Search Results (22)

With the rapid development of in-vehicle communication technology, the Internet of Vehicles (IoV) is gradually becoming a core component of next-generation transportation networks. However, ensuring the activity and reliability of IoV nodes remains a critical challenge. The emergence of blockchain technology offers new solutions to the problem of node selection in IoV. Nevertheless, traditional blockchain networks may suffer from malicious nodes, which pose security threats and disrupt normal blockchain operations. To address the issues of low participation and security risks among IoV nodes, this paper proposes a federated learning (FL) scheme based on blockchain and reputation value changes. This scheme encourages active involvement in blockchain consensus and facilitates the selection of trustworthy and reliable IoV nodes. First, we avoid conflicts between computing power for training and consensus by constructing state-channel transitions to move training tasks off-chain. Task rewards are then distributed to participating miner nodes based on their contributions to the FL model. Second, a reputation mechanism is designed to measure the reliability of participating nodes in FL, and a Proof of Contribution Consensus (PoCC) algorithm is proposed to allocate node incentives and package blockchain transactions. Finally, experimental results demonstrate that the proposed incentive mechanism enhances node participation in training and successfully identifies trustworthy nodes. Full article

The development of electricity spot markets necessitates more refined and accurate load forecasting capabilities to enable precise dispatch control and the creation of new trading products. Accurate load forecasting relies on high-quality historical load data, with complete load data serving as the cornerstone for both forecasting and transactions in electricity spot markets. However, historical load data at the distribution network or user level often suffers from anomalies and missing values. Data-driven methods have been widely adopted for anomaly detection due to their independence from prior expert knowledge and precise physical models. Nevertheless, single network architectures struggle to adapt to the diverse load characteristics of distribution networks or users, hindering the effective capture of anomaly patterns. This paper proposes a PLS-VAE-BiLSTM-based method for anomaly identification and correction in load data by combining the strengths of Variational Autoencoders (VAE) and Bidirectional Long Short-Term Memory Networks (BiLSTM). This method begins with data preprocessing, including normalization and preliminary missing value imputation based on Partial Least Squares (PLS). Subsequently, a hybrid VAE-BiLSTM model is constructed and trained on a loaded dataset incorporating influencing factors to learn the relationships between different data features. Anomalies are identified and corrected by calculating the deviation between the model’s reconstructed values and the actual values. Finally, validation on both public and private datasets demonstrates that the PLS-VAE-BiLSTM model achieves average performance metrics of 98.44% precision, 94% recall rate, and 96.05% F1 score. Compared with VAE-LSTM, PSO-PFCM, and WTRR models, the proposed method exhibits superior overall anomaly detection performance. Full article

Real estate mass appraisal is increasingly gaining popularity as a critical issue, reflecting its growing importance and widespread adoption in economic spheres. And data-driven machine learning methods have made new contributions to enhancing the accuracy and intelligence level of mass appraisal. This study employs python web scraping technology to collect raw data on second-hand house transactions spanning from January 2015 to June 2023 in China. Through a series of data processing procedures, including feature indicator acquisition, the removal of irrelevant sample cases, feature indicator quantification, the handling of missing and outlier values, and normalization, a dataset suitable for direct use by mass appraisal models is constructed. A dynamic neural network model composed of three cascaded sub-models is designed, and the optimal parameter combination for model training is identified using grid searching. The appraisal results demonstrate the reliability of the dynamic neural network model proposed in this study, which is applicable to real estate mass appraisal. A comparison with the common methods indicates that the proposed model exhibits a superior performance in real estate mass appraisal. Full article

