Vision-Language Models (VLMs), with their powerful content generation capabilities, have been successfully applied to data annotation processes. However, the VLM-generated labels exhibit dual limitations: low quality (i.e., label noise) and absence of error correction mechanisms. To enhance label quality, we propose Human-Corrected Labels (HCLs), a novel setting that efficient human correction for VLM-generated noisy labels. As shown in Figure 1(b), HCL strategically deploys human correction only for instances with VLM discrepancies, achieving both higher-quality annotations and reduced labor costs. Specifically, we theoretically derive a risk-consistent estimator that incorporates both human-corrected labels and VLM predictions to train classifiers. Besides, we further propose a conditional probability method to estimate the label distribution using a combination of VLM outputs and model predictions. Extensive experiments demonstrate that our approach achieves superior classification performance and is robust to label noise, validating the effectiveness of HCL in practical weak supervision scenarios.

Recent advances in weakly multi-label learning (MLL) have demonstrated impressive potential in multi-label classification tasks. Unfortunately, collecting multi-labels for each instance proves to be time-consuming and labor-intensive, since these MLL methods requires the assessment of all the candidate labels. To alleviate this challenge, a novel labeling setting termed Determined Multi-Label Learning is proposed, aiming to effectively reduce the cost for browsing labels in multi-label tasks. In this setting, each training instance is associated with a determined multi-label, which indicates whether the instance contains the provided class label. Besides, each instance only need to be determined once, which significantly reduce the annotation cost of the labeling task for multi-label datasets. In this paper, we theoretically derive an risk-consistent estimator to learn from these determined-labeled training data. Additionally, we introduce a similarity-based prompt learning method, which minimizes the risk-consistent loss of large-scale pre-trained models to learn a supplemental prompt with richer semantic information. Extensive experimental validation underscores the efficacy of our approach. Our code is available at the link: https://github.com/WilsonMqz/DMLL

To reduce pressure of manual annotation, researchers have explored various weakly supervised learning methods and achieved remarkable results in multi-class classification tasks. However, these methods still require annotating from the entire set of candidate labels, which becomes particularly time-consuming when the labeling space is large. To alleviate this problem, we propose a novel labeling mechanism called stochastic labels, which reduces the time spent browsing labeling space by annotating the instance from a small labels subset. In this paper, we introduce an unbiased risk estimator and establish a prototype baseline to learn a multi-class classifier from these stochastic labels. Besides, we derive the estimation error bound of the proposed method, showing that the empirical risk could converge to the true classification risk as the number of training samples increases. Finally, we conduct extensive experiments on widely-used benchmark datasets to validate the effectiveness of our approach. Our method surpasses state-of-the-art weakly supervised methods, highlighting its efficiency and robustness. Our code is available at: https://github.com/WilsonMqz/SLL

Pre-trained Vision-Language Models (VLMs) exhibit strong zero-shot classification abilities, demonstrating great potential for generating weakly supervised labels. Unfortunately, existing weakly supervised learning methods are short of ability in generating accurate labels via VLMs. In this paper, we propose a novel weakly supervised labeling setting, namely True-False Labels (TFLs) which can achieve high accuracy when generated by VLMs. The TFL indicates whether an instance belongs to the label, which is randomly and uniformly sampled from the candidate label set. Specifically, we theoretically derive a risk-consistent estimator to explore and utilize the conditional probability distribution information of TFLs. Besides, we propose a convolutional-based Multi-modal Prompt Retrieving (MRP) method to bridge the gap between the knowledge of VLMs and target learning tasks. Experimental results demonstrate the effectiveness of the proposed TFL setting and MRP learning method. The code to reproduce the experiments is at https://github.com/Tranquilxu/TMP.

Recent advances in vision-language models (VLMs) have demonstrated remarkable capabilities in image classification by leveraging predefined sets of labels to construct text prompts for zero-shot reasoning. However, these approaches face significant limitations in undefined domains, where the label space is vocabulary-unknown and composite. We thus introduce Generative Semantic Labels (GSLs), a novel task that aims to predict a comprehensive set of semantic labels for an image without being constrained by a predefined labels set. Unlike traditional zero-shot classification, GSLs generates multiple semantic-level labels, encompassing objects, scenes, attributes, and relationships, thereby providing a richer and more accurate representation of image content. In this paper, we propose Chain-of-Action (CoA), an innovative method designed to tackle the GSLs task. CoA is motivated by the observation that enriched contextual information significantly improves generative performance during inference. Specifically, CoA decomposes the GSLs task into a sequence of detailed actions. Each action extracts and merges key information from the previous step, passing enriched context to the next, ultimately guiding the VLM to generate comprehensive and accurate semantic labels. We evaluate the effectiveness of CoA through extensive experiments on widely-used benchmark datasets. The results demonstrate significant improvements across key performance metrics, validating the capability of CoA to generate accurate and contextually rich semantic labels. Our work not only advances the state-of-the-art in generative semantic labels but also opens new avenues for applying VLMs in open-ended and dynamic real-world scenarios.

