Code-Enhanced Cross-Perspective Bug Question Retrieval

Retrievability provides an alternative way to assess an Information Retrieval (IR) system by measuring how easily documents can be retrieved. Retrievability can also be used to determine the level of retrieval bias a system exerts upon a collection of documents. It has been hypothesised that reducing the retrieval bias will lead to improved performance. To date, it has been shown that this hypothesis does not appear to hold on standard retrieval performance measures (MAP and [email protected]) when exploring the parameter space of a given retrieval model. However, the evidence is limited and confined to only a few models, collections and measures. In this paper, we perform a comprehensive empirical evaluation analysing the relationship between retrieval bias and retrieval performance using several well known retrieval models, five large TREC test collections and ten performance measures (including the recently proposed PRES, Time Biased Gain (TBG) and U-Measure). For traditional relevance based measures (MAP, [email protected], MRR, Recall, etc) the correlation between retrieval bias and performance is moderate. However, for TBG and U-Measure, we find that there is strong and significant negative correlations between retrieval bias and performance (i.e as bias drops, performance increases). These findings suggest that for these more sophisticated, user oriented measures the retrievability bias hypothesis tends to hold. The implication is that for these measures, systems can then be tuned using retrieval bias, without recourse to relevance judgements.

본 논문에서는 데이터마이닝모듈과 정보융합모듈을 핵심구성요소로 가지는 지능형에이전트 시스템을 설계하고 다각도 정보를 융합하여 진단전문가시스템으로 활용할 수 있는 가능성을 제시한다. 데이터마이닝모듈에서는 퍼지신경망 OFUN-NET에 의하여 다각도의 데이터를 분석하고 퍼지 클러스터 정보를 지식베이스로 구축한다. 정보융합모듈과 응용모듈에서는 가능성정도로 제공되는 진단결과와 불확실 결정상태나 비대칭의 발견과 같은 전문가의 진단에 유용한 정보를 제공해 주고 있다. 또한 DDSM 벤치마크 데이터베이스로부터 획득한 디지털 유방 x선 영상의 BI-RADS 기반 특징데이터를 가지고 실험한 결과는 기존의 방법보다 높은 분류 정확도를 보여주면서 컴퓨터보조진단시스템으로서의 가능성을 보여주고 있다. In this paper, we design an intelligent agent system with the data mining module and information fusion module as the core components of the system and investigate the possibility for the medical expert system. In the data mining module, fuzzy neural network, OFUN-NET analyzes multi-view data and produces fuzzy cluster knowledge base. In the information fusion module and application module, they serve the diagnosis result with possibility degree and useful information for diagnosis, such as uncertainty decision status or detection of asymmetry. We also present the experiment results on the BI-RADS-based feature data set selected form DDSM benchmark database. They show higher classification accuracy than conventional methods and the feasibility of the system as a computer aided diagnosis system.

Geometrical structures and the internal local region relationship, such as symmetry, regular array, junction, etc., are essential for understanding a 3D shape. This paper proposes a point cloud feature extraction network named PointSCNet, to capture the geometrical structure information and local region correlation information of a point cloud. The PointSCNet consists of three main modules: the space-filling curve-guided sampling module, the information fusion module, and the channel-spatial attention module. The space-filling curve-guided sampling module uses Z-order curve coding to sample points that contain geometrical correlation. The information fusion module uses a correlation tensor and a set of skip connections to fuse the structure and correlation information. The channel-spatial attention module enhances the representation of key points and crucial feature channels to refine the network. The proposed PointSCNet is evaluated on shape classification and part segmentation tasks. The experimental results demonstrate that the PointSCNet outperforms or is on par with state-of-the-art methods by learning the structure and correlation of point clouds effectively.

The new generation of organic light emitting diode display is designed to enable the high dynamic range (HDR), going beyond the standard dynamic range (SDR) supported by the traditional display devices. However, a large quantity of videos are still of SDR format. Further, most pre-existing videos are compressed at varying degrees for minimizing the storage and traffic flow demands. To enable movie-going experience on new generation devices, converting the compressed SDR videos to the HDR format (i.e., compressed-SDR to HDR conversion) is in great demands. The key challenge with this new problem is how to solve the intrinsic many-to-many mapping issue. However, without constraining the solution space or simply imitating the inverse camera imaging pipeline in stages, existing SDR-to-HDR methods can not formulate the HDR video generation process explicitly. Besides, they ignore the fact that videos are often compressed. To address these challenges, in this work we propose a novel imaging knowledge-inspired parallel networks (termed as KPNet) for compressed-SDR to HDR (CSDR-to-HDR) video reconstruction. KPNet has two key designs: Knowledge-Inspired Block (KIB) and Information Fusion Module (IFM). Concretely, mathematically formulated using some priors with compressed videos, our conversion from a CSDR-to-HDR video reconstruction is conceptually divided into four synergistic parts: reducing compression artifacts, recovering missing details, adjusting imaging parameters, and reducing image noise. We approximate this process by a compact KIB. To capture richer details, we learn HDR representations with a set of KIBs connected in parallel and fused with the IFM. Extensive evaluations show that our KPNet achieves superior performance over the state-of-the-art methods.

