Recently, social media platforms like Weibo have introduced mandatory IP address displays to enhance information evaluation, but their effectiveness remains unclear. In this study, we conducted an online experiment with 722 participants to examine the effectiveness of mandatory IP address displays under different conditions (none, matched, unmatched, unknown) on social media. This study investigated how these conditions influence users’ trust in social media information and whether this process is moderated by users’ patterns of social media usage. Results showed that matched IPs increased trust, unmatched IPs reduced it, and unknown IP labels were perceived as neutral. Frequent social media use and active participation correlated with higher trust in the presented information, indicating susceptibility to misinformation. Trust in technology also amplified trust in social media information under unknown or mismatched IPs. These findings highlight risks in over-relying on social media features, emphasizing the need for careful design to counter misinformation.

Artificial intelligence-generated content (AIGC), a rapidly advancing technology, is transforming content creation across domains, such as text, images, audio, and video. Its growing potential has attracted more and more researchers and investors to explore and expand its possibilities. This review traces AIGC’s evolution through four developmental milestones, ranging from early rule-based systems to modern transfer learning (TL) models, within a unified framework that highlights how each milestone contributes uniquely to content generation. In particular, this article employs a common example across all milestones to illustrate the capabilities and limitations of methods within each phase, providing a consistent evaluation of AIGC methodologies and their development. Furthermore, this article addresses critical challenges associated with AIGC and proposes actionable strategies to mitigate them. This study aims to guide researchers and practitioners in selecting and optimizing AIGC models to enhance the quality and efficiency of content creation across diverse domains.

Given the capability of multimodal data to provide information from multiple perspectives, it is beneficial for improving the accuracy of Alzheimer’s disease (AD) classification. However, during practical multimodal learning, there is a phenomenon where certain modalities dominate the decision-making, leading to insufficient learning from other modalities. Moreover, redundant information within multimodal data can also hinder accurate classification decisions. Therefore, we propose a robust multimodal representation learning method for AD classification. Specifically, we first construct dedicated encoders for each multimodal data, including structural Magnetic Resonance Imaging (sMRI) images, Positron Emission Tomography (PET) images, and Mini-Mental State Examination (MMSE) scores, to extract their respective representations. Then, we employ the information bottleneck (IB) theory to guide the model to retain classification-related information in multimodal representations while reducing redundancy among modalities. Furthermore, to promote a balanced fusion of multimodal data, we redefine the classification confidence of each modality’s representation using an orthogonal weight classifier and then introduce a regularization term to amplify the prediction score differences for modalities with lower confidence. The experimental results on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset demonstrate that our method enhances the robustness of multimodal representations and achieves promising performance in AD-related classification tasks.

The goal of RGB-T tracking is to enhance the accuracy and robustness by leveraging the complementary features of RGB and TIR modalities in complex scenarios. Previous methods have overlooked the power of semantic features in extracting valuable information from different modalities and improving interactions across them. Moreover, using Bounding Boxes (BBox) for target initialization can cause issues like bounding box blurring and tracking drift when the target’s appearance changes or gets occluded. To address these challenges, we propose the CLIP-based RGBT tracking algorithm TIETracker, which aims to to exploit the complementary advantages of multimodality more effectively using textual information. Textual descriptions direct the backbone network to learn target representations in multimodality and facilitate the interaction of multi-modal features. Additionally, in scenarios of occlusion and scale transformations that lead to missing or altered target features, textual information adaptively supplements the target representation. This approach also improves the response in the image region of the target, addressing issues with bounding box accuracy and tracking drift. Our extensive evaluation on three leading RGB-T tracking benchmarks demonstrates that TIETracker achieves competitive compared to state-of-the-art methods, effectively countering feature loss from changes in target appearance and occlusion.