Learning from Multi-Positive and Unlabeled (MPU) data has gradually attracted significant attention from practical applications. Unfortunately, the risk of MPU also suffer from the shift of minimum risk, particularly when the models are very flexible. In this paper, to alleviate the shifting of minimum risk problem, we propose an Example Sieve Approach (ESA) to select examples for training a multi-class classifier. Specifically, we sieve out some examples by utilizing the Certain Loss (CL) value of each example in the training stage and analyze the consistency of the proposed risk estimator. Besides, we show that the estimation error of proposed ESA obtains the optimal parametric convergence rate. Extensive experiments on various real-world datasets show the proposed approach outperforms previous methods.

Multi-label learning (MLL) learns from samples associated with multiple labels, where it is expensive and time consuming to provide detailed annotation for each sample in real-world datasets. To deal with this challenge, single positive multi-label learning (SPML) has been studied in recent years. In SPML, each sample is annotated with only one positive label, which is much easier and less costly. However, in many real-world scenarios, single positive labels may have global unannotated categories (GUCs) in annotation process, which exist in the label space but do not serve as single positive label for any samples. Unfortunately, previous SPML approaches are less applicable to classify GUCs due to the absence of supervised information. To solve this problem, we propose a novel prompt expanding framework that leverages a large-scale pretrained vision and language model called the Recognize Anything Model (RAM) to offer supervision signals for GUCs. Specifically, we first provide a simple but effective strategy to generate reliable pseudo-labels for GUCs by utilizing zero-shot predictions of RAM. Subsequently, we introduce additional prompts from a large common category list and fuse them by learnable weighting factors, which expends the semantic representation of GUCs. Experiments show that our method achieves state-of-the-art results on all four benchmarks. The code to reproduce the experiments is at: https://github.com/yingpenga/VLSPE

Long-tailed data is prevalent in real-world classification tasks and heavily relies on supervised information, which makes the annotation process exceptionally labor-intensive and time-consuming. Unfortunately, despite being a common approach to mitigate labeling costs, existing weakly supervised learning methods struggle to adequately preserve supervised information for tail samples, resulting in a decline in accuracy for the tail classes. To alleviate this problem, we introduce a novel weakly supervised labeling setting called Reduced Label. The proposed labeling setting not only avoids the decline of supervised information for the tail samples, but also decreases the labeling costs associated with long-tailed data. Additionally, we propose an straightforward and highly efficient unbiased framework with strong theoretical guarantees to learn from these Reduced Labels. Extensive experiments conducted on benchmark datasets including ImageNet validate the effectiveness of our approach, surpassing the performance of state-of-the-art weakly supervised methods. Source code is available at \hrefhttps://github.com/WilsonMqz/LTRL https://github.com/WilsonMqz/LTRL

Annotating data for sensitive labels (e.g., disease, smoking) poses a potential threats to individual privacy in many real-world scenarios. To cope with this problem, we propose a novel setting to protect privacy of each instance, namely learning from concealed labels for multi-class classification. Concealed labels prevent sensitive labels from appearing in the label set during the label collection stage, which specifies none and some random sampled insensitive labels as concealed labels set to annotate sensitive data. In this paper, an unbiased estimator can be established from concealed data under mild assumptions, and the learned multi-class classifier can not only classify the instance from insensitive labels accurately but also recognize the instance from the sensitive labels. Moreover, we bound the estimation error and show that the multi-class classifier achieves the optimal parametric convergence rate. Experiments demonstrate the significance and effectiveness of the proposed method for concealed labels in synthetic and real-world datasets. Source code is available at https://github.com/WilsonMqz/CLF

Adversarial training (AT) has shown excellent high performance in defending against adversarial examples. Recent studies demonstrate that examples are not equally important to the final robustness of models during AT, that is, the so-called hard examples that can be attacked easily exhibit more influence than robust examples on the final robustness. Therefore, guaranteeing the robustness of hard examples is crucial for improving the final robustness of the model. However, defining effective heuristics to search for hard examples is still difficult. In this article, inspired by the information bottleneck (IB) principle, we uncover that an example with high mutual information of the input and its associated latent representation is more likely to be attacked. Based on this observation, we propose a novel and effective adversarial training method (InfoAT). InfoAT is encouraged to find examples with high mutual information and exploit them efficiently to improve the final robustness of models. Experimental results show that InfoAT achieves the best robustness among different datasets and models in comparison with several state-of-the-art methods.

MOTIVATION: As the third-generation sequencing technology, nanopore sequencing has been used for high-throughput sequencing of DNA, RNA, and even proteins. Recently, many studies have begun to use machine learning technology to analyze the enormous data generated by nanopores. Unfortunately, the success of this technology is due to the extensive labeled data, which often suffer from enormous labor costs. Therefore, there is an urgent need for a novel technology that can not only rapidly analyze nanopore data with high-throughput, but also significantly reduce the cost of labeling. To achieve the above goals, we introduce active learning to alleviate the enormous labor costs by selecting the samples that need to be labeled. This work applies several advanced active learning technologies to the nanopore data, including the RNA classification dataset (RNA-CD) and the Oxford Nanopore Technologies barcode dataset (ONT-BD). Due to the complexity of the nanopore data (with noise sequence), the bias constraint is introduced to improve the sample selection strategy in active learning. Results: The experimental results show that for the same performance metric, 50% labeling amount can achieve the best baseline performance for ONT-BD, while only 15% labeling amount can achieve the best baseline performance for RNA-CD. Crucially, the experiments show that active learning technology can assist experts in labeling samples, and significantly reduce the labeling cost. Active learning can greatly reduce the dilemma of difficult labeling of high-capacity nanopore data. We hope active learning can be applied to other problems in nanopore sequence analysis. AVAILABILITY AND IMPLEMENTATION: The main program is available at https://github.com/guanxiaoyu11/AL-for-nanopore. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The detection of electrical insulators in unmanned aerial vehicle (UAV) images using deep learning has made great progress in recent years, but little research has been conducted in the same field in remote sensing (RS) images. In this article, a novel method was proposed to detect insulators on 500-kV transmission towers in RS images. The proposed method consists of three components including 1) a super-resolution (SR) network to improve image resolution; 2) an object detection model to detect 110-, 220-, and 500-kV electrical power towers along transmission pipelines; and 3) a semantic segmentation network to identify insulators on the detected 500-kV towers. In addition, the online hard example mining (OHEM) method and class weight calculation method were utilized to handle the imbalanced data among different classes during training. The proposed model was evaluated on SuperView-1 and WorldView-3 satellite images collected in four regions. Experimental results show that the proposed method can effectively detect insulators in high-resolution satellite images and achieved the highest F1 score of 0.7952. The codes are available athttps://github.com/hardworking-jws/insulator-detection-remote-sensing

Low-Dose Computed Tomography (LDCT) technique, which reduces the radiation harm to human bodies, is now attracting increasing interest in the medical imaging field. As the image quality is degraded by low dose radiation, LDCT exams require specialized reconstruction methods or denoising algorithms. However, most of the recent effective methods overlook the inner-structure of the original projection data (sinogram) which limits their denoising ability. The inner-structure of the sinogram represents special characteristics of the data in the sinogram domain. By maintaining this structure while denoising, the noise can be obviously restrained. Therefore, we propose an LDCT denoising network namely Sinogram Inner-Structure Transformer (SIST) to reduce the noise by utilizing the inner-structure in the sinogram domain. Specifically, we study the CT imaging mechanism and statistical characteristics of sinogram to design the sinogram inner-structure loss including the global and local inner-structure for restoring high-quality CT images. Besides, we propose a sinogram transformer module to better extract sinogram features. The transformer architecture using a self-attention mechanism can exploit interrelations between projections of different view angles, which achieves an outstanding performance in sinogram denoising. Furthermore, in order to improve the performance in the image domain, we propose the image reconstruction module to complementarily denoise both in the sinogram and image domain.

At present, the urban functional system (UFS) has been changing with the rapid development of urbanization, which has brought serious challenges for the decision-making of urban planners. It is of great significance to investigate the robustness evaluation of urban functional system. Firstly, the composition map of urban functional area is obtained. Secondly, the center points of each functional area in the system are extracted to represent each functional area and to establish the coupling relationship between different functional areas. Thirdly, the robustness indices for different functional systems are designed. A series of simulation experiments about attack and damage are designed, and the change trend of robustness indices of urban functional system is investigated. Finally, the evaluation indices are established and a variety of simulation experiments are carried out to analyze the change trend of robustness indices. Our experimental results showed that the local attack in batches mode was the most serious mode to destroy the urban functional system. Therefore, more attention should be paid to avoid or alleviate the influence of the local attack in batches.

