As wireless sensing has developed, wireless behavior recognition has become a promising research area, in which human motion duration is one of the basic and significant parameters to measure human behavior. At present, however, there is no consideration of the duration estimation of human motion leveraging wireless signals. In this paper, we propose a novel system for robust duration estimation of human motion (R-DEHM) with WiFi in the area of interest. To achieve this, we first collect channel statement information (CSI) measurements on commodity WiFi devices and extract robust features from the CSI amplitude. Then, the back propagation neural network (BPNN) algorithm is introduced for detection by seeking a cutting line of the features for different states, i.e., moving human presence and absence. Instead of directly estimating the duration of human motion, we transform the complex and continuous duration estimation problem into a simple and discrete human motion detection by segmenting the CSI sequences. Furthermore, R-DEHM is implemented and evaluated in detail. The results of our experiments show that R-DEHM achieves the human motion detection and duration estimation with the average detection rate for human motion more than 94% and the average error rate for duration estimation less than 8%, respectively.

Explicit feedback and implicit feedback are two important types of heterogeneous data for constructing a recommendation system. The combination of the two can effectively improve the performance of the recommendation system. However, most of the current deep learning recommendation models fail to fully exploit the complementary advantages of two types of data combined and usually only use binary implicit feedback data. Thus, this paper proposes a neural matrix factorization recommendation algorithm (EINMF) based on explicit-implicit feedback. First, neural network is used to learn nonlinear feature of explicit-implicit feedback of user-item interaction. Second, combined with the traditional matrix factorization, explicit feedback is used to accurately reflect the explicit preference and the potential preferences of users to build a recommendation model; a new loss function is designed based on explicit-implicit feedback to obtain the best parameters through the neural network training to predict the preference of users for items; finally, according to prediction results, personalized recommendation list is pushed to the user. The feasibility, validity, and robustness are fully demonstrated in comparison with multiple baseline models on two real datasets.

With the booming of online social networks in the mobile internet, an emerging recommendation scenario has played a vital role in information acquisition for user, where users are no longer recommended with a single item or item list, but a combination of heterogeneous and diverse objects (called a package, e.g., a package including news, publisher, and friends viewing the news). Different from the conventional recommendation where users are recommended with the item itself, in package recommendation, users would show great interests on the explicitly displayed objects that could have a significant influence on the user behaviors. However, to the best of our knowledge, few effort has been made for package recommendation and existing approaches can hardly model the complex interactions of diverse objects in a package. Thus, in this paper, we make a first study on package recommendation and propose an Intra- and inter-package attention network for Package Recommendation (IPRec). Specifically, for package modeling, an intra-package attention network is put forward to capture the object-level intention of user interacting with the package, while an inter-package attention network acts as a package-level information encoder that captures collaborative features of neighboring packages. In addition, to capture users preference representation, we present a user preference learner equipped with a fine-grained feature aggregation network and coarse-grained package aggregation network. Extensive experiments on three real-world datasets demonstrate that IPRec significantly outperforms the state of the arts. Moreover, the model analysis demonstrates the interpretability of our IPRec and the characteristics of user behaviors. Codes and datasets can be obtained at https://github.com/LeeChenChen/IPRec.

When responding to emergencies such as sudden natural disasters, communication networks face challenges such as network traffic surge and complex geographic environments. Aiming at the problems of high transmission delay and insensitivity to user's preference in the current UAV edge caching strategy, this paper proposes a UAV caching content recommendation algorithm based on graph neural network. Firstly, the location of UAV is determined by clustering algorithm; secondly, the interest preferences of user nodes in the cluster are predicted by GCLRSAN model, and the UAV cache content is designed according to the result; finally, simulation experiments show that the model and algorithm proposed in this paper can effectively reduce the backhaul link overhead and outperform the comparison algorithms in the indexes such as accuracy rate, recall rate, cache hit rate, and transmission delay.

Multi-objective evolutionary algorithms (MOEAs) encounters many difficulties when dealing with many objective optimization problems. In order to better balance convergence and diversity, we propose a two-stage evolutionary algorithm with two-archive named TSTA. Specifically, the entire search process is divided into two stages, the first stage mainly pursues convergence, using subregion dominance in the convergent archive, and crowding distance sorting in the diversity archive, and the second stage mainly pursues the balance of convergence and diversity, in which the convergence archive remains the same, and the diversity archive is changed to use fitness. To evaluate the performance of our algorithms, 18 benchmark problems are used as the test suite. The experimental results show that TSTA achieves competitive performance in comparison with 6 state-of-the-art MOEAs.