Search

With the development of the Internet, the types and quantities of malware have grown rapidly, and how to identify unknown malware is becoming a new challenge. The traditional malware detection method based on fixed features is becoming more and more difficult. In order to improve detection accuracy and efficiency for mobile terminals, this paper proposed a malware detection method for mobile terminals based on application programming interface (API) call sequence, which was characterized by the API call sequence and used a series of feature preprocessing techniques to remove redundant processing of the API call sequence. Finally, the recurrent neural network method (RNN) was used to build the model and perform detection and verification. Furthermore, this paper constructed a malware detection model based on a two-way recurrent neural network and used the two-way long short-term memory network model (LSTM) to train the data set containing 5986 malware samples and 5065 benign software samples to obtain the final detection model and its parameters. Finally, the feature vector of the APK file to be detected was passed into the model and obtained the detection results. The experimental results indicated that the detection accuracy of this method can reach 93.68%. [ABSTRACT FROM AUTHOR]

Hyperspectral imaging (HSI) offers rich spectral and spatial data, beneficial for a variety of applications. However, challenges persist in HSI classification due to spectral variability, non-linearity, limited samples, and a dearth of spatial information in conventional spectral classifiers. While various spectral–spatial classifiers and dimension reduction techniques have been developed to mitigate these issues, they are often constrained by the utilization of handcrafted features. Deep learning has been introduced to HSI classification, with pixel- and patch-level deep learning (DL) classifiers gaining substantial attention. Yet, existing patch-level DL classifiers encounter difficulties in concentrating on long-distance dependencies and managing category areas of diverse sizes. The proposed Self-Adaptive 3D atrous spatial pyramid pooling (ASPP) Multi-Scale Feature Fusion Network (SAAFN) addresses these challenges by simultaneously preserving high-resolution spatial detail data and high-level semantic information. This method integrates a modified hyperspectral superpixel segmentation technique, a multi-scale 3D ASPP convolution block, and an end-to-end framework to extract and fuse multi-scale features at a self-adaptive rate for HSI classification. This method significantly enhances the classification accuracy of HSI with limited samples. [ABSTRACT FROM AUTHOR]

In an attempt to solve the problems of the low intelligent distribution degree and high working intensity of auxiliary transportation systems in underground coal mines, an intelligent distribution strategy of materials in the whole mine is put forward. Firstly, combined with the characteristics of materials and standard containers, a three-dimensional loading model is established with the goal of maximizing the space utilization of standard containers, and a three-dimensional space segmentation heuristic algorithm is used to solve the material loading scheme. Then, the multi-objective optimization model of distribution parameters is established with the goal of the shortest delivery distance, the shortest delay time, and the fewest number of delivery vehicles, and the dual-layer genetic algorithm is used to solve the distribution scheme. Finally, the spatiotemporal conversion coefficient is designed to solve the task list by hierarchical clustering, and the solution time is reduced by 30%. The results show that the dual-layer genetic algorithm based on hierarchical clustering has good adaptability in complex material scheduling scenarios. [ABSTRACT FROM AUTHOR]

Trajectory prediction technology uses the trajectory data of historical ships to predict future ship trajectory, which has significant application value in the field of ship driving and ship management. With the popularization of Automatic Identification System (AIS) equipment in-stalled on ships, many ship trajectory data are collected and stored, providing a data basis for ship trajectory prediction. Currently, most of the ship trajectory prediction methods do not fully consider the influence of ship density in different sea areas, leading to a large difference in the prediction effect in different sea areas. This paper proposes a hybrid trajectory prediction model based on K-Nearest Neighbor (KNN) and Long Short-Term Memory (LSTM) methods. In this model, different methods are used to predict trajectory based on trajectory density. For offshore waters with a high density of trajectory, an optimized K-Nearest Neighbor algorithm is used for prediction. For open sea waters with low density of trajectory, the Long Short-Term Memory model is used for prediction. To further improve the prediction effect, the spatio-temporal characteristics of the trajectory are fully considered in the prediction process of the model. The experimental results for the dataset of historical data show that the mean square error of the proposed method is less than 2.92 × 10−9. Compared to the prediction methods based on the Kalman filter, the mean square error decreases by two orders of magnitude. Compared to the prediction methods based on recurrent neural network, the mean square error decreases by 82%. The advantage of the proposed model is that it can always obtain a better prediction result under different conditions of trajectory density available for different sea areas. [ABSTRACT FROM AUTHOR]

Code search is a process that takes a given query as input and retrieves relevant code snippets from a code base. The relationship between query and code is commonly built on code annotation, which is extracted from code comments or other documents. The current code search studies approximately treat code annotation as a common natural language, regardless of its hidden structural information. To address the information loss, this work proposes a code annotation model to extract features from five perspectives, and further conduct a code search engine, i.e., CodeHunter. CodeHunter is evaluated on a dataset of 7 million code snippets and query descriptions. The experimental results show that CodeHunter obtains more effective results than Lucene and DeepCS. And we also prove that the effectiveness comes from the rich features and search models, CodeHunter can work well with different sizes of query descriptions. [ABSTRACT FROM AUTHOR]

Ecotourism is considered to be an effective means of promoting nature conservation and sustainable development in less developed regions. However, its widespread adoption may be the result of a misunderstanding due to confusion about definitions and interpretations. Using web map browsers, we assessed the distribution pattern of ecotourism sites in both number and density in the 31 provinces of mainland China, and found that it positively correlated with gross domestic products (GDP) and population size, showing spatial dynamics similar to the general tourism model. However, negative-weak or no correlation at all was found with the presence and size of nature variables such as protected areas. These results support previous suspicions that the term ecotourism and its associated concept may be misused in China and that the regions that could benefit the most from this form of tourism have yet to properly develop it. Although this pattern could reflect a huge demand for genuine ecotourism, we recommend that China, to achieve its ambitious sustainable development goals, adapt ecotourism policies in its environmental and socio-cultural context, manage them with a trans-disciplinary expert board, and regulate its market by introducing a rigorous admittance system with continuous monitoring and evaluation. [ABSTRACT FROM AUTHOR]

A large-eddy simulation of three-dimensional turbulent flow for a hydro-turbine in the transitional process of decreasing load from rated power to no-load has been implemented by using ANSYS-Fluent in this paper. The survival space occupied by different scale flow structures for the different guide vane opening degrees was well captured. The flow characteristics in the transitional process were obtained. Different forms of the channel vortex were studied. The features of the vortex cascade and dissipation of the turbulent energy in blade passage were analyzed. The results show that the scales of the vortex structures have a large change in the transitional process of rejecting load, and the vortex distributions in the blade passage are significantly distinguished. The survival space of the different scale eddies in the blade passage is closely related to the scales of the vortex. The survival volume ratio of the adjacent scale vortex in the runner is about 1.2–1.6. The turbulent kinetic energy and eddy viscosity increase rapidly along the blade passage with the small-scale eddies going up, which implies that a dissipating path for the energy in the blade passage is formed. [ABSTRACT FROM AUTHOR]