Semi-supervised learning (SSL) has been widely used to learn from both a few labeled images and many unlabeled images to overcome the scarcity of labeled samples in medical image segmentation. Most current SSL-based segmentation methods use pixel values directly to identify similar features in labeled and unlabeled data. They usually fail to accurately capture the intricate attachment structures in the left atrium, such as the areas of inconsistent density or exhibit outward curvatures, adding to the complexity of the task. In this paper, we delve into this issue and introduce an effective solution, CORAL(Correlation-Aligned)-Correlation Consistency Network (CORN), to capture the global structure shape and local details of Left Atrium. Diverging from previous methods focused on each local pixel value, the CORAL-Correlation Consistency Module (CCM) in the CORN leverages second-order statistical information to capture global structural features by minimizing the distribution discrepancy between labeled and unlabeled samples in feature space. Yet, direct construction of features from unlabeled data frequently results in "Sample Selection Bias", leading to flawed supervision. We thus further propose the Dynamic Feature Pool (DFP) for the CCM, which utilizes a confidence-based filtering strategy to remove incorrectly selected features and regularize both teacher and student models by constraining the similarity matrix to be consistent. Extensive experiments on the Left Atrium dataset have shown that the proposed CORN outperforms previous state-of-the-art semi-supervised learning methods.

Optical coherence tomography angiography (OCTA) is a non-invasive imaging technique that can reveal blood flow and the detailed structure of the retinal and choroidal vasculature. However, uneven image quality and the high complexity of blood vessel distribution bring great challenges to accurate blood vessel segmentation. In this paper, we propose an OCTA blood vessel segmentation network based on the classic encoder-decoder architecture called TTCNet, which integrates a dual-branch encoder to capture global context information effectively. In addition, Snake Detail Attention Block is designed to enhance the perception of the tubular structure of blood vessels and provide richer feature representation in the network. We also design a module named Pyramid Feature Attention Module in each level of skip connection to better extract feature information at different scales. Experiments are conducted on two public datasets, OCTA_6M and OCTA_3M. G-mean Score and Area Under the Curve of our network on these two datasets are 93.05, 93.18, and 95.21, 94.95%, respectively, achieving better results than other state-of-the-art methods.

Medical image segmentation’s accuracy is crucial for clinical analysis and diagnosis. Despite progress with U-Net-inspired models, they often underuse multi-scale encoding layers crucial for enhancing detailing visual features and overlooking the importance of merging multi-scale features within the channel dimension to enhance decoder complexity. To address these limitations, we introduce a dual-scale hybrid encoder network DSENet for medical image segmentation. Our network design is characterized by the strategic employment of dual-scale convolutional kernels at each encoder level, integrating the robust feature extraction capabilities of CNNs with the contextual awareness of Transformer models. This synergy enables the precise capture of both granular and broader context features throughout the encoding phase. We further enhance the model by integrating a channel attention fusion (CAF) mechanism within the skip connections. This innovation effectively integrates dual-scale features, subsequently integrating them with the same-level decoder feature map, thereby reinforcing the feature representation. To refine the predicted segmentation, we employ a novel strategy that merges dual-scale feature maps from the initial encoder stage with the segmentation map through a cascade operation. The output fusion feature map is then processed by a self-attention Transformer structure, ensuring a meticulous refinement of the segmentation output, preserving essential details, and enhancing segmentation accuracy. Our proposed DSENet has been evaluated on three distinct medical image datasets, and the experimental results demonstrate that it achieves more accurate segmentation performance and adaptability to varying target segmentation, making it more competitive compared to existing SOTA methods.

In this paper, we propose a wavelet-aware transformer network (WATNet) for multi-contrast knee MRI super-resolution. Unlike conventional image domain-based super-resolution methods that can not explicitly model the lost high-frequency information, our WATNet endeavors to adaptively fuse the complementary frequency information of the multi-contrast image in the wavelet domain and further refine it in the image domain. The proposed WATNet consists of the multi-scale wavelet transformation (MSWT) module, wavelet-aware transformer (WAT) module, and reconstruction (Rec) module. Specifically, the MSWT module learns to transform the MR image to multi-scale wavelet domain features by the wavelet transformation. The WAT module can adaptively search and transfer similar wavelet domain reference information to the low-resolution one. The Rec module can restore high-quality images in the image domain. To further capture more high-frequency details, we also design the wavelet-based high-frequency loss. The qualitative and quantitative experimental results indicate that our proposed WATNet outperforms most state-of-the-art methods.

