cover
Contact Name
Andi Adriansyah
Contact Email
andi@mercubuana.ac.id
Phone
+628111884220
Journal Mail Official
admin@asasijournal.id
Editorial Address
Surapati Core M3, Jl. Surapati, Bandung, Jawa Barat
Location
Kota bandung,
Jawa barat
INDONESIA
Journal of Integrated and Advanced Engineering (JIAE)
ISSN : 2774602X     EISSN : 27746038     DOI : https://dx.doi.org/10.51662/jiae
Journal of Integrated and Advanced Engineering JIAE adalah jurnal ilmiah peer-review yang menerima makalah penelitian yang terkait erat dengan bidang Teknik, seperti Mekanik, Listrik, Industri, Sipil, Kimia, Material, Fisik, Komputer, Informatika, Lingkungan dan Arsitektur.
Articles 59 Documents
Learning a Multimodal 3D Face Embedding for Robust RGBD Face Recognition Ahmed Rimaz Faizabadi; Hasan Firdaus Mohd Zaki; Zulkifli Zainal Abidin; Muhammad Afif Husman; Nik Nur Wahidah Nik Hashim
Journal of Integrated and Advanced Engineering (JIAE) Vol 3, No 1 (2023)
Publisher : Asosiasi Staf Akademik Perguruan Tinggi Seluruh Indonesia (ASASI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51662/jiae.v3i1.84

Abstract

Machine vision will play a significant role in the next generation of IR 4.0 systems. Recognition and analysis of faces are essential in many vision-based applications. Deep Learning provides the thrust for the advancement in visual recognition. An important tool for visual recognition tasks is Convolution Neural networks (CNN). However, the 2D methods for machine vision suffer from Pose, Illumination, and Expression (PIE) challenges and occlusions. The 3D Race Recognition (3DFR) is very promising for dealing with PIE and a certain degree of occlusions and is suitable for unconstrained environments. However, the 3D data is highly irregular, affecting the performance of deep networks. Most of the 3D Face recognition models are implemented from a research aspect and rarely find a complete 3DFR application. This work attempts to implement a complete end-to-end robust 3DFR pipeline. For this purpose, we implemented a CuteFace3D. This face recognition model is trained on the most challenging dataset, where the state-of-the-art model had below 95% accuracy. An accuracy of 98.89% is achieved on the intellifusion test dataset. Further, for open world and unseen domain adaptation, embeddings learning is achieved using KNN. Then a complete FR pipeline for RGBD face recognition is implemented using a RealSense D435 depth camera. With the KNN classifier and k-fold validation, we achieved 99.997% for the open set RGBD pipeline on registered users. The proposed method with early fusion four-channel input is found to be more robust and has achieved higher accuracy in the benchmark dataset.
Design of Smart Shoes for Blind People Muhammad Aiman Mohd Razin; Muhammad Afif Husman; Siti Fauziah Toha; Aisyah Ibrahim
Journal of Integrated and Advanced Engineering (JIAE) Vol 3, No 1 (2023)
Publisher : Asosiasi Staf Akademik Perguruan Tinggi Seluruh Indonesia (ASASI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51662/jiae.v3i1.89

Abstract

Our daily lives depend heavily on our eyes. Eyesight is our most valuable gift, enabling us to see the world around us. However, some people suffer from visual impairments that hinder their ability to visualize such things. As a result, such people will experience difficulties moving comfortably in public places. One crucial aspect of mobile accessibility is detecting elevation changes. These include changes in the height of the ground or a floor, such as stairs, curbing, and potholes. They are common in both indoor and outdoor environments. People who are blind or visually impaired must detect these changes and assess their distance and extent to navigate them safely and effectively. Depth perception is essential to doing so and can be challenging for those with visual impairments. Therefore, this research aims to design a smart shoe that assists in climbing up and down the stairs using an IMU sensor to detect the user's movement. Before constructing a controller, the system is modelled using mathematical and physical modelling. Mathematical modelling is derived based on the mobility of people with visual impairment. The smart shoes are modelled in a 3D virtual world using the SolidWorks software. In addition, the shoe integrates with ultrasonic sensors whenever it detects any obstacles or barriers; they alert the users via vibration. This resulted in the intelligent shoes unlocking the heels whenever the low or high elevation was detected and vibrating if there was an obstacle. With the help of this device, the confidence level of people with visual impairment to walk independently will be improved.
Conversational Analysis Agents for Depression Detection: A Systematic Review Akeem Olowolayemo; Maymuna Gulfam Tanni; Intiser Ahmed Emon; Umayma Ahhmed; ‘Arisya Mohd Dzahier; Md Rounak Safin; Nusrat Zahan Nisha
Journal of Integrated and Advanced Engineering (JIAE) Vol 3, No 1 (2023)
Publisher : Asosiasi Staf Akademik Perguruan Tinggi Seluruh Indonesia (ASASI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51662/jiae.v3i1.85