In response to the recent formalization of Filipino Sign Language (FSL) and the lack of comprehensive studies, this paper introduces a real-time FSL gesture recognition system. Unlike existing systems, which are often limited to static signs and asynchronous recognition, it offers dynamic gesture capturing and recognition of 10 common expressions and five transactional inquiries. To this end, the system sequentially employs cropping, contrast adjustment, grayscale conversion, resizing, and normalization of input image streams. These steps serve to extract the region of interest, reduce the computational load, ensure uniform input size, and maintain consistent pixel value distribution. Subsequently, a Convolutional Neural Network and Long-Short Term Memory (CNN-LSTM) model was employed to recognize nuances of real-time FSL gestures. The results demonstrate the superiority of the proposed technique over existing FSL recognition systems, achieving an impressive average accuracy, recall, and precision rate of 98%, marking an 11.3% improvement in accuracy. Furthermore, this article also explores lightweight conversion methods, including post-quantization and quantization-aware training, to facilitate the deployment of the model on resource-constrained platforms. The lightweight models show a significant reduction in model size and memory utilization with respect to the base model when executed in a Raspberry Pi minicomputer. Lastly, the lightweight model trained with the quantization-aware technique (99%) outperforms the post-quantization approach (97%), showing a notable 2% improvement in accuracy. Full article

Electronic toll collection (ETC) data mining has become one of the hotspots in the research of intelligent expressway extension applications. Ensuring the integrity of ETC data stands as a critical measure in upholding data quality. ETC data are typical structured data, and although deep learning holds great potential in the ETC data restoration field, its applications in structured data are still in the early stages. To address these issues, we propose an expressway ETC missing transaction data restoration model considering multi-attribute features (MAF). Initially, we employ an entity embedding neural network (EENN) to automatically learn the representation of categorical features in multi-dimensional space, subsequently obtaining embedding vectors from networks that have been adequately trained. Then, we use long short-term memory (LSTM) neural networks to extract the changing patterns of vehicle speeds across several continuous sections. Ultimately, we merge the processed features with other features as input, using a three-layer multilayer perceptron (MLP) to complete the ETC data restoration. To validate the effectiveness of the proposed method, we conducted extensive tests using real ETC datasets and compared it with methods commonly used for structured data restoration. The experimental results demonstrate that the proposed method significantly outperforms others in restoration accuracy on two different datasets. Specifically, our sample data size reached around 400,000 entries. Compared to the currently best method, our method improved the restoration accuracy by 19.06% on non-holiday ETC datasets. The MAE and RMSE values reached optimal levels of 12.394 and 23.815, respectively. The fitting degree of the model to the dataset also reached its peak ($R^2$ = 0.993). Meanwhile, the restoration stability of our method on holiday datasets increased by 5.82%. An ablation experiment showed that the EENN and LSTM modules contributed 7.60% and 9% to the restoration accuracy, as well as 4.68% and 7.29% to the restoration stability. This study indicates that the proposed method not only significantly improves the quality of ETC data but also meets the timeliness requirements of big data mining analysis. Full article

Individualized learning plans and corresponding training programs are maintained and organized in most organizations. Employees may be averse to training if they do not see how it contributes to their professional advancement. This is an example of conflict between management and employee interests in a business. The misalignment between management’s offerings and employees’ desires is a significant factor contributing to such a situation. Our research focused on how companies and individuals put training resources to use from a perspective of divergent goals. It provides insights into making employee training more effective. We investigate the relationship between organizational, individual, and training efficacy using the principal–agent theory and the concept of bounded rationality. We attempted to validate three a priori conditions relating to goal congruence, training motivation, and decision-making through in-depth interviews and focus group discussions. As per participant inputs, career aspirations drive employees’ training preferences. The significance of goal congruence in achieving corporate objectives is often neglected in the academic literature. Although goal congruence can be a useful tool in assisting organizations in achieving their stated objectives, enhanced communication and discussion between managers and employees are required in order to improve and align employee goals with the company’s, for the sake of the individual’s and organization’s development. Furthermore, firms should invest in technology-enabled learning that ensures better access to learning, in order to achieve the kind of productivity and profit margins that would benefit everyone involved. We have also proposed a training value transaction model that accommodates the diverse interests. The model depicts the role of goal congruence in enhanced value fulfilment of the principals as well as agents. Full article

