Robust and Discriminative Feature Learning via Mutual Information Maximization for Object Detection in Aerial Images

Object detection in unmanned aerial vehicle(UAV)aerial images has become increasingly important in military and civil applications.General object detection models are not robust enough against interclass similarity and intraclass variability of small objects,and UAV-specific nuisances such as uncontrolledweather conditions.Unlike previous approaches focusing on high-level semantic information,we report the importance of underlying features to improve detection accuracy and robustness fromthe information-theoretic perspective.Specifically,we propose a robust and discriminative feature learning approach through mutual information maximization(RD-MIM),which can be integrated into numerous object detection methods for aerial images.Firstly,we present the rank sample mining method to reduce underlying feature differences between the natural image domain and the aerial image domain.Then,we design a momentum contrast learning strategy to make object features similar to the same category and dissimilar to different categories.Finally,we construct a transformer-based global attention mechanism to boost object location semantics by leveraging the high interrelation of different receptive fields.We conduct extensive experiments on the VisDrone and Unmanned Aerial Vehicle Benchmark Object Detection and Tracking(UAVDT)datasets to prove the effectiveness of the proposed method.The experimental results show that our approach brings considerable robustness gains to basic detectors and advanced detection methods,achieving relative growth rates of 51.0%and 39.4%in corruption robustness,respectively.Our code is available at https://github.com/cq100/RD-MIM(accessed on 2 August 2024).

The Fusion of Temporal Sequence with Scene Priori Information in Deep Learning Object Recognition

For some important object recognition applications such as intelligent robots and unmanned driving, images are collected on a consecutive basis and associated among themselves, besides, the scenes have steady prior features. Yet existing technologies do not take full advantage of this information. In order to take object recognition further than existing algorithms in the above application, an object recognition method that fuses temporal sequence with scene priori information is proposed. This method first employs YOLOv3 as the basic algorithm to recognize objects in single-frame images, then the DeepSort algorithm to establish association among potential objects recognized in images of different moments, and finally the confidence fusion method and temporal boundary processing method designed herein to fuse, at the decision level, temporal sequence information with scene priori information. Experiments using public datasets and self-built industrial scene datasets show that due to the expansion of information sources, the quality of single-frame images has less impact on the recognition results, whereby the object recognition is greatly improved. It is presented herein as a widely applicable framework for the fusion of information under multiple classes. All the object recognition algorithms that output object class, location information and recognition confidence at the same time can be integrated into this information fusion framework to improve performance.

Research on Heterogeneous Information Network Link Prediction Based on Representation Learning

A heterogeneous information network,which is composed of various types of nodes and edges,has a complex structure and rich information content,and is widely used in social networks,academic networks,e-commerce,and other fields.Link prediction,as a key task to reveal the unobserved relationships in the network,is of great significance in heterogeneous information networks.This paper reviews the application of presentation-based learning methods in link prediction of heterogeneous information networks.This paper introduces the basic concepts of heterogeneous information networks,and the theoretical basis of representation learning,and discusses the specific application of the deep learning model in node embedding learning and link prediction in detail.The effectiveness and superiority of these methods on multiple real data sets are demonstrated by experimental verification.

Effects of Media and Distributed Information on Collaborative Concept-Learning

The present study explores the effects of media and distributed information on the performance of remotely located pairs of people′s completing a concept-learning task. Sixty pairs performed a concept-learning task using either audio-only or audio-plus-video for communication. The distribution of information includes three levels: with totally same information, with partly same information, and with totally different information. The subjects′ primary psychological functions were also considered in this study. The results showed a significant main effect of the amount of information shared by the subjects on the number of the negative instances selected by the subjects, and a significant main effect of media on the time taken by the subjects to complete the task.

Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning

The development of precision agriculture demands high accuracy and efficiency of cultivated land information extraction. As a new means of monitoring the ground in recent years, unmanned aerial vehicle （UAV） low-height remote sensing technique, which is flexible, efficient with low cost and with high resolution, is widely applied to investing various resources. Based on this, a novel extraction method for cultivated land information based on Deep Convolutional Neural Network and Transfer Learning （DTCLE） was proposed. First, linear features （roads and ridges etc.） were excluded based on Deep Convolutional Neural Network （DCNN）. Next, feature extraction method learned from DCNN was used to cultivated land information extraction by introducing transfer learning mechanism. Last, cultivated land information extraction results were completed by the DTCLE and eCognifion for cultivated land information extraction （ECLE）. The location of the Pengzhou County and Guanghan County, Sichuan Province were selected for the experimental purpose. The experimental results showed that the overall precision for the experimental image 1, 2 and 3 （of extracting cultivated land） with the DTCLE method was 91.7%, 88.1% and 88.2% respectively, and the overall precision of ECLE is 9o.7%, 90.5% and 87.0%, respectively. Accuracy of DTCLE was equivalent to that of ECLE, and also outperformed ECLE in terms of integrity and continuity.