Abstract

Depression is known as a non-cognitive disturbance that can be seen among different people all over the world. This pertains to disorders that have affected cognitions and behaviors that arise from overt disorders in cerebral function. It is more common for young adults to elderly people based on lifestyles, work pressure, personal problems, diseases, people who had strokes or hemorrhages, certain brain diseases, and paralysis. This paper is focused on reviewing the research papers previously done on detecting depression. Utilizing predefined search systems, we have gone through a couple of studies zeroing in on gloom and involved conversational information for location and conclusion. The objective of this research is to review large research studies on whether conversational agents can detect and diagnose depression by using smart texting analysis. The study was done by searching IEEE Xplore, Sci-hub, Doi, Scopus, and Pubmed using a predefined search strategy. This review was focused on studies that include the possibilities and steps of detecting depression and diagnosis that involved conversational data or analysis agents after assessing them by independent reviewers and relevancy for eligibility. After retrieving more than 117 references initially it was narrowed down to 95 references that were found relevant as most of them applied analytical techniques and technology-based solutions. Detecting depression and diagnosing it through smart texting analysis is a broad and emerging field and has a promising future but not every research studies were robust enough to get valid results in the end. This study aimed to keep the review as precise and informative as possible. 
Sentiment Analysis and Text Classification for Depression Detection Iffah Nadhirah Joharee; Nik Nur Wahidah Nik Hashim; Nur Syahirah Mohd Shah
Journal of Integrated and Advanced Engineering (JIAE) Vol 3, No 1 (2023)
Publisher : Asosiasi Staf Akademik Perguruan Tinggi Seluruh Indonesia (ASASI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51662/jiae.v3i1.86

Abstract

Depression is an illness that can harm someone's life. However, many people still do not know that they are having depression and tend to express their feelings through text or social media. Thus, text-based depression detection could help in identifying the early detection of the illness. Therefore, the research aims to build a depression detection that can identify possible depression cues based on Bahasa Malaysia text. The data, in the form of text, has been collected from depressed and healthy people via a google form. There are three questions asked which are “Apakah kenangan manis yang anda ingat?”, “Apakah rutin harian anda?” and “Apakah keadaan yang membuatkan anda stress?” which obtained 172, 169 and 170 responses for each question respectively. All the datasets are stored in a CSV file. Using Python, TF-IDF was extracted as the feature and pipeline into several classifier models such as Random Forest, Multinomial Naïve Bayes, and Logistic Regression. The results were presented using the classification metrics of confusion matrix, accuracy, and F1-score. Also, another method has been conducted using the text sentiment techniques Vader and Text Blob onto the datasets to identify whether depressive text falls under negative sentiment or vice versa. The percentage differences were determined between the actual sentiment compared to Vader and Text Blob sentiment. From the experiment, the highest score is achieved by AdaBoost Classifier with a 0.66-F1 score. The best model is chosen to be utilized in the Graphical User Interface (GUI).
Enzymatic hydrolysis of cellulose banana stem (alkaline microwave-assisted pre-treatment) Samara, Faras Saskia; Novia, Novia; Melwita, Elda
Journal of Integrated and Advanced Engineering (JIAE) Vol 4, No 1 (2024)
Publisher : Akademisi dan Saintis Indonesia (ASASI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51662/jiae.v4i1.120

