Search

Abstract Automatic target tracking in emerging remote sensing video-generating tools based on microwave imaging technology and radars has been investigated in this paper. A moving target tracking system is proposed to be low complexity and fast for implementation through edge nodes in a mini-satellite or drone network enabling machine intelligence into large-scale vision systems, in particular, for marine transportation systems. The system uses a group of image processing tools for video pre-processing, and Kalman filtering to do the main task. For testing the system performance, two measures of accuracy and false alarms probability are computed for real vision data. Two types of scenes are analyzed including the scene with single target, and the scene with multiple targets that is more complicated for automatic target detection and tracking systems. The proposed system has achieved a high performance in our tests.

Traditional BDS positioning technology has limitations in accuracy, robustness, and availability in certain real-time monitoring applications. Therefore, this article designs and implements a monitoring platform based on Beidou high-precision positioning technology to solve the limitations of traditional BDS positioning technology and provide more accurate, reliable, and real-time positioning services. The research first analyzes and optimizes the positioning algorithms of the existing Beidou system to improve the accuracy of position measurement. Then apply the optimized algorithm to the system architecture of the monitoring platform to achieve high-precision positioning function. Finally, design a suitable user interface and data processing module so that users can easily obtain and analyze positioning data. Through experimental verification, this platform has achieved high accuracy and stability in position measurement. Users can obtain real-time location information through this platform and further analyze and process it.

The Sine–Levy tuna swarm optimization (SLTSO) algorithm is a novel method based on the sine strategy and Levy flight guidance. It is presented as a solution to the shortcomings of the tuna swarm optimization (TSO) algorithm, which include its tendency to reach local optima and limited capacity to search worldwide. This algorithm updates locations using the Levy flight technique and greedy approach and generates initial solutions using an elite reverse learning process. Additionally, it offers an individual location optimization method called golden sine, which enhances the algorithm’s capacity to explore widely and steer clear of local optima. To plan UAV flight paths safely and effectively in complex obstacle environments, the SLTSO algorithm considers constraints such as geographic and airspace obstacles, along with performance metrics like flight environment, flight space, flight distance, angle, altitude, and threat levels. The effectiveness of the algorithm is verified by simulation and the creation of a path planning model. Experimental results show that the SLTSO algorithm displays faster convergence rates, better optimization precision, shorter and smoother paths, and concomitant reduction in energy usage. A drone can now map its route far more effectively thanks to these improvements. Consequently, the proposed SLTSO algorithm demonstrates both efficacy and superiority in UAV route planning applications.

Personalized recommender systems play a crucial role in assisting users in discovering items of interest from vast amounts of information across various domains. However, developing accurate personalized recommender systems remains challenging due to the need to balance model architectures, input feature combinations, and fusion of heterogeneous data sources. This study investigates the impacts of these factors on recommendation performance using the MovieLens and Book Recommendation datasets. Six models, including single-task neural networks, multi-task learning, and baselines, were evaluated with various input feature combinations using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The multi-task learning approach achieved significantly lower RMSE and MAE by effectively leveraging heterogeneous data sources for personalized recommendations through a shared neural network architecture. Furthermore, incorporating user data and content data progressively enhanced performance compared to using only item identifiers. The findings highlight the importance of advanced model architectures and fusing heterogeneous data sources for high-quality recommendations, providing valuable insights for designing effective recommender systems across diverse domains.

Abstract Background Alzheimer’s disease (AD) is a progressive and irreversible brain disorder. Hippocampus is one of the involved regions and its atrophy is a widely used biomarker for AD diagnosis. We have recently developed DenseCNN, a lightweight 3D deep convolutional network model, for AD classification based on hippocampus magnetic resonance imaging (MRI) segments. In addition to the visual features of the hippocampus segments, the global shape representations of the hippocampus are also important for AD diagnosis. In this study, we propose DenseCNN2, a deep convolutional network model for AD classification by incorporating global shape representations along with hippocampus segmentations. Methods The data was obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and was T1-weighted structural MRI from initial screening or baseline, including ADNI 1,2/GO and 3. DenseCNN2 was trained and evaluated with 326 AD subjects and 607 CN hippocampus MRI using 5-fold cross-validation strategy. DenseCNN2 was compared with other state-of-the-art machine learning approaches for the task of AD classification. Results We showed that DenseCNN2 with combined visual and global shape features performed better than deep learning models with visual or global shape features alone. DenseCNN2 achieved an average accuracy of 0.925, sensitivity of 0.882, specificity of 0.949, and area under curve (AUC) of 0.978, which are better than or comparable to the state-of-the-art methods in AD classification. Data visualization analysis through 2D embedding of UMAP confirmed that global shape features improved class discrimination between AD and normal. Conclusion DenseCNN2, a lightweight 3D deep convolutional network model based on combined hippocampus segmentations and global shape features, achieved high performance and has potential as an efficient diagnostic tool for AD classification.

The task of dialogue generation has attracted increasing attention due to its diverse downstream applications, such as question-answering systems and chatbots. Recently, the deep neural network (DNN)-based dialogue generation models have achieved superior performance against conventional models utilizing statistical machine learning methods. However, despite that an enormous number of state-of-the-art DNN-based models have been proposed, there lacks detailed empirical comparative analysis for them on the open Chinese corpus. As a result, relevant researchers and engineers might find it hard to get an intuitive understanding of the current research progress. To address this challenge, we conducted an empirical study for state-of-the-art DNN-based dialogue generation models in various Chinese corpora. Specifically, extensive experiments were performed on several well-known single-turn and multi-turn dialogue corpora, including KdConv, Weibo, and Douban, to evaluate a wide range of dialogue generation models that are based on the symmetrical architecture of Seq2Seq, RNNSearch, transformer, generative adversarial nets, and reinforcement learning respectively. Moreover, we paid special attention to the prevalent pre-trained model for the quality of dialogue generation. Their performances were evaluated by four widely-used metrics in this area: BLEU, pseudo, distinct, and rouge. Finally, we report a case study to show example responses generated by these models separately.