Fine-grained open-set semi-supervised learning (OSSL) investigates a practical scenario where unlabeled data may contain fine-grained out-of-distribution (OOD) samples. Due to the subtle visual differences among in-distribution (ID) samples, as well as between ID and OOD samples, it is extremely challenging to separate the ID and OOD samples. Recent Vision-Language Models, such as CLIP, have shown excellent generalization capabilities. However, it tends to focus on general attributes, and thus is insufficient to distinguish the fine-grained details. To tackle the issues, in this paper, we propose a novel CLIP-driven coarse-to-fine semantic-guided framework, named CFSG-CLIP, to progressively focus on the distinctive fine-grained clues. Specifically, CFSG-CLIP comprises a coarse-guidance branch and a fine-guidance branch derived from the pre-trained CLIP model. In the coarse-guidance branch, we design a semantic filtering module to initially filter and highlight local visual features guided by cross-modality features. Then, in the fine-guidance branch, we further design a visual-semantic injection strategy, which embeds category-related visual cues into the visual encoder to further refine the local visual features. By the designed dual-guidance framework, local subtle cues are progressively discovered to distinct the subtle difference between ID and OOD samples. Extensive experiments demonstrate that CFSG-CLIP achieves competitive performance on multiple fine-grained datasets. The source code is available at https://github.com/LxxxxK/CFSG-CLIP.

T-cell receptors (TCR), which are heterodimers of $\alpha $ and $\beta $ chains that recognize foreign antigens, are of great significance to current immunotherapy. Although artificial intelligence (AI) has explosively accelerated de novo protein design, the challenge of therapeutic TCR design has been overlooked by most researchers. Existing TCR engineering relies heavily on isolating antigen-specific TCRs from tumor tissues, which requires a large amount of labor resources and wet experimental verification. To mitigate this issue, we present TCRdesign, a pretrained generative protein language model (PLM) for the de novo design of artificial TCR $\beta $-chain complementarity-determining region 3 sequences conditioned on antigen-binding specificity (BS). In parallel, we develop a high-accuracy binding predictor (TCRBinder) that couples paired $\alpha $/$\beta $ chain information with antigen sequences to assess BS. Our in silico comparisons demonstrate that (i) TCRdesign surpasses state-of-the-art baselines in generating antigen-specific TCR sequences. The model leverages paired-chain coherence to refine amino-acid level interaction patterns. (ii) TCRdesign-generated TCR sequences exhibit better antigen binding capability to diverse oncogenic hotspots compared with natural counterparts. (iii) TCRdesign inherits the intrinsic properties of large PLMs, enabling effectively identify the determinant residues in TCR-antigen binding, which enhances its interpretability. These results highlight the significant capability of TCRdesign in understanding and generating TCR sequences with an antigen-specific interaction pattern, charting a versatile path toward AI-driven T-cell engineering for precision immunotherapy.

Protein kinases regulate diverse cellular functions, including cell cycle progression, metabolism, differentiation, and survival, with their dysregulation implicated in multiple carcinogenic processes. Phosphatidylinositol 3-kinase alpha inhibitors (PI3K$ \alpha $is) have revolutionized breast cancer treatment, but acquired resistance remains a major clinical challenge, with around 40% of patients experiencing progression within 4-6 months. Current drug response prediction (DRP) methods typically rely on individual pathways or biomarkers, limiting their ability to capture complex cancer-specific molecular interactions and predict resistance mechanisms. To overcome these limitations, we present AdaSemb, an adaptive, knowledge-driven deep learning framework that uses a multi-protein assembly map to predict responses and resistance to PI3K$ \alpha $i. AdaSemb comprises two modules: the AdaSemb-PA module incorporates tumor genomic variations into a biological structural neural network, while the AdaSemb-DRP module uses conditional domain adversarial networks to enhance gene-drug distribution generalization. By combining genomic data with drug molecular structures, AdaSemb identifies critical protein combinations linked to drug resistance. In validation with 1244 cancer cell lines and patient-derived xenografts (PDX), AdaSemb outperformed existing DRP models. In a cohort of 116 breast cancer patients from the Cancer Genome Atlas (TCGA), it predicted significantly longer survival for sensitive patients, surpassing traditional biomarkers in precision. Furthermore, we identified seven key assemblages that integrate mutations from 93 genes, which distinguish alpelisib sensitive and resistant cell lines. These results are applicable to breast cancer patient samples and PDX models, demonstrating AdaSemb's significant clinical potential in personalized treatment and prediction of resistance for breast cancer.