Abstract

The banana stem waste holds immense promise as a readily available and abundant source of lignocellulosic biomass, making it a compelling alternative for biofuel and biochemical applications. Therefore, this study focuses on investigating the impact of both time and substrate loading on the enzymatic hydrolysis of banana stem cellulose that has undergone alkaline microwave-assisted pre-treatment. The pre-treatment method involves subjecting the biomass to 5% KOH for 30 min, followed by microwave exposure at 300 W for 5 min, a process aimed at enhancing the accessibility of cellulose. Enzymatic hydrolysis experiments were carried out utilizing cellulase enzymes derived from Aspergillus niger, with variations in hydrolysis times (ranging from 5 to 45 h) and enzyme-to-substrate ratios (ranging from 1:1 to 1:10). The results of this investigation revealed a substantial improvement in hydrolysis efficiency, owing to the synergistic effects of alkaline microwave-assisted pre-treatment, signifying enhanced cellulose accessibility. Notably, the highest concentration of reducing sugars (1.3 mg mL−1) was achieved at a substrate-to-enzyme ratio of 1:1 and a hydrolysis duration of 45 h. These findings provide valuable insights into the conversion of lignocellulosic biomass, emphasizing the potential of integrated pre-treatment strategies for sustainable biorefinery applications. This research contributes to advancing our understanding of lignocellulosic biomass utilization, offering a promising avenue for biofuel and biochemical production from banana stem waste.
A study on the operational performance of the Trans Padang bus Corridor VI (City center - Andalas University) Adji, Bayu Martanto; Jonrinaldi, Jonrinaldi; Masrilayanti, Masrilayanti; Narny, Yenny; Andriani, Andriani; Handayani, Putri Bian; Putri, Amalia Yunia
Journal of Integrated and Advanced Engineering (JIAE) Vol 4, No 1 (2024)
Publisher : Akademisi dan Saintis Indonesia (ASASI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51662/jiae.v4i1.131

Abstract

Trans Padang is an integrated highway bus system in Padang City that has operated since January 2014. Buses run every day from 06.00 WIB to 19.00 WIB. No literature has been cited. Trans Padang Corridor VI Bus serves the corridor Andalas University to the city center, and the route distance is ±13. 14 km. In this research, a study was carried out to determine whether the operations of the Trans Padang Corridor VI Bus were following the Decree of the Director General of Land Transportation No. SK.687/AJ.206/DRJD/2002. Six parameters were studied: load factor, headway, waiting time, travel time, stopping time at bus stops, bus speed, and bus fleets. Two methods were used to collect data: a dynamic and static survey. dynamic survey was carried out to record the departure and arrival times of buses at each bus stop, the number of passengers getting on and off, the distance traveled by the bus, the bus route, the bus stop, the bus travel time, and the bus stopping time. static survey is carried out to record the arrival and departure times of buses at certain stops. The study results show that only the waiting time parameters follow the technical instructions; the existing waiting time is 6.03, and in the technical instructions, the waiting time is set at 5-10 minutes.
Collision avoidance of mobile robot using Alexnet and NVIDIA Jetson Nano B01 Kristanto, Ferryawan Harris; Iklima, Zendi
Journal of Integrated and Advanced Engineering (JIAE) Vol 4, No 1 (2024)
Publisher : Akademisi dan Saintis Indonesia (ASASI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51662/jiae.v4i1.118

Abstract

In this research, an intelligence collision avoidance system on a mobile robot was designed using the AlexNet image classifier method. AlexNet is a convolutional neural network architecture that managed to win the ImageNet Large Scale Visual Recognition Challenge in 2012. The dataset consists of three categorical labels: blocked right, blocked left, and free. Images of 224 x 224 pixels were trained into two CNN architectures: AlexNet and ResNet-18. The performance of both architectures was examined in a testing environment. The system was built without real-time obstacles, instead using the side boundaries of the test lane. Analogously, if the mobile robot moves either through the side lane or off track, then these conditions are defined as a crash. From the entire research that was done, it was determined that intelligence collision avoidance models based on AlexNet were the most reliable models, with an average accuracy deviation rate of 6,00%. The true pre-trained AlexNet adopted from PyTorch Transfer Learning had 92.22% overall accuracy, while the non-trained AlexNet achieved 90.81% accuracy. It is also supported by the evidence that Intelligence Collision Avoidance Model-1 and Model-3 based on AlexNet didn’t lead the mobile robot to spin out and were stable in the test lane.
Identification of Alzheimer's disease using Convolutional Neural Network Nnah, Cedric Obundaa; Zhang, Yu-Dong
Journal of Integrated and Advanced Engineering (JIAE) Vol 4, No 1 (2024)
Publisher : Akademisi dan Saintis Indonesia (ASASI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51662/jiae.v4i1.144

