Multi-information Integration Research Articles

Graph-based multi-information integration network with external news environment perception for Propaganda detection

PurposePropaganda is a prevalent technique used in social media to intentionally express opinions or actions with the aim of manipulating or deceiving users. Existing methods for propaganda detection primarily focus on capturing language features within its content. However, these methods tend to overlook the information presented within the external news environment from which propaganda news originated and spread. This news environment reflects recent mainstream media opinions and public attention and contains language characteristics of non-propaganda news. Therefore, the authors have proposed a graph-based multi-information integration network with an external news environment (abbreviated as G-MINE) for propaganda detection.Design/methodology/approachG-MINE is proposed to comprise four parts: textual information extraction module, external news environment perception module, multi-information integration module and classifier. Specifically, the external news environment perception module and multi-information integration module extract and integrate the popularity and novelty into the textual information and capture the high-order complementary information between them.FindingsG-MINE achieves state-of-the-art performance on both the TSHP-17, Qprop and the PTC data sets, with an accuracy of 98.24%, 90.59% and 97.44%, respectively.Originality/valueAn external news environment perception module is proposed to capture the popularity and novelty information, and a multi-information integration module is proposed to effectively fuse them with the textual information.

A Multi-Module Information-Optimized Approach to English Language Teaching and Development in the Context of Smart Sustainability

With high-tech advancements, intelligent, sustainable development has become widespread in daily life. However, due to developmental differences among various regions, continuity in English language teaching can be challenging. The goal of teaching in the context of sustainable development is to tailor learning plans for students through intelligent intervention. In this paper, we address the issues of classifying students’ interests and jointly assessing the listening, reading, and writing modules in online English teaching. Our results demonstrate that an autoencoder can accurately recognize students’ interests in the four modules, with a recognition accuracy as high as 93.1%. Additionally, the mean squared error (MSE) between the comprehensive assessment and the teacher’s given grade under GRUs is only 0.63, significantly outperforming other RNN-type methods. Therefore, the proposed framework in this paper is crucial in promoting future research development in the sustainable development of English teaching intelligence and the problems of multi-module assessment problem and multi-information integration.

Camera-Based Lane-Aided Multi-Information Integration for Land Vehicle Navigation

Accurate positioning, especially lateral positioning, is an essential requirement of autonomous driving. Although high accuracy vehicle positioning can be conducted in open-sky environments by global navigation satellite system (GNSS), the positioning accuracy cannot be guaranteed in GNSS-denied environments such as urban canyons and tunnels. To solve this issue, inertial navigation systems, vehicle speed sensors, and vehicle motion constraints are often fused to mitigate positioning errors. However, this integration cannot meet the decimeter-level lateral positioning accuracy of autonomous vehicles’ localization requirements. This article proposes a multi-information integration method aided by lane distance to further eliminate lateral error. In the proposed method, the lateral vehicle-to-lane distance measurements from camera-based systems, and the map-matching lane distance based on high-definition map were utilized to provide absolute lane distance measurement corrections in GNSS-denied environments. Field vehicular tests with low-cost integration systems were conducted to evaluate the navigation performance of the proposed multi-information integration method, and the results indicated that it is feasible for the proposed method to maintain continuous and reliable lateral positioning accuracy of better than 0.6 m under reliable lane line detection conditions in GNSS-denied environments.

The Application of Internet of Things in Robot Route Planning Based on Multisource Information Fusion.

With the advent of the Internet of Everything era, multi-information integration, and development, technology has penetrated into all aspects of life, promoting the continuous progress of social development, and people's requirements for a happy life are getting higher and higher. In this, robots play an extremely important role. It is especially important for the route planning of robots. This paper analyzes the DWA dynamic window algorithm through the verification of the global route planning algorithm, namely, the Dijkstra algorithm and the A∗ algorithm; the verification of the local route planning algorithm; the application of the DWA mobile robot algorithm in the robot route planning. The three aspects of the evaluation function are described by a formula, the experimental simulation is carried out, the relationship between the evaluation function terms is obtained, and the feasibility of the algorithm is verified.

MCnet: Multiple Context Information Segmentation Network of No-Service Rail Surface Defects

Surface defect segmentation of no-service rail is important for its quality assessment. There are several challenges of uneven illumination, complex background, and difficulty of sample collection for no-service rail surface defects (NRSDs). In this article, we propose an acquisition scheme with two lamp light and color scan line charge-coupled device (CCD) to alleviate uneven illumination. Then, a multiple context information segmentation network is proposed to improve NRSD segmentation. The network makes full use of context information based on dense block, pyramid pooling module, and multi-information integration. Besides, the attention mechanism is applied to optimize extracted information by filtering noise. For the problem of real sample shortage, we propose to utilize artificial samples to train the network. And an NRSD data set NRSD-MN is built with artificial NRSDs and natural NRSDs. Experimental results show that our method is feasible and has a good segmentation effect on artificial and natural NRSDs.

A completed local shrinkage pattern for texture classification

Visual texture classification plays a critical role in computer vision and pattern recognition. As one of the most popular texture descriptors, local binary pattern(LBP) has achieved extensive development and applications due to its simplicity and high efficiency. However, it is hard for most LBP-based methods to represent completed local texture information efficiently as they either only encode the sign of local difference or fuse low-discriminative features with high dimensionality. To alleviate these problems, this paper groundbreaking introduces a new insight in analyzing completed local texture information, called completed local shrinkage pattern(CLSP), which achieves a high tradeoff between discriminativeness and dimensionality. First, we map the completed local difference to a new encoding space through a shrinkage function and present the local shrinkage pattern. As the important supplement of local texture information, the center pixel is also encoded to build the local center pattern. Finally, the two sub-features are combined to generate the completed local shrinkage pattern. Moreover, we design a multi-information integration texture classification framework, which utilizes the original texture images and the gradient texture images to enrich the diversity of texture information. Experimental results on four popular texture databases demonstrate that the proposed CLSP descriptor achieves superior classification performance with low dimensionality.

