Search Results (36)

With the increase in the amount of images online, the whole Internet is becoming an image database. Since there are so many available images, it is difficult for users to find the desired images. Unlike text search engines, image search engines cannot fully recognize the visual meaning of an image. In addition, it is difficult to obtain the desired images from the keywords provided by the user, since a keyword may contain multiple meanings. To solve these problems, this paper proposes a psychological intention diagram of past users, if inquiring using a keyword, to predict the images that these users want. Based upon the novel psychological diagram, this paper proposes a search engine that analyzes images in the sequential probing of the current user if he/she inquires after the same keywords as previous users. Moreover, this paper also constructs a psychological intention diagram of the designers of the web pages containing the keyword. This type of psychological intention diagram is used when a query is not issued by past users. To the best of our knowledge, this paper is the first one considering the psychological viewpoint of users and web designers in guiding the retrieval of the search engine. The experimental results show that the proposed image search engine has high precision; therefore, the method of providing images can help users to find their desired image more easily. Full article

With the development of the digital and intelligent transformation of the power grid, the structure and operation and maintenance technology of the power grid are constantly updated, which leads to problems such as difficulties in information acquisition and screening. Therefore, we propose a recommendation method for power knowledge retrieval based on a graph neural network (RPKR-GNN). The method first uses a graph neural network to learn the network structure information of the power fault knowledge graph and realize the deep semantic embedding of power entities and relations. After this, it fuses the power knowledge graph paths to mine the potential power entity relationships and completes the power fault knowledge graph through knowledge inference. At the same time, we combine the user retrieval behavior features for knowledge aggregation to form a personal subgraph, and we analyze the user retrieval subgraph by matching the similarity of retrieval keyword features. Finally, we form a fusion subgraph based on the subgraph topology and reorder the entities of the subgraph to generate a recommendation list for the target users for the prediction of user retrieval intention. Through experimental comparison with various classical models, the results show that the models have a certain generalization ability in knowledge inference. The method performs well in terms of the MR and Hit@10 indexes on each dataset, and the F1 value can reach 87.3 in the retrieval recommendation effect, which effectively enhances the automated operation and maintenance capability of the power system. Full article

Hepatocellular carcinoma (HCC) is the fourth most common malignancy worldwide and exhibits a universal burden as the incidence of the disease continues to rise. In addition to curative-intent therapies such as liver resection and transplantation, locoregional and systemic therapy options also exist. However, existing treatments carry a dismal prognosis, often plagued with high recurrence and mortality. For this reason, understanding the tumor microenvironment and mutational pathophysiology has become the center of investigation for disease control. The use of precision medicine and genetic analysis can supplement current treatment modalities to promote individualized management of HCC. In the search for personalized medicine, tools such as next-generation sequencing have been used to identify unique tumor mutations and improve targeted therapies. Furthermore, investigations are underway for specific HCC biomarkers to augment the diagnosis of malignancy, the prediction of whether the tumor environment is amenable to available therapies, the surveillance of treatment response, the monitoring for disease recurrence, and even the identification of novel therapeutic opportunities. Understanding the mutational landscape and biomarkers of the disease is imperative for tailored management of the malignancy. In this review, we summarize the molecular targets of HCC and discuss the current role of precision medicine in the treatment of HCC. Full article

This study proposes a random forest model to address the limited explanation of consumer purchase behavior in search advertising, considering the influence of anchoring effects on rational consumer behavior. The model comprises two components: prediction and explanation. The prediction part employs various algorithms, including logistic regression (LR), adaptive boosting (ADA), extreme gradient boosting (XGB), multilayer perceptron (MLP), naive bayes (NB), and random forest (RF), for optimal prediction. The explanation part utilizes the SHAP explainable framework to identify significant indicators and reveal key factors influencing consumer purchase behavior and their relative importance. Our results show that (1) the explainable machine learning model based on the random forest algorithm performed optimally (F1 = 0.8586), making it suitable for analyzing and predicting consumer purchase behavior. (2) The dimension of product information is the most crucial attribute influencing consumer purchase behavior, with features such as sales level, display priority, granularity, and price significantly influencing consumer perceptions. These attributes can be considered by merchants to develop appropriate tactics for improving the user experience. (3) Consumers’ purchase intentions vary based on the presented anchor point. Specifically, high anchor information related to product quality ratings increases the likelihood of purchase, while price anchors prompted consumers to compare similar products and opt for the most economical option. Our findings provide guidance for optimizing marketing strategies and improving user experience while also contributing to a deeper understanding of the decision−making mechanisms and pathways in online consumer purchase behavior. Full article

