Explore the vast range of titles available.

The increase in the number of social media users and smartphone usage has a positive relationship with the diversity of applications. People use mobile applications that provide location-based service either directly or indirectly to share location with their smartphones. With the increase in the use of applications that determine location information by determining location information on mobile devices, mobile applications have become an important research area for user behavior. These applications are also utilized by users for communication and socialization purposes. The literature has usually focused on popular social media applications and studies on location-based applications (LBAs) have been insufficient. In this study, we investigate the impact of location-based services, such as Swarm and Foursquare. This study uses the technology acceptance model (TAM) and the expectation confirmation model (ECM) to understand why users continue using mobile applications. This article examines the role of hedonic comprised of application aesthetics and perceived enjoyment and utilitarian benefits (comprised of application quality and application utility) for consumer behavior in the development of application markets on satisfaction and application continuance intention. Besides, we show the benefits of the strongest effect on application users. By using the mediation satisfaction effect between hedonic and utilitarian benefits; we test the application continuance intention with regression analyses and the Sobel test. We surveyed young subjects as our sapling frame who regularly use mobile applications. We collected data from 400 users by convenience sampling method to test our hypotheses. Given our findings, we show that utilitarian and hedonic benefits are positively related to the application continuance intention. Besides, we show that satisfaction significantly mediates the relationship between hedonic/utilitarian benefits and application continuance intention. Since the main purpose of the application developers is using the application per se in the long term, they need to focus chiefly on user satisfaction. We also show that determining the relevant factors that affect application continuance intention positively is important for the businesses in a competitive environment.

Adaptive learning is an educational methodology that allows the personalization of learning according to the student’s pedagogical path. In digital environments, the strategic use of technologies enhances adaptive learning initiatives, enabling a dynamic understanding of intricate contextual nuances and the ability to identify and recommend appropriate learning activities. Therefore, this work proposes developing and evaluating a prototype that uses a large language model to create adaptive educational activities in face-to-face and virtual environments automatically. The applied methodology involves the implementation of a large language model with advanced cognitive capabilities to generate learning activities that adapt to individual needs. A proof of concept was developed to evaluate the practicality and usability of this approach. The research results indicate that the approach is practical and adaptable to different educational contexts, reinforcing the synergy between adaptive learning, artificial intelligence, and learning environments. The proof of concept evaluation showed that the prototype is highly usable, validating the proposal as an innovative solution to the growing needs of modern education.

This textbook focuses on the development of large-scale web-based applications, websites, and software systems. It covers various topics such as web design, web programming, web testing, and web project management. The book is an essential resource for software engineers, web developers, project managers, and anyone involved in the development of web-based applications. It provides readers with a comprehensive understanding of the process of web engineering and the skills required to develop high-quality web-based systems.

A traffic network possesses all the basic characteristics of networks, as well as its own distinct features, which have research significance. In this study, we address the issues of poor adaptability to predefined topology graphs and fuzzy representation of graph structures through a Dynamic Topology Man-GCN (DTM-GCN) model based on dynamic graph convolutional networks for spatiotemporal traffic flow prediction. By incorporating an adaptive dynamic topology graph module and an MK temporal prediction module, the model effectively addresses the characteristics of self-similarity and spatial heterogeneity in traffic network flow, thereby resolving the issue of poor adaptability. The proposed model was evaluated using the Los Angeles and PeMS07 datasets for 15-min predictions, with respective RMSE values of 4.9651 and 4.8861, MAE values of 3.4906 and 3.2754, MAPE values of 6.642% and 6.548%, and R2 values of 0.9034 and 0.8905. ChatGPT has achieved some success in predicting traffic flow, but it is not as good as the graph convolution method, and there are also some limitations in long-term prediction. The experimental results indicate that the DTM-GCN model is widely used and has good processing ability in dealing with network mutations.

In this paper, we propose a large language models (LLMs) assisted algorithm that uses ChatGPT to summarize clinical notes and then concatenate these generated summaries with structured data to predict sepsis. We perform a human evaluation of the summaries generated by ChatGPT and evaluate our algorithm using an independent test set. Our algorithm achieves a high prediction AUC of 0.93 (95% CI 0.92-0.93), accuracy of 0.92 (95% CI 0.91-0.92), and specificity of 0.89 (95% CI 0.88-0.90) 4 hours before the onset of sepsis. The ablation study demonstrated a 2% improvement in predicted AUC score when utilizing ChatGPT for clinical notes summarization compared to traditional methods, 4 hours before the sepsis onset. The experiment results in turn revealed the remarkable performance of ChatGPT in the domain of clinical notes summarization.

