International Journal on Advanced Science, Engineering and Information Technology
Not a member yet
2006 research outputs found
Sort by
Decision Support System in Fisheries Industry: Current State and Future Agenda
Get PDFDecision Support Systems (DSS) are systems that assist decision-makers and aim to synthesize domain and technical knowledge and package it so non-scientists can use and comprehend it. This study aims to compile initial empirical studies that can objectively reject or confirm the central hypothesis. The materials were retrieved after applying the filtered query across all sources. All search engine providers use five query strings. In each example, five findings were collected, sorted, and compared to one another, and 152 papers were generated. Seventy-six documents were discovered after applying the inclusion and exclusion criteria. Each of the 70 papers was independently examined and analyzed. The method of study followed a specific procedure explicitly developed to minimize the risk of researcher bias. It is primarily concerned with whether fisheries have decision-making systems and what empirical outcomes these systems produce, particularly in real-time analysis. The result shows a dearth of research on intelligent DSS, which accounts for less than 3% of all DSS types discussed in the article. This study offers academics and professionals an overview of the implementation of DSS. These new contributions imply the form of several different new contributions to further research. Furthermore, the possibility of identifying research gaps increases once merged with geoinformation technology or spatial information. We introduced a new model that combines spatial logistics techniques with GIS-based tracing and tracking. The envisioned logistics ensure spatial and logistical traceability in the process of fish products
Eco-Efficiency Comparative Analysis of Informal and Formal Smartphone Recycling Practices Using Life Cycle Assessment
Get PDFDue to a lack of environmental protection awareness and knowledge, many practices informally recycle smartphone waste to get precious metals. Smartphones are hazardous and toxic waste materials, so they require proper handling not to cause problems for the environment. This study aims to measure the environmental impact and eco-efficiency level of formal recycling practices carried out by licensed companies and compare them with informal recycling practices carried out by the community. Environmental impact measurement uses Life Cycle Assessment with the eco-cost method. The measurement results show informal recycling practices have a higher environmental impact than formal recycling practices. Informal recycling practices harm almost every category, while formal recycling has a significant positive impact on the acidification and metal scarcity categories. Based on the value of the eco-efficiency index, formal recycling practices are affordable and sustainable and have an eco-efficiency level of 100%. Economically, formal recycling provides higher financial benefits than informal recycling. Thus, formal recycling practices are better and more profitable than informal recycling practices from the economic and environmental aspects. So, it is time for Indonesia to switch to a formal recycling process carried out by licensed companies considering the vast potential for waste as a raw material. The government's role is to invite the public to distribute smartphone waste to licensed recycling companies
Lower Limb Analysis Based on Surface Electromyography (sEMG) Using Different Time-frequency Representation Techniques
Get PDFUsing time-frequency representation techniques, projecting 1D sEMG signals onto a 2D image space can help diagnose several muscle activities. The acquired sEMG signal can provide valuable representative information about the muscle activity firing rates during muscle contraction. Different phases of muscle activity can be discernible via the sEMG signals by extracting discriminating features. The behavior of muscle activity was acquired in measurements of five muscles, i.e., RF, BF, VM, ST, and FX. Previous attempts to visualize lower limb analysis to extract sEMG features adopted One-dimensional (1D) sEMG segments. This work proposes a comparative experiment between three time-frequency representation techniques. The three time-frequency representation techniques, scalogram, spectrogram, and persistence spectrum, were used to map muscles' (1D) sEMG signal straightening the knee. The two-dimensional (2D) projected images are then fed into a convolutional neural network (CNN) model for detecting knee abnormality. The experiments are performed via 10-fold cross-validation. The number of kernels is incremented along with model layers. The fully connected layers were adjusted according to the loss value. Besides, tuning the hyper-parameters of the dropout parameters and the ReLU activation function to verify optimal performance. This research shows that the scalogram image representation gives significantly better performance than the spectrogram and persistence spectrum in recognizing knee abnormality. In addition, this study may help in guiding the diagnosis of several human muscle activities via the sEMG signal. A more diverse of muscles can be further investigated and can be useful for future work to enhance the diagnosis accuracy
Prediction of Drug Demand Based on Deep Learning Approach and Classification Model