Wearable exoskeletons can help people with mobility impairments by improving their rehabilitation. As electromyography (EMG) signals occur before movement, they can be used as input signals for the exoskeletons to predict the body’s movement intention. In this paper, the OpenSim software is used to determine the muscle sites to be measured, i.e., rectus femoris, vastus lateralis, semitendinosus, biceps femoris, lateral gastrocnemius, and tibial anterior. The surface electromyography (sEMG) signals and inertial data are collected from the lower limbs while the human body is walking, going upstairs, and going uphill. The sEMG noise is reduced by a wavelet-threshold-based complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) reduction algorithm, and the time-domain features are extracted from the noise-reduced sEMG signals. Knee and hip angles during motion are calculated using quaternions through coordinate transformations. The random forest (RF) regression algorithm optimized by cuckoo search (CS), shortened as CS-RF, is used to establish the prediction model of lower limb joint angles by sEMG signals. Finally, root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) are used as evaluation metrics to compare the prediction performance of the RF, support vector machine (SVM), back propagation (BP) neural network, and CS-RF. The evaluation results of CS-RF are superior to other algorithms under the three motion scenarios, with optimal metric values of 1.9167, 1.3893, and 0.9815, respectively. Full article

Transfer learning (TL) has been proven to be one of the most significant techniques for cross-subject classification in electroencephalogram (EEG)-based brain-computer interfaces (BCI). Hence, it is widely used to address the challenges of cross-session and cross-subject variability with more accurate intention prediction. In this case, TL utilizes knowledge (signal features) in the source domain(s) to improve the classification in the target domain. However, current existing transfer learning approaches on EEG-based BCI are mostly limited to two-class cross-subject classification problems, while multi-class problems are only implemented with a focus on within-subject classification due to the complexity of multi-class cross-subject classification problems. In this paper, we first extended the transfer learning approaches to a multi-class cross-subject scenario, then investigated the reason for transfer learning performance being poor in multi-class cross-subject classification. Secondly, we address the challenge of significant sessional and subject-to-subject variations originating from both known and unknown factors. It is discovered that such variations have a massive influence on the classification because of the negative transfer (NT) across domains. Based on this discovery, we propose a multi-class transfer learning approach based on multi-source manifold feature transfer learning (MMFT) framework and an enhanced version to minimize the effects of NT. The proposed multi-class transfer learning approach extends the existing MMFT to multi-class cases. Then enhanced multi-class MMFT firstly searches for domains with high transferability and selects only the best combination among source domains (SD), then utilize the best-selected combination of domains for transfer learning. Experimental results illustrate that the proposed multi-class MMFT can be employed in the cross-subject classification of both three-class and four-class problems. Experimental results also demonstrated that the enhanced multi-class MMFT could effectively minimize the effect of negative transfer and significantly increase the prediction rates across individual target domains (TD). The highest classification accuracy (CA) of 98% is obtained by the enhanced multi-class MMFT. Full article

This systematic review synthesizes the findings of quantitative studies examining the relationships between Health Belief Model (HBM) constructs and COVID-19 vaccination intention. We searched PubMed, Medline, CINAHL, Web of Science, and Scopus using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and identified 109 eligible studies. The overall vaccination intention rate was 68.19%. Perceived benefits, perceived barriers, and cues to action were the three most frequently demonstrated predictors of vaccination intention for both primary series and booster vaccines. For booster doses, the influence of susceptibility slightly increased, but the impact of severity, self-efficacy, and cues to action on vaccination intention declined. The impact of susceptibility increased, but severity’s effect declined sharply from 2020 to 2022. The influence of barriers slightly declined from 2020 to 2021, but it skyrocketed in 2022. Conversely, the role of self-efficacy dipped in 2022. Susceptibility, severity, and barriers were dominant predictors in Saudi Arabia, but self-efficacy and cues to action had weaker effects in the USA. Susceptibility and severity had a lower impact on students, especially in North America, and barriers had a lower impact on health care workers. However, cues to action and self-efficacy had a dominant influence among parents. The most prevalent modifying variables were age, gender, education, income, and occupation. The results show that HBM is useful in predicting vaccine intention. Full article

