HighTech and Innovation Journal
Not a member yet
317 research outputs found
Sort by
Contextual Semantic Embeddings Based on Transformer Models for Arabic Biomedical Questions Classification
Full text linkArabic biomedical question classification (ABQC) is a challenging task due to various reasons including, the specialized jargon expressed in Arabic language, complex semantics of Arabic vocabulary and the lack of specific datasets and corpora. When representing questions, only a few studies deal with ABQC by taking into account the word context. In this work, we propose a classification model designed for Arabic biomedical questions. We build vector representations capturing the contextual and semantic information of Arabic biomedical text, which presents numerous challenges, such as the derivational morphology of Arabic language, the specialized terminology of biomedical terms and the lack of capitalization in text. Our representation adapts the extensive knowledge encoded in BERT (Bidirectional Encoder Representations from Transformers) and other transformer models, to address the aforementioned challenges. Several experiments have been conducted on a dedicated Arabic biomedical dataset namely: MAQA, with well-known transformer models including BERT, AraBERT, BioBERT, RoBERTa, and DistilBERT fine-tuned for the classification task. Obtained results show that our method achieves remarkable performance with an accuracy of 93.31% and an F1-score of 93.35%. Doi: 10.28991/HIJ-2024-05-04-011 Full Text: PD
Exploring Key Factors Influencing Sports Enthusiasts' Purchase of Sponsored Brands
Full text linkThis research examines the purchasing intentions of soccer enthusiasts in China regarding products from sports sponsorship brands, extending the theory of planned behavior. The main goal is to evaluate how attitudes, subjective norms, brand identification, perceived brand quality, and corporate social responsibility influence these intentions. Data were gathered from 321 active soccer players using a structured questionnaire and analyzed with confirmatory factor analysis and structural equation modeling. Results show that attitudes, subjective norms, brand identification, and perceived brand quality significantly affect purchasing intentions. Furthermore, attitudes partially mediate the relationships between subjective norms, brand identification, perceived brand quality, and purchasing intentions. Corporate social responsibility also emerges as a vital factor, shaping brand identification, which in turn influences purchasing behavior. The findings indicate that sports sponsorship brands can increase purchasing intentions by enhancing product quality, engaging in corporate social responsibility, and fostering strong brand identification. This study offers a fresh perspective by applying the theory of planned behavior within the sports sponsorship context, enriching both theoretical insights and practical strategies. The results provide valuable recommendations for brand managers aiming to boost consumer engagement and loyalty through sponsorship initiatives. Doi: 10.28991/HIJ-2024-05-04-07 Full Text: PD
Fast and Accurate Pupil Estimation Through Semantic Segmentation Fine-Tuning on a Shallow Convolutional Backbone
Full text linkIn the diverse realms of computer vision, psychology, biometrics, medicine, and robotics, the accurate estimation of pupil size and position holds paramount importance for applications like eye tracking, medical diagnostics, and facial recognition. Traditional pupil estimation techniques often grapple with speed and error issues, impeding their applicability in real-world scenarios. To address this challenge, our study introduces an innovative approach that significantly enhances both the speed and accuracy of pupil estimation. This method hinges on the fine-tuning of a pre-trained semantic segmentation model integrated with a shallow convolutional neural network (CNN) backbone. Our methodology employs a dual-phase process: initially leveraging a robust pre-trained semantic segmentation model, subsequently refined through targeted fine-tuning using a diverse collection of eye images. This process intricately learns pupil characteristics, substantially elevating detection precision. The incorporation of a shallow CNN backbone streamlines the model, ensuring rapid processing suitable for real-time applications. The novelty of our approach lies in its adept handling of varying lighting and camera conditions, establishing new benchmarks in both speed and accuracy, as evidenced by our experimental findings. This advancement marks a significant leap in pupil estimation technology, offering a practical, efficient solution with far-reaching implications in several key technological domains. Doi: 10.28991/HIJ-2024-05-02-016 Full Text: PD
The Impact of Brand Value on Business Performance: An Analysis of Moderating Effects of Product Involvement