Ribonucleic acid (RNA) is a pivotal nucleic acid that plays a crucial role in regulating many biological activities. Recently, one study utilized a machine learning algorithm to automatically classify RNA structural events generated by a Mycobacterium smegmatis porin A nanopore trap. Although it can achieve desirable classification results, compared with deep learning (DL) methods, this classic machine learning requires domain knowledge to manually extract features, which is sophisticated, labor-intensive and time-consuming. Meanwhile, the generated original RNA structural events are not strictly equal in length, which is incompatible with the input requirements of DL models. To alleviate this issue, we propose a sequence-to-sequence (S2S) module that transforms the unequal length sequence (UELS) to the equal length sequence. Furthermore, to automatically extract features from the RNA structural events, we propose a sequence-to-sequence neural network based on DL. In addition, we add an attention mechanism to capture vital information for classification, such as dwell time and blockage amplitude. Through quantitative and qualitative analysis, the experimental results have achieved about a 2% performance increase (accuracy) compared to the previous method. The proposed method can also be applied to other nanopore platforms, such as the famous Oxford nanopore. It is worth noting that the proposed method is not only aimed at pursuing state-of-the-art performance but also provides an overall idea to process nanopore data with UELS.

optimizing spectral filters for hyperspectral reconstruction has received increasing attentions recently. However, current filter selection methods suffer from extremely high computational complexity due to exhaustive optimization. In this paper, in order to reduce the computational complexity, we propose a novel Filter Selection Network (FS-Net) to select filters and learn the reconstruction network simultaneously. Specifically, we propose an end-to-end method to embed filter selection in FS-Net by setting spectral response functions as the input layer. Furthermore, we propose a non-negative Ll sparse regularization (NN-LI) to select optical filters automatically by sparsifying the input layer. Besides, we develop a two-stage training strategy for adjusting the number of selected filters. Experiments on public datasets show that our proposed method can considerably improve the reconstruction quality.

Landslides are common natural disasters that often cause serious impact and damage to human society. Since landslide disasters threaten people's production and life all the time, it is particularly important to predict the risk of landslides and to control landslide disasters. When studying landslide risk and deciding whether to treat the landslide, it is meaningful to classify and compare the risk of landslides so as to select those landslides with a higher degree of danger for priority treatment. The target of this paper is to extract factors related to landslide risk, and train a classification models for landslide risk. It employs ensemble machine learning algorithms to classify landslide hazards. Because the landslide feature has a large number of dimensions, this paper uses the PCA method to reduce the dimension. Due to the imbalance of the samples, this paper uses the SMOTE method to handle the imbalanced learning. The results of study show that the selected factors are highly related to landslide risk, the classification model in this paper has good accuracy.

With the development of urbanization in China, the land economy accounts for more and more percentage in the gross domestic product (GDP) of China. Therefore, the accurate assessment of urban residential land price is of great interest for the governments. In the paper, we introduced the transfer learning to assess the urban residential land price, taking the Shenzhen city in China as a case. First, we collected housing price, land price data and points of interest (POI) data. The POI data was quantified as the influencing factors of two price data. Second, we used housing price data and influencing factors to train a high-accuracy model based on deep belief network (DBN). Third, we kept the DBN model unchanged, and then used three new models connected in order to better assess land price. The three models are back propagation (BP) neural network, support vector machine (SVM), and random forest (RF). Finally, we used land price data and influencing factors with three models to find the best one. The models were trained by the method of five-fold cross validation. Our results showed that all of three transfer learning models had good accuracy but the model with random forest was more suitable for the urban residential land price assessment. Therefore, our proposed method is an efficient approach to assess the urban residential land price with transfer learning.

With the vigorous advocacy of the concept of green development, the protection and management of natural resources become more and more important. It is of great significance to study the classification of surface natural resources by remote sensing. In this paper, a high-resolution net (HR-Net) model is used to classify surface natural resources by Gaofen-1 (GF-1) satellite images and digital elevation model (DEM) data. First of all, we obtained the GF-1 satellite images, DEM data and census data of geographical conditions of the study area. And the first two kinds of data are integrated into five channels, which are red (R), green (G), blue (B), near infrared (NIR) and elevation channels. Second, we chose an area to make the labeled image with several classes contain surface natural resources. Third, we cut the image into training images and testing images, and the training images were made into 5000 images, 128 × 128 pixels to train the HR-Net model. Also for comparison, the experiment was carried out used the image without DEM data. Finally, we compared the accuracy, and our results showed that HR-Net model is useful and the image with DEM data has the better accuracy. Therefore, HR-Net and DEM data can be applied in practice to support the classification of surface natural resources.