The co-located normalized radar backscatter cross section measurements from the Global Precipitation Measurement (GPM) Ku/Ka-band dual-frequency precipitation radar (DPR) and sea surface wind; wave and temperature observations from the National Data Buoy Center (NDBC) moored buoys are used to analyze the dependence and sensitivity of Ku- and Ka-band backscatter on surface conditions at low-incidence angles. Then the potential for inverting wind and wave parameters directly from low-incidence σ0 measurements is discussed. The results show that the KaPR σ0 is more sensitive to surface conditions than the KuPR σ0 overall. Nevertheless; both the KuPR σ0 and KaPR σ0 are strongly correlated with wind speed (U10) and average wave steepness (δa) with the exception of specific transitional incidence angles. Moreover, U10 and δa could be retrieved from pointwise σ0 near nadir and near 18°. Near 18°; wind direction information is needed as the effect of wind direction on σ0 becomes increasingly significant with incidence angle. To improve the performance of U10 retrieval; especially for low U10; auxiliary δa information would be most helpful; and sea surface temperature is better taken into account. Other wave parameters; such as significant wave height; wave period and wave age; are partly correlated with σ0. It is generally more difficult to retrieve those parameters directly from pointwise σ0. For the retrieval of those wave parameters; various auxiliary information is needed. Wind direction and wave direction cannot be retrieved from pointwise σ0.

Within many domains, such as news, medicine and patent, documents contain a variety of fields such as title, author, body, source, etc. As such fielded retrieval models that query across these fields are often employed. It is largely presumed that fielding provides a better representation of the document and offers more control when querying and that this will lead to improved retrieval performance. However, depending on how the fields are weighted and if the fields are populated, the retrieval algorithm may unduly favour certain documents over others. This is known as algorithmic bias and it can be detrimental to retrieval systems performance. In this paper, we explore the impact of fielding on retrieval bias and performance across a variety of TREC News Test Collections. We perform an extensive large‐scale analysis on two types of fielded retrieval model variations that are based on the popular BM25 retrieval algorithm where either: fields are scored independently and then combined (Model 1), or fields are first combined and then scored (Model 2). Our findings show that for Model 1 fielding, a strong correlation exists between retrieval bias and performance such that as title fields are weighted more heavily, bias increases, while retrieval performance decreases. When weighting is applied to content‐based fields, performance increases as bias decreases, showing that relying more on content may be favourable in terms of fairness and performance. On the other hand, for Model 2 fielding, the relationship between retrieval bias and performance is more complex. But, crucially we show that Model 2 fielding results in lower retrieval bias and greater performance than Model 1 fielding. And, we observed that under Model 1, news articles without titles are substantially less retrievable (i.e. more susceptible to algorithmic bias). These findings have serious ramifications as many popular Open Source Information Retrieval frameworks, commonly used by professional searchers, use the default implementation of Model 1 for their fielded search capability. This research shows the importance of analysing retrieval algorithms with respect to both bias and performance to ensure they minimize any unwanted or unintended biases when maximising performance. Further work is required to examine this phenomenon in more detail and to design fielded retrieval models that have the advantages of control and performance without detrimental biases.

To address the challenges of difficult detection of small targets and limited computational resources prevalent in power switchgear. This paper presents an enhanced switchgear detection model, ELGS-YOLOv8, which addresses the limitations of existing models. First, ELGS-YOLOv8 employs a lightweight Efficient Mutil Scal Conv (EMSC) in the backbone network. This module reduces the number of parameters and computation of the model while improving the extraction of feature information. In addition, the local-global information extraction and fusion module (LGEF) for small targets has been proposed to further improve the detection capability of the indicator. The module integrates local information extraction module(LIEM)and local-global information fusion module (LGFM) at the neck, which are used to improve the extraction and fusion of feature information, respectively. Finally, a lightweight detection head based on the Separated and Enhancement Attention Module (LSEAM) is designed to reduce the model complexity while further improve the model’s detection performance in complex scenes. Experimental results show that the improved ELGS-YOLOv8 model achieves 90.4% in mAP@0.5, with a model size reduction of 15% and an increase in AP s by 7.7%, meeting the real-time and accuracy requirements for on-site deployment. Therefore, the improved strategy provides a more reliable and efficient solution for switchgear detection in substation inspections.