Full text linkThe purposes of this study are to investigate the impact of brand value on business performance and to examine whether the impact of brand value on business performance differs between high and low product involvement. Based on the top 100 brands ranked by Interbrand in 2021, linear regression analysis and moderation analysis by SPSS and AMOS were used to examine our proposed hypotheses. The results showed that brand value had a significantly positive effect on business performance. The findings imply that stronger brand valuation impacts are associated with companies that do better financially. In other words, business revenue is significantly determined by a higher brand valuation. The result of the moderation effect reveals that product involvement moderates the effect of brand value on business performance in such a way that the association between brand value and business performance is stronger in low-involvement products than in high-involvement products. The findings validate the notion that a marketer's endeavors toward brand investments constitute a noteworthy origin of activity that adds value. Our study is one of the first to investigate, using empirical data on leading brands across several industries, the impact that brand value can have on business performance. It also broadens the scope of existing understanding regarding the moderating effect of product involvement in regulating a brand's effectiveness. Doi: 10.28991/HIJ-2024-05-01-06 Full Text: PD
Real-Time Online Banking Fraud Detection Model by Unsupervised Learning Fusion
Full text linkDigital trades and payments are becoming increasingly popular, as they typically entail monetary transactions. This not only makes electronic transactions more convenient for the end customer, but it also raises the likelihood of fraud. An adequate fraud detection system with a cutting-edge model is critical to minimizing fraud costs. Identifying fraud at the ideal time entails establishing and setting up ubiquitous systems to consume and analyze massive amounts of streaming data. Recent advances in data analytics methods and introducing open-source technology for big data storage and processing opened new options for detecting fraud. This study aims to tackle this critical issue by providing a newly real-time e-transaction fraud detection schema that consolidates the advantages of both unsupervised learners, including autoencoder and extended isolation forests, with cutting-edge big data gadgets such as Spark streaming and sparkling water. It addresses the shortage of non-fraudulent instances and handles the excessive dimension of the set of features. On two real-world transactional datasets, we assess our suggested technique. Compared with other current fraud identification systems, our methodology delivers an elevated accuracy yield of 99%. Furthermore, it outperforms state-of-the-art approaches in reliably identifying fraudulent samples. Doi: 10.28991/HIJ-2024-05-01-014 Full Text: PD
IoT Attacks Detection Using Supervised Machine Learning Techniques
Full text linkIn recent times, the growing significance of Internet of Things (IoT) devices in people's lives is undeniable, driven by their myriad benefits. However, these devices confront cybersecurity threats akin to traditional network devices, as they depend on networks for connectivity and synchronization. Artificial Intelligence (AI) techniques, specifically Machine Learning (ML) and Deep Learning (DL), have demonstrated notable reliability in the field of cyberattack detection. This study focuses on detecting Flood and Brute Force cyberattacks using Machine Learning (ML) and Deep Learning (DL) models. The primary emphasis lies in identifying traffic features that significantly detect these types of attacks. The experimental study incorporates eight models: Decision Tree (DT), K-Nearest Neighbor (KNN), Random Forest (RF), Support Vector Machines (SVM), Logistic Regression (LR), Gradient Boosting (GB), Naí¯ve Bayes (NB), and Artificial Neural Network (ANN). Two sets of experiments were conducted, with the first set involving six features and the subsequent set, after feature selection, focusing on a reduced set of three features. The evaluation of the proposed model's efficiency and performance relied on metrics such as Accuracy, Precision, Recall, and F1-score. Remarkably, all proposed models exhibited high performance in both sets of experiments. However, the Gradient Boosting (GB) classifier suppressed others, attaining an impressive accuracy level of 95.94% and 95.28% in the sets with six features and three features, respectively. Doi: 10.28991/HIJ-2024-05-03-01 Full Text: PD
Prediction of Dust Emissions in Highway Subgrade-Filling Construction Based on Deep Neural Network
Full text linkDust pollution can harm the urban environment and the health of citizens. Each stage in highway construction generates unorganized dust emissions to varying degrees, which complicates their quantification. To precisely forecast dust emissions during the construction of highway subgrades and reduce the associated pollution risks, this study introduces a predictive model based on a deep neural network (DNN) for dust emissions during highway subgrade-filling operations. Dust concentration is treated as a nonlinear multivariate problem, with predictive indicators encompassing particulate matter 2.5 (PM2.5), particulate matter 10 (PM10), ground surface temperature, wind speed, air temperature, surface pressure, and relative humidity. Using a DNN model, this study forecasts the concentrations of PM2.5 and PM10 at highway construction sites. Based on a highway project in Hebei Province, this study predicts dust-emission concentrations via field monitoring conducted using self-developed equipment. The model's predictions exhibit a small mean-absolute-percentage error and root-mean-square error compared with the actual values, and the model's accuracy significantly surpasses that of conventional regression models. Accurate forecasting can facilitate the timely control of dust concentrations at construction sites, thus facilitating more environmentally friendly and efficient construction. Doi: 10.28991/HIJ-2024-05-02-03 Full Text: PD
