Information Sciences最新文献

英文中文

PMformer: A novel informer-based model for accurate long-term time series prediction PMformer：基于信息的新型长期时间序列精确预测模型

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-10-23 DOI: 10.1016/j.ins.2024.121586

Yuewei Xue, Shaopeng Guan, Wanhai Jia

When applied to long-term time series forecasting, Informer struggles to capture temporal dependencies effectively, leading to suboptimal forecasting accuracy. To address this issue, we propose PMformer, a novel model based on Informer for long-term time series prediction. First, we introduce a probabilistic patch sampling attention mechanism that utilizes a patch-based strategy to compute attention scores within randomly selected sequence patches. This localized approach enhances the model's capability to capture local temporal dependencies, allowing it to better understand and process critical local features in time series while reducing computational complexity. Additionally, we propose a multi-scale scaling sparse attention technique that balances attention distribution by combining coarse- and fine-grained attention scores, thereby improving the model's ability to capture global sequence information. Finally, we design a dilated causal pooling layer and a multilayer perceptual cross self-attention decoder to further enhance the model's prediction accuracy by capturing key information in long-term correlations and precisely focusing on sequences. We conducted experiments on both multivariate and univariate time series forecasting tasks. The results show that PMformer outperforms six baseline models, including PatchTST and FEDformer, in terms of MAE and MSE metrics. This demonstrates its superior ability to capture temporal dependencies, achieving more accurate predictions.

在应用于长期时间序列预测时，Informer 难以有效捕捉时间依赖性，导致预测精度不理想。为了解决这个问题，我们提出了基于 Informer 的用于长期时间序列预测的新型模型 PMformer。首先，我们引入了概率补丁采样注意力机制，利用基于补丁的策略在随机选择的序列补丁中计算注意力分数。这种局部方法增强了模型捕捉局部时间依赖性的能力，使其能够更好地理解和处理时间序列中的关键局部特征，同时降低计算复杂度。此外，我们还提出了一种多尺度缩放稀疏注意力技术，通过结合粗粒度和细粒度注意力分数来平衡注意力分布，从而提高模型捕捉全局序列信息的能力。最后，我们设计了一个扩张因果池层和一个多层感知交叉自我注意力解码器，通过捕捉长期相关性中的关键信息和精确关注序列来进一步提高模型的预测准确性。我们对多变量和单变量时间序列预测任务进行了实验。结果表明，就 MAE 和 MSE 指标而言，PMformer 优于包括 PatchTST 和 FEDformer 在内的六个基准模型。这表明 PMformer 具备捕捉时间依赖性的卓越能力，可以实现更准确的预测。

{"title":"PMformer: A novel informer-based model for accurate long-term time series prediction","authors":"Yuewei Xue, Shaopeng Guan, Wanhai Jia","doi":"10.1016/j.ins.2024.121586","DOIUrl":"10.1016/j.ins.2024.121586","url":null,"abstract":"<div><div>When applied to long-term time series forecasting, Informer struggles to capture temporal dependencies effectively, leading to suboptimal forecasting accuracy. To address this issue, we propose PMformer, a novel model based on Informer for long-term time series prediction. First, we introduce a probabilistic patch sampling attention mechanism that utilizes a patch-based strategy to compute attention scores within randomly selected sequence patches. This localized approach enhances the model's capability to capture local temporal dependencies, allowing it to better understand and process critical local features in time series while reducing computational complexity. Additionally, we propose a multi-scale scaling sparse attention technique that balances attention distribution by combining coarse- and fine-grained attention scores, thereby improving the model's ability to capture global sequence information. Finally, we design a dilated causal pooling layer and a multilayer perceptual cross self-attention decoder to further enhance the model's prediction accuracy by capturing key information in long-term correlations and precisely focusing on sequences. We conducted experiments on both multivariate and univariate time series forecasting tasks. The results show that PMformer outperforms six baseline models, including PatchTST and FEDformer, in terms of MAE and MSE metrics. This demonstrates its superior ability to capture temporal dependencies, achieving more accurate predictions.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"690 ","pages":"Article 121586"},"PeriodicalIF":8.1,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530662","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}

引用次数: 0

TS-MAE: A masked autoencoder for time series representation learning TS-MAE：用于时间序列表示学习的掩码自动编码器

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-10-23 DOI: 10.1016/j.ins.2024.121576

Qian Liu , Junchen Ye , Haohan Liang , Leilei Sun , Bowen Du

Self-supervised learning (SSL) has been widely researched in recent years. In Particular, generative self-supervised learning methods have achieved remarkable success in many AI domains, such as MAE in computer vision, well-known BERT, GPT in natural language processing, and GraphMAE in graph learning. However, in the context of time series analysis, not only is the work that follows this line limited but also the performance has not reached the potential as promised in other fields. To fill this gap, we propose a simple and elegant masked autoencoder for time series representation learning. Firstly, unlike most existing work which uses the Transformer as the backbone, we build our model based on neural ordinary differential equation which possesses excellent mathematical properties. Compared with the position encoding in Transformer, modeling the evolution patterns continuously could better extract the temporal dependency. Secondly, a timestamp-wise mask strategy is provided to cooperate with the autoencoder to avoid bias, and it also could reduce the cross-imputation between variables to learn more robust representations. Lastly, extensive experiments conducted on two classical tasks demonstrate the superiority of our model over the state-of-the-art ones.

近年来，自监督学习（SSL）得到了广泛的研究。其中，生成式自监督学习方法在许多人工智能领域都取得了显著的成就，如计算机视觉领域的 MAE、众所周知的 BERT、自然语言处理领域的 GPT 以及图学习领域的 GraphMAE 等。然而，在时间序列分析中，沿袭这一思路的工作不仅有限，而且其性能也没有达到其他领域所承诺的潜力。为了填补这一空白，我们提出了一种用于时间序列表示学习的简单而优雅的掩码自动编码器。首先，与大多数以变换器为骨干的现有研究不同，我们的模型是基于神经常微分方程建立的，而神经常微分方程具有优异的数学特性。与变换器中的位置编码相比，连续演化模式建模能更好地提取时间依赖性。其次，提供了一种时间戳掩码策略来配合自动编码器，以避免偏差，同时还能减少变量间的交叉输入，从而学习到更健壮的表征。最后，在两个经典任务中进行的大量实验证明了我们的模型优于最先进的模型。

{"title":"TS-MAE: A masked autoencoder for time series representation learning","authors":"Qian Liu , Junchen Ye , Haohan Liang , Leilei Sun , Bowen Du","doi":"10.1016/j.ins.2024.121576","DOIUrl":"10.1016/j.ins.2024.121576","url":null,"abstract":"<div><div>Self-supervised learning (SSL) has been widely researched in recent years. In Particular, generative self-supervised learning methods have achieved remarkable success in many AI domains, such as MAE in computer vision, well-known BERT, GPT in natural language processing, and GraphMAE in graph learning. However, in the context of time series analysis, not only is the work that follows this line limited but also the performance has not reached the potential as promised in other fields. To fill this gap, we propose a simple and elegant masked autoencoder for time series representation learning. Firstly, unlike most existing work which uses the Transformer as the backbone, we build our model based on neural ordinary differential equation which possesses excellent mathematical properties. Compared with the position encoding in Transformer, modeling the evolution patterns continuously could better extract the temporal dependency. Secondly, a timestamp-wise mask strategy is provided to cooperate with the autