Precision oncology relies on the accurate characterization of spatial molecular distributions in cancer tissues to uncover critical biomarkers and guide clinical decision-making. However, the high dimensionality and complexity of mass spectrometry imaging (MSI) data pose significant challenges for effective analysis. This study presents an unsupervised manifold learning framework to address these challenges by mapping high-dimensional MSI data into a low-dimensional space while preserving essential molecular patterns. This method enables efficient dimensionality reduction, clustering, and visualization of MSI data, facilitating the discovery of spatially resolved molecular features. Applied to datasets from prostate cancer and colorectal adenocarcinoma, the proposed method accurately identifies cancerous regions and reveals highly correlated molecular markers with Pearson correlation coefficients up to 0.79. These findings demonstrate the potential of unsupervised manifold learning to enhance the interpretability and utility of MSI data in precision oncology, paving the way for improved biomarker discovery and cancer diagnostics.

Weakly supervised point cloud semantic segmentation (WSPCSS) has gained attention for reducing reliance on densely annotated data. However, inefficiencies in utilizing sparse annotations hinder comprehensive understanding of complex scenes. Inspired by masked autoencoder (MAE) techniques in image processing, researchers have adapted these methods to WSPCSS. Yet, current 3D masking strategies often fail to capture intricate geometric properties, resulting in generated to-be-filled content that inaccurately represents the underlying 3D scene structure. To address these limitations, this study proposes a novel stereo-wise masking strategy, which extends 2D plane masking into 3D space to generate coherent and semantically rich masked regions with contextual relevance. These regions serve as high-quality learning targets, enabling the model to better comprehend complex point cloud structures. Experimental results demonstrate that, at a 0.01 % annotation density, the proposed method achieves improvements in mIoU by 1.9 % and 4.72 % on the indoor datasets S3DIS and ScanNet V2, respectively, compared to previous methods. Furthermore, at a 0.1% annotation density on the forest dataset For-Instance, the method exhibits a 0.29 % improvement. These results substantiate the effectiveness and stability of the stereo-wise masking strategy.

This article presents a novel neural network–based approach for designing effective control policies for Caputo‐type nonlinear fractional‐order systems. The proposed approach iteratively refines the neural network to generate a control policy that stabilizes the system within a predefined neighborhood around the zero equilibrium. Stability of the controlled system is guaranteed by rigorously formulated theorems and empirically verified using a neural Lyapunov function. The effectiveness of the proposed methodology is demonstrated through simulations on two classical Caputo fractional‐order systems, showcasing its capability to ensure stability and its potential applicability to a broader range of fractional‐order nonlinear systems.

We observe two phenomenons with respect to quantity and capacity: 1) more teacher is not always better for multi-teacher knowledge distillation, and 2) stronger teacher is not always better for single-teacher knowledge distillation. To trade off the quantity and capacity of teacher ensemble, in this paper, we propose a new distillation paradigm named Dynamic Knowledge Distillation (DynaKD) that learn an adaptive categorical distribution to stochastically employ a teacher from a teacher ensemble in each step, to transfer knowledge from teacher ensemble into student. DynaKD has three advantages: 1) it can preserve diversity of each teacher via one-to-one distillation manner instead of several-for-one, 2) it can make the best of powerful teacher via those multi-level assistant teachers in ensemble, and 3) it can also dynamically determine the importance of each teacher for various tasks. To verify the effectiveness of the proposed approach, we conduct extensive experiments for BERT compression on GLUE benchmark. Experimental results show that the proposed approach achieves state-of-the-art score compared to previous compression approaches on five out of seven downstream tasks, including pushing MRPC F1 and accuracy to 92.2 (1.4 point absolute improvement), RTE accuracy to 76.2 (2.8 point absolute improvement). Moreover, we conduct also extensive experiments for image classification on CIFAR-100. Similarly, DynaKD achieves also state-of-the-art performance.