This work-in-progress research-to-practice paper provides ongoing results from the development and testing of a personalized learning system integrated into a serious game. Given limited instructor resources, the use of computerized systems to help tutor students offers a way to provide higher quality education and to improve educational efficacy. Personalized learning systems like the one proposed in this paper offer an accessible solution. Furthermore, by combining such a system with a serious game, students are further engaged in interacting with the system. The proposed learning system combines expert-driven structure and lesson planning with computational intelligence methods and gamification to provide students with a fun and educational experience. As the project is ongoing from past years, numerous design iterations have been made on the system based on feedback from students and classroom observations. Using computational intelligence, the system adaptively provides support to students based on data collected from both their in-game actions and by estimating their emotional state from webcam images. For our evaluation, we focus on student data gathered from in-classroom testing in relevant courses, with both educational efficacy results and student observations. To demonstrate the effect of our proposed system, students in an early electrical engineering course were instructed to interact with the system in place of their standard lab assignments. The system would then measure and help them improve their background knowledge before allowing them to complete the lab assignment. As they played through the game, we observed their interactions with the system to gather insights for future developments, which are presented in this work. Additionally, we demonstrate the system's educational efficacy through early pre-post-test results from students who played the game with and without the personalized learning system integration.

This Research to Practice Work-in-Progress paper discusses a next-generation learning system for K-12 students to educate them on scientific concepts surrounding the human body. Specifically, our gamified learning system is designed to make learning more fun, engaging, and effective through game and experiment elements that align with science and math learning standards. It will also increase systematic problem-solving and algorithmic reasoning for K-12 students. Since the human body can be thought of as a combination of interacting systems, the game also introduces students to computational thinking by introducing internal body functions. To achieve these goals, this project has two components. First, an educational virtual reality game will be built according to the natural human body structure. During the game process, students will experience the same as the human body functions, travel along the blood circulation, help with the heartbeat, and participate in oxygen exchange. While students are playing the game, our gamified adaptive learning system tracks and controls the student's learning progress. As the AI component collects student data and uses this information, our system adjusts game content and addresses possible learner issues to refine the learning curriculum for a faster and more effective learning experience. Second, a series of hands-on activities will be conducted based on the functions of the human body (e.g., developing an artificial heart and experiencing how the heart works). Through this project, an attractive and efficient next-generation learning system will be developed and used to expose K-12 students to this learning system. The education of students will be accomplished in different dimensions through games and hands-on practice, respectively. Additionally, compared to traditional learning methods, our learning system not only increases students' interest in learning but also makes it more personalized compared to the conventional learning process. Likewise, we will refer to the results of self-efficacy surveys administered to students and teachers separately to test their perceptions of their abilities and the new system.

In order to solve the problem that the existing methods in the field of diabetic retinopathy (DR) intelligent diagnosis have not fully exploited the effective DR lesion information in the fundus map, as well as the problem that the traditional attention mechanism have not fully explored the influencing factors of different lesion category in DR grading. This paper proposed a diagnostic method that fuses multi-level patch attention and lesion location. The method contains a multi-level patch lesion attention generator (MPAG) and lesion location module (LLM). The MPAG generates a attention map containing the lesion level imformation of different fundus patches, which is weighted with the fundus map and classified by a global network. The LLM is able to indicate lesion and generate a localization-based global attention and increasing the weights of lesion details in the classification network. This paper demonstrated the effectiveness of the proposed method through extensive experiments on the DDR dataset, obtained an accuracy of 0.8064.

In recent years, there has been a great development in the research of automated detection of diabetic retinopathy, and deep learning algorithms have been more and more widely used in this field. In this paper, we propose a channel cross enhancement network based on a two-stream model for diabetic retinopathy severity grading for the detailed performance of diabetic retinopathy images on different channels (RGB). The model takes the features of the full-channel input image as global features and the features extracted from the green channel of the original image as local features, and the local features complement the global features to enhance the model's ability to extract the global channel information of the image. In addition, a channel cross-attention module (CCAM) is designed to achieve the effective extraction of global channel features and the interaction of local channel features with global channel features. The proposed method is validated on the Messidor-2 dataset, and the experimental results show that the proposed method outperforms the existing methods in terms of accuracy and AUC values. After experimental validation, the method proposed in this paper can be effectively used for the auxiliary diagnosis of diabetic retinopathy, helping doctors to provide an effective basis for early clinical treatment.

The recently proposed learned bloom filter (LBF) opens a new perspective on how to reconstruct bloom filters with machine learning. However, the LBF has a massive time cost and does not apply to multidimensional spatial data. In this paper, we propose a prefix‐based and adaptive learned bloom filter (PA‐LBF) for spatial data, which efficiently supports the insertion and deletion. The proposed PA‐LBF is divided into three parts: (1) the prefix‐based classification. The Z‐order space‐filling curve is used to extract data, prefix it, and classify it. (2) The adaptive learning process. The multiple independent adaptive sub‐LBFs are designed to train the suffixes of data, combined with part 1, to reduce the false positive rate (FPR), query, and learning process time consumption. (3) The backup filter uses CBF. Two kinds of backup CBF are constructed to meet the situation of different insertion and deletion frequencies. Experimental results prove the validity of the theory and show that the PA‐LBF reduces the FPR by 84.87%, 79.53%, and 43.01% with the same memory usage compared with the LBF on three real‐world spatial datasets. Moreover, the time consumption of PA‐LBF can be reduced to 5× and 2.05× that of the LBF on the query and learning process, respectively.

Hospital Information Systems (HIS) are now widely used in various medical institutions due to the rapid advancement of information technology. However, owing to the sensitivity of medical data, the data is usually managed solely by the relevant department of the institution, leaving patients and other departments unable to verify its integrity and authenticity. This unilateral data management by the department erodes the credi-bility of the data and complicates building trust between doctors and patients. To address this issue effectively, we propose a scheme of patient-controlled medical data auditing in institutions by leveraging blockchain technology. We establish a permissioned blockchain network among medical departments and program smart contracts that allow patients to authorize changes to their data to build trust in the data while maintaining patient ownership. More specifically, we propose different evidence on-chain strategies that can be adapted to meet various data integrity and recoverability requirements for different data characteristics. Additionally, we present an adaptive hash method that ensures outstanding computational efficiency across a wide range of file sizes. Therefore, MeDA enables patient-controlled data auditing within the medical institution, guaranteeing data integrity and authenticity. The analysis and evaluation demonstrate that the proposed strategies are able to audit various types of data securely and efficiently.

Document-level relation extraction intends to extract relation facts among different entity pairs in the entire document. Previously proposed methods make numerous efforts for this task, however, these researches neglect to treat the two entities in an entity pair as an organic unity for relation extraction, which leads to the lack of valuable information about the entity pairs and insufficient information interaction. To tackle the above problem, we propose a framework, named Entity-level Attention Pooling and Information Gating (EAPIG), for document-level relation extraction. Specifically, we first utilize an encoder module to capture the long-distance dependencies of entities in the document, and then we propose two modules: the Entity-level Attention Pooling module obtains the local information of entity pairs, and the Information Gating module introduces the global information of entity pairs and promotes sufficient interaction between the local information and the global information. Experimental results on the benchmark dataset DocRED show that our approach can efficiently capture and combine the abundant information from the entity pairs to achieve better performance than the previous baselines.

Nowadays, simulation environments are widely used in different research fields. As the complexity of the problem increases, Cameras-Sampling in a simulation environment is important since it can provide highly realistic training data for online machine learning and reinforcement learning, etc. This paper attempts to improve the throughput and efficiency when multiple camera sampling are performed simultaneously. We implement a high-throughput platform for Real-time Cameras-Sampling based on Unreal Engine 4. The platform uses multi-graphics queues to support multi-cameras sampling in parallel. We construct a virtual desert scene to verify the correctness and effectiveness of the proposed platform. The experiments show that the proposed platform can generate eight 960x640 pixels pictures at a frequency of 30Hz. The throughput and GPU utilization have been increased by 2.57x and 1.43x, respectively, compared with Unreal Engine4.

Abstract Optical coherence tomography angiography (OCTA), as a noninvasive imaging modality, has been widely used in clinical ophthalmology. However, the segmentation of retinal vessels in OCTA is under‐studied due to OCTA is a relatively new technology. In this article, an effective feature extraction network, OVS‐Net, is proposed for OCTA vessel segmentation. The OVS‐Net is divided into coarse stage and refine stage which structures are basically the same. In each stage, we utilize OctaveResBlock as the basic block to better extract the hierarchical multifrequency features of OCTA and capture the multiscale semantic features of the vessels. In order to improve the feature characterization, feature enhanced attention block is introduced into the network, which is proved to be more conducive for microvessel segmentation in our experiments. Multiscale feature blocks are introduced into the network to promote the deep integration of semantic features at different scales. Experiments on OCTA‐SS and OCTA‐500 datasets show that our proposed OVS‐Net achieves more competitive segmentation results than the existing methods, especially for microvessel segmentation.

Complex categorical data is often hierarchically coupled with heterogeneous relationships between attributes and attribute values and the couplings between objects. Such value-to-object couplings are heterogeneous with complementary and inconsistent interactions and distributions. Limited research exists on unlabeled categorical data representations, ignores the heterogeneous and hierarchical couplings, underestimates data characteristics and complexities, and overuses redundant information, etc. The deep representation learning of unlabeled categorical data is challenging, overseeing such value-to-object couplings, complementarity and inconsistency, and requiring large data, disentanglement, and high computational power. This work introduces a shallow but powerful UNsupervised heTerogeneous couplIng lEarning (UNTIE) approach for representing coupled categorical data by untying the interactions between couplings and revealing heterogeneous distributions embedded in each type of couplings. UNTIE is efficiently optimized w.r.t. a kernel k-means objective function for unsupervised representation learning of heterogeneous and hierarchical value-to-object couplings. Theoretical analysis shows that UNTIE can represent categorical data with maximal separability while effectively represent heterogeneous couplings and disclose their roles in categorical data. The UNTIE-learned representations make significant performance improvement against the state-of-the-art categorical representations and deep representation models on 25 categorical data sets with diversified characteristics.

Segmenting small retinal vessels with width less than 2 pixels in fundus images is a challenging task. In this paper, in order to effectively segment the vessels, especially the narrow parts, we propose a local regression scheme to enhance the narrow parts, along with a novel multi-label classification method based on this scheme. We consider five labels for blood vessels and background in particular: the center of big vessels, the edge of big vessels, the center as well as the edge of small vessels, the center of background, and the edge of background. We first determine the multi-label by the local de-regression model according to the vessel pattern from the ground truth images. Then, we train a convolutional neural network (CNN) for multi-label classification. Next, we perform a local regression method to transform the previous multi-label into binary label to better locate small vessels and generate an entire retinal vessel image. Our method is evaluated using two publicly available datasets and compared with several state-of-the-art studies. The experimental results have demonstrated the effectiveness of our method in segmenting retinal vessels.

Unsupervised representation learning on mixed data is highly challenging but rarely explored. It has to tackle significant challenges related to common issues in real-life mixed data, including sparsity, dynamics and heterogeneity of attributes and values. This work introduces an effective and efficient unsupervised deep representer called Mix2Vec to automatically learn a universal representation of dynamic mixed data with the above complex characteristics. Mix2Vec is empowered with three effective mechanisms: random shuffling prediction, prior distribution matching, and structural informativeness maximization, to tackle the aforementioned challenges. These mechanisms are implemented as an unsupervised deep neural representer Mix2Vec. Mix2Vec converts complex mixed data into vector space-based representations that are universal and comparable to all data objects and transparent and reusable for both unsupervised and supervised learning tasks. Extensive experiments on four large mixed datasets demonstrate that Mix2Vec performs significantly better than state-of-the-art deep representation methods. We also empirically verify the designed mechanisms in terms of representation quality, visualization and capability of enabling better performance of downstream tasks.

