- Article
In the field of recommendation, negative samples that are close to positive samples are referred to as “hard negative samples”. These hard negative samples are more likely to be incorrectly recommended to users. Therefore, researching how...
In the field of recommendation, negative samples that are close to positive samples are referred to as “hard negative samples”. These hard negative samples are more likely to be incorrectly recommended to users. Therefore, researching how...
Most current graph neural network (GNN)-based social recommendation systems mainly extract negative samples from explicit feedback, and are unable to accurately learn the boundaries of similar positive and negative samples, which leads to misjudgment...
Speaker recognition is a technology that identifies the speaker in an input utterance by extracting speaker-distinguishable features from the speech signal. Speaker recognition is used for system security and authentication; therefore, it is crucial...
Deep Neural Network (DNN)-based point cloud semantic segmentation has presented significant breakthrough using large-scale labeled aerial laser point cloud datasets. However, annotating such large-scaled point clouds is time-consuming. Self-Supervise...
External intrusion hazards such as construction machinery pose serious threats to the safe operation of transmission lines. However, reliable detection in transmission corridors remains challenging because hazardous targets usually exhibit articulate...
Cross-view geo-localization tries to find the matching place in large satellite or aerial pictures from photos taken at ground level, which is useful for applications like self-driving cars, flying drones, and adding virtual objects to real city scen...
Recently, the focus of entity linking research has centered on the zero-shot scenario, where the entity purposed to be labeled at the time of testing was never observed during the training phase, or it may belong to a different domain than the source...
In this paper, we propose a generative framework to produce similar yet novel samples for a specified image. We then propose the use of these images as hard-negatives samples, within the framework of hard-negative mining, in order to improve the perf...
In recent years, deep learning has become prevalent in Remaining Useful-Life (RUL) prediction of bearings. The current deep-learning-based RUL methods tend to extract high dimensional features from the original vibration data to construct the Health...
Negative-sample construction is an important step in machine learning-based landslide susceptibility assessment. Traditional negatives selected from flat or clearly stable terrain may introduce easy-negative bias and inflate apparent model performanc...
Model robustness is an important index in medical cybersecurity, and hard-negative samples in electronic medical records can provide more gradient information, which can effectively improve the robustness of a model. However, hard negatives pose diff...
Multiple studies have concluded that the selection of input samples is key for deep metric learning. For triplet networks, the selection of the anchor, positive, and negative pairs is referred to as triplet mining. The selection of the negatives is c...
AI-based multi-hazard susceptibility mapping has become an important approach for identifying slope-instability hazards over large areas. However, in multi-hazard modeling, negative samples do not have a consistent stable meaning across hazard types:...
Contrastive learning has emerged as a dominant paradigm for understanding 3D open-world environments, particularly in the realm of multi-modalities. However, due to the nature of self-supervised learning and the limited size of 3D datasets, pre-train...
Recently, with the rapid growth of the number of datasets with remote sensing images, it is urgent to propose an effective image retrieval method to manage and use such image data. In this paper, we propose a deep metric learning strategy based on Si...
Learning discriminative features between abnormal and normal instances is crucial for video anomaly detection within the multiple instance learning framework. Existing methods primarily focus on instances with the highest anomaly scores, neglecting t...
Logical Analysis of Data is a procedure aimed at identifying relevant features in data sets with both positive and negative samples. The goal is to build Boolean formulas, represented by strings over {0,1,-} called patterns, which can be used to clas...
Although the application of shot peening facilitates increasing hardness and corrosion resistance of stainless steel, the inappropriate peening parameters result in overestimated hardening and exaggerated surface roughness, which deteriorate the surf...
Bone is a nanocomposite material where the hard inorganic (hydroxyapatite crystallites) and organic (collagen fibrils) components are hierarchically arranged in the nanometer scale. Bone quality is dependent on the spatial distributions in the shape,...
Pine wilt is a devastating disease that typically kills affected pine trees within a few months. In this paper, we confront the problem of detecting pine wilt disease. In the image samples that have been used for pine wilt disease detection, there is...
Laser powder bed fusion (L-PBF) shows potential in metal additive manufacturing for producing complex components. However, achieving ideal hardness and minimizing porosity poses a significant challenge. This study explores the impact of part orientat...
The current in vitro study evaluated the Vickers hardness number (VHN) and hardness ratio of four bulk-fill composites (VisCalor bulk; Admira Fusion x-tra; x-tra fil; and GrandioSO x-tra-Voco, Cuxhaven, Germany) to assess the risk of bacterial coloni...
Retrieval-time augmentation can correct hard test samples but may also introduce harmful interference when retrieved neighbors are unreliable. We propose TDI-SF (trustworthy dynamic inference via similarity-gated strict fallback), a safety-oriented d...
Attributed graph clustering partitions nodes in an unsupervised manner by leveraging graph topology and node attributes. Existing deep methods face challenges including local structural bias, high noise in unsupervised graph editing, and insufficient...
Existing methods for identifying Tactics, Techniques, and Procedures (TTPs) from complex cyber-attack descriptions face three core challenges: (1) severe semantic asymmetry between unstructured attack narratives and standardized TTP definitions; (2)...
