Adding to societal changes today, are the miscellaneous bigdata produced in different fields. Coupled with these data is the appearance of risk management. Admittedly, to predict future trend by using these data is c...
详细信息
Adding to societal changes today, are the miscellaneous bigdata produced in different fields. Coupled with these data is the appearance of risk management. Admittedly, to predict future trend by using these data is conducive to make everything more efficient and easy. Now, no matter companies or individuals, they increasingly focus on identifying risks and managing them before risks. Effective risk management will lead them to deal with potential problems. This thesis focuses on risk management of flight delay area using big real time data. It proposes two different prediction models, one is called General Long Term Departure Prediction Model and the other is named as Improved Real Time Arrival Prediction Model. By studying the main factors lead to flight delay, this thesis takes weather, carrier, National Aviation System, security and previous late aircraft as analysis factors. By utilizing our models can do not only long time but also short term flight delay predictions. The results demonstrate goodness of fit. Besides the theory part, it also presents a practical and beautiful web application for real time flight arrival prediction based on our second model.
A key challenge in personalized product search is to capture user’s preferences. Recent work attempted to model sequences of user historical behaviors, i.e., product purchase histories, to build user profiles and to ...
详细信息
A key challenge in personalized product search is to capture user’s preferences. Recent work attempted to model sequences of user historical behaviors, i.e., product purchase histories, to build user profiles and to personalize results accordingly. Although these approaches have demonstrated promising retrieval performances, we notice that most of them focus solely on the intra-sequence interactions between items. However, as there is usually a small amount of historical behavior data, the user profiles learned by these approaches could be very sensitive to the noise included in it. To tackle this problem, we propose incorporating out-of-sequence external information to enhance user modeling. More specifically, we inject the external item-item relations (e.g., belonging to the same brand), and query-query relations (e.g., the semantic similarities between them), into the intra-sequence interaction to learn better user profiles. In addition, we devise two auxiliary decoders, with the historical item sequence reconstruction task and the global item similarity prediction task, to further improve the reliability of user modeling. Experimental results on two datasets from simulated and real user search logs respectively show that the proposed personalized product search method outperforms existing approaches.
Distributed Collaborative Machine Learning (DCML) has emerged in artificial intelligence-empowered edge computing environments, such as the Industrial Internet of Things (IIoT), to process tremendous data generated by...
详细信息
Distributed Collaborative Machine Learning (DCML) has emerged in artificial intelligence-empowered edge computing environments, such as the Industrial Internet of Things (IIoT), to process tremendous data generated by smart devices. However, parallel DCML frameworks require resource-constrained devices to update the entire Deep Neural Network (DNN) models and are vulnerable to reconstruction attacks. Concurrently, the serial DCML frameworks suffer from training efficiency problems due to their serial training nature. In this paper, we propose a Model Pruning-enabled Federated Split Learning framework (MP-FSL) to reduce resource consumption with a secure and efficient training scheme. Specifically, MP-FSL compresses DNN models by adaptive channel pruning and splits each compressed model into two parts that are assigned to the client and the server. Meanwhile, MP-FSL adopts a novel aggregation algorithm to aggregate the pruned heterogeneous models. We implement MP-FSL with a real FL platform to evaluate its performance. The experimental results show that MP-FSL outperforms the state-of-the-art frameworks in model accuracy by up to 1.35%, while concurrently reducing storage and computational resource consumption by up to 32.2% and 26.73%, respectively. These results demonstrate that MP-FSL is a comprehensive solution to the challenges faced by DCML, with superior performance in both reduced resource consumption and enhanced model performance.
暂无评论