The anonymity of blockchain has caused Ponzi schemes to be transferred to smart contract platforms by scammers. These Ponzi schemes wearing the mask of smart contracts caused huge losses to people, which makes the detection of smart Ponzi schemes attract people's attention. Recent methods mainly focus on machine learning technology to enable automatic detection for smart Poniz schemes. However, there are some problems with their methods. Firstly, the gradient boosting algorithm in machine learning they used have the problem of prediction shift due to target leakage when processing category features and calculating gradient estimates. Secondly, they ignored the imbalance and repetitiveness of Ponzi schemes on smart contract platforms. These problems can directly lead to model overfitting and affect the generalization ability of trained models. This paper proposes a novel Ponzi schemes detection method on smart contract platform for blockchain. Our method addresses the above issues with the following strategies. Firstly, we leverage ordered target statistic (TS) to process the category features of smart contract. Secondly, we solve the imbalance of dataset through a data augmentation method. Thirdly, with the idea of ordered boosting algorithm, we train a PonziTect model to fight prediction shift caused by target leakage. Based on the above ideas, the experimental results fully manifest the effectiveness and reliability of our model in detecting smart Ponzi schemes on the blockchain. Specifically, our model achieves 98% F-score on the real-world dataset, which significantly outperforms the existing methods. Using our method, we estimate that there are about 532 Ponzi schemes on Ethereum.

Representing short text is becoming extremely important for a variety of valuable applications. However, representing short text is critical yet challenging because it involves lots of informal words and typos (i.e. the noise problem) but only few vocabularies in each text (i.e. the sparsity problem). Most of existing work on representing short text relies on noise recognition and sparsity expansion. However, the noises in short text are with various forms and changing fast, but, most of the current methods may fail to adaptively recognize the noise. Also, it is hard to explicitly expand a sparse text to a high-quality dense text. In this paper, we tackle the noise and sparsity problems in short text representation by learning multi-grain noise-tolerant patterns and then embedding the most significant patterns in a text as its representation. To achieve this goal, we propose a bi-level multi-scale masked CNN-RNN network to embed the most significant multi-grain noise-tolerant relations among words and characters in a text into a dense vector space. Comprehensive experiments on five large real-world data sets demonstrate our method significantly outperforms the state-of-the-art competitors.

Fraud review significantly damages the business reputation and also customers' trust to certain products. It has become a serious problem existing on the current social media. Various efforts have been put in to tackle such problems. However, in the case of cold-start where a review is posted by a new user who just pops up on the social media, common fraud detection methods may fail because most of them are heavily depended on the information about the user's historical behavior and its social relation to other users, yet such information is lacking in the cold-start case. This paper presents a novel Joint-bEhavior-and-Social-relaTion-infERable (JESTER) embedding method to leverage the user reviewing behavior and social relations for cold-start fraud review detection. JESTER embeds the deep characteristics of existing user behavior and social relations of users and items in an inferable user-item-review-rating representation space where the representation of a new user can be efficiently inferred by a closed-form solution and reflects the user's most probable behavior and social relations. Thus, a cold-start fraud review can be effectively detected accordingly. Our experiments show JESTER (i) performs significantly better in detecting fraud reviews on four real-life social media data sets, and (ii) effectively infers new user representation in the cold-start problem, compared to three state-of-the-art and two baseline competitors.

BACKGROUND: Glaucoma is an irreversible eye disease caused by the optic nerve injury. Therefore, it usually changes the structure of the optic nerve head (ONH). Clinically, ONH assessment based on fundus image is one of the most useful way for glaucoma detection. However, the effective representation for ONH assessment is a challenging task because its structural changes result in the complex and mixed visual patterns. METHOD: We proposed a novel feature representation based on Radon and Wavelet transform to capture these visual patterns. Firstly, Radon transform (RT) is used to map the fundus image into Radon domain, in which the spatial radial variations of ONH are converted to a discrete signal for the description of image structural features. Secondly, the discrete wavelet transform (DWT) is utilized to capture differences and get quantitative representation. Finally, principal component analysis (PCA) and support vector machine (SVM) are used for dimensionality reduction and glaucoma detection. RESULTS: The proposed method achieves the state-of-the-art detection performance on RIMONE-r2 dataset with the accuracy and area under the curve (AUC) at 0.861 and 0.906, respectively. CONCLUSION: In conclusion, we showed that the proposed method has the capacity as an effective tool for large-scale glaucoma screening, and it can provide a reference for the clinical diagnosis on glaucoma.