Get PDFThe high demand for drugs in the last period has caused problems with drug shortages in several pharmacies. Almost all pharmacies experience the same problem, causing many people who do not to get their drug needs during the current pandemic. To overcome this, analyzing the process of predicting drug demand in the next period is necessary. The prediction process can be used as an initial solution in solving problems to see the number of drug demand numbers that will occur. This study aims to develop a predictive analysis model for drug demand using a deep learning approach and a classification model. Deep learning is an approach that does well in the case of prediction. The classification model also includes the right concept for solving the problem. The prediction and classification analysis methods include K-Means clustering, Multiple Linear Regression (MRL), Artificial Neural Network (ANN), and Decision Tree algorithms C.45. This method can provide better performance results in the prediction process to get precise and accurate output. Prediction results obtained from the learning process provide an accuracy rate of 99.99%. The output of the classification model also provides an overview of the knowledge base in the form of a decision tree. The level of classification model testing carried out gives the accuracy of the classification pattern of 97.05% so that the analytical model developed can predict future drug demand
Environmental Impact Assessment in the Synthesis of Antistatic Bionanocomposite Compared with the Synthesis of Polypropylene
Get PDFThis study aims to identify the environmental impact in the synthesis of antistatic bionanocomposites compared to polypropylene synthesis. It is done using the Life Cycle Assessment (LCA) method with SimaPro 9.1.1 software. The results showed that using 2% of M-DAG and 2.5% of CNC in the synthesis of antistatic bionanocomposites can reduce the environmental impact compared with the synthesis of PP. This is indicated by the decline in the impact value per impact categories, namely 4.46% of ADP, 3.70% of ADP-FF, 4.21% of GWP, 4.48% of ODP, 4.63% of HTP, 5.10% of FWAEP, 4.84% of MAEP, 2021% of TEP, 4.08% of POP, 4.41% of AP, and 4.85% of EP. After normalization of the impact category, the total environmental impact per function unit in antistatic bionancomposite synthesis is smaller than PP synthesis, with a percentage reduction of the environmental impact of 4.58%. The efficient use of energy and natural resources is considered necessary to reduce the environmental impact per kg of antistatic bionanocomposite pellets. The higher percentage of reduced by products, the lower total environmental impact per kg of antistatic bionanocomposite pellets. The application of reuse, reduce, and recycle methods on co-products from antistatic bio-nanocomposite synthesis needs to be done because it positively impacts the environment. Further research needs to be carried out to identify environmental impacts in synthesizing antistatic bionanocomposites in a wider scope of the study, namely cradle to grave, if possible
Analysis of Propagation Characteristics in Unmanned Aerial Vehicle (UAV) System
Get PDFUnmanned Aerial Vehicle (UAV) has gained great attention to the spread of communication in civilian and military applications. UAV communication channel has its own characteristics compared to cellular and satellite systems, which are widely used. Thus, an accurate channel characterization is very important to optimize the performance and design of an efficient UAV communication system. However, several challenges exist in UAV channel modeling. For example, channel propagation characteristics of UAVs are still less explored. Therefore, this research discusses the propagation characteristics of UAV communication systems. Due to the limitation of the measurement tools, the propagation characteristics identified in this research was the pathloss coefficient value and optimum height based on the value of Received Signal Strength Indicator (RSSI) measurement results at different distance and heights. The link communication used 433 MHz telemetry. The results of pathloss coefficient at heights of 10 m, 20 m, and 30 m are 1.56 m, 1.77 m, and 1.99 m. While the results of the optimum height of 10 m, 20 m, and 30 m are 1.39 m, 1.32 m, and 1.47 m
Analysis and Evaluation of PointNet for Indoor Office Point Cloud Semantic Segmentation
Get PDFIndoor modeling is one of the primary sources of information in building management due to the increased use of BIM in the AEC industry. The indoor model can be acquired with several survey instruments, but TLS is the most popular resulting point cloud that can be processed into a 3D model. However, the process commonly still uses inefficient manual methods. Point cloud data have irregular, unordered, unstructured characteristics, making them more challenging to process. The deep learning algorithm can be a solution to solve the problem. PointNet is the first deep learning algorithm that directly accepts point cloud data as input. This study aims to analyze and evaluate the office indoor point cloud segmentation using PointNet. The office indoor point cloud data was acquired using TLS and then pre-processed for deep learning input. Transfer learning strategy is used as a weight initialization technique. The pre-trained model was trained with the S3DIS dataset and then fine-tuned to segment nine indoor classes in this study. The result shows PointNet achieves 85% overall accuracy and 66% average class IoU score to predict indoor classes using this study’s point cloud data. Geometry control shows that the predicted point cloud has an RMSE score of 1.8 cm, meaning the geometries of the segmented point cloud are accurate. Using the transfer learning method has increased the performance of the deep learning model. Further research is needed to evaluate the model thoroughly using more training and evaluation data and different transfer learning strategies