It has been documented that there is a positive relationship between a worker’s subjective well-being and productivity, and individuals who are happy in their work have a better attitude when performing activities: happier employees are more productive. Turnover intention, on the other hand, may arise from various factors rather than merely the need to increase a salary, as the traditional economic theory states. The fact that the work performed does not contribute to the worker’s life purpose, that there might be a bad relationship with colleagues, or else might play a role in the search for a new job. This study aims to show the relevance of meaningful work in happiness at work and turnover intention. Data from 937 professionals, in 2019, in Mexico were analyzed. Regression analyses were used to assess the impact of meaningful work on happiness at work and turnover intention. Results show that meaningful work, feeling appreciated by coworkers, and enjoyment of daily tasks significantly predict happiness at work. A logit model showed that having a job that contributes to people’s life purpose, feeling appreciated, and enjoyment of daily tasks reduces turnover intention. The main contribution of the study is to identify the importance of elements of purpose and meaning in the work context, contributing to economic theory. Limitations include the use of single items from a more extensive survey, which might diminish the validity and reliability of the constructs under scrutiny. Future directions point towards the need for more robust indicators of the variables of interest, but the findings emphasize the importance of research focused on the meaning workers attribute to their own work and the effects this attribution might have on their own wellbeing, organizational results, and productivity, including a return of investment (ROI) indicators. Full article

Online-to-offline (O2O) commerce is a specific form of omnichannel retailing, wherein consumers search and purchase online and then consume offline. There are many different O2O models, and new O2O businesses are emerging during the COVID-19 pandemic; they can be categorized into two types of O2O services: to-shop and to-home. However, few studies have focused on consumer behavior in a comprehensive O2O scenario, and no study has attempted to compare the differences between to-shop and to-home consumers. Therefore, this study aimed to propose a universal model to predict consumers’ continued intention to use O2O services and to compare the differences between to-shop and to-home O2O in terms of factors influencing consumer behavior. A cross-sectional survey was conducted, and the PLS-SEM was used for data analysis. The basic SEM results indicated that habit, performance expectancy, confirmation, and offline facilitating conditions are the main predictors. The multigroup analysis showed differences between to-shop and to-home consumers regarding hedonic motivation, price value, and perceived risk. The study suggests that marketers and designers in various O2O scenarios can use the framework to build their business plans and develop different marketing strategies or sub-platforms for to-shop and to-home consumers. Full article

This study systematically analyzed the literature using the theory of planned behavior (TPB) as a theoretical framework to examine the influence of its constructs on vaccination intention against COVID-19. Quantitative studies were searched in PubMed, CINAHL, Web of Science, and Google Scholar following the PRISMA guidelines. The average rate of COVID-19 vaccination intention was 73.19%, ranging from 31% to 88.86%. Attitude had the strongest association with vaccination intention (r₊ = 0.487, 95% CI: 0.368–0.590), followed by subjective norms (r₊ = 0.409, 95% CI: 0.300–0.507), and perceived behavioral control (r₊ = 0.286, 95% CI: 0.198–0.369). Subgroup analyses showed that the pooled effect sizes of TPB constructs on vaccination intention varied across geographic regions and study populations. Attitude had large effect sizes in Asia, Europe, and Oceania, especially among the adult general population, parents, and patients. Subjective norms had large effect sizes in Asia and Oceania, especially among parents and patients. Perceived behavioral control was the most dominant predictor of vaccination acceptance in Africa among patients. These findings suggest that TPB provides a useful framework for predicting intention to receive a COVID-19 vaccine. Hence, public awareness and educational programs aimed at promoting COVID-19 vaccination intention should consider using TPB as a framework to achieve the goal. Full article

Computer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This article focuses on the development of an automated CAD system with the intent to perform diagnosis as accurately as possible. Deep learning methods have been able to produce impressive results on medical image datasets. This study employs deep learning methods in conjunction with meta-heuristic algorithms and supervised machine-learning algorithms to perform an accurate diagnosis. Pre-trained convolutional neural networks (CNNs) or auto-encoder are used for feature extraction, whereas feature selection is performed using an ant colony optimization (ACO) algorithm. Ant colony optimization helps to search for the best optimal features while reducing the amount of data. Lastly, diagnosis prediction (classification) is achieved using learnable classifiers. The novel framework for the extraction and selection of features is based on deep learning, auto-encoder, and ACO. The performance of the proposed approach is evaluated using two medical image datasets: chest X-ray (CXR) and magnetic resonance imaging (MRI) for the prediction of the existence of COVID-19 and brain tumors. Accuracy is used as the main measure to compare the performance of the proposed approach with existing state-of-the-art methods. The proposed system achieves an average accuracy of 99.61% and 99.18%, outperforming all other methods in diagnosing the presence of COVID-19 and brain tumors, respectively. Based on the achieved results, it can be claimed that physicians or radiologists can confidently utilize the proposed approach for diagnosing COVID-19 patients and patients with specific brain tumors. Full article