The segmentation of small blood vessels whose width is less than 2 pixels in retinal images is a challenging problem. Existed methods rarely focus on the differences between small vessels and big vessels when doing segmentation. Therefore, previous methods are not accurate enough on small blood vessel segmentation. To effectively segment small blood vessels in retinal images including big vessels, we proposed a novel multi-label classification scheme for retinal vessel segmentation. In our proposed scheme, a local de-regression model is designed for multi-labeling and a convolutional neural network is used for multi-label classification. At addition, a local regression method is utilized to transform multi-label into binary label for locating small vessels. The experimental results show that our method achieves prominent performance for automatic retinal vessel segmentation, especially for small blood vessels.

Non-IID recommender system discloses the nature of recommendation and has shown its potential in improving recommendation quality and addressing issues such as sparsity and cold start. It leverages existing work that usually treats users/items as in- dependent while ignoring the rich couplings within and between users and items, leading to limited performance improvement. In reality, users/items are related with various couplings existing within and between users and items, which may better ex- plain how and why a user has personalized pref- erence on an item. This work builds on non- IID learning to propose a neural user-item cou- pling learning for collaborative filtering, called CoupledCF. CoupledCF jointly learns explicit and implicit couplings within/between users and items w.r.t. user/item attributes and deep features for deep CF recommendation. Empirical results on two real-world large datasets show that CoupledCF significantly outperforms two latest neural recom- menders: neural matrix factorization and Google’s Wide&Deep network.

As a powerful learning tool, Extreme Learning Machine (ELM) shows its merits in classification, regression and clustering by offering both high prediction accuracy and high learning speed. Among numerous ELM varieties, multiple kernel ELM draws intensive attention from researchers because it can leverage information from multiple heterogeneous sources, which is a common scenario in big data era. Despite remarkable efforts for supervised multiple kernel ELM, few publications have addressed the unsupervised case, which is more critical yet challenging for tackling realistic problem. In this paper, we address this problem by proposing a two-stage unsupervised multiple kernel extreme learning machine, which is suitable for fast multiple-view clustering. This approach learns the cluster and kernel combination weights alternatively. At the first stage, it generates cluster label based on a given combined kernel. Then, at the second stage, the kernel combination weights are learned by distance label based extreme learning machine based on the label generated at the previous stage. Experimental results on both synthetic and real data sets demonstrate its outstanding performance in term of both accuracy and learning speed.

Abnormal event detection in video surveillance is a valuable but challenging problem. Most methods adopt a supervised setting that requires collecting videos with only normal events for training. However, very few attempts are made under unsupervised setting that detects abnormality without priorly knowing normal events. Existing unsupervised methods detect drastic local changes as abnormality, which overlooks the global spatio-temporal context. This paper proposes a novel unsupervised approach, which not only avoids manually specifying normality for training as supervised methods do, but also takes the whole spatio-temporal context into consideration. Our approach consists of two stages: First, normality estimation stage trains an autoencoder and estimates the normal events globally from the entire unlabeled videos by a self-adaptive reconstruction loss thresholding scheme. Second, normality modeling stage feeds the estimated normal events from the previous stage into one-class support vector machine to build a refined normality model, which can further exclude abnormal events and enhance abnormality detection performance. Experiments on various benchmark datasets reveal that our method is not only able to outperform existing unsupervised methods by a large margin (up to 14.2% AUC gain), but also favorably yields comparable or even superior performance to state-of-the-art supervised methods.