Credit card transactions may contain some categorical attributes with large domains, involving up to hundreds of possible values, also known as high-cardinality attributes. The inclusion of such attributes makes analysis harder, due to results with poorer generalization and higher resource usage. A common practice is, therefore, to ignore such attributes, removing them, albeit wasting the information they provided. Contrariwise, this paper reports our findings on the positive impacts of using high-cardinality attributes on credit card fraud detection. Thus, we present a new algorithm for domain reduction that preserves the fraud-detection capabilities. Experiments applying a deep feedforward neural network on real datasets from a major Brazilian financial institution have shown that, when measured by the F-1 metric, the inclusion of such attributes does improve fraud-detection quality. As a main contribution, this proposed algorithm was able to reduce attribute cardinality, improving the training times of a model while preserving its predictive capabilities. Full article

Present-day smartphones provide various conveniences, owing to high-end hardware specifications and advanced network technology. Consequently, people rely heavily on smartphones for a myriad of daily-life tasks, such as work scheduling, financial transactions, and social networking, which require a strong and robust user authentication mechanism to protect personal data and privacy. In this study, we propose draw-a-deep-pattern (DDP)—a deep learning-based end-to-end smartphone user authentication method using sequential data obtained from drawing a character or freestyle pattern on the smartphone touchscreen. In our model, a recurrent neural network (RNN) and a temporal convolution neural network (TCN), both of which are specialized in sequential data processing, are employed. The main advantages of the proposed DDP are (1) it is robust to the threats to which current authentication systems are vulnerable, e.g., shoulder surfing attack and smudge attack, and (2) it requires few parameters for training; therefore, the model can be consistently updated in real-time, whenever new training data are available. To verify the performance of the DDP model, we collected data from 40 participants in one of the most unfavorable environments possible, wherein all potential intruders know how the authorized users draw the characters or symbols (shape, direction, stroke, etc.) of the drawing pattern used for authentication. Of the two proposed DDP models, the TCN-based model yielded excellent authentication performance with average values of 0.99%, 1.41%, and 1.23% in terms of AUROC, FAR, and FRR, respectively. Furthermore, this model exhibited improved authentication performance and higher computational efficiency than the RNN-based model in most cases. To contribute to the research/industrial communities, we made our dataset publicly available, thereby allowing anyone studying or developing a behavioral biometric-based user authentication system to use our data without any restrictions. Full article

Digital currencies such as Ethereum and XRP allow for all transactions to be carried out online. To emphasize the decentralized nature of fiat currency, we can refer, for example, to the fact that all virtual currency users may access services without third-party involvement. Cryptocurrency price swings are non-stationary and highly erratic, similarly to the price changes of conventional stocks. Owing to the appeal of cryptocurrencies, both investors and researchers have paid more attention to cryptocurrency price forecasts. With the rise of deep learning, cryptocurrency forecasting has gained great importance. In this study, we present a long short-term memory (LSTM) algorithm that can be used to forecast the values of four types of cryptocurrencies: AMP, Ethereum, Electro-Optical System, and XRP. Mean square error (MSE), root mean square error (RMSE), and normalize root mean square error (NRMSE) analyses were used to evaluate the LSTM model. The findings obtained from these models showed that the LSTM algorithm had superior performance in predicting all forms of cryptocurrencies. Thus, it can be regarded as the most effective algorithm. The LSTM model provided promising and accurate forecasts for all cryptocurrencies. The model was applied to forecast the future closing prices of cryptocurrencies over a period of 180 days. The Pearson correlation metric was applied to assess the correlation between the prediction and target values in the training and testing processes. The LSTM algorithm achieved the highest correlation values in training (R = 96.73%) and in testing (96.09%) in predicting XRP currency prices. Cryptocurrency prices could be accurately predicted using the established LSTM model, which displayed highly efficient performance. The relevance of applying these models is that they may have huge repercussions for the economy by assisting investors and traders in identifying trends in the sales and purchases of different types of cryptocurrencies. The results of the LSTM model were compared with those of existing systems. The results of this study demonstrate that the proposed model showed superior accuracy based on the low prediction errors of the proposed system. Full article