The effectiveness of early intensive interventions for Autism Spectrum Disorder (ASD) is now well-established, but there continues to be great interindividual variability in treatment response. The purpose of this systematic review is to identify putative predictors of response to two different approaches in behavioral treatment: Early Intensive Behavioral Interventions (EIBI) and the Early Start Denver Model (ESDM). Both are based upon the foundations of Applied Behavioral Analysis (ABA), but the former is more structured and therapist-driven, while the latter is more naturalistic and child-driven. Four databases (EmBase, PubMed, Scopus and WebOfScience) were systematically screened, and an additional search was conducted in the reference lists of relevant articles. Studies were selected if participants were children with ASD aged 12–48 months at intake, receiving either EIBI or ESDM treatment. For each putative predictor, p-values from different studies were combined using Fisher’s method. Thirteen studies reporting on EIBI and eleven on ESDM met the inclusion criteria. A higher IQ at intake represents the strongest predictor of positive response to EIBI, while a set of social cognitive skills, including intention to communicate, receptive and expressive language, and attention to faces, most consistently predict response to ESDM. Although more research will be necessary to reach definitive conclusions, these findings begin to shed some light on patient characteristics that are predictive of preferential response to EIBI and ESDM, and may provide clinically useful information to begin personalizing treatment. Full article

Hotel organizations today are in a state of constant change due to high competition, the emergence of pandemics, and cyclical economic crises. Hospitality employees are currently affected by job insecurity. The purpose of this research was to investigate the effect of job insecurity on intention to quit among hospitality workers, integrating the mediating effect of psychological distress and resistance to change and their mutual relationship. A total of 312 surveys were completed in four four- and five-star hotels in the UAE (Dubai and Sharjah). The SmartPLS 4 software was used to test the hypotheses in a mediation model with the bootstrapping method. The results showed that all of the direct links were positive and significant, and mediating relationships were confirmed. This study found that job insecurity predicts intention to quit through psychological distress and resistance to change acting as mediators, and these factors themselves also impact significantly on intention to quit. Resistance to change is impacted significantly by job insecurity and psychological distress, which suggests that a deeper approach to employees’ resistance to change should be taken, especially when conducting performance appraisals in the hotel industry, by searching for its roots and aiming to minimize employees’ intention to quit. Full article

Wearable technologies are small electronic and mobile devices with wireless communication capabilities that can be worn on the body as a part of devices, accessories or clothes. Sensors incorporated within wearable devices enable the collection of a broad spectrum of data that can be processed and analysed by artificial intelligence (AI) systems. In this narrative review, we performed a literature search of the MEDLINE, Embase and Scopus databases. We included any original studies that used sensors to collect data for a sporting event and subsequently used an AI-based system to process the data with diagnostic, treatment or monitoring intents. The included studies show the use of AI in various sports including basketball, baseball and motor racing to improve athletic performance. We classified the studies according to the stage of an event, including pre-event training to guide performance and predict the possibility of injuries; during events to optimise performance and inform strategies; and in diagnosing injuries after an event. Based on the included studies, AI techniques to process data from sensors can detect patterns in physiological variables as well as positional and kinematic data to inform how athletes can improve their performance. Although AI has promising applications in sports medicine, there are several challenges that can hinder their adoption. We have also identified avenues for future work that can provide solutions to overcome these challenges. Full article

This study analyses the importance of the entrepreneurial intention of university students to promote social change by green entrepreneurship in regard to the three most vibrant components of AMO (Ability, Motivation, and Opportunity) theory, developed by the partial least square structural equation model (PLS-SEM). The entrepreneurial intention among students is identified via a deductive approach and this approach is developed using a PLS-SEM. The literature exploited and the methodology used comprise a full exploratory analysis technique to collect empirical data to find the predictor variables that influence the promotion of social changes connected to the mediating variable of green entrepreneurship. The survey data were collected from a total of 302 respondents through survey questionnaires from the students. The data were examined statistically to demonstrate the hypotheses predicted from the literature review. The outcomes of the hypothesis association showed that AMO theory influences the predictor variables of skills, incentives, and entrepreneurship education, and that these skills are statistically significant and accepted towards green entrepreneurship. However, the importance of a green entrepreneurship strategy is influenced by the entrepreneurial intention that encourages the promotion of social change. Therefore, the present study helps researchers to find the structural relationship between different wings connecting AMO theory with the entrepreneurial intention that incurs and develops sustainable business performance to create jobs, instead of searching for jobs. Secondly, this study also indicates a mixed approach where participants can openly discuss their opinion and understanding. Ultimately, this study encourages the use of the covariance-based structural equation model (CB-SEM) by confirming its theory, and testing the confirmatory factor analysis in particular. Full article