HighTech and Innovation Journal
Not a member yet
317 research outputs found
Sort by
BERT: A Review of Applications in Sentiment Analysis
Full text linkE-commerce reviews are becoming more valued by both customers and companies. The high demand for sentiment analysis is driven by businesses relying on it as a crucial tool to improve product quality and make informed decisions in a fiercely competitive business environment. The purpose of this review paper is to explore and evaluate the applications of the BERT model, a Natural Language Processing (NLP) technique, in sentiment analysis across various fields. The model has been utilized in certain studies for various languages, restaurant businesses, agriculture, Automated Essay Scoring (AES), Twitter, and Google Play. The BERT model's fine-tuning steps involve using pre-trained BERT to perform various language understanding tasks. Text pre-processing is conducted to clean up the data and convert it to numbers before feeding it into BERT, which generates vectors for each input token. We found that BERT outperformed the norm on a range of general language understanding tasks, including sentiment analysis, paraphrase recognition, question-answering, and linguistic acceptability. The detection of neutral reviews and the presence of false reviews in the dataset are two problems that have an impact on the model's accuracy. Training is also slow because it is huge and there are many weights to update. Additional research could be conducted to improve the BERT model's accuracy by constructing a false review categorization model and providing more training to the model in recognizing neutral reviews. Doi: 10.28991/HIJ-2023-04-02-015 Full Text: PD
Reinventing Formulas for Construction Project Delay Index Due to Management and Production
Full text linkThe objective of this study is to construct a precise formula for the management and production delay indicators that are integrated into Ms. Project's dashboard. Two simulation techniques, such as the manual formula computation and calculation integrated into the Ms. Project dashboard, were employed. Due to management and the production team's tardiness, the data were obtained through trial-and-error methods. Excel was used to analyze the data, and Ms. Project was used to enter the calculations. The research showed that the Ms. Project dashboard formula gave more detailed information about the construction project, including: (1) contract value; (2) actual progress value during monitoring; (3) value of plan progress during monitoring; (4) progress deviation; (5) cause of delay; and (6) management delay index and production delay index. The novelty of this study is that project delays have traditionally been held against the production party (contractor), whereas implementation delays have never been taken against the management party (consultant). However, using this method makes it evident who is responsible for a project delay, whether it comes from management (a consultant) or the manufacturing side (a contractor). Doi: 10.28991/HIJ-2023-04-04-06 Full Text: PD
Study on the Test Error of Silt Dynamic Characteristic and Its Influence on the Peak Ground Acceleration
Full text linkIn order to grasp the nonlinear experimental errors of dynamic shear modulus ratio (DSMR) and damping ratio (DR), as well as the current level of resonant column testing, the GZ-1 resonant column instrument was used to study the probability statistical indicators, basic laws, and the impact of experimental errors on peak acceleration of DSMR and DR of silt under 8 typical shear strains. The results show that, firstly, the DSMR and DR of silt under different shear strains obey normal distributions. Secondly, there is no significant difference between the reference range of the standard deviation of the DSMR and DR of silt and the outer envelope line. This result indicates that the dispersion of experimental errors for the same person is very small. Thirdly, in medium to hard sites, the influence of experimental errors in DSMR and DR on peak acceleration can be ignored. And the impact of DR test errors on peak acceleration should not be ignored on soft ground with a probability range exceeding 95%. Overall, the testing accuracy of the testing personnel proved to generally meet the requirements, while in other special cases, it is necessary to increase the number of parallel tests and improve the testing technology. Otherwise, it will cause certain risks to the estimation of seismic input for engineering structures. Doi: 10.28991/HIJ-2023-04-01-05 Full Text: PD
Role of the Magnitude of Digital Adaptability in Sustainability of Food and Beverage Small Enterprises Competitiveness
Full text linkThis study aimed to (1) determine and (2) improve the sustainability of competitiveness for the food and beverage business. This was achieved through causal studies, which involved determining causal relationships between variables. The study population was selected using a purposive sampling technique with a focus on small food and beverage entrepreneurs, and the data retrieved were analyzed using both quantitative and qualitative methods. Moreover, IBM SPSS AMOS 21 (Moment Structure Analysis) tool was used for the descriptive analysis as well as to test models and hypotheses. The results showed that stakeholder engagement had a positive and significant influence on the magnitude of digital adaptability and costless signaling. It was further noted that the magnitude of digital adaptability and costless signaling had the same effect on sustainability. A similar relationship was established between costless signaling and the magnitude of digital adaptability. These results proved that stakeholder engagement has a significant effect on cost-effective signaling and the magnitude of digital adaptability. Costless signaling has a significant effect on the magnitude of digital adaptability and sustainability of small food and beverage enterprises performance. The novelty of this study lies in the influence of stakeholder engagement on the magnitude of digital adaptability, which can be used to increase the sustainability and performance of food and beverage small enterprises. Doi: 10.28991/HIJ-2023-04-02-02 Full Text: PD
