3 and Sentinel-2 is 72.2313%, the kappa value is 0.6394. The classification of two comparisons is quite accurate, with an accuracy of more than 70%. The LA3 classification successfully identifies water and coastal areas. The producer and accuracy is substantiated by comparing the results with both Landsat-8 and Sentinel-2 satellite data, which exhibit an accuracy rate exceeding 85%. Finally, LAPAN-A3 has great potential for classifying land use and land cover when compared to Landsat 8 and Sentinel-2 images, but future research should increase the number of datasets and vary the research area to improve the results
A Mobile Palmprint Authentication System Using a Modified MNT Algorithm, Circular Local Binary Pattern, and CNN (mobileNet)
Full text linkA few approaches have been proposed for hand segmentation in palmprint recognition. Skin-color information does not process sufficient information for discrimination in complex backgrounds and variable illumination. The use of guides has also been proposed, which restricts hand placement during capturing. Contour tracing algorithms have also been proposed in the literature. This worked in an even background scenario with no objects or patterns around the hand. In the case of uneven background with objects present, the traditional contour tracing algorithm cannot accurately segment the hand from the background. Hence, this paper proposes a modified Moore Neighbor Tracing (MNT) algorithm for hand detection and key-point extraction in complex backgrounds. The hand image is converted to grey, and the edges in the hand image are detected. The modified algorithm then transverses selected edges and returns the peak and valleys of each finger. This is then used to crop the palm. The modified algorithm improves the accuracy of hand detection in complex backgrounds with an F-Score of 0.8657. A mobile palmprint biometric system was also presented using Circular Local Binary Pattern (CLBP) and Convolutional Neural Network (CNN). The system showed an accuracy of 98.3% for hands captured with the mobile device and the CASIA online database. An accuracy of 99.0% was also recorded for GPDS and PolyU online databases
Hydraulic Analysis of Dredging Impacts in Downstream Reach of The Tulang Bawang River
Full text linkThe Tulang Bawang river is one of the largest rivers in Lampung Province, Indonesia, transporting humans and goods. Changes in upstream land use, climate, and sedimentation are silting the riverbed and disrupting transportation. To this end, investors and government agencies have submitted various proposals to carry out sand mining downstream to assist the local government in revitalizing transportation. However, some government and community assets are likely to be affected in the upstream part that is planned to be dredged. Therefore, this study aimed to conduct a modeling scenario of riverbed dredging in the lower reaches of the Tulang Bawang River from the estuary to 11.8 km upstream. It also aimed to review the impact on the environment, especially the impact of flooding and sedimentation by 17.8 km upstream, using the HEC-RAS software. The scenarios of upstream and downstream boundary conditions were used to determine the significance of the impact. The results showed that dredging would cause water level elevation to drop upstream and sediment deposition along the river section dredged. However, the decrease in river water level was insignificant for the upstream assets and beneficial for reducing flood inundation. The result of sedimentation analysis shows that river dredging leads to morphological changes and may have an environmental impact. Therefore, effective environmental management for dredging needs to be applied to minimize the environmental impact
On the Potential of Solar Energy for Chemical and Metal Manufacturing Plants in Malaysia
Full text linkThe manufacturing sector constitutes a cornerstone of Malaysia's economic landscape, significantly contributing to the nation's Gross Domestic Product (GDP). This pivotal role, however, is accompanied by substantial energy requirements, placing the manufacturing sector among the highest energy consumers across various industries in the country. This study primarily focuses on assessing the solar energy potential within the manufacturing sector. The objectives encompass two key facets: firstly, simulating the attainable energy yield from a photovoltaic (PV) system integrated into manufacturing industry facilities, and secondly, evaluating whether the PV system's generated electricity aligns with the energy requirements of selected manufacturing sectors, namely chemical and metal manufacturing plants. Sixteen companies have been selected from the chemical and metallurgical sectors for this study. The design process for the solar photovoltaic systems within these facilities necessitates determining the factory's location and rooftop area. Additionally, assessing the total savings is imperative to gauge the viability of the solar energy generated by these manufacturing plants. Among the 16 companies analyzed, intriguingly, 5 companies have demonstrated the capacity to fully transition to solar energy to cater to their energy needs. Notably, one of these companies can harness solar power to meet an impressive 179.91% of their energy demand by optimizing available space for solar power generation. This transition could potentially translate into substantial savings exceeding RM1 million in electricity costs
Performance Analysis of Environmental Monitoring System (EMS) towards POLMEDs Green Campus
Full text linkUI GreenMetric is a guide for higher education institutions to raise awareness of sustainable development, sustainable research, building a green campus, and social influence. There are six assessment categories in UI GreenMetric. One of them is energy and climate change. The assessment point in energy and climate change is the implementation of smart buildings within the campus area. There is often pollution on campus. The campus still uses groundwater for daily sanitation; workshops' waste is discharged directly into the ground without any sewage treatment process; many private vehicles are in the campus area; and 30% of campus land has been used as vehicle parking lots. It is necessary to carry out a monitoring process to determine the concentration of CO2 in the air. For this reason, further study is needed on smart features that will be built to support UI GreenMetric concepts. It is expected to help monitor water, soil, and air environmental parameters. This smart would later be monitored remotely using the Internet of Things (IoT) method. The maximum result of air temperature is 32,3°C, the maximum level of CO2 is 526,8 ppm, the minimum humidity level is 47,2%RH, and the maximum level of PAR is 589,3 µ*mol/m2*s. The noise maximum level is 84 dB, and pH water maximum is 7,01. The density of students also caused an increase in some parameters. POLMED must concentrate on environmental sustainability. Therefore, we should pay for internal recycling water treatment, reducing the use of private vehicles, and expanding green open space