Accurate prediction of binding between human leukocyte antigen (HLA) class I molecules and antigenic peptide segments is a challenging task and a key bottleneck in personalized immunotherapy for cancer. Although existing prediction tools have demonstrated significant results using established datasets, most can only predict the binding affinity of antigenic peptides to HLA and do not enable the immunogenic interpretation of new antigenic epitopes. This limitation results from the training data for the computational models relying heavily on a large amount of peptide-HLA (pHLA) eluting ligand data, in which most of the candidate epitopes lack immunogenicity. Here, we propose an adaptive immunogenicity prediction model, named MHLAPre, which is trained on the large-scale MS-derived HLA I eluted ligandome (mostly presented by epitopes) that are immunogenic. Allele-specific and pan-allelic prediction models are also provided for endogenous peptide presentation. Using a meta-learning strategy, MHLAPre rapidly assessed HLA class I peptide affinities across the whole pHLA pairs and accurately identified tumor-associated endogenous antigens. During the process of adaptive immune response of T-cells, pHLA-specific binding in the antigen presentation is only a pre-task for CD8+ T-cell recognition. The key factor in activating the immune response is the interaction between pHLA complexes and T-cell receptors (TCRs). Therefore, we performed transfer learning on the pHLA model using the pHLA-TCR dataset. In pHLA binding task, MHLAPre demonstrated significant improvement in identifying neoepitope immunogenicity compared with five state-of-the-art models, proving its effectiveness and robustness. After transfer learning of the pHLA-TCR data, MHLAPre also exhibited relatively superior performance in revealing the mechanism of immunotherapy. MHLAPre is a powerful tool to identify neoepitopes that can interact with TCR and induce immune responses. We believe that the proposed method will greatly contribute to clinical immunotherapy, such as anti-tumor immunity, tumor-specific T-cell engineering, and personalized tumor vaccine.

Adaptive immunity is a targeted immune response that enables the body to identify and eliminate foreign pathogens, playing a critical role in the anti-tumor immune response. Tumor cell expression of antigens forms the foundation for inducing this adaptive response. However, the human leukocyte antigens (HLA)-restricted recognition of antigens by T-cell receptors (TCR) limits their ability to detect all neoantigens, with only a small subset capable of activating T-cells. Accurately predicting neoantigen binding to TCR is, therefore, crucial for assessing their immunogenic potential in clinical settings. We present THLANet, a deep learning model designed to predict the binding specificity of TCR to neoantigens presented by class I HLAs. THLANet employs evolutionary scale modeling-2 (ESM-2), replacing the traditional embedding methods to enhance sequence feature representation. Using scTCR-seq data, we obtained the TCR immune repertoire and constructed a TCR-pHLA binding database to validate THLANet's clinical potential. The model's performance was further evaluated using clinical cancer data across various cancer types. Additionally, by analyzing divided complementarity-determining region (CDR3) sequences and simulating alanine scanning of antigen sequences, we provided new insights into the 3D binding interactions of TCRs and antigens. Predicting TCR-neoantigen pairing remains a significant challenge in immunology, THLANet provides accurate predictions using only the TCR sequence (CDR3β), antigen sequence, and class I HLA, offering novel insights into TCR-antigen interactions.

While significant strides have been made in predicting neoepitopes that trigger autologous CD4+ T cell responses, accurately identifying the antigen presentation by human leukocyte antigen (HLA) class II molecules remains a challenge. This identification is critical for developing vaccines and cancer immunotherapies. Current prediction methods are limited, primarily due to a lack of high-quality training epitope datasets and algorithmic constraints. To predict the exogenous HLA class II-restricted peptides across most of the human population, we utilized the mass spectrometry data to profile >223 000 eluted ligands over HLA-DR, -DQ, and -DP alleles. Here, by integrating these data with peptide processing and gene expression, we introduce HLAIImaster, an attention-based deep learning framework with adaptive domain knowledge for predicting neoepitope immunogenicity. Leveraging diverse biological characteristics and our enhanced deep learning framework, HLAIImaster is significantly improved against existing tools in terms of positive predictive value across various neoantigen studies. Robust domain knowledge learning accurately identifies neoepitope immunogenicity, bridging the gap between neoantigen biology and the clinical setting and paving the way for future neoantigen-based therapies to provide greater clinical benefit. In summary, we present a comprehensive exploitation of the immunogenic neoepitope repertoire of cancers, facilitating the effective development of "just-in-time" personalized vaccines.

