Multi-sensor integrated navigation technology has been applied to the indoor navigation and positioning of robots. For the problems of a low navigation accuracy and error accumulation, for mobile robots with a single sensor, an indoor mobile robot positioning method based on a visual and inertial sensor combination is presented in this paper. First, the visual sensor (Kinect) is used to obtain the color image and the depth image, and feature matching is performed by the improved scale-invariant feature transform (SIFT) algorithm. Then, the absolute orientation algorithm is used to calculate the rotation matrix and translation vector of a robot in two consecutive frames of images. An inertial measurement unit (IMU) has the advantages of high frequency updating and rapid, accurate positioning, and can compensate for the Kinect speed and lack of precision. Three-dimensional data, such as acceleration, angular velocity, magnetic field strength, and temperature data, can be obtained in real-time with an IMU. The data obtained by the visual sensor is loosely combined with that obtained by the IMU, that is, the differences in the positions and attitudes of the two sensor outputs are optimally combined by the adaptive fade-out extended Kalman filter to estimate the errors. Finally, several experiments show that this method can significantly improve the accuracy of the indoor positioning of the mobile robots based on the visual and inertial sensors.

Extraction of Application Programming Interfaces (APIs) and their semantic relations from unstructured text (e.g., Stack Overflow) is a fundamental work for software engineering tasks (e.g., API recommendation). However, existing approaches are rule based and sequence labeling based. They must manually enumerate the rules or label data for a wide range of sentence patterns, which involves a significant amount of labor overhead and is exacerbated by morphological and common-word ambiguity. In contrast to matching or labeling API entities and relations, this article formulates heterogeneous API extraction and API relation extraction task as a sequence-to-sequence generation task and proposes the API Entity-Relation Joint Extraction framework (AERJE), an API entity-relation joint extraction model based on the large pre-trained language model. After training on a small number of ambiguous but correctly labeled data, AERJE builds a multi-task architecture that extracts API entities and relations from unstructured text using dynamic prompts. We systematically evaluate AERJE on a set of long and ambiguous sentences from Stack Overflow. The experimental results show that AERJE achieves high accuracy and discrimination ability in API entity-relation joint extraction, even with zero or few-shot fine-tuning.

Positioning accuracy can be compromised by the heterogeneity of software and hardware among different intelligent mobile devices. This is due to the fact that the heterogeneity of different devices leads to a significant difference in the received signal strength index (RSSI) of the same Bluetooth access point (AP) captured at the same acquisition point of the device. To address this issue, we propose to use the Honey Badger Algorithm Backpropagation Neural Network (HBA-BPNN) model for calibration. The aim of this study is to calibrate the received signal strength indicator (RSSI) received by Bluetooth sensors of distinct intelligent mobile terminal devices to solve software and hardware heterogeneity issues. Second, this paper uses an indoor fingerprint localization algorithm based on an improved generalized regression neural network (GRNN) model and combines it with the calibration algorithm to build a better localization model. Finally, we verified the effectiveness of the HBA-BPNN calibration model for different test intelligent mobile terminal devices and then compared and analyzed the calibration algorithm proposed in this study with different calibration algorithms. The experimental comparative analysis results show that the positioning accuracy can reach 0.84 m by combining the proposed calibration algorithm with the positioning algorithm.

Owing to the heterogeneity of software and hardware in different types of mobile terminals, the received signal strength indication (RSSI) from the same Wi-Fi access point (AP) varies in indoor environments, which can affect the positioning accuracy of fingerprint methods. To solve this problem and consider the nonlinear characteristics of Wi-Fi signal strength propagation and attenuation, we propose a whale optimisation algorithm-back-propagation neural network (WOA-BPNN) model for indoor Wi-Fi RSSI calibration. Firstly, as the selection of the initial parameters of the BPNN model has a considerable impact on the positioning accuracy of the calibration algorithm, we use the WOA to avoid blindly selecting the parameters of the BPNN model. Then, we propose an improved nonlinear convergence factor to balance the searchability of the WOA, which can also help to optimise the calibration algorithm. Moreover, we change the structure of the BPNN model to compare its influence on the calibration effect of the WOA-BPNN calibration algorithm. Secondly, in view of the low positioning accuracy of indoor fingerprint positioning algorithms, we propose a region-adaptive weighted K-nearest neighbour positioning algorithm based on hierarchical clustering. Finally, we effectively combine the two proposed algorithms and compare the results with those of other calibration algorithms such as the linear regression (LR), support vector regression (SVR), BPNN, and genetic algorithm-BPNN (GA-BPNN) calibration algorithms. The test results show that among different mobile terminals, the proposed WOA-BPNN calibration algorithm can increase positioning accuracy (one sigma error) by 41%, 42%, 44% and 36%, on average. The indoor field tests suggest that the proposed methods can effectively reduce the indoor positioning error caused by the heterogeneous differences of software and hardware in different mobile terminals.

Smart contracts, which automatically execute transactions based on predefined conditions, play a crucial role in asset and money exchanges. Due to their involvement in significant financial transactions, these contracts are attractive targets for hackers, leading to substantial financial losses through exploitable vulnerabilities. While various program analysis methods such as Oyente, Mythril, and Securify have been proposed to address these security concerns, they rely on rule-based patterns that are time-consuming to develop and offer limited coverage. Deep learning methods present an alternative by automatically learning code features to detect vulnerabilities. However, existing approaches face critical challenges, including feature limitations and lack of interpretability. To address these gaps, we propose the interpretable smart contract vulnerability detector, a Graph Isomorphism Network (GIN)-based vulnerability prediction model for smart contracts, enhanced with code subgraph explanations. Our approach identifies and incorporates 43 domain-specific features, augmenting GIN with domain knowledge attention mechanisms to improve vulnerability prediction. In addition, we develop an interpreter called SubgraphV, which provides explanations for vulnerability predictions through interpreted subgraphs. Our model demonstrates superior performance over traditional tools, achieving F1 score improvements from 0.254 to 0.489 on a dataset of 103 smart contract function vulnerabilities. SubgraphV outperforms existing explainability methods like GNNexplainer, PGExplainer, and SubgraphX in pinpointing vulnerabilities, accurately reflecting vulnerability patterns, and enhancing the understanding of vulnerabilities.

In complex pattern recognition scenarios, multi-source information fusion faces critical challenges in handling conflicting evidence. This paper proposes an innovative conflict evidence combination rule based on a multi-dimensional weighted evidence optimization method to address this issue. First, systematic indicator classification and coefficient of variation analysis are conducted to rigorously select key conflict evaluation metrics. This approach effectively addresses the issues of incomplete evaluation dimensions and limited indicator selection observed in prior research. Subsequently, the multi-dimensional weighted evidence optimization method is employed to calculate the relative importance of each piece of evidence. On this basis, conflicting evidence is effectively discounted to reduce conflict and uncertainty among the evidence. Finally, the Dempster combination rule is applied to fuse the discounted conflict evidence for decision-making, achieving more accurate and robust judgments. Furthermore, this paper constructs a decision-level multi-source information fusion model. The model integrates the outputs of three basic classifiers—K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Random Forests (RF)—as multi-source information, and applies the proposed conflict evidence combination rule for fusion. This approach fully leverages the advantages of different classifiers, thereby enhancing the accuracy and robustness of pattern recognition. To verify the effectiveness and practical application potential of the proposed method, this paper conducts empirical analysis on multiple sets of experiments. The experimental results demonstrate that, compared with existing methods, the proposed method exhibits significant advantages in accuracy and robustness, proving its potential application value in addressing pattern recognition problems in complex scenarios.