In the presented article, machine learning (ML) is employed on advanced Himawari imager (AHI) to examine real-time fire and map damaged zone over Yunnan, China. The main emphasis lies in employing machine learning as an alternative to primeval thresholding, extricating, and scrutinizing thermal anomaly using infrared (IR). Firstly, Himawari brightness temperature (BT), band ratio, albedo, and BT differences are utilized to scrutinize fire break out. Then, to ensure pixels are clear and free from clouds, the Himawari cloud product is implemented. Finally, machine learning models such as random forest (RF), artificial neural network (ANN), and time-series long short-term memory (LSTM), a deep learning model, are used to precisely classify the active fire pixels and achieved accuracies of 0.96%, 0.95%, 0.92% respectively. The results evaluated using another AHI wildfire product and inter-compared with multi-source fire products.

In recent years, the problem of land subsidence in urban areas has attracted more attention. differential interferometric synthetic aperture radar (D-InSAR) is a common surface deformation measurement technology. About our research, first of all, the processing effects of the ascending and descending images, VV polarization and VH polarization of Sentinel-1A data in the study area are compared. The ascending image with better coverage in the study area and VV polarization with better interference processing effect are selected. Second, the filtering algorithm and unwrapping algorithm in D-InSAR are contrasted. In terms of filtering algorithms, the improved Goldstein method with the coherence coefficient to adjust the power exponent of the weighting function in the frequency domain had the best filtering effect. In terms of unwrapping algorithms, there are fewer unwrapping islands in the minimum cost network flow method. Finally, D-InSAR is used to process the Sentinel-1A data to obtain the surface deformation results of downtown Chengdu. Therefore, the deformation of downtown Chengdu based on Sentinel-1A data is abtained.

In the power system, there are a large number of capacitive devices, accounting for 40% to 50% of the total substation equipment. The healthy operation of capacitive devices is vital to the power system. With the vigorous advancement of power grid information construction, various types of power data have exploded, which has provided strong data support for the healthy operation of capacitive equipment. There is little research on the relationship between the defects of capacitive equipment and topography at home and abroad, such as altitude, slope, and aspect. This project conducts research on the relationship between defects of capacitive equipment and topography, and provides technical support and assistance for decision-making of power system construction. Firstly, 60 TIFF images with a resolution of 30m were obtained from the website, and 60 images were stitched using ArcGIS software, and then the slope and aspect data of the target location were extracted based on the latitude and longitude information. Secondly, we perform data cleaning and code on the original data. Thirdly, the relationship between the number of occurrences of equipment defects and altitude, slope, and aspect is programmed. The correlation is roughly deduced by calculating the number of occurrences of equipment defects and the parameters such as the covariance, correlation coefficient.

In addition to GPS and leveling, there are also synthetic aperture radar (SAR) measurements in the field of remote sensing. Differential interferometric SAR (D-InSAR) is a surface deformation measurement technology developed from synthetic aperture radar interferometry (InSAR). In the research of D-InSAR, although the processing flow is certain, the selection of data and process method is not universal. In the process of InSAR interferometric data processing, phase unwrapping is the key link, which directly affects the accuracy of digital elevation model (DEM). In this paper, the phase unwrapping methods of dual pass D-InSAR are compared. There will be islands in the process of unwrapping, and the less the islanding, the better. Through the situation of islanding, the unwrapping effect of region growth method and minimum network cost flow method is compared. The results show that the best method is the minimum cost network flow method.

Wildfires may cause great casualties and heavy wildfires are becoming more and more frequently all over the world in recent years. However, due to the environmental limitation, high manual-dependent operation is often impractical with other limits. In this paper, a transfer learning neural network based on long short term memory (LSTM) was used to detect wildfire based on Himawari-8. The real time dynamic threshold value detection for cloud mask based on the modified Otsu algorithm was used to fast and accurately remove cloud areas where wildfire detection is failed due to signal blocking. Then, the experiments were conducted with LSTM and other models. The experimental results showed that our method was positive for wildfire detection.