MOTIVATION: Understanding the intermolecular interactions of ligand-target pairs is key to guiding the optimization of drug research on cancers, which can greatly mitigate overburden workloads for wet labs. Several improved computational methods have been introduced and exhibit promising performance for these identification tasks, but some pitfalls restrict their practical applications: (i) first, existing methods do not sufficiently consider how multigranular molecule representations influence interaction patterns between proteins and compounds; and (ii) second, existing methods seldom explicitly model the binding sites when an interaction occurs to enable better prediction and interpretation, which may lead to unexpected obstacles to biological researchers. RESULTS: To address these issues, we here present DrugMGR, a deep multigranular drug representation model capable of predicting binding affinities and regions for each ligand-target pair. We conduct consistent experiments on three benchmark datasets using existing methods and introduce a new specific dataset to better validate the prediction of binding sites. For practical application, target-specific compound identification tasks are also carried out to validate the capability of real-world compound screen. Moreover, the visualization of some practical interaction scenarios provides interpretable insights from the results of the predictions. The proposed DrugMGR achieves excellent overall performance in these datasets, exhibiting its advantages and merits against state-of-the-art methods. Thus, the downstream task of DrugMGR can be fine-tuned for identifying the potential compounds that target proteins for clinical treatment. AVAILABILITY AND IMPLEMENTATION: https://github.com/lixiaokun2020/DrugMGR.

Open-set semi-supervised learning (OSSL) provides a practical solution by filtering out-of-distribution (OOD) samples from unlabeled data to guarantee the reliance on large unlabeled data in semi-supervised setting. However, existing OSSL methods mainly focus on identifying in-distribution (ID) samples and discarding OOD samples, while ignoring to make full use of samples that could not be exactly identified as ID or OOD samples. Those samples are more likely to be hard samples, which should be carefully explored to boost the performance in OSSL task. Hence, in this paper, we propose a novel framework, named Mutual Filter Teaching (MFT), where two networks are trained simultaneously to divide the unlabeled data into three parts: ID samples, OOD samples and hard samples. The samples are regarded as ID or OOD samples only if two networks give consistent decisions according to Mahalanobis distance between the unlabeled samples and their closest class prototypes. For those samples with inconsistent decisions, we treat them as hard samples and design an efficient mutual teaching scheme where the samples detected by only one network as positive samples are fed to its peer network for training. Furthermore, we propose to employ the prediction variance of two networks to dynamically rectify the learning from hard samples. Experiments on multiple benchmark datasets demonstrate that our approach achieves the state-of-the-art performance.

Numerous researches emphasized that long non-coding RNA (lncRNA) plays a vital factor in various biological processes, and its mismatched expression and dysfunction are tightly linked with the occurrence of human diseases. Thus, computational models were designed to identify lncRNA-disease interactions by merging heterogeneous biological data. However, most of them neglected the intrinsic structure of multi-source information, which limits the performance for potential lncRNA-disease association prediction. Here, GCN-NIMC is introduced to alleviate the dilemma for disease-associated lncRNA genes identification based on the graph convolutional network with neural inductive matrix. This method builds a feature matrix with multi-source heterogeneous data and then learn the various information contained in the feature matrix for the sake of acquiring better feature expressions of the lncRNA-disease interactions. Experimental results on 10-repeated 5-fold cross-validation demonstrated that our proposed GCN-NIMC is superior to existing cutting-edge methods for identifying disease-related lncRNA genes. Furthermore, case studies confirmed our computational method as a practical tool with clinical benefits to develop the therapeutic schedule at lncRNA-level.

Identification of active candidate compounds for target proteins, also called drug-protein interaction (DPI) prediction, is an essential but time-consuming and expensive step, which leads to fostering the development of drug discovery. In recent years, deep network-based learning methods were frequently proposed in DPIs due to their powerful capability of feature representation. However, the performance of existing DPI methods is still limited by insufficiently labeled pharmacological data and neglected intermolecular information. Therefore, overcoming these difficulties to perfect the performance of DPIs is an urgent challenge for researchers. In this article, we designed an innovative 'multi-modality attributes' learning-based framework for DPIs with molecular transformer and graph convolutional networks, termed, multi-modality attributes (MMA)-DPI. Specifically, intermolecular sub-structural information and chemical semantic representations were extracted through an augmented transformer module from biomedical data. A tri-layer graph convolutional neural network module was applied to associate the neighbor topology information and learn the condensed dimensional features by aggregating a heterogeneous network that contains multiple biological representations of drugs, proteins, diseases and side effects. Then, the learned representations were taken as the input of a fully connected neural network module to further integrate them in molecular and topological space. Finally, the attribute representations were fused with adaptive learning weights to calculate the interaction score for the DPIs tasks. MMA-DPI was evaluated in different experimental conditions and the results demonstrate that the proposed method achieved higher performance than existing state-of-the-art frameworks.