Pedestrian detection aided by fusion of binocular information

Diabetic Retinopathy (DR) is a vascular disorder affecting the retina due to prolonged Diabetes. It can lead to sudden vision loss in advanced stages. Screening and routine monitoring is the most effective way of avoiding vision loss due to DR. Abramoff et al. developed and evaluated an automated DR screening system. One of the most important parts of this system, the information fusion module, combines information obtained from different images and various image properties. Niemeijer et al. compared several methods for DR information fusion and concluded that k-Nearest Neighbour (kNN) provided the best performance for their system. The aim of this work was to compare performance of the Random Forest (RF) classifier with that of the kNN classifier for DR information fusion. We performed experiments on a dataset containing images from 10303 eye examinations. Additionally we also compared performance of the two classifiers in an important sub-problem of DR screening - red lesion detection. In both the experiments, the RF classifier showed significantly better performance.

In this paper an integrated vision system for autonomous land vehicle is described. The vision system includes 2D and 3D vision modules and information fusion module. The task of 2D vision is to provide the physical and geometry information of road, and the task of 3D vision system is to detect the obstacles in the surrounding. Fusion module combines 2D and 3D information to generate a feasible region provided for vehicle navigation.

Currently, single-sensor data is frequently utilized in technologies such as object detection. However, in certain scenarios, some sensors may experience failure or information loss, significantly impacting model performance. Given the notable complementarity between infrared and visible images at the information level, it is helpful to improve the robustness and reliability of the model by fusing them and applying them to object detection and other technologies. Nevertheless, most prevalent infrared and visible image fusion methods focus on exploring invariant features across multimodal images, somewhat neglecting the inherent characteristics of the images themselves, leading to issues like structural blurriness and unclear detailed textures in the fused images, which fail to meet application demands. To overcome this challenge, this paper proposes an Infrared and visible image fusion network based on multistage progressive injection, termed MPIFusion. To effectively leverage the inherent characteristics and complementarity of images, and address the issues of structural blurriness and unclear detailed textures in fused images, we introduce a Dual-channel Shallow Detail Fusion Module (DC-SDFM) and a Deep Feature Fusion Block (DFFB). These modules first enhance the original features and then fuse the hierarchical features of infrared and visible images with the aid of an attention mechanism module. Furthermore, we construct a progressive injection layer based on the Information Fusion Module (IFM), integrating the fused features within the same framework to generate high-quality infrared and visible fused images. Extensive experiments demonstrate that our MPIFusion outperforms 15 existing fusion methods in terms of performance. The generated fused images not only highlight global and local detail features but also exhibit higher clarity and contrast. Finally, we apply fusion methods to object detection scenarios, and the results show that MPIFusion exhibits significant superiority in such scenarios, providing more robust and reliable image support. The source code is available at https://github.com/Kaixuan-Chang/MPIFusion.

In this paper an integrated vision system for autonomous land vehicle is described. The vision system includes 2D and 3D vision modules and information fusion module. The task of 2D vision is to provide the physical and geometry information of road, and the task of 3D vision system is to detect the obstacles in the surrounding. Fusion module combines 2D and 3D information to generate a feasible region provided for vehicle navigation.

Classifying the task of automatically assigning unlabeled questions into predefined categories (or topics) and effectively retrieving a similar question are crucial aspects of an effective cQA service. We first address the problems associated with estimating and utilizing the distribution of words in each category of word weights. We then apply an automatic expansion word generation technique that is based on our proposed weighting method and the pseudo relevance feedback to question classification. Secondly to address the lexical gap problem in question retrieval, the case frame of the sentence is first defined using the extracted components of a sentence, and a similarity measure based on the case frame and the word embedding is then derived to determine the similarities between two sentences. These similarities are then used to reorder the results of the first retrieval model. Consequently, the proposed methods significantly improve the performance of question classification and retrieval.

Based on multi-sensor information fusion theory, a Gas fire-extinguishing control panel is introduced in this paper. The intelligent algorithm of neural network and fuzzy consequence is used to get the fire probability. According this principle, we designed an information fusion module which would send the probability to the main control panel to carry out the alarm and linkage. The practical application results indicate that the proposed method can effectively decrease the mistake rate of the fire detector and fire extinguisher.

The current application of vibration‐based damage detection is constrained by the low spatial resolution of signals obtained from contact sensors and an overreliance on hand‐engineered damage indices. In this paper, we propose a novel vision‐aided framework featuring convolutional multihead self‐attention neural network (CMSNN) to deal with damage detection tasks. To meet the requirement of spatially intensive measurements, a computer vision algorithm called optical flow estimation is employed to provide informative enough mode shapes. As a downstream process, a CMSNN model is designed to autonomously learn high‐level damage representations from noisy mode shapes without any manual feature design. In contrast to the conventional approach of solely stacking convolutional layers, the model is enhanced by combining a convolutional neural network (CNN)–based multiscale information extraction module with an attention‐based information fusion module. During the training process, various scenarios are considered, including measurement noise, data missing, multiple damages, and undamaged samples. Moreover, the parameter transfer strategy is introduced to enhance the universality of the application. The performance of the proposed framework is extensively verified via datasets based on numerical simulations and two laboratory measurements. The results demonstrate that the proposed framework can provide reliable damage detection results even when the input data are corrupted by noise or incomplete.