In this paper, we propose Stochastic Knowledge Distillation (SKD) to obtain compact BERT-style language model dubbed SKDBERT. In each distillation iteration, SKD samples a teacher model from a pre-defined teacher team, which consists of multiple teacher models with multi-level capacities, to transfer knowledge into student model in an one-to-one manner. Sampling distribution plays an important role in SKD. We heuristically present three types of sampling distributions to assign appropriate probabilities for multi-level teacher models. SKD has two advantages: 1) it can preserve the diversities of multi-level teacher models via stochastically sampling single teacher model in each distillation iteration, and 2) it can also improve the efficacy of knowledge distillation via multi-level teacher models when large capacity gap exists between the teacher model and the student model. Experimental results on GLUE benchmark show that SKDBERT reduces the size of a BERT model by 40% while retaining 99.5% performances of language understanding and being 100% faster.

Personal Identification Number (PIN), as one of the primary means of protecting digital properties and privacy on mobile devices, has been suffering from shoulder surfing attacks and weak password guessing for the long term. Recent years witness the growing interest in two-factor authentication that takes advantage of two different ways for mutual verification, thereby strengthening user authentication's accuracy and reliability. Especially with the popularity of smartwatches, more physiological signals are readily available to facilitate two-factor authentication. This paper presents a lightweight and unobtrusive two-factor authentication scheme, P2Auth, integrating the PIN and unique keystroke-related Photoplethysmography (PPG) measurement on wearables. Specifically, we propose the transformation of the multivariate PPG signal induced by the keystrokes to extract reliable biometric features. We develop short-time energy-based methods to identify the input cases, thus enabling support the authentication for both one-handed and two-handed input cases. Furthermore, we also consider the situation where there is no fixed PIN and design a new enhanced privacy scheme by combining the PPG measurements of different keystrokes to improve authentication security. The experiments involving 15 volunteers demonstrate that our prototype system can achieve an average authentication accuracy of over 95% for one-handed cases and over 90% for two-handed cases.

Most e-commerce platforms consist of multiple entries (e.g., recommendation, search, shopping cart and etc.) for users to purchase their liked items. Among the research on the recommendation entry, most of them focus on improving the conversion volumes merely in the recommendation entry. However, such way could not ensure an increase in the global conversion volumes of the e-commerce platform. To achieve this goal by optimizing the recommendation entry only, in this paper, we focus on modeling the causality between the recommendation-entry-impression and the conversion by proposing the two-stage Causality Enhanced Conversion (CEC) model. In the first stage, we define the recommendation-entry-impression as treatment, then we estimate the conversion rate conditioned on the inclusion or exclusion of treatment respectively and calculate the corresponding individual treatment effect (ITE). In the second stage, we propose a propensity-normalization (PN) based method to transform the learned ITE to a weight term for instance weighting in the conversion loss. Extensive offline and online experiments on a large-scale food e-commerce scenario demonstrate that the CEC model could focus more on those conversed instances that can improve the global conversion volumes of the platform.

This study introduced a parameterization scheme based on a neural network algorithm that can be potentially used in weather forecast models to estimate typhoon-induced ocean cooling (TOC). The proposed scheme is applied for the typhoon case Neoguri (2014). Significant improvement in predicting ocean temperature changes is achieved and thereby the model simulated storm intensity is improved by about 20%,. In contrast to previous TOC schemes, which all are based on linear ocean temperature equations, the neural network-based scheme is fully non-linear, free of physical equations, and is trained directly using historical atmospheric and oceanic data observed under typhoon conditions. The experiments with/without the TOC scheme indicated that the simulated storm intensity depends not only on the cooling amplitude, but also its position. Lacking of consideration of ocean cooling to typhoon growth, the atmosphere-only model tends to overestimate the storm intensity due to the ocean warm bias, and this bias can be efficiently corrected by applying the neural network-based ocean cooling scheme.

The transpiration from shelterbelts and the evapotranspiration (ET) from cropland (maize and vegetables) and orchards (apple) in an irrigated area in the middle reaches of the Heihe River, China, were estimated using a modified Penman-Monteith (P-M) formula and airborne remote sensing data. The results were compared to the shelter transpiration results obtained from measurements of sup flow in tree trunks made with thermal dissipation probes and the latent heat fluxes observed by the eddy covariance technique at flux towers in croplands. The modified P-M formula was found to be an effective means to estimate not only the cropland and orchard ET but also the shelter transpiration. The seasonal variation of shelterbelt transpiration was smaller than those of cropland and orchard ET. Estimates of ET made using the P-M formula along with the remote sensing data showed that 9.9%, 3.1%, and 87.0% of the total ET were allotted to shelterbelts, apple orchards, and cropland, respectively.