Interpreting ocean remote sensing images is still a challenge that is worth studying because they can carry valuable information for various important applications. Due to the absence of labeled datasets, unsupervised object-based image analysis (OBIA) methods provide an effective solution to understand remote sensing images with the advantage of grouping local similar pixels into a homogeneous area. However, ocean remote sensing images usually have the characteristics of large size, large background, and coexisting of large and small objects, which results in previous OBIA methods easily falling into the difficulty of accurately segmenting the large and small objects at the same time and the dilemma of time-consuming computation. To solve this problem, a novel multiscale and multisubgraph (MSMSG)-based image segmentation method is presented in this article. First, a coarse-to-fine superpixel generation method is designed to generate optimal superpixels, which can not only solve the problem of coexisting large objects and small objects but also the problem of manually setting the initial segmentation number. Second, the proposed background removal strategy helps to eliminate the trouble of large background areas in ocean remote sensing images. Third, a multisubgraph is constructed with the help of background removal. Finally, the MSMSG merging strategy is addressed to group all similar superpixels into the same cluster, which not only reduces the useless computation of nonadjacent superpixels but also avoids segmentation errors with the same scale. Experiments conducted on three different datasets show that the proposed segmentation method is high-performance and high-efficiency.

3D object detection with LiDAR point clouds is a challenging problem which requires 3D scene understanding, yet this task is critical to autonomous driving. Existing voxel-based 3D object detectors are becoming increasingly popular but have several shortcomings. For example, during voxelization, features of distant sparse point clouds are largely discarded, which leads to the missing detection of objects. Additionally, the correlation of points between voxels and the importance of different voxels within a region are not well learned. Therefore, we present a robust network (VP-Net) that views voxels as points to accurately detect 3D objects in LiDAR point clouds and can capture objects’ internal relationships. 3D CNN processing shows the output features of VP-Net as key points. The relationship between key points is then constructed into local graphs to enhance object feature extraction via a self-attention mechanism. Finally, the Euclidean distance between the extracted features guides our model’s weight reassignment for strengthening the importance of neighbor points, thereby enhancing the internal feature aggregation of objects. Experiments on KITTI and nuScenes 3D object detection benchmarks demonstrate the efficiency of enhancing inter-voxel validity within object features and show that the proposed VP-Net can achieve state-of-the-art performance.

Identifying new disease indications for the approved drugs can help reduce the cost and time of drug development. Most of the recent methods focus on exploiting the various information related to drugs and diseases for predicting the candidate drug-disease associations. However, the previous methods failed to deeply integrate the neighborhood topological structure and the node attributes of an interested drug-disease node pair. We propose a new prediction method, ANPred, to learn and integrate pairwise attribute information and neighbor topology information from the similarities and associations related to drugs and diseases. First, a bi-layer heterogeneous network with intra-layer and inter-layer connections is established to combine the drug similarities, the disease similarities, and the drug-disease associations. Second, the embedding of a pair of drug and disease is constructed based on integrating multiple biological premises about drugs and diseases. The learning framework based on multi-layer convolutional neural networks is designed to learn the attribute representation of the pair of drug and disease nodes from its embedding. The sequences composed of neighbor nodes are formed based on random walk on the heterogeneous network. A framework based on fully-connected autoencoder and skip-gram module is constructed to learn the neighbor topological representations of nodes. The cross-validation results indicate the performance of ANPred is superior to several state-of-the-art methods. The case studies on 5 drugs further confirm the ability of ANPred in discovering the potential drug-disease association candidates.