A Comparative Study of Sentiment Analysis Methods for Detecting Fake Reviews in E-Commerce
Full text linkThe popularity of the e-commerce system has increased, especially under the COVID scenario. Consumer product reviews from the past have had a significant impact on influencing consumers' purchasing decisions. Fake reviews”those written by humans and computers that engage in dishonest behavior”are consequently generated to increase product sales. The fake reviews hurt consumers and are dishonest. The goal of this research is to examine and evaluate the performance of various methods for identifying fake reviews. The well-known and widely-used Amazon Review Data (2018) dataset was used for this research. The first 10 product categories on Amazon.com with favorable feedback will be provided in the data section. After that, perform fundamental data preparation procedures such as special character trimming, bag of words, TF-IDF, etc. The models are trained to create a dataset for detecting fake reviews. This research compares the performance of four different models: GPT-2, NBSVM, BiLSTM, and RoBERTa. The hyperparameters of the models are also tuned to find the optimal values. The research concludes that the RoBERTa model performs the best overall, with an accuracy of 97%. GPT-2 has an overall accuracy of 82%, NBSVM has an overall accuracy of 95%, and BiLSTM has an overall accuracy of 92%. The research also calculates the Area Under the Curve (AUC) for each model and finds that RoBERTa has an AUC of 0.9976, NBSVM has an AUC of 0.9888, BiLSTM has an AUC of 0.9753, and GPT-2 has an AUC of 0.9226. It can be observed that the RoBERTa model has the highest AUC value, which is close to 1. Therefore, it can be concluded that this model provides the most accurate prediction for detecting fake reviews, which is the main focus of this research. Doi: 10.28991/HIJ-2023-04-02-08 Full Text: PD
Numerical Behavior of Extended End-Plate Bolted Connection under Monotonic Loading
Full text linkExtended end-plate connections, which act as joints providing resistance against moments between beams and columns, are commonly categorized as semi-rigid or partial-strength connections. The reason for their extensive application in steel frame constructions lies in their straightforward design, their ability to be reproduced easily, and the convenience they offer in the fabrication process. This research used the ABAQUS FE software to construct a three-dimensional finite element model (FEM) with the main objective of exploring how different geometric parameters impact the behavior of the extended end-plate bolted connection, which functions as a semi-rigid, partial-strength beam-to-column connection. Accurately determining the moment-rotation relationship and connection stiffness is of utmost importance for semi-rigid connections. The developed FEM models incorporate various factors such as geometric and material non-linearities, bolt pretension force, as well as contact and sliding between the connection elements. To establish the credibility of the numerical outcomes, the developed FEM model was meticulously calibrated and verified against experimental data obtained from previous studies available in the literature. Subsequently, using the validated finite element model, a parametric investigation was undertaken to evaluate the influence of distinct geometric parameters, namely the thickness of the end plate and column web stiffeners. This numerical model facilitates a comprehensive analysis of the extended end-plate bolted connection, encompassing critical aspects such as the moment-rotation curve and failure mode. The results demonstrated that the analyzed finite element model aligns well with experimental findings and that the use of column stiffeners is inevitable in the joint, as well as a moderated thickness of the end plate. Doi: 10.28991/HIJ-2023-04-02-04 Full Text: PD
Lip-Reading with Visual Form Classification using Residual Networks and Bidirectional Gated Recurrent Units