MINDTL： Multiple Incomplete Domains Transfer Learning for Information Recommendation

Collaborative filtering is the most popular and successful information recommendation technique. However, it can suffer from data sparsity issue in cases where the systems do not have sufficient domain information. Transfer learning, which enables information to be transferred from source domains to target domain, presents an unprecedented opportunity to alleviate this issue. A few recent works focus on transferring user-item rating information from a dense domain to a sparse target domain, while almost all methods need that each rating matrix in source domain to be extracted should be complete. To address this issue, in this paper we propose a novel multiple incomplete domains transfer learning model for cross-domain collaborative filtering. The transfer learning process consists of two steps. First, the user-item ratings information in incomplete source domains are compressed into multiple informative compact cluster-level matrixes, which are referred as codebooks. Second, we reconstruct the target matrix based on the codebooks. Specifically, for the purpose of maximizing the knowledge transfer, we design a new algorithm to learn the rating knowledge efficiently from multiple incomplete domains. Extensive experiments on real datasets demonstrate that our proposed approach significantly outperforms existing methods.

Iterative Learning Control With Incomplete Information： A Survey

Abstract--This paper conducts a survey on iterative learn- ing control （ILC） with incomplete information and associated control system design, which is a frontier of the ILC field. The incomplete information, including passive and active types, can cause data loss or fragment due to various factors. Passive incomplete information refers to incomplete data and information caused by practical system limitations during data collection, storage, transmission, and processing, such as data dropouts, delays, disordering, and limited transmission bandwidth. Active incomplete information refers to incomplete data and information caused by man-made reduction of data quantity and quality on the premise that the given objective is satisfied, such as sampling and quantization. This survey emphasizes two aspects： the first one is how to guarantee good learning performance and tracking performance with passive incomplete data, and the second is how to balance the control performance index and data demand by active means. The promising research directions along this topic are also addressed, where data robustness is highly emphasized. This survey is expected to improve understanding of the restrictive relationship and trade-off between incomplete data and tracking performance, quantitatively, and promote further developments of ILC theory. Index Terms--Data dropout, data robustness, incomplete in- formation, iterative learning controi（ILC）, quantized control, sampled control, varying lengths.

Data-Driven Learning Control Algorithms for Unachievable Tracking Problems

For unachievable tracking problems, where the system output cannot precisely track a given reference, achieving the best possible approximation for the reference trajectory becomes the objective. This study aims to investigate solutions using the Ptype learning control scheme. Initially, we demonstrate the necessity of gradient information for achieving the best approximation.Subsequently, we propose an input-output-driven learning gain design to handle the imprecise gradients of a class of uncertain systems. However, it is discovered that the desired performance may not be attainable when faced with incomplete information.To address this issue, an extended iterative learning control scheme is introduced. In this scheme, the tracking errors are modified through output data sampling, which incorporates lowmemory footprints and offers flexibility in learning gain design.The input sequence is shown to converge towards the desired input, resulting in an output that is closest to the given reference in the least square sense. Numerical simulations are provided to validate the theoretical findings.

Physics informed machine learning: Seismic wave equation

Similar to many fields of sciences,recent deep learning advances have been applied extensively in geosciences for both small-and large-scale problems.However,the necessity of using large training data and the’black box’nature of learning have limited them in practice and difficult to interpret.Furthermore,including the governing equations and physical facts in such methods is also another challenge,which entails either ignoring the physics or simplifying them using unrealistic data.To address such issues,physics informed machine learning methods have been developed which can integrate the governing physics law into the learning process.In this work,a 1-dimensional(1 D)time-dependent seismic wave equation is considered and solved using two methods,namely Gaussian process(GP)and physics informed neural networks.We show that these meshless methods are trained by smaller amount of data and can predict the solution of the equation with even high accuracy.They are also capable of inverting any parameter involved in the governing equation such as wave velocity in our case.Results show that the GP can predict the solution of the seismic wave equation with a lower level of error,while our developed neural network is more accurate for velocity(P-and S-wave)and density inversion.

Multi-agent reinforcement learning for edge information sharing in vehicular networks

To guarantee the heterogeneous delay requirements of the diverse vehicular services,it is necessary to design a full cooperative policy for both Vehicle to Infrastructure(V2I)and Vehicle to Vehicle(V2V)links.This paper investigates the reduction of the delay in edge information sharing for V2V links while satisfying the delay requirements of the V2I links.Specifically,a mean delay minimization problem and a maximum individual delay minimization problem are formulated to improve the global network performance and ensure the fairness of a single user,respectively.A multi-agent reinforcement learning framework is designed to solve these two problems,where a new reward function is proposed to evaluate the utilities of the two optimization objectives in a unified framework.Thereafter,a proximal policy optimization approach is proposed to enable each V2V user to learn its policy using the shared global network reward.The effectiveness of the proposed approach is finally validated by comparing the obtained results with those of the other baseline approaches through extensive simulation experiments.