Today the technological society is developing quickly, recommendation system is becoming an increasingly important technology. Session-based recommendation systems have become a hot research topic due to their ability to provide recommendations for anonymous users. Traditional session-based recommendation systems have some limitations. They either lack the ability to learn complex dependencies or only focus on the current session without explicitly considering collaborative information. We propose a collaborative attention for session-based recommendation model called CASR, which can mine users’ long-term and short-term preferences to obtain users’ real intention by using the close interaction relationship in time structure. We first model a Gate Recurrent Unit (GRU) framework with attention mechanism to obtain short-term preferences of users in a period of the time. Then, we propose a collaborative session search strategy and design a neighbor session search algorithm. It can not only obtain users’ long-term preferences, but also alleviate the sparseness of the original session data to a certain extent. Finally, we use the capsule network with update strategy to get better prediction results. Extensive experiments on two real datasets show that our CASR model outperforms many mainstream methods.

BACKGROUND: An increasing number of studies have shown that lncRNAs are crucial for the control of hormones and the regulation of various physiological processes in the human body, and deletion mutations in RNA are related to many human diseases. LncRNA- disease association prediction is very useful for understanding pathogenesis, diagnosis, and prevention of diseases, and is helpful for labelling relevant biological information. RESULTS: In this manuscript, we propose a computational model named bidirectional generative adversarial network (BiGAN), which consists of an encoder, a generator, and a discriminator to predict new lncRNA-disease associations. We construct features between lncRNA and disease pairs by utilizing the disease semantic similarity, lncRNA sequence similarity, and Gaussian interaction profile kernel similarities of lncRNAs and diseases. The BiGAN maps the latent features of similarity features to predict unverified association between lncRNAs and diseases. The computational results have proved that the BiGAN performs significantly better than other state-of-the-art approaches in cross-validation. We employed the proposed model to predict candidate lncRNAs for renal cancer and colon cancer. The results are promising. Case studies show that almost 70% of lncRNAs in the top 10 prediction lists are verified by recent biological research. CONCLUSION: The experimental results indicated that our proposed model had an accurate predictive ability for the association of lncRNA-disease pairs.

Although deep neural networks have made significant progress in semantic segmentation, speed and computational cost still can't meet the strict requirements of real-world applications. In this paper, we present an enhanced asymmetric convolution network (EACNet) to seek a balance between accuracy and speed. Specifically, we design a pair of enhancing asymmetric convolution modules constructed by depth-wise asymmetric convolution and dilated convolution to extract short-range and long-range features, which are efficient and powerful. Additionally, we apply a bilateral structure in which the detail branch preserves low-level spatial details while the semantic branch captures high-level context information. The two branches are merged at different stages of the network to strengthen information propagation between different levels. The experiments on the Cityscapes dataset show that our method achieves high accuracy and speed with relatively small parameters. Compared with other real-time semantic segmentation methods, our network attains a good trade-off among parameters, speed, and accuracy.

Named Data Networking (NDN) is a promising technology for content centric networks, and it is suitable for vehicular networks since no IP architecture is required. Quite a number of solutions have been proposed for vehicular NDN (V- NDN), but high communication cost due to frequent topology changes caused by high mobility of vehicles is still a challenge to be addressed. In this paper, we study how to disseminate traffic information to vehicles via V-NDN. Different from existing works, we consider navigation route based data interests, i.e., a vehicle is concerned about the traffic information along road segments planned to take. According to such a data interest scenario, we propose a tree based data interest structure and associated maintenance operations to merge identical data interests due to overlapping navigation routes among different vehicles. With the tree based data interest management, the number of interest packets can be significantly reduced. Then, we propose trigger based mechanisms for data interest packet re-sending and forwarding, which can avoid unnecessary interest packets re-sending. With our design, traffic information can be disseminated to interested nodes with high success ratio and low communication cost simultaneously. Simulations via SUMO and ndnSIM confirm such advantages of our work.

Hyperspectral imaging (HSI) sensors capture the spectral signature of targets and thus provide the capability of remotely identifying ground objects smaller than a full pixel in HSI images. Conventional methods for subpixel target detection rely on estimating a large-size covariance matrix of the background and using the matrix for target detection. To complete the estimation, a large set of target-free training pixels is needed, which makes the estimation impractical for a heterogeneous environment and also computationally expensive. In this paper, we propose to generate a parametric model, named knowledge-aided non-stationary autoregressive (KANS-AR) model, for target detection. Instead of estimating the large-size covariance matrix explicitly, the proposed parametric model can be estimated from a small-size training pixels and used directly in timeseries- based whitening. This advantage makes a KANS-AR based target detector work well in both homogenous and heterogeneous environments. Experimental results demonstrate the efficiency of the proposed method.