Outlier Detection in VPN Authentication Logs for Corporate Computer Networks Access using CRISP-DM
Full text linkA Virtual Private Network (VPN) serves as a critical network access solution widely employed by corporations, enabling users to connect to company computer networks via a global infrastructure. Amid the ongoing Covid-19 pandemic, heightened reliance on computer network access has increased the vulnerability to data breaches by unauthorized parties. This necessitates a proactive approach from companies to safeguard data integrity, particularly by identifying abnormal access patterns and timestamps. This study aims to develop a model for detecting anomalous activities within authentication log data obtained from VPN usage. The dataset comprises log entries from September to November 2022, totaling 36,807 records, selected via a systematic sampling approach. Two key attributes, namely user ID and access time, are analyzed to trace access patterns. Employing the CRISP-DM method ensures a structured and efficient research process. The selection of the k value in the K-Nearest Neighbors (K-NN) method significantly impacts outlier detection and can be tailored to suit organizational requirements. By utilizing the K-Means algorithm for data clustering and K-NN for measuring inter-point distances, the study identifies outliers that warrant further investigation by the company. Integration of the proposed model into the company's big data platform facilitates real-time monitoring, enabling the security team to preemptively address potential threats and mitigate network access misuse. By enhancing awareness and responsiveness to information security risks, the model contributes to fortifying the company's cyber security posture amidst evolving digital landscapes. Doi: 10.28991/HIJ-2024-05-04-016 Full Text: PD
An Improved Fire Detection Algorithm Based on YOLOv8 Integrated with DGIConv, FourBranchAttention and GSIoU
Full text linkFire detection is highly important for people's lives and property, and enhancing its accuracy is essential. This study focused on utilizing and improving YOLOv8 to obtain higher detection accuracy for fire detection. Three methods were used. First, the newly designed DGIConv module replaces the original Conv module, thereby decreasing the computational complexity while enhancing the model's performance. Second, to enhance the recognition ability of flame targets, a new attention mechanism named FourBranchAttention was designed, and a comparison was made with other attention mechanisms. The experiments revealed that the newly designed attention mechanism performed best on the mAP50 and mAP50-95 metrics. Finally, to improve the convergence speed and localization ability of the model, the loss function is optimized by adopting better hyperparameters of the TaskAlignedAssigner and employing the newly designed GSIoU as an alternative to the original CIoU. Through ablation experiments, all three improvements improved the detection performance to a certain extent, and the model using the three improvements achieved the best performance. Compared with the baseline, the YOLOv8 model with DGIConv, FourBranchAttention, and the optimized loss function increased the mAP50 by 2.52% and the mAP50-95 by 3.37%. The mAP50 and mAP50-95 had reached 98.46% and 75.26%, respectively. Compared with previous models, such as SSD/YOLOv7, the performance metrics of enhanced YOLOv8 also exhibited significant enhancements, thereby augmenting the accuracy of fire detection. Doi: 10.28991/HIJ-2024-05-03-09 Full Text: PD
The Influence Factors of Economic Development of Tourism Industry
Full text linkObjectives: This paper aims to conduct research on the factors that impact the advancement of the tourism economy in order to adapt to the rapidly changing demands of the tourism market. Methods: A case study was performed using a gray correlation model to analyze the tourism industry in Henan Province. Findings: Among the first-level indicators, tourism economic support had the highest correlation with tourism economic development, followed by tourism physical base, tourism transportation influence, tourism human resources, and tourism information service. Then, relevant suggestions were given according to the analysis results. Novelty:The novelty of this article lies in utilizing the gray correlation model to examine the factors that influence the tourism economy and analyzing the gray system with incomplete information. Doi: 10.28991/HIJ-2024-05-01-03 Full Text: PD