Knowledge-Based Systems最新文献

{"title":"Deep time-series clustering via latent representation alignment","authors":"","doi":"10.1016/j.knosys.2024.112434","DOIUrl":"10.1016/j.knosys.2024.112434","url":null,"abstract":"<div><p>In practice, obtaining sufficient label information from a dataset is challenging. Consequently, various clustering methods have been studied to homogeneously group data without label information. Recently, deep clustering approaches that utilize deep neural networks have garnered considerable attention. However, time series data possess unique characteristics, including temporal relationships between observations in a sequence, which can decrease the performance of existing deep clustering methods when applied to time series. Despite this, few studies on deep clustering have addressed the characteristics of time series. Thus, we propose a novel approach for deep time-series clustering using <em>topological information</em>, enabling the capture of underlying temporal patterns to generate cluster-oriented representations. We address the topological information of a time series by introducing a novel loss function based on the eigendecomposition of representations in latent space. Through experiments on various time-series datasets, we demonstrate the efficacy of the proposed method in achieving superior clustering performance compared to state-of-the-art deep clustering methods. To the best of our knowledge, this is the first approach that utilizes topological information for deep time-series clustering.</p></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":null,"pages":null},"PeriodicalIF":7.2,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142094819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel and efficient risk minimisation-based missing value imputation algorithm","authors":"","doi":"10.1016/j.knosys.2024.112435","DOIUrl":"10.1016/j.knosys.2024.112435","url":null,"abstract":"<div><p>Missing value imputation (MVI) is a key task in data science, in which learning models are built from incomplete data. In contrast to externally driven MVI algorithms, this study proposes a novel risk minimisation-based MVI algorithm (RM-MVI) that considers both the internal characteristics of missing data and the external performance for specific classification applications. RM-MVI is technically designed for labelled data and is applied in two stages: <em>filling</em> with structural risk minimisation (SRM) and <em>refining</em> with empirical risk minimisation (ERM). In the filling stage, an autoencoder with a single hidden layer is trained on the original dataset without missing values. Missing values are first initialised with random numbers, and the imputation values are then preliminarily optimised based on the derived updating rule to minimise the structural risk-oriented objective function. After the imputation values have been preliminarily optimised in the filling stage, a neural-network-based classifier is trained in the refining stage to optimise the imputation values sophisticatedly by reducing the empirical risk. Experiments were conducted on several benchmark datasets to validate the feasibility, rationality, and effectiveness of the proposed RM-MVI algorithm. The results show that (1) the optimisation processes of the imputation values corresponding to the SRM and ERM are convergent so that the optimised imputation values can be obtained; (2) SRM can ensure distribution consistency of the imputation values that are preliminarily optimised in the filling stage, while ERM can optimise the imputation values sophisticatedly in the refining stage, which is more helpful for classifier training; and (3) the RM-MVI algorithm can yield considerably better MVI performance on benchmark datasets than 11 well-known MVI algorithms, such as a 26% higher distribution consistency ratio and 2% to 5% higher testing accuracies for 6 classifiers on average. This demonstrates that RM-MVI is a viable approach for addressing MVI problems.</p></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":null,"pages":null},"PeriodicalIF":7.2,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142147772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explicit-implicit priori knowledge-based diffusion model for generative medical image segmentation","authors":"","doi":"10.1016/j.knosys.2024.112426","DOIUrl":"10.1016/j.knosys.2024.112426","url":null,"abstract":"<div><p>The diffusion probabilistic model (DPM) has achieved unparalleled results in current image generation tasks, and some recent research works employed it in several computer vision tasks, such as image super-resolution, object detection, etc. Thanks to DPM's superior ability to generate fine-grained details, these research efforts have yielded significant successes. In this paper, we propose a new DPM-based generative medical image segmentation method, named EIDiffuSeg. Specifically, we first construct an explicit-implicit aggregation priori knowledge with directional supervision ability by mining the semantic distribution pattern in the frequency and spatial domains. Then, the explicit-implicit aggregation priori knowledge is integrated into the different encoding stages of the denoising backbone network using a novel unsupervised priori knowledge induction strategy, which can guide the model to generate a segmentation mask of the region of interest directionally from a random inference process. We evaluate our method on three medical image segmentation benchmark datasets with different modalities and achieve the best segmentation results compared to state-of-the-art methods. Especially, compared to several current diffusion-based image segmentation methods, we achieved a 9% Dice improvement in the polyp segmentation benchmark. Our code will be available at <span><span>https://github.com/Notmezhan/EIDiffuSeg</span><svg><path></path></svg></span>.