As the volume of spatial data has rapidly increased over the last several decades, there is a growing concern about missing and incomplete observations that may result in biased conclusions. Several recent studies have reported that machine learning techniques can more efficiently address this limitation in emerging data sets than conventional interpolation approaches, such as inverse distance weighting and kriging. However, most existing studies focus on data from environmental sciences; so, further evaluations are required to assess their strengths and limitations for socioeconomic data, such as house price data. In this study, we conducted a comparative analysis of four commonly used methods: neural networks, random forests, inverse distance weighting, and kriging. We applied these methods to the real estate transaction data of Seoul, South Korea, and demonstrated how the values of the houses at which no transactions are recorded could be predicted. Our empirical analysis suggested that the neural networks and random forests can provide a more accurate estimation than the interpolation counterparts. Of the two machine learning techniques, the results from a random forest model were slightly better than those from a neural network model. However, the neural network appeared to be more sensitive to the amount of training data, implying that it has the potential to outperform the other methods when there are sufficient data available for training. Full article

The significance of human resources (HRs) has increased with the increasing awareness of sustainability issues and corporate social responsibility. However, the rapidly emerging financial technology (FinTech) sector still presents an HR challenge. Southeast Asia, which accounts for the highest adoption rate of mobile banking, has set new records regarding the number of transactions, as well as funding amount, in recent years. Moreover, borderless financial cooperation, coupled with in-demand tech talents, will rapidly boost the development of the region. Thus, this study explored the new opportunities as well as challenges of a new business model, FinTech, in Southeast Asia’s banking and enterprise sector in the post-COVID-19 era. It also examined how organizations can achieve sustainable development via the interaction of the new operating model with existing ones by developing relevant strategies in the context of the “new normal” working condition. By reviewing the literature on HR management (HRM), we proposed how banking and FinTech companies could supply tech talent with the relevant experience or engage in training projects before recruiting. Additionally, since organizations desire sustainability-minded employees, they offer flexible working arrangements and well-established reward policies that can create remote work performance and retention rates. Being committed to upskilling and reskilling global talent by offering talent mobility opportunities across the organization, as well as by fully embracing the creation of value for cross-cultural talent, companies can support their employees’ long-term career goals and maintain competitive strength. Finally, organizations must focus more on flexible adjustments and cross-domain communication for global talent. Forming strategic alliances with FinTech companies would be an alternative conduit that can ensure that regional laws comply with the local culture and national law, for bias and conflict reduction. Full article

Property rights of natural resources have been acting as a critical legislative tool for promoting sustainable resource utilization and conservation in various regions of the globe. However, incorporating ecological property rights into the natural resources property rights structure may significantly influence farmers’ behavior in forestry investment. It may also trigger forest protection, water conservation, and urban water security. The main aim of the research is to evaluate the impact of ecological property rights and farmers’ investment behavior in the economic forest. We have constructed an analytical framework of collective forest rights from two indicators of integrity and stability, by adopting the theory of property rights and ecological capital to fulfill the study’s aims. The empirical data has been comprised of the microdata of 708 farmers, collected from the confluence area of the Heihe Reservoir, Shaanxi, China. The study also conducted pilot ecological property rights transactions in the surveyed area. The study utilized the double-hurdle model to test the proposed framework empirically. The results show that forest land use rights, economic products, and eco-product income rights positively affect farmers’ forestry investment intensity, and disposal rights (forest land transfer rights) negatively affect farmers’ investment intensity. However, in terms of the integrity of property rights, only the right to profit from ecological products affects farmers’ forestry investment willingness, and other property rights are insignificant. The study also found that the lower the farmers’ forest land expropriation risk is expected, the greater the possibility of investment and the higher the input level. However, we traced that the farmers’ forest land adjustment has no significant impact on farmers’ willingness to invest. Obtaining the benefits of ecological products has been found as the primary motivation for forestry investment within the surveyed area. The completeness of ownership rights positively impacted farmers’ investment intensity. Farmers should realize the ecological value of water conservation forests through the market orientation of the benefit of ecological products. Therefore, the government should encourage farmers and arrange proper training to facilitate a smooth investment. A well-established afforestation program should also be carried out. Full article

