Observational genome-wide association studies are now widely used for causal inference in genetic epidemiology. To maintain privacy, such data is often only publicly available as summary statistics, and often studies for the endogenous covariates and the outcome are available separately. This has necessitated methods tailored to two-sample summary statistics. Current state-of-the-art methods modify linear instrumental variable (IV) regression—with genetic variants as instruments—to account for unmeasured confounding. However, since the endogenous covariates can be high dimensional, standard IV assumptions are generally insufficient to identify all causal effects simultaneously. We ensure identifiability by assuming the causal effects are sparse and propose a sparse causal effect two-sample IV estimator, spaceTSIV, adapting the spaceIV estimator by Pfister and Peters (2022) for two-sample summary statistics. We provide two methods, based on L0- and L1-penalization, respectively. We prove identifiability of the sparse causal effects in the two-sample setting and consistency of spaceTSIV. The performance of spaceTSIV is compared with existing two-sample IV methods in simulations. Finally, we showcase our methods using real proteomic and gene-expression data for drug-target discovery.

Causal reasoning and discovery, two fundamental tasks of causal analysis, often face challenges in applications due to the complexity, noisiness, and high-dimensionality of real-world data. Despite recent progress in identifying latent causal structures using causal representation learning (CRL), what makes learned representations useful for causal downstream tasks and how to evaluate them are still not well understood. In this paper, we reinterpret CRL using a measurement model framework, where the learned representations are viewed as proxy measurements of the latent causal variables. Our approach clarifies the conditions under which learned representations support downstream causal reasoning and provides a principled basis for quantitatively assessing the quality of representations using a new Test-based Measurement EXclusivity (T-MEX) score. We validate T-MEX across diverse causal inference scenarios, including numerical simulations and real-world ecological video analysis, demonstrating that the proposed framework and corresponding score effectively assess the identification of learned representations and their usefulness for causal downstream tasks. Reproducible code can be found at https://github.com/shimenghuang/a-measurement-perspective-of-crl.

Supervised learning, such as regression and classification, is an essential tool for analyzing modern high-throughput sequencing data, for example in microbiome research. However, due to the compositionality and sparsity, existing techniques are often inadequate. Either they rely on extensions of the linear log-contrast model (which adjust for compositionality but cannot account for complex signals or sparsity) or they are based on black-box machine learning methods (which may capture useful signals, but lack interpretability due to the compositionality). We propose KernelBiome, a kernel-based nonparametric regression and classification framework for compositional data. It is tailored to sparse compositional data and is able to incorporate prior knowledge, such as phylogenetic structure. KernelBiome captures complex signals, including in the zero-structure, while automatically adapting model complexity. We demonstrate on par or improved predictive performance compared with state-of-the-art machine learning methods on 33 publicly available microbiome datasets. Additionally, our framework provides two key advantages: (i) We propose two novel quantities to interpret contributions of individual components and prove that they consistently estimate average perturbation effects of the conditional mean, extending the interpretability of linear log-contrast coefficients to nonparametric models. (ii) We show that the connection between kernels and distances aids interpretability and provides a data-driven embedding that can augment further analysis. KernelBiome is available as an open-source Python package on PyPI and at https://github.com/shimenghuang/KernelBiome.

The detection and classification of moving targets have always been a key technology in intelligent video surveillance. Current detection and classification algorithms for moving targets still face many difficulties, mainly because of the complexity of the monitoring environment and the limitations of target characteristics. Therefore, this article conducts corresponding research on moving target detection and classification in intelligent video surveillance. According to the Gaussian Mixture Background Model and Frame Difference Method, this paper proposes a moving target detection method based on GMM (Gaussians Mixture Model) and Frame Difference Method. This method first proposes a new image combination algorithm that combines GMM and frame difference method, which solves the problems of noise and voids inside the target caused by the fusion of traditional GMM and frame difference method. The moving target detection method can effectively solve the problems of incomplete moving target detection, target internal gap, and noise, and it plays a vital role in the subsequent moving target classification process. Then, the method adds image inpainting technology to compensate the moving target in space and obtain a better target shape. The innovation of this paper is that in order to solve the multiobject classification problem, a binary tree decision support vector machine based on statistical learning is constructed as a classifier for moving object classification. Improve the learning efficiency of the classifier, solve the competitive classification problem of the traditional SVM, and increase the efficiency of the mobile computing intelligent monitoring method by more than 70%.

