Dimensionality Reduction Representation Research Articles

Cyclone: an accessible pipeline to analyze, evaluate, and optimize multiparametric cytometry data.

In the past decade, high-dimensional single-cell technologies have revolutionized basic and translational immunology research and are now a key element of the toolbox used by scientists to study the immune system. However, analysis of the data generated by these approaches often requires clustering algorithms and dimensionality reduction representation, which are computationally intense and difficult to evaluate and optimize. Here, we present Cytometry Clustering Optimization and Evaluation (Cyclone), an analysis pipeline integrating dimensionality reduction, clustering, evaluation, and optimization of clustering resolution, and downstream visualization tools facilitating the analysis of a wide range of cytometry data. We benchmarked and validated Cyclone on mass cytometry (CyTOF), full-spectrum fluorescence-based cytometry, and multiplexed immunofluorescence (IF) in a variety of biological contexts, including infectious diseases and cancer. In each instance, Cyclone not only recapitulates gold standard immune cell identification but also enables the unsupervised identification of lymphocytes and mononuclear phagocyte subsets that are associated with distinct biological features. Altogether, the Cyclone pipeline is a versatile and accessible pipeline for performing, optimizing, and evaluating clustering on a variety of cytometry datasets, which will further power immunology research and provide a scaffold for biological discovery.

Autonomous relative optical navigation based on unified modeling of external systematic errors

To solve the problem that external systematic errors of the optical camera cannot be fully estimated due to limited computing resources, a unified dimensionality reduction representation method for the external systematic errors of the optical camera is proposed, and autonomous relative optical navigation is realized. The camera translational and misalignment errors are converted into a three-dimensional rotation error, whose differential model can be established through specific attitude control and appropriate assumption. Then, the rotation error and the relative motion state are jointly estimated in an augmented Kalman filter framework. Compared with the traditional method that estimates the camera translational and misalignment errors, the proposed method reduces the computational complexity in that the estimated state dimension is reduced. Furthermore, as demonstrated by numerical simulation, the estimation accuracy is improved significantly.

Dynamic Malware Analysis Based on API Sequence Semantic Fusion

The existing dynamic malware detection methods based on API call sequences ignore the semantic information of functions. Simply mapping API to numerical values does not reflect whether a function has performed a query or modification operation, whether it is related to network communication, the file system, or other factors. Additionally, the detection performance is limited when the size of the API call sequence is too large. To address this issue, we propose Mal-ASSF, a novel malware detection model that fuses the semantic and sequence features of the API calls. The API2Vec embedding method is used to obtain the dimensionality reduction representation of the API function. To capture the behavioral features of sequential segments, Balts is used to extract the features. To leverage the implicit semantic information of the API functions, the operation and the type of resource operated by the API functions are extracted. These semantic and sequential features are then fused and processed by the attention-related modules. In comparison with the existing methods, Mal-ASSF boasts superior capabilities in terms of semantic representation and recognition of critical sequences within API call sequences. According to the evaluation with a dataset of malware families, the experimental results show that Mal-ASSF outperforms existing solutions by 3% to 5% in detection accuracy.

Hyperspectral Remote Sensing Image Feature Representation Method Based on CAE-H with Nuclear Norm Constraint

Due to the high dimensionality and high data redundancy of hyperspectral remote sensing images, it is difficult to maintain the nonlinear structural relationship in the dimensionality reduction representation of hyperspectral data. In this paper, a feature representation method based on high order contractive auto-encoder with nuclear norm constraint (CAE-HNC) is proposed. By introducing Jacobian matrix in the CAE of the nuclear norm constraint, the nuclear norm has better sparsity than the Frobenius norm and can better describe the local low dimension of the data manifold. At the same time, a second-order penalty term is added, which is the Frobenius norm of the Hessian matrix expressed in the hidden layer of the input, encouraging a smoother low-dimensional manifold geometry of the data. The experiment of hyperspectral remote sensing image shows that CAE-HNC proposed in this paper is a compact and robust feature representation method, which provides effective help for the ground object classification and target recognition of hyperspectral remote sensing image.

Application of Data Classification Method Based on Non-Negative Matrix Factorization

At present, there are many methods for data dimensionality reduction, but most of the results of decomposition methods allow negative values. Obviously, these negative values have no physical meaning in practical problems. The non-negative matrix factorization method is a dimensionality reduction under the condition of ensuring non-negative values. This paper mainly uses a non-negative matrix factorization algorithm to perform dimensionality reduction representation and local feature extraction of data, and then classify. Experiments show that the algorithm in this paper is reasonable and effective.