</p></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":null,"pages":null},"PeriodicalIF":7.2,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142122363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ITRE: Low-light image enhancement based on illumination transmission ratio estimation","authors":"","doi":"10.1016/j.knosys.2024.112427","DOIUrl":"10.1016/j.knosys.2024.112427","url":null,"abstract":"<div><p>Noise, artifacts, and over-exposure are substantial challenges in the field of low-light image enhancement. Existing methods often struggle to address these issues simultaneously. In this paper, we propose a method that is based on Illumination Transmission Ratio Estimation (ITRE) to handle the challenges at the same time. Specifically, we assume that there must exist a pixel which is least disturbed by low light for pixels of each color cluster. First, we cluster the pixels on the RGB color space to find the Illumination Transmission Ratio (ITR) matrix of the whole image, which determines that noise is not over-amplified easily. Next, we consider the ITR of the image as the initial illumination transmission map to construct a base model for refining transmission map, which prevents artifacts. In addition, we design an over-exposure module that captures the fundamental characteristics of pixel over-exposure and seamlessly integrates it into the base model. Finally, there is a possibility of weak enhancement when the interclass distance of pixels with the same color is too small. To counteract this, we design an Robust-Guard (RG) module that safeguards the robustness of the image enhancement process. Extensive experiments demonstrate the superiority of the proposed method over state-of-the-art methods in terms of visual quality and quantitative metrics. Our code is available at <span><span>https://github.com/wangyuro/ITRE</span><svg><path></path></svg></span>.</p></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":null,"pages":null},"PeriodicalIF":7.2,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142129548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Personalized process–type learning path recommendation based on process mining and deep knowledge tracing","authors":"","doi":"10.1016/j.knosys.2024.112431","DOIUrl":"10.1016/j.knosys.2024.112431","url":null,"abstract":"<div><p>Personalized learning path recommendation considers learning goals, learning abilities, and other personalized characteristics of learners to generate a suitable learning path. Existing approaches include global optimal and local iterative path recommendation, which recommend a sequence of learning objects. Consequently, the learner can only learn in the order specified by the learning path, which provides limited flexibility for the learner. In addition, existing studies cannot both present the complete path and handle changes in the learner's knowledge state while learning along the path. This study proposes a process-type learning path model and its recommendation approach, which presents a learning path in the form of a flowchart and dynamically recommends path branches according to the knowledge states of the learner during the learning process. Specifically, deep knowledge tracing is used to annotate the knowledge states of learners in historical logs, and process mining is used to generate a personalized process–type learning path that contains sequences, parallel relationships, and selection relationships between learning objects. In addition, the correlation between the knowledge state and the selection of different branches of a learning path in historical logs can be obtained via decision mining. Thus, a branch recommendation model is trained and used to recommend a path branch in a process-type path with the highest probability of mastering the target learning object of the learner based on the learner's knowledge state. The experimental results demonstrate that the learning effectiveness and efficiency of the proposed approach are better than those of the existing approaches.