We introduce a new autoencoder-based algorithm for non-negative matrix factorization. Instead of stochastic gradient descent-based update rules, our approach employs exponentiated gradient decent which, unlike the former, inherently guarantees the non-negativity of basis vectors when they are initialized to non-negative values. Moreover, we explore the potential of our autoencoder-based non-negative matrix factorization model for clustering applications, and show that it can learn hierarchical factorizations, each of which corresponding to a different and meaningful clustering. Further, we show that adding a supervised loss at intermediate layers results in more diverse representations at the different layers of the NMF hierarchy. We provide extensive empirical evaluations on text and image datasets and compare our proposed model to two alternative approaches, including another autoencoder-based algorithm.

This paper proposes a compact configuration of aircraft flows at intersections. The goal is to achieve a higher capacity of the airspace, allowing more aircraft to safely fly through a fixed region. Intersections of aircraft flows can be considered as basic building blocks for air traffic networks, and traffic networks can be designed through finding optimal arrangements of intersections whose conflict zones do not overlap. A conflict zone is defined as a minimal circular area centered at the intersection of two flows, which allows aircraft approaching the intersections to resolve conflict completely within the conflict zone. This paper derives the relationship between the size of a conflict zone and the intersection angle of the two flows. Such a relationship guides the choice of the most compact configuration for intersecting aircraft flows. An example involving multiple converging flows of aircraft demonstrates the efficiency of the proposed configuration of intersections. The result of conflict resolution shows a greatly reduced traffic complexity. Therefore, our study provides a potential solution to increase airspace capacity.

Cardiovascular disease (CVD) is the single leading cause of global mortality and is projected to remain so. Cardiac arrhythmia is a very common type of CVD and may indicate an increased risk of stroke or sudden cardiac death. The ECG is the most widely adopted clinical tool to diagnose and assess the risk of arrhythmia. ECGs measure and display the electrical activity of the heart from the body surface. During patients' hospital visits, however, arrhythmias may not be detected on standard resting ECG machines, since the condition may not be present at that moment in time. While Holter-based portable monitoring solutions offer 24-48 h ECG recording, they lack the capability of providing any real-time feedback for the thousands of heart beats they record, which must be tediously analyzed offline. In this paper, we seek to unite the portability of Holter monitors and the real-time processing capability of state-of-the-art resting ECG machines to provide an assistive diagnosis solution using smartphones. Specifically, we developed two smartphone-based wearable CVD-detection platforms capable of performing real-time ECG acquisition and display, feature extraction, and beat classification. Furthermore, the same statistical summaries available on resting ECG machines are provided.

To date, spike sorting for neural processing in brain-computer interfaces has been performed using off-chip analysis or custom ASIC designs. In this paper, we propose and test the feasibility of performing on-chip, real-time spike sorting on a commercially available and programmable smartdust wireless sensor network mote since such a platform is currently the closest to an implantable chip due to its small size and similar physical and environmental constraints.

Brain-computer interfaces (BCIs) offer tremendous promise for improving the quality of life for disabled individuals. BCIs use spike sorting to identify the source of each neural firing. To date, spike sorting has been performed using off-chip analysis, which requires a wired connection penetrating the skull to a bulky external power/processing unit, or ASIC designs, which lack the programmability to perform different algorithms and upgrades. In this research, we propose and test the feasibility of performing on-chip, real-time spike sorting on a programmable smartdust, including feature extraction, classification, compression, and wireless transmission. A detailed power/performance trade-off analysis using DVFS is presented. Our experimental results show that the execution time and power density meet the requirements to perform real-time spike sorting and wireless transmission on a single neural channel.