Due to the evident increase in tick-borne diseases worldwide, it is necessary to constantly update information on the distribution and zoonotic potential of hard ticks. We studied diversity, population structure, and seasonal dynamics of hard tick fa...
Burnishing is an advanced finishing process that produces higher-quality surfaces with better hardness and roughness than conventional finishing processes. Herein, a flexible magnetic burnishing brush comprising stainless steel pins under permanent m...
Micro-arc oxidation (MAO) is a promising technology for enhancing the wear resistance of engine cylinders by growing a high hardness alumina ceramic film on the surface of light aluminum engine cylinders. However, the positive and negative pulse coor...
Natural aging after solution treatment has a negative effect on the precipitation strengthening of Al–Mg–Si alloys since Cluster(1) formed at a room temperature cannot be dissolved or transformed into precipitates during artificial aging...
This research investigates the statistical correlation between Vickers hardness and tensile properties of helical submerged arc welded high-strength low-alloy (HSLA) API X70 pipeline steel. Tensile tests were performed on cross-weld joints from 138 p...
Remote sensing images are featured by massiveness, diversity and complexity. These features put forward higher requirements for the speed and accuracy of remote sensing image retrieval. The extraction method plays a key role in retrieving remote sens...
The relationship between the tendencies towards rigidity (measured by shear modulus, G) and hardness (measured by Vickers hardness, HV) of early transition metal (ETM)-based refractory high-entropy alloys (RHEA) and bond parameters (i.e., valence ele...
Existing noisy-label hyperspectral image classification (HSIC) methods usually address clean sample selection and representation regularization as separate problems, although the reliability of observed labels varies substantially across samples in h...
Although adventure tourism is divided into two subgroups based on the level of risk, most previous research has not made a distinction in their research. However, due to the high risk, skills, experience, and physical condition required of participan...
In this study, Al-1.00 Mg-0.65 Si-0.24 Cu alloy was solution heat-treated, water-quenched, and then pre-deformed for 5% before aging. The peak hardness and yield strength of the pre-deformed sample with subsequent artificial aging were similar to tha...
Background/Objectives: Functional tissue units (FTUs), including tertiary lymphoid structures (TLSs), blood vessels, and glands, encode localized immune, vascular, and epithelial organization in histopathology. Accurate quantification of these struct...
As energy exploration and development continue to advance into deep and ultradeep formations, systematic studies of rock mechanical properties face significant challenges due to high core acquisition costs and sample damage under extreme conditions....
Hard-anodized is a widely used method in the aeronautical sector to improve aluminum alloys abrasion and corrosion resistance. Aim of this work was to characterize the mechanical properties and resistance hard-anodized aluminum 6061 in citric acid so...
Nanoindentation testing using a Berkovich indenter was conducted to explore the relationships among indentation hardness (H), elastic work energy (We), plastic work energy (Wp), and total energy (Wt = We + Wp) for deformation among a wide range of pu...
Conglomerate reservoirs present significant technical challenges during drilling operations due to their complex mineral composition and heterogeneous characteristics, yet the quantitative relationships between mineral composition and microscopic mec...
Wire and arc additive manufacturing (WAAM) is a promising method of producing medium- and large-sized aluminum alloy structures, though it faces challenges such as porosity, residual stresses and inconsistent mechanical properties. This study investi...
This study proposes ViTWGAN, a novel and effective intrusion detection model designed to enhance data privacy protection by detecting malicious traffic within network flows. By improving the discriminator’s loss function, our approach reduces b...
Light-activated liposomes permit site and time-specific drug delivery to ocular and systemic targets. We combined a light activation technology based on indocyanine green with a hyaluronic acid (HA) coating by synthesizing HA–lipid conjugates....
Potentially inappropriate medications (PIMs) identified by the American Geriatrics Society should generally be avoided by older adults because of ineffectiveness or excess risk of adverse effects. Few studies have examined the effects of PIMs on driv...
Error detection is a critical step in data cleaning. Most traditional error detection methods are based on rules and external information with high cost, especially when dealing with large-scaled data. Recently, with the advances of deep learning, so...
The aim of this research was to evaluate the influence of strawberry variety on the effectiveness of ozone application on the harvested fruit during 12 days of storage. Batches (400 g) of strawberries of the San Andreas (SA) and Camino Real (CR) vari...
Eutectic aluminum-silicon alloys present high frictional coefficient and a high wear rate due to the low hardness under sliding friction conditions. In this paper, the eutectic aluminum-silicon alloy was textured firstly by micro-milling operations....
Detecting small anomalous targets in hyperspectral imagery is challenging when neither target spectra nor spatial morphologies are known, because most unsupervised detectors still encode implicit assumptions about background statistics or target stru...
Cutter rings form an integral part of tunnel boring machines (TBM). These cutters are deployed in various hard rock tunneling projects. The life of the cutter rings governs the economics of tunneling significantly. This paper presents a novel methodo...
In this work, ethyl cellulose nanoparticles loaded with rosemary extract (RCL-NPs) were synthesized and utilized to reinforce high-density polyethylene (HDPE) packaging bags as a nanotechnological alternative for rabbit meat preservation. The synthes...
of 6