</p></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":null,"pages":null},"PeriodicalIF":7.2,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142095265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Geometric interpretation of efficient weight vectors","authors":"","doi":"10.1016/j.knosys.2024.112403","DOIUrl":"10.1016/j.knosys.2024.112403","url":null,"abstract":"<div><p>Pairwise comparison matrices (PCMs) are frequently used in different multicriteria decision making problems. A weight vector is said to be efficient if no other weight vector is at least as good in estimating the elements of the PCM, and strictly better in at least one position. Understanding the efficient weight vectors is crucial to determine the appropriate weight calculation technique for a given problem. In this paper we study the set of efficient weight vectors for three and four dimensions (alternatives) from a geometric viewpoint, which is a complementary to the algebraic approach used in the literature. Besides providing well-interpretable demonstrations, we also draw attention to the particular role of weight vectors calculated from spanning trees. Weight vectors corresponding to line graphs are vertices of the (polyhedral, but usually nonconvex) set of efficient weight vectors, while weight vectors corresponding to other spanning trees are also on the boundary.</p></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":null,"pages":null},"PeriodicalIF":7.2,"publicationDate":"2024-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0950705124010372/pdfft?md5=d2357383b0b1fd8f0f64eeccf147c178&pid=1-s2.0-S0950705124010372-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142094817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Retrieval augmented generation using engineering design knowledge","authors":"","doi":"10.1016/j.knosys.2024.112410","DOIUrl":"10.1016/j.knosys.2024.112410","url":null,"abstract":"<div><p>Aiming to support Retrieval Augmented Generation (RAG) in the design process, we present a method to identify explicit, engineering design facts – {<em>head entity:: relationship:: tail entity}</em> from patented artefact descriptions. Given a sentence with a pair of entities (selected from noun phrases) marked in a unique manner, our method extracts their relationship that is explicitly communicated in the sentence. For this task, we create a dataset of 375,084 examples and fine-tune language models for relation identification (token classification task) and relation elicitation (sequence-to-sequence task). The token classification approach achieves up to 99.7% accuracy. Upon applying the method to a domain of 4,870 fan system patents, we populate a knowledge base of over 2.93 million facts. Using this knowledge base, we demonstrate how Large Language Models (LLMs) are guided by explicit facts to synthesise knowledge and generate technical and cohesive responses when sought out for knowledge retrieval tasks in the design process.</p></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":null,"pages":null},"PeriodicalIF":7.2,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142095266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive and Priority-Based Data Aggregation and Scheduling Model for Wireless Sensor Network","authors":"","doi":"10.1016/j.knosys.2024.112393","DOIUrl":"10.1016/j.knosys.2024.112393","url":null,"abstract":"<div><p>Wireless Sensor Networks (WSN) use sensor nodes placed in potential places to collect sensitive information. These sensor nodes monitor necessary data and send it to the sink node. Sensor nodes have resource constraints, especially energy and power depletion. The majority of sensor and battery power is wasted on redundant data transmission. The redundant data transmission consumes a significant amount of the sensor and battery life, decreasing the total lifespan of the sensor nodes. Data aggregation is an approach that expands the useful lifetime of sensor nodes overall and removes unnecessary data and delays. There are many types of data aggregation techniques, such as centralized, tree-based, in-network, and cluster-based. The available tree-based data aggregation mechanism performs well, but the whole tree may be down due to single-node failure. Due to bottlenecks, node data aggregation suffers from an increased packet failure ratio. Another limitation is that every node aggregates data into slices, which consumes more energy. For this purpose, an adaptive and priority-based data aggregation and scheduling model (APB-DASM) for WSNs is proposed in this paper to address these issues. It is proposed that APB-DASM be used to improve quality of service (QoS) with regard to energy consumption and data transmission. The APB-DASM model aggregates sensor data into cluster heads and divides it into three formats: The first format categorizes the most important data that consists of four slices, and the second format categorizes the important data that consists of three slices. Format three data is represented in two slices, which is normal data. These three types of format data are aggregated on a priority basis, such that the highest priority is given to the first format, i.e., most important data; moderate priority is given to the second format, i.e., important data; and then low priority is given to the normal data. Due to an efficient priority-based data aggregation and scheduling algorithm, our proposed model sends the most important data first, and so on. Theoretical study and simulation research demonstrate that our proposed approach improves the existing tree-based models. By using APB-DASM, significant decreases in energy usage, packet delivery ratio, and overall QoS are achieved, and as a result, the WSNs' lifetime is thus increased. The proposed model is implemented in MATLAB, and the results are compared with existing tree-based models. Simulations comparing our model to the most recent models indicate that it worked effectively, reducing the packet failure ratio and energy usage by 36.8% and 30%, respectively, for CBF-ADA, D-SMART, and WDARS. This article emphasizes how the suggested methodology can be effectively used in the aggregation of coronavirus patient data. It demonstrates how adaptable and applicable our method is in the real world<strong>.