The planning of activities of e-commerce enterprises and their behavior has been influenced by the emergence of the COVID-19 pandemic. The behavior of e-commerce enterprises has been highlighted at the level of EU countries through an analysis elaborated on four variables: the value of e-commerce sales, cloud computing services, enterprises that have provided training to develop/upgrade the ICT skills of their personnel, e-commerce, customer relationship management (CRM) and secure transactions. Using the hierarchical clustering method, analysis was carried out on these variables to identify certain economic and behavioral patterns of e-commerce activity from 2018 and 2020. The study of the relationships involved in the e-commerce activity of these enterprises is reflected in models of the economic behavior of 31 European states in relation to the targeted variables. The results show that the impacts of the COVID-19 pandemic are strongly manifested in the direction of the evolution of each indicator but differ from one country to another. The trends depend on the level of development and the particularities of each country’s economy in adapting to the repercussions reported in relation to the level of impact of the COVID-19 pandemic. This is highlighted by the significant regrouping of countries in 2020 compared with 2018 in relation to the average values of the indicators. The results show that, in 2020, the most significant percentages of the value of e-commerce sales were recorded in Belgium, Ireland and Czechia, as in 2018. In e-commerce, customer relationship management and secure transactions, Denmark and Sweden were superior in 2020 to the countries mentioned above, which were dominant in 2018. For the other two indicators, Finland and Norway were the top countries included in the analysis in both years. The conclusion supports the continuous model of e-commerce enterprise behavior in order to meet the requirements of online customers. Full article

The accurate estimation of real estate value helps the development of real estate policies that can respond to the complexities and instability of the real estate market. Previously, statistical methods were used to estimate real estate value, but machine learning methods have gained popularity because their predictions are more accurate. In contrast to existing studies that use various machine learning methods to estimate the transactions or list prices of real estate properties without separating the building and land prices, this study estimates land price using a large amount of land-use information obtained from various land- and building-related datasets. The random forest and XGBoost methods were used to estimate 52,900 land prices in Seoul, South Korea, from January 2017 to December 2020. The models were also separately trained for different land uses and different time periods. Overall, the results revealed that XGBoost yields a higher prediction accuracy. Whereas the XGBoost models were more accurate on the 2020 data than on the 2017–2020 data when analyzing residential areas, the random forest models were more accurate on the 2017–2020 data than on the 2020 data. Further analysis will extend the prediction model to consider submarkets determined by price volatility and locality. Full article

Getting to know the price that users assign to maintenance, repair and operations (MRO) has arisen as an essential consideration in gathering financial sustainability for metro public transport systems. The current research reveals customer reservation price for MRO in the main metro stations in Qatar. The purpose of the present work is to assess the willingness to pay for MRO services in eight metro stations in Doha in order to have a better understanding of user preferences. Qualitative research was carried out employing primary and secondary source of information. Primary data was collected by means of a mixture of data accumulation approaches: key informant meetings and focus-group conversations. Secondary data was collected from the account books, contracts, recordings of trans-actions, statements of work and activity reports given by the local rail committees. A stated preference investigation was applied through open text format questions to more than 1000 customers, and a Poisson regression model was used to evaluate the considerations affecting every higher value. Outputs reveal normal customer reservation prices per month and per train journey. The results also indicate a significant willingness to pay differential among the studied railway stations. The study of the decisive considerations elicits that the degree to which the MRO service can exclude paying consumers, the attending of rail conferences and the possibility of using another rail station are related with the customer reservation price. The outputs of this research are significant for railway public authorities willing to set up reasonable, adequate and realistic fares that support fund competent railway systems in Qatar. Full article