Detection of Learner’s Concentration in Distance Learning System with Multiple Biological Information

The trend of distance learning education has increased year by year because of the rapid advancement of information and communication technologies. Distance learning system can be regarded as one of ubiquitous computing applications since the learners can study anywhere even in mobile environments. However, the instructor cannot know if the learners comprehend the lecture or not since each learner is physically isolated. Therefore, a framework which detects the learners’ concentration condition is required. If a distance learning system obtains the information that many learners are not concentrated on the class due to the incomprehensible lecture style, the instructor can perceive it through the system and change the presentation strategy. This is a context-aware technology which is widely used for ubiquitous computing services. In this paper, an efficient distance learning system, which accurately detects learners’ concentration condition during a class, is proposed. The proposed system uses multiple biological information which are learners’ eye movement metrics, i.e. fixation counts, fixation rate, fixation duration and average saccade length obtained by an eye tracking system. The learners’ concentration condition is classified by using machine learning techniques. The proposed system has performed the detection accuracy of 90.7% when Multilayer Perceptron is used as a classifier. In addition, the effectiveness of the proposed eye metrics has been confirmed. Furthermore, it has been clarified that the fixation duration is the most important eye metric among the four metrics based on the investigation of evaluation experiment.

Semantic Information Extraction from Multi-Corpora Using Deep Learning

Information extraction plays a vital role in natural language processing,to extract named entities and events from unstructured data.Due to the exponential data growth in the agricultural sector,extracting significant information has become a challenging task.Though existing deep learningbased techniques have been applied in smart agriculture for crop cultivation,crop disease detection,weed removal,and yield production,still it is difficult to find the semantics between extracted information due to unswerving effects of weather,soil,pest,and fertilizer data.This paper consists of two parts.An initial phase,which proposes a data preprocessing technique for removal of ambiguity in input corpora,and the second phase proposes a novel deep learning-based long short-term memory with rectification in Adam optimizer andmultilayer perceptron to find agricultural-based named entity recognition,events,and relations between them.The proposed algorithm has been trained and tested on four input corpora i.e.,agriculture,weather,soil,and pest&fertilizers.The experimental results have been compared with existing techniques and itwas observed that the proposed algorithm outperformsWeighted-SOM,LSTM+RAO,PLR-DBN,KNN,and Na飗e Bayes on standard parameters like accuracy,sensitivity,and specificity.

Iterative Learning Control for Discrete-time Stochastic Systems with Quantized Information

An iterative learning control (ILC) algorithm using quantized error information is given in this paper for both linear and nonlinear discrete-time systems with stochastic noises. A logarithmic quantizer is used to guarantee an adaptive improvement in tracking performance. A decreasing learning gain is introduced into the algorithm to suppress the effects of stochastic noises and quantization errors. The input sequence is proved to converge strictly to the optimal input under the given index. Illustrative simulations are given to verify the theoretical analysis. © 2014 Chinese Association of Automation.

A Survey of Image Information Hiding Algorithms Based on Deep Learning

With the development of data science and technology,information security has been further concerned.In order to solve privacy problems such as personal privacy being peeped and copyright being infringed,information hiding algorithms has been developed.Image information hiding is to make use of the redundancy of the cover image to hide secret information in it.Ensuring that the stego image cannot be distinguished from the cover image,and sending secret information to receiver through the transmission of the stego image.At present,the model based on deep learning is also widely applied to the field of information hiding.This paper makes an overall conclusion on image information hiding based on deep learning.It is divided into four parts of steganography algorithms,watermarking embedding algorithms,coverless information hiding algorithms and steganalysis algorithms based on deep learning.From these four aspects,the state-of-the-art information hiding technologies based on deep learning are illustrated and analyzed.

Information Detection of Seismic Debris Flow by UAV High-resolution Image Based on Transfer Learning

A large number of debris flow disasters(called Seismic debris flows) would occur after an earthquake, which can cause a great amount of damage. UAV low-altitude remote sensing technology has become a means of quickly obtaining disaster information as it has the advantage of convenience and timeliness, but the spectral information of the image is so scarce, making it difficult to accurately detect the information of earthquake debris flow disasters. Based on the above problems, a seismic debris flow detection method based on transfer learning(TL) mechanism is proposed. On the basis of the constructed seismic debris flow disaster database, the features acquired from the training of the convolutional neural network(CNN) are transferred to the disaster information detection of the seismic debris flow. The automatic detection of earthquake debris flow disaster information is then completed, and the results of object-oriented seismic debris flow disaster information detection are compared and analyzed with the detection results supported by transfer learning.