</strong></p></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":null,"pages":null},"PeriodicalIF":7.2,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142151580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pseudo-unknown uncertainty learning for open set object detection","authors":"","doi":"10.1016/j.knosys.2024.112414","DOIUrl":"10.1016/j.knosys.2024.112414","url":null,"abstract":"<div><p>Despite the significant strides made by modern object detectors in the closed-set scenarios, open-set object detection (OSOD) remains a formidable challenge. This is particularly evident in misclassifying objects from unknown categories into pre-existing known classes or ignored background classes. A novel approach called PUDet (Pseudo-unknown Uncertainty Detector) based on Evidential Deep Learning (EDL) is proposed, incorporating two modules: the Class-wise Contrastive Learning Network (CCL) and the Uncertainty-Aware Labeling Network (UAL). For CCL, the module leverages class-wise contrastive learning to encourage intra-class compactness and inter-class separation, thereby reducing the overlap between known and unknown classes. Simultaneously, it establishes compact boundaries for known classes and generates pseudo-unknown candidates to facilitate UAL for better learning pseudo-unknown uncertainty. For UAL, the Weight-Impact EDL (WI-EDL) approach is introduced to enhance uncertainty in edge samples by collecting categorical evidence and weight impact. Subsequently, UAL refines uncertainty via localization quality calibration, facilitating the mining of pseudo-unknown samples from foreground and background proposals to construct compact boundaries between known and unknown categories. In comparison to the state of the arts, the proposed PUDet showcases a substantial improvement, achieving a reduction in Absolute Open-Set Errors by 13%–16% across six OSOD benchmarks.</p></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":null,"pages":null},"PeriodicalIF":7.2,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142089231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TABLE: Time-aware Balanced Multi-view Learning for stock ranking","authors":"","doi":"10.1016/j.knosys.2024.112424","DOIUrl":"10.1016/j.knosys.2024.112424","url":null,"abstract":"<div><p>Stock ranking is a significant and challenging problem. In recent years, the use of multi-view data, such as price and tweet, for stock ranking has gained considerable attention in the research field. Most existing methods are performed in (some of) the 3 steps: 1) view-specific representation learning; 2) cross-view representation interaction; 3) multi-view representation fusion. Although these methods make breakthroughs in stock ranking, they often treat all views equally. This neglects the unbalanced phenomenon in multi-view stock data, i.e., the dimension of the text view may be extremely big compared with those of other views; the price view exhibits standard and high-quality data, whereas the text view contains noise and has irregular time intervals. To solve this, we propose a Time-Aware Balanced multi-view LEarning (TABLE) method. TABLE method consists of a view-specific learning stage and a multi-view fusion stage. In the first stage, we aim to improve the quality of the low-quality text view. We achieve this by attenuating the negative impact of irrelevant texts using a hierarchical temporal attention mechanism that captures text correlations. Additionally, we explicitly model the time irregularities between sequential texts. In the fusion stage, we address the dimensions unbalance problem by establishing a multi-view decision fusion paradigm by weighted averaging the view-specific stock predictions. These weights are dynamic and determined based on the quality discrepancy between the views. Finally, we obtain the optimal stock ranking list by optimizing the point-wise regression loss and the ranking-aware loss. We empirically compare TABLE method with state-of-the-art baselines using the publicly available dataset, <span><math><mrow><mi>S</mi><mi>&amp;</mi><mi>P</mi><mn>500</mn></mrow></math></span>. The experimental results demonstrate that TABLE method outperforms the baseline methods in terms of accuracy and investment revenue.</p></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":null,"pages":null},"PeriodicalIF":7.2,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142129549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}