Learning appropriate metric is critical for effectively capturing complex data characteristics. The metric learning of categorical data with hierarchical coupling relationships and local heterogeneous distributions is very challenging yet rarely explored. This paper proposes a Heterogeneous mEtric Learning with hIerarchical Couplings (HELIC for short) for this type of categorical data. HELIC captures both low-level value-to-attribute and high-level attribute-to-class hierarchical couplings, and reveals the intrinsic heterogeneities embedded in each level of couplings. Theoretical analyses of the effectiveness and generalization error bound verify that HELIC effectively represents the above complexities. Extensive experiments on 30 data sets with diverse characteristics demonstrate that HELIC-enabled classification significantly enhances the accuracy (up to 40.93 percent), compared with five state-of-the-art baselines.

Along with the penetration of smart devices and mobile applications in our daily life, how to effectively manage the mobility issues in wireless networks becomes a challenging task. The ability to continuously and accurately track the target object’s position plays a vital role in mobility management. In this paper, we propose a novel indoor localization algorithm that fuses multiple signal features as the location fingerprints. The rationale that motivates our algorithm design stems from the following observation: although using one special signal feature (e.g., channel state information (CSI)) might achieve statistically higher accuracy than using another signal feature (e.g., received signal strength (RSS)), the accuracy for individual position estimations is usually diversified when only one signal feature is used in localization. For example, using RSS can obtain more accurate location estimation than using CSI for some individual positions. Thus, we propose a novel indoor localization algorithm that fuses multiple types of signal features as fingerprint of positions, which can effectively improve localization accuracy. We designed several fusion schemes and evaluated their performance. Experiments show that our algorithm achieves localization error below 0.5m and 1.1m in two typical indoor environments, about 30% lower than the accuracy of algorithms by fusing multiple signal features.

In recommender systems, users' preference and items' attraction are heavily determined by users' and items' attributes information. The aim of this study was to incorporate these attributes information into a matrix factorization model. In this paper, users' and items' attributes were used to calculate similarity, and then a nonparametric Bayesian method was applied to cluster users and cluster items, based on the similarity. These clustering results were used to mine coupling relationships and improve the accuracy of recommendation. Experimental results on Movielens 1M demonstrate the superiority of our proposed model over existing methods.

This paper propose an improved supervised method for retinal vessel segmentation based on Extreme Learning Machine (ELM). Firstly, a 36-D feature vector is extracted for each pixel of the fund us image consisting of local features, morphological features and divergence of vector fields. Then a matrix for pixels of the training set using the feature vector and the manual segmentation is constructed as the input of the ELM. Finally a classifier is obtained to segment the retinal vessels. The method is evaluated with the DRIVE database and the average accuracy is 0.9581. And the running time is greatly decreased by using ELM. It is applicable for computer-aided diagnosis and disease screening.

In this paper, we propose an unsupervised feature selection framework which simultaneously preserves the local geometric structure and global discriminative structure of data. Also, the spectral clustering algorithm is incorporated into this framework to exploit the discriminative structure. To demonstrate the generality of our framework, we instantiate our framework into two specific algorithms by characterizing the local geometric structure of data with two well-known models, i.e., locally linear embedding and linear preserve projection. After that, we provide an efficient algorithm with proved convergence to solve the resultant optimization problem. Comprehensive experiments have been conducted on eleven benchmark data sets and the results demonstrate the superior performance of our framework.

In this paper, we propose a binary feature selection framework in kernel spaces, where each feature is projected into kernel spaces and a binary classification task is constructed in this space. Subsequently, the features are selected according to the normal vector of the learned classifier, which reflects the importance of each feature. To achieve the effect of feature selection, an £i-norm regularization is imposed on the normal vector to enforce its sparsity. Also, our framework can be naturally extended to the semi-supervised feature selection scenario via the well-known manifold regularization technique. Furthermore, the issue of eliminating the potential redundancy among the selected features is well discussed. Finally, we provide some theoretical results which guarantee the feasibility of the proposed framework. Comprehensive experiments have been conducted on six benchmark data sets and the results demonstrate the performance of our framework.