EEG Time-Frequency Domain Analysis for Describing Healthy Subjects and Stroke Patients during Stroke Rehabilitation Motion Tasks
Get PDFTo overcome the long-term impact of stroke attacks on society, stroke rehabilitation is the only solution WHO and many healthcare organizations suggested. Until recently, stroke rehabilitation monitoring has been done using visual observation, which has several drawbacks. EEG is a new approach to understanding how the central nervous system controls motion. This study compares the motion pattern done by a group of 12 healthy subjects and nine stroke patients during the rehabilitation motion tasks using the OpenBCI system. Time-frequency domain features, namely PSD, MAV, and STD are used to explore how the patterns differ. Three rehabilitation motions are implemented: grasping, elbow flexion extension, and shoulder flexion-extension. The result shows that the healthy cross-brain correlation happens in healthy subjects. This means that when the left-side arm does the motion, the EEG feature values from the right hemisphere are higher, and vice versa. However, this healthy cross-brain correlation pattern did not happen within the stroke patient group. The overall value of PSD, MAV, and STD from both hemispheres during all motions is higher in the healthy group than in stroke patients. The type of motion also contributes to describing the time-frequency domain feature comparison. In conclusion, this gap value using time-frequency domain features can be used as a target for stroke rehabilitation programs by implementing the EEG technology to monitor it
Intention to Adopt Online Food Delivery Using Augmented Reality Mobile Apps: A Perspective of SOR Framework
Get PDFGlobally, the COVID-19 pandemic has affected all sectors, including the food and beverage industry. The pandemic has changed customers' behavior from dine-in services to online food ordering systems. Technology advancements make ordering food easier with Online Food Delivery (OFD) service. However, before buying food online, consumers require a physical assessment to decide to buy the food or beverage. Augmented Reality (AR) is a popular technology to show 3D virtual elements. Meanwhile, the stimulus-organism-response (SOR) framework can be used to analyze consumers' behavior. More specifically, the SOR model has been used to evaluate the user's behavior intention to accept online shopping apps. However, in the OFD context, there is a lack of research investigating the customer's intention to use the AR app based on the SOR perspective. This study aims to assess the factors influencing consumers' intention to adopt augmented reality apps. 52 AR OFD app customers participate in this study. Partial Least Square-Structural Equation Modeling (PLS-SEM) and SMARTPLS 3 was used to analyze the research model. This study evaluated from measurement and structural model. The measurement model using factor loading, Composite Reliability (CR), Average Variance Extracted (AVE), and heterotrait-monotrait (HTMT) ratio. The structural model assessed the variance inflation factor (VIF), R2, path coefficient (β), f2, and p-value. The results showed the significance of food image on hedonic, utilitarianism, and perceived informativeness. Furthermore, hedonism was the only determinant that positively influenced the customers' intention to use the AR OFD apps
Application of Analytical Hierarchy Process (AHP) in Determining the Development Strategy of Tempeh Processed Product
Get PDFThis study aims to determine the criteria and best strategies for developing new products processed tempeh in Surakarta City. The research design used is descriptive-analytical by basing data from key informants through in-depth interviews combined with focus group discussions. The collected data is compiled, analyzed, and discussed to illustrate the reality of tempeh-processed SMEs in the field. Aggregation techniques for making conclusions from diverse information using source triangulation. While analytical tools determine strategic priorities using the analytical hierarchy process (AHP). The study results obtained six criteria for developing new products for processed tempeh. These criteria are market demand, risk of production failure, tempeh processed technology that has been mastered, waste handling, absorbing labor, and profits. In contrast, the alternative strategies that are successfully formulated based on the SWOT matrix consist of three alternative strategies: product differentiation, improving product quality and packaging, and the legality of products supported by digital marketing. Based on AHP obtained, the most important criterion is profit. In contrast, the priority strategy for developing processed tempeh products is to improve the product's quality and packaging. This study provides helpful information in solving the problem of SMEs in determining the priorities of various alternatives faced by SMEs. AHP-based analysis can overcome the weakness of SMEs who do not orderly document quantitative data because AHP can process both quantitative and qualitative data