Full text linkLip-reading is a method that focuses on the observation and interpretation of lip movements to understand spoken language. Previous studies have exclusively concentrated on a single variation of residual networks (ResNets). This study primarily aimed to conduct a comparative analysis of several types of ResNets. This study additionally calculates metrics for several word structures included in the GRID dataset, encompassing verbs, colors, prepositions, letters, and numerals. This component has not been previously investigated in other studies. The proposed approach encompasses several stages, namely pre-processing, which involves face detection and mouth location, feature extraction, and classification. The architecture for feature extraction comprises a 3-dimensional convolutional neural network (3D-CNN) integrated with ResNets. The management of temporal sequences during the classification phase is accomplished through the utilization of the bidirectional gated recurrent units (Bi-GRU) model. The experimental results demonstrated a character error rate (CER) of 14.09% and a word error rate (WER) of 28.51%. The combination of 3D-CNN ResNet-34 and Bi-GRU yielded superior outcomes in comparison to ResNet-18 and ResNet-50. The correlation between increased network depth and enhanced performance in lip-reading models was not consistently observed. Nevertheless, the incorporation of additional trained parameters offers certain benefits. Moreover, it has demonstrated superior levels of precision in comparison to human professionals in the task of distinguishing diverse word structures. Doi: 10.28991/HIJ-2023-04-02-010 Full Text: PD
Revolutionizing Pharmaceutical Cold Chain Competency Framework with Reference Process Model and Reference Architecture
Full text linkThe utilization of the reference process model (RPM) and reference architecture (RA) as disruptive information and communication technologies (ICT) in the pharmaceutical cold chain (PCC) industry has enabled the management of tasks through a model-architecture-based approach. This research presents an innovative method for competency development in the cold chain sector, leveraging RPM and RA. By introducing a comprehensive conceptual framework encompassing RPM and RA design and workflow into cold chain competency development, this study outlines the key areas for incorporating RPM and RA into the PCC field. The framework elucidates the functioning of RPM and RA concerning occupational standards (OS) and units of competencies (UOC) within the industry. The study generates a research framework for the PCC industry by systematically implementing RPM and RA using a proposed method. The primary outcomes and empirical evidence are UOC and OS derived from RPM and RA implementation and integration, substantiating the conceptual framework's validity. The research highlights the evolutionary aspects and the significance of the conceptual framework in guiding the research framework and proposes a method for competency development. Furthermore, recommendations are provided for future research endeavors. Doi: 10.28991/HIJ-2023-04-02-011 Full Text: PD
Simulation of Vehicular Bots-Based DDoS Attacks in Connected Vehicles Networks
Full text linkConnected vehicles are more vulnerable to attacks than wired networks since they involve rapid mobility, continuous data flow across connected nodes, and dynamic network design in a distributed network environment. Distributed Denial of Service (DDOS) is one of the most common and dangerous security attacks on connected vehicle networks. Attackers can remotely control malicious nodes that are programmed to attack other nodes known. The compromised nodes are known as botnets, which will constantly flood the target nodes with User Datagram Protocol (UDP) packets, disrupting the target nodes data flow and operation. Hence, the goal of this research is to create and simulate a vehicular bot-based Distributed Denial of Service (DDoS) assault in connected vehicle networks. A simulation-based methodology is implemented to observe the impact of the number of bots, DDoS rate, and maximum bulk packet size on network performance. Using the NS-3 network simulator, 73 random mobile vehicle nodes with up to 100 vehicle bots were simulated, and the results are discussed. Regardless of the computational constraints, the findings from this study adds to understanding the risks and problems associated with data transmission by analyzing the impact of vehicular bot-based DDoS attacks on connected vehicle performance. Doi: 10.28991/HIJ-2023-04-04-014 Full Text: PD
Workhorse or White Elephant? End User Acceptance of ERP System in a Shared Service Center
Full text linkBusinesses globally heavily invest in Enterprise Resource Planning (ERP) implementation to meet high customer demands and maintain competitiveness. Despite significant investments, underutilization hampers reaping the system's full benefits, leading to stagnant or adverse performance. Hence, this study aims to uncover reasons for the lack of end-user adoption of ERP systems. It focuses on the correlation between performance expectancy, effort expectancy, social influence, and organizational support in determining ERP system acceptance by end users. This study utilized a quantitative methodology. Data were collected from 392 respondents within a Malaysian shared service center. Multiple regression analysis was conducted employing the UTAUT model and perceived organizational support theory to evaluate and interpret the collected data. The study's key findings include the significant positive association between performance expectancy and ERP system adoption, reinforcing the influence of effort expectancy on technology adoption. Despite its positive effects, social influence had little effect on end-user adoption. Additionally, it was observed that ERP system adoption was consistently facilitated by organizational support. This study confirms the essential factors that drive the adoption of ERP systems by end-users. It emphasizes the crucial role of leadership in prioritizing these elements for organizations to enhance user acceptance and ensure the successful implementation of ERP systems. Doi: 10.28991/HIJ-2023-04-04-013 Full Text: PD