Abstract

Alzheimer's disease (AD) as a brain disease has caused a progressive, devastating effect on the memory and general mental and physical coordination of victims. The impact on victims is irreversible, and the cause has yet to be identified. The treatment at full-blown can be difficult, but it could be properly managed in the early phase. Hence, there is a need for an efficient and effective early diagnosis. Machine learning techniques have proved to be successful in image classification. It was on this premise that this paper adopted a machine learning approach. The approach used a convolutional neural network with transfer learning to classify structural Magnetic Resonance Images (sMRI) into a multi-classification of 3 classes. The classes were Normal Cognitive (NC), Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD). K-fold cross validation was employed to validate the test set. The sMRI subjects included 97 NC, 57 MCI, and 24 AD patients. The proposed method achieved an overall accuracy of 94% on classification based on the multiclass classification.
Exergy analysis and Exergetic sustainability index of package boiler Bustan, Muhammad Djoni; Haryati, Sri; Serigianto, Serigianto
Journal of Integrated and Advanced Engineering (JIAE) Vol 4, No 1 (2024)
Publisher : Akademisi dan Saintis Indonesia (ASASI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51662/jiae.v4i1.124

Abstract

Energy is one of the basic human needs. Economic growth and population growth in a country which continues to increase is directly proportional to the growth in energy needs required by society. Indonesia is the largest energy user in Southeast Asia, namely more than 36% of Southeast Asia's primary energy use. Utilization of the energy used will reduce the increase in production costs for an industry. The use of energy is better known as energy conservation. Energy and exergy analysis based on the first and second laws of thermodynamics is used to analyze the thermal system of industrial units. This can be applied to equipment units in the fertilizer industry to identify sources of inefficiency, determine their location and the amount of exergy destruction that occur. To reduce exergy destruction, this can be done by modifying the operating conditions of the package boiler. The results show that 94.3% of the total exergy destruction from the boiler package is obtained from the evaporator component with a value of 2.7 x 108 kJ/hr Modification of the operating conditions of the evaporator is carried out by reducing Boiler Feed Water (BFW) inlet temperature with T 100C (196 – 116 oC). The decrease BFW temperature will increase the amount of required latent heat and reduce the convection heat that will be carried by the flue gas to generate superheated steam. Optimization of the BFW temperature is performed be calculating the flue gas temperature and exergoeconomic analysis. Exergoeconomic analysis is performed by calculating the cost rate of exergy destruction (ĊD,k) and exergoeconomic factor (fk). The results obtained were that the temperature was optimum of BFW is at 161°C which resulted the reduction of exergy destruction of 6,2x106 kJ/hr and resulting difference cost losses based on actual data (196 oC) of Rp 1,370,354,743/hr. Exergetic Sustainability Index (ESI) used to demonstrate how reducing a system's environmental impact can be achieved by reducing its exergy consumption (destruction and losses) or increasing its exergetic efficiency. In this research, ESI Value was achieved at 0.918.
The effect of rising prices of subsidized fuel on the use of private cars Yosritzal, Yosritzal; Anisa, Zahra; Putri, Elsa Eka
Journal of Integrated and Advanced Engineering (JIAE) Vol 4, No 1 (2024)
Publisher : Akademisi dan Saintis Indonesia (ASASI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51662/jiae.v4i1.125

Abstract

The rising fuel prices on September 3, 2022, are expected to reduce the use of private cars and increase the use of public transport. This expectation has raised optimism among public transport operators and is expected to encourage them to invest more. However, there is no evidence to support the expectation. Therefore, it is essential to study the effect of the fuel price on the use of a particular transport mode, thus motivating this study. This paper aims to investigate the impact of the rising costs of subsidized fuel on private cars. A Likert-scale type of questionnaire was used to collect data. The data was analyzed descriptively, and then a conclusion was made based on the results. The study found that the daily commute of respondents changed after fuel prices increased. Distance, duration, and frequency of travel tend to be reduced and prioritized over primary activities. To reduce travel costs, the respondents who usually use cars are more likely to use motorcycles than public transport. The findings of this study disprove that an increase in fuel prices would increase the use of public transport. Why is public transport less favoured compared to motorcycles? It seems that the quality of service provided by public transport fails to satisfy the consumers' needs.