This paper presents the first study on Sign-aware Perturbations Regression (SaPR), where the observed response variables contain the aware sign (negative or positive) perturbations.In order to predict the non-perturbation response variables, we propose a novel parameter estimator SZOM (i.e.,Setting Zero Operator Method), which aims at taking full advantage of the aware perturbations information to correct the mistake values in the estimation process with computationally efficiency.In this paper, the two aspects of theoretical analysis are proposed to deeply understand our method.Firstly, we establish the perturbation parameter error upper bound and prove consistency guarantee in the linear regression scenario.Secondly, we introduce the generalization error bound for the proposed SZMO, which indicates that the error bound is related to the value and the number of negative and positive perturbations.The effectiveness of the proposed approach is well validated by the experimental results on both synthetic and real datasets.

In Compressive Sensing MRI (CS-MRI), measurement matrix learning has been developed as a promising method for measurement matrix designing. Research on MRI measurement task suggests that Relative 2-Norm Error (RLNE) of measurement images is imbalanced. However, current learning-based investigations suffer from the lack of probing imbalanced characteristic on measurement matrix learning. In this paper, we propose a novel Measurement Matrix Learning via Correlation Reweighting (MML-CR) approach for exploring and solving this problem by optimizing reweighted model.Specifically,we introduce a reweighting expected minimization model to obtain an essential measurement matrix in k-space. Besides, we propose an example correlation regularizer to prevent trivial solution for learning weights. Furthermore, we present an alternating solution and perform convergence analysis for the optimization. We also demonstrate quantitative and qualitative experimental results which show that our algorithm outperforms several state-of-art measurements methods. Compared with conventional methods, MML-CR achieves better performance on universal task.

Generative Adversarial Networks (GANs) are powerful tools for reconstructing Compressed Sensing Magnetic Resonance Imaging (CS-MRI). However most recent works lack exploration of structure information of MRI images that is crucial for clinical diagnosis. To tackle this problem, we propose the Structure-Enhanced GAN (SEGAN) that aims at restoring structure information at both local and global scale. SEGAN defines a new structure regularization called Patch Correlation Regularization (PCR) which allows for efficient extraction of structure information. In addition, to further enhance the ability to uncover structure information, we propose a novel generator SU-Net by incorporating multiple-scale convolution filters into each layer. Besides, we theoretically analyze the convergence of stochastic factors contained in training process. Experimental results show that SEGAN is able to learn target structure information and achieves state-of-theart performance for CS-MRI reconstruction.

Relay stations (RSs) can enhance signal quality for mobile stations (MSs) close to the cell boundary. To abundantly exploit the advantages of RSs, it is a critical task to investigate the impact of RSs location on link reliability and system capacity in two-hop cellular networks. In this paper, the closed-form of the number of disconnect MSs and the expression of system capacity for varying RSs location are obtained in two-hop cellular networks with decode-and-forward scheme. Finally, the Monte-Carlo simulations are performed to verify the theoretical results and to get the optimal RSs location with different objective functions.

In this paper, a novel dynamic full frequency reuse scheme is proposed to improve the spectral efficiency in orthogonal frequency division multiple access (OFDMA) cellular relay networks. Different from the conventional full frequency reuse scheme which only allows the base station (BS) reusing the subcarriers in the specific regions, we proposed an improved full frequency reuse scheme to allow the BS reusing all the subcarriers in the whole BS coverage region to exploit more multiuser diversity gain. In order to dynamically reuse the frequency resource among the BS and relay stations (RSs) to further improve the spectral efficiency, the adaptive subcarrier scheduling is introduced into the improved full frequency reuse scheme, which forms the proposed novel dynamic full frequency reuse scheme. Simulation results show that the proposed scheme can obtain high spectral efficiency, fine fairness and low outage probability.

The Rao-Blackwellized particle filter (RBPF) is proposed to estimate the carrier frequency offset (CFO) and channel state information (CSI) for uplink multiple-input multiple-output orthogonal frequency division multiple access (MIMO-OFDMA) systems. In the proposed scheme, the channel response and the frequency offset are described as auto- regressive (AR) model and generalized AR model, respectively. The carrier frequency offset can be estimated using the particle filter, and the distribution of the fading channel is updated analytically using the Kalman filter, which is associated with each particle. Furthermore, the expectation-maximization (EM) algorithm is evolved to learn model parameters recursively. Simulation results show that the proposed RBPF algorithm has lower block error rate (BLER) than the conventional particle filter and the Rao-Blackwellized Gauss-Hermite filter (RB-GHF), while the processing complexity is rather reasonable.