Aiming at the problem of abnormal target occlusion and unclearness caused by insufficient light and different shooting angles during abnormal event detection, referring to the idea of Chat GPT using attention mechanism to conduct a large number of text training to learn dialogue mode and structure, a supervised abnormal event detection model integrating attention learning is proposed. The model consists of a target detection module and a behavior classification module. Firstly, the target detection network YOLOv7 is used as the basic model to extract the foreground target. Secondly, the three-channel attention module CSAM of Chat GPT is integrated. Through spatial attention, channel attention and self-attention, the problem of target occlusion and target ambiguity can be effectively solved. Finally, the relevant output of the C3 D network model is extracted as the spatio-temporal feature of the foreground target, and the abnormal event detection is realized by classifying the positive and abnormal events through the full connection layer and the activation function. In this paper, AUC evaluation index is used to conduct experiments on public datasets UCSD and UCF-Crime. The results showed that the AUC value of abnormal event detection in UCSD reached 93.17, and the AUC value in UCF-Crime reached 89.13. This method effectively improves the accuracy of abnormal event detection, reduces the rate of missed detection and error detection, and has practical application value.

Accurate customer churn prediction are increasingly crucial in improving customer retention and corporate revenue. The collected customer churn data generally exhibits the classical multimodal property, i.e., different types of user behaviors. However, existing customer churn prediction methods fail to capture more meaningful details of multimodal interaction resulting in unideal customer churn prediction accuracy. Specifically, to better deal with the heterogeneity and consistency problems in the acquired multimodal data, in this paper we propose a multimodal autoencoder-decoder framework for customer churn prediction model, which is referred to as MFCCP. By using Chat-GPT to analyze detailed data predicted as lost customers, we aim to customize targeted solutions to recover customers.First, the features under numerical and textual characteristics that reflect user behavior cues are characterized by a feature encoding network (FE-Net) module to condense the most relevant information for each modality. We then construct a multimodal fusion network (MF-Net) that effectively captures the cross-modal interactions to integrate modality-specific representations. Finally, the multimodal feature reconstruction network (MFR-Net) is selected to decode the fused representations into target modalities, ensuring that the reconstructed results closely resemble the original ones. The experimental results show that the proposed method has higher accuracy and better generalization compared with current customer prediction methods.Incorporating Chat-GPT into the MFCCP framework enables businesses to make informed decisions and take proactive measures to retain valuable customers, ultimately driving revenue growth.

This paper mainly studies the problem of finding new fault classes under different modes in the field of intelligent fault diagnosis, that is, in the case of some labeled faults, new classes are revealed in unlabeled fault samples. In this paper, we introduce a comprehensive multi-modal framework for novel fault discovery and explore the impact of different modalities on the task of identifying new fault classes. To enhance the robustness of feature representation in complex environments, We adopted the approach inspired by ChatGPT, wherein we conducted pre-training on a substantial amount of labeled data to learn general features, patterns, and representations of various fault types. During the pre-training process, we integrated multiple modalities of data to prevent the loss of information due to the absence of single-modal data, thereby enhancing the accuracy of clustering. Furthermore, we introduced a multi-modal fusion method based on saliency correlation to complementarily fuse the information from different modalities. This approach effectively eliminated data redundancy arising from diverse modalities. Adhering to the principle that improving the quality of pseudo-label generation during the new class discovery phase enhances the accuracy of clustering for new classes, we extend the multi-modal concept. We introduce a Discriminative Relationship Enhancement method that capitalizes on cross-validation of pseudo-label predictions from different modalities during the pseudo-label prediction phase. This augmentation enhances the precision of pseudo-labels during the new class discovery phase. We evaluated the effectiveness of our proposed framework on fault datasets CWRU and PU, achieving promising results.

With the proliferation of IoT technology, it is anticipated that healthcare services, particularly for the elderly persons, will become a major thrust area of research in the coming days. Aim of this work is to design a fit-band containing multiple sensors to provide remote healthcare services for the elderly persons. An application has been designed to capture health data from the fit-band, pre-process the data and then send them to cloud for further analysis. A wireless Bluetooth enabled connection is proposed to establish communications between sensors and the application for data transmission. In the proposed application, there are three different front-end interfaces for three different users: system administrator, patient and doctor. The data collected from the patient’s fit-band are sent to a cloud data storage, where the data will be analyzed to detect anomaly (e.g., heart attack, sleep apnea, etc.). A Convolution Neural Network (CNN) model is proposed for anomaly detection. For the classification of anomaly, a Long Short Term Memory (LSTM) model is proposed. In the presence of anomaly, the system immediately connects a doctor through a phone call. A prototype system termed as Shubhchintak has been developed in Android/IOS environment and tested with a number of users. The fit-band provides data tracking with an overall accuracy of 99%; the system provides a response with 3000 requests in less than 100 ms. Also, Shubhchintak provides a real-time feedback with an accuracy of 97%. Shubhchintak is also tested by patients and doctors of a nearby hospital. Shubhchintak is shown to be a simple to use, cost effective, comfortable, and efficient system compared to the existing state of the art solutions.