To address the challenges in critical care monitoring, we present a multi-modality bio-signal modeling and analysis modeling framework for real-time human state classification and predication. The novel bioinformatic framework is developed to solve the human state classification and predication issues from two aspects: a) achieve 1:1 mapping between the bio-signal and the human state via discriminant feature analysis and selection by using probabilistic principle component analysis (PPCA); b) avoid time-consuming data analysis and extensive integration resources by using Dynamic Bayesian Network (DBN). In addition, intelligent and automatic selection of the most suitable sensors from the bio-sensor array is also integrated in the proposed DBN.

An eye-tracking integrated head-mounted display (ET-HMD) system can be used in many applications. Its complexity imposes great challenges on designing a compact, portable, and robust system. For an ET-HMD system, having accurate eye-gazed field-of-view (FOV) estimation and performing fast high-fidelity rendering only on the identified FOV is its crucial technique for augmented video/image/graphics display. In this paper, an energy-controlled iterative curve fitting method is proposed for accurate pupil detection and tracking. Based on a 3D eye model and the pupil tracking results, eye-gazed FOV can be identified precisely. The experimental results show that the average tracking error of using the proposed method is less than 0.5 degree for pupil rotation while the other conventional methods can only achieve 1.0 degree.

Three-dimensional (3D) data processing and modeling from range images plays an important role in many applications. Since overlap elimination of registered range images is a necessary step in 3D object modeling, many research efforts have been made. In this paper, a novel approach for eliminating overlaps of a registered data set is proposed. Firstly, the input data (registered range images) which contain overlaps is represented by a bd-tree data structure. Then, Moving Least Squares (MLS) and Spin Map (SM) together with the nearest neighbor searching are used to identify and eliminate the overlaps. The method manipulates the registered images directly without meshing them first, therefore, provides a straightforward way to remove redundant data, which makes it different from the conventional methods. The experimental results demonstrate the efficiency of the proposed algorithm.

BACKGROUND: The availability of 12 fully sequenced Drosophila species genomes provides an excellent opportunity to explore the evolutionary mechanism, structure and function of gene families in Drosophila. Currently, several important resources, such as FlyBase, FlyMine and DroSpeGe, have been devoted to integrating genetic, genomic, and functional data of Drosophila into a well-organized form. However, all of these resources are gene-centric and lack the information of the gene families in Drosophila. DESCRIPTION: FlyPhy is a comprehensive phylogenomic analysis platform devoted to analyzing the genes and gene families in Drosophila. Genes were classified into families using a graph-based Markov Clustering algorithm and extensively annotated by a number of bioinformatic tools, such as basic sequence features, functional category, gene ontology terms, domain organization and sequence homolog to other databases. FlyPhy provides a simple and user-friendly web interface to allow users to browse and retrieve the information at multiple levels. An outstanding feature of the FlyPhy is that all the retrieved results can be added to a workset for further data manipulation. For the data stored in the workset, multiple sequence alignment, phylogenetic tree construction and visualization can be easily performed to investigate the sequence variation of each given family and to explore its evolutionary mechanism. CONCLUSION: With the above functionalities, FlyPhy will be a useful resource and convenient platform for the Drosophila research community. The FlyPhy is available at http://bioinformatics.zj.cn/fly/ .

To address the challenges on non-cooperative long-distance human identification and verification, we propose an innovative cost-efficient system for automatic long-range biometric recognition of non-cooperative individuals in 24/7 operations. The system has three cameras. One is a wide field of view (WFOV) CCD video camera with an Infrared (IR) filter and powerful IR illuminators for human scan in a wide area at a long distance. The other two cameras are high resolution video cameras with narrow field of view (NFOV) and an IR filter & illuminators, mounted on a pan-tilt-unit (PTU) to capture the frontal view of human face and iris respectively. Once the frontal views of moving individuals are captured by the NFOV cameras, the face/iris models will be extracted and classified by the state-of-the-art face/iris recognizers. The hardware of the biometric system also includes one FPGA, three DSP processors, and one Zigbee module for fast bio-data analysis and wireless data transmission.