Deep learning in extracting tropical cyclone intensity and wind radius information from satellite infrared images—A review

热带气旋(TC)严重危害人类生命和财产安全,TC的实时监测一直是研究热点,随着空间和传感器技术的发展,卫星遥感已成为监测TC的主要手段.此外,深度学习具有卓越的数据挖掘能力,在地球科学中的表现优于基于物理或统计的算法,越来越多的深度学习算法被开发和应用于TC信息的提取,本文系统地回顾了深度学习在TC信息提取中的应用,并给出了深度学习模型在TC强度和风圈半径提取中的应用.此外,本文还展望了深度学习在TC信息提取中的应用前景.

Aortic Dissection Diagnosis Based on Sequence Information and Deep Learning

Aortic dissection(AD)is one of the most serious diseases with high mortality,and its diagnosis mainly depends on computed tomography(CT)results.Most existing automatic diagnosis methods of AD are only suitable for AD recognition,which usually require preselection of CT images and cannot be further classified to different types.In this work,we constructed a dataset of 105 cases with a total of 49021 slices,including 31043 slices expertlevel annotation and proposed a two-stage AD diagnosis structure based on sequence information and deep learning.The proposed region of interest(RoI)extraction algorithm based on sequence information(RESI)can realize high-precision for RoI identification in the first stage.Then DenseNet-121 is applied for further diagnosis.Specially,the proposed method can judge the type of AD without preselection of CT images.The experimental results show that the accuracy of Stanford typing classification of AD is 89.19%,and the accuracy at the slice-level reaches 97.41%,which outperform the state-ofart methods.It can provide important decision-making information for the determination of further surgical treatment plan for patients.

Dynamic Evolution with Limited Learning Information on a Small-World Network

This paper investigates the dynamic evolution with limited learning information on a small-world network.In the system, the information among the interaction players is not very lucid, and the players are not allowed to inspectthe profit collected by its neighbors, thus the focal player cannot choose randomly a neighbor or the wealthiest one andcompare its payoff to copy its strategy.It is assumed that the information acquainted by the player declines in theform of the exponential with the geographical distance between the players, and a parameter V is introduced to denotethe inspect-ability about the players.It is found that under the hospitable conditions, cooperation increases with therandomness and is inhibited by the large connectivity for the prisoner's dilemma; however, cooperation is maximal atthe moderate rewiring probability and is chaos with the connectivity for the snowdrift game.For the two games, theacuminous sight is in favor of the cooperation under the hospitable conditions; whereas, the myopic eyes are advantageousto cooperation and cooperation increases with the randomness under the hostile condition.

CoLM^(2)S:Contrastive self‐supervised learning on attributed multiplex graph network with multi‐scale information

Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently.However,there are still two challenges.First,most of the real‐word system are multiple relations,where entities are linked by different types of relations,and each relation is a view of the graph network.Second,the rich multi‐scale information(structure‐level and feature‐level)of the graph network can be seen as self‐supervised signals,which are not fully exploited.A novel contrastive self‐supervised representation learning framework on attributed multiplex graph networks with multi‐scale(named CoLM^(2)S)information is presented in this study.It mainly contains two components:intra‐relation contrast learning and interrelation contrastive learning.Specifically,the contrastive self‐supervised representation learning framework on attributed single‐layer graph networks with multi‐scale information(CoLMS)framework with the graph convolutional network as encoder to capture the intra‐relation information with multi‐scale structure‐level and feature‐level selfsupervised signals is introduced first.The structure‐level information includes the edge structure and sub‐graph structure,and the feature‐level information represents the output of different graph convolutional layer.Second,according to the consensus assumption among inter‐relations,the CoLM^(2)S framework is proposed to jointly learn various graph relations in attributed multiplex graph network to achieve global consensus node embedding.The proposed method can fully distil the graph information.Extensive experiments on unsupervised node clustering and graph visualisation tasks demonstrate the effectiveness of our methods,and it outperforms existing competitive baselines.

An Analysis Model of Learners’ Online Learning Status Based on Deep Neural Network and Multi-Dimensional Information Fusion

The learning status of learners directly affects the quality of learning.Compared with offline teachers,it is difficult for online teachers to capture the learning status of students in the whole class,and it is even more difficult to continue to pay attention to studentswhile teaching.Therefore,this paper proposes an online learning state analysis model based on a convolutional neural network and multi-dimensional information fusion.Specifically,a facial expression recognition model and an eye state recognition model are constructed to detect students’emotions and fatigue,respectively.By integrating the detected data with the homework test score data after online learning,an analysis model of students’online learning status is constructed.According to the PAD model,the learning state is expressed as three dimensions of students’understanding,engagement and interest,and then analyzed from multiple perspectives.Finally,the proposed model is applied to actual teaching,and procedural analysis of 5 different types of online classroom learners is carried out,and the validity of the model is verified by comparing with the results of the manual analysis.