Cone Sleeve Center Measurement Algorithm based on Multi-information Integration

In order to meet the high-precision docking requirements of autonomous aerial refueling, this paper proposes a high-precision and fast positioning algorithm for the center of the cone sleeve based on two-dimensional and three-dimensional multi-information fusion. The algorithm performs target detection and tracking on the cone sleeve in the image after calibration and calibration, and adaptively selects the region of interest in the positioning area; the region of interest is calibrated based on the gray-scale constrained two-dimensional model and the three-dimensional model based on the depth gradient. The two-dimensional and three-dimensional information fusion result is back-projected and compensated to the region of interest to realize the high-precision center point position measurement of the center point. The algorithm is used in the semi-physical simulation experiment on the ABB mechanical arm to verify its feasibility, robustness, fast and high precision and other characteristics.

Evaluating the navigation performance of multi-information integration based on low-end inertial sensors for precision agriculture

The main objective of this research was to evaluate the navigation performance of multi-information integration based on a low-end inertial measurement unit (IMU) in precision agriculture by utilizing different auxiliary information (i.e., GNSS real-time kinematic (RTK), non-holonomic constraints (NHC) and dual antenna GNSS). A series of experiments with different operation scenes (e.g., open sky in wet and dry soils) were carried out for quantitative analysis. For the position drift error during a 20-s GNSS outage, the dual-antenna GNSS-assisted approach did not provide a reduction, and the NHC reduced the maximum error in the lateral and vertical directions by over 80% in the dry soil test, but only by approximately 30% in the wet soil test. The heading error with continuous GNSS assistance can be less than 0.03° and be reduced by more than 90% with the aid of dual-antenna GNSS. Additionally, the NHC reduced the heading error from 0.54° to 0.21° and from 0.34° to 0.25° in the dry and wet soil tests respectively. The results suggested that the multi-information integration improved the positioning and orientation reliability. Moreover, the lateral positioning accuracy required for the control of agriculture autonomous vehicles was achieved at approximately 3.0 mm with over a 60% accuracy improvement brought by the dual-antenna GNSS assistance. In contrast to the vulnerability of a single system, multi-information integration can provide comprehensive navigation information with higher reliability and lower costs. Hence, multi-information fusion will be a great opportunity for agriculture to meet the high-accuracy and high-reliability requirements of precision agriculture.

Research of Multi-Information Integration for the Aircraft Ground Centralized Deicing Monitoring System Based on Wireless Data Transmission

In this paper, an aircraft ground centralized deicing monitoring system of multi-information integration is proposed. The multi-information integration system consists of system architecture, database, and monitoring terminal. Among them, the prediction module of ice accumulation calculates ice thickness of the aircraft based on the meteorological data that are collected by the data acquisition module and saved in the database. At the same time, the system uses the methods that GIS is used for making map to locate deicing vehicle precisely, data are transmitted through GPRS, and computer scheduling is adopted, which can ensure the smooth aircraft deicing process and improve the efficiency of the aircraft ground deicing. The practical results show that the proposed monitoring system of aircraft ground centralized deicing increases the efficiency of deicing by 26%. Furthermore, the feasibility and effectiveness of the proposed system are verified.

Research on 3D Visualization and Data Management Integration Modeling of Digital Mine: A Case Study of Eastern Gejiu Sn-Cu Deposit in Yunnan Province, China

In the era of big data, new information technologies introduced into the study of mining exploration to realize the wisdom prospecting has important significance. Based on 3S technology, 3D modeling and visualization technology, database technology and virtual reality technology, this paper studied the 3D integrated digital mine construction of big data era and presented a new concept of 3D visualization and data management integration modeling of digital mine. A case study of eastern Gejiu Sn-Cu deposit in Yunnan province of China achieved the integrated modeling of ground and underground, and also the multi-information integration and analysis of geology, geography, 2D and 3D. An integrated management platform was built in the application to integrate a variety of mine data organically, which provided support for mine production management, the deep prospecting practice and the comprehensive study and application of geological big data of mine.

Multi-information Integrated Method for Text Extraction from Videos

Video text provides important semantic information in video content analysis. However, video text with complex background has a poor recognition performance for OCR. Most of the previous approaches to extracting overlay text from videos are based on traditional binarization and give little attention on multi-information integration, especially fusing the background information. This paper presents an effective method to precisely extract characters from videos to enable it for OCR with a good recognition performance. The proposed method combines multi-information together including background information, edge information, and character’s spatial information. Experimental results show that it is robust to complex background and various text appearances.

ML Systems: A Proof Theory for Contexts

In the last decade the concept of context has been extensively exploited in many research areas, e.g., distributed artificial intelligence, multi agent systems, distributed databases, information integration, cognitive science, and epistemology. Three alternative approaches to the formalization of the notion of context have been proposed: Giunchiglia and Serafini's Multi Language Systems (ML systems), McCarthy's modal logics of contexts, and Gabbay's Labelled Deductive Systems. Previous papers have argued in favor of ML systems with respect to the other approaches. Our aim in this paper is to support these arguments from a theoretical perspective. We provide a very general definition of ML systems, which covers all the ML systems used in the literature, and we develop a proof theory for an important subclass of them: the MR systems. We prove various important results; among other things, we prove a normal form theorem, the sub-formula property, and the decidability of an important instance of the class of the MR systems. The paper concludes with a detailed comparison among the alternative approaches.