Robust voice activity detection (VAD) is a very crucial step and a challenging problem in developing real-time and high-performance speech recognition systems used in noisy environments. In this paper, we present a novel and efficient VAD algorithm for robust and real-time speech activity detection. The key idea of the algorithm is considering speech energy and edge information simultaneously when processing speech signals. A new finite state automaton is also developed for correctly detecting voice activities in noisy environments. Extensive and comparative experimental results show that the proposed VAD algorithm can greatly speed up speech recognition while reducing word error rate (WER) significantly. Compared with the state-of-the-art, the average improvement of using the proposed algorithm on noisy data is 46.5% for processing speed and 15.3% for WER.

Currently available methods for object recognition and classification primarily rely on static information in single-frame images. However, for the combat aerial video (usually low resolution video), all these static indexes used for object classification and recognition are almost impossible to obtain. To address this challenge, we propose an innovative 3D and dynamic semantic scene analysis based approach that exploits surveillance video data mainly captured from UAV platforms to classify static object (e.g. buildings) and moving object (e.g. vehicles) automatically. In our proposed automatic object detection and classification framework, in addition to 3D static object's visual features (e.g. building's or vehicle's shape, line orientation, color, and texture) and the 3D static structures of the urban environment, we also explore dynamic video features which include vehicle motion patterns over time. All these static and dynamic features will be considered to construct spatial-temporal feature vectors, and the new generated vectors will then be sent to a probabilistic dynamic influence diagram (DID) reasoning model for real-time and automatic building and vehicle classification. In addition, we also propose novel 3D algorithms on automatic building detection, 3D terrain modeling, and visualization to support accurate object categorization/classification.

UNLABELLED: Malaria, one of the world's most common diseases, is caused by the intracellular protozoan parasite known as Plasmodium. Recently, with the arrival of several malaria parasite genomes, we established an integrated system named PlasmoGF for comparative genomics and phylogenetic analysis of Plasmodium gene families. Gene families were clustered using the Markov Cluster algorithm implemented in TribeMCL program and could be searched using keywords, gene-family information, domain composition, Gene Ontology and BLAST. Moreover, a number of useful bioinformatics tools were implemented to facilitate the analysis of these putative Plasmodium gene families, including gene retrieval, annotation, sequence alignment, phylogeny construction and visualization. In the current version, PlasmoGF contained 8980 sets of gene families derived from six malaria parasite genomes: Plasmodium. falciparum, P. berghei, P. knowlesi, P. chabaudi, P. vivax and P. yoelii. The availability of such a highly integrated system would be of great interest for the community of researchers working on malaria parasite phylogenomics. AVAILABILITY: PlasmoGF is freely available at http://bioinformatics.zj.cn/pgf/

A novel approach for highway traffic event detection in video is presented. The proposed algorithm extracts event features directly from compressed video and detects traffic event using a Gaussian mixture hidden Markov model (GMHMM). First, an invariant feature vector is extracted from discrete cosine transform (DCT) domain and macro-block vectors after MPEG video stream is parsed. The extracted feature vector accurately describes the change of traffic state and is robust towards different camera setups and illumination situations, such as sunny, cloud, and night. Six traffic patterns are studied and a GMHMM is trained to model these patterns in offline stage. Then, Viterbi algorithm is used to determine the most likely traffic condition. The proposed algorithm is efficient both in terms of computational complexity and memory requirement. The experimental results prove the system has a high detection rate. The presented model based system can be easily extended for detection of similar traffic events.

A robust skeleton-based shape matching method for model-based shape recovery applications is presented. The object model consists of both a skeleton model and a contour segments model, which are used in tandem and in a complementary manner. Initially, the skeleton of the contour, provided by a deformable contour method (DCM), is matched against a set of object skeleton models to select a candidate model and determine the corresponding landmarks on the contours. Segments obtained from these landmarks are then matched against the detected model segments for errors. For any large segment mismatch error, a fine-tuning process, which is formulated as a maximization of a posteriori probability, given the contour segments model and image features, is performed for the final result. The skeleton matching algorithm is illustrated by using a set of animal profile examples. Experimental results of shape recovery from practical applications, such as an MR knee image, are very encouraging.

The improvements in structured lighting based 3D optical camera measurement systems have made these non-contact inspection systems more applicable. In this paper, a basic calibration problem, caused by systematical errors particular to structured lighting based 3D optical camera systems, is addressed. The analysis of these errors is discussed and two model-based approaches, line model (LM) and area model (AM), are proposed to model the pattern of systematical error. The main step of either approach is to build a lookup table based on collected planar data at predetermined working distances and orientation angles. The lookup table is then used to correct the systematical error existing in the inspected data. The experimental results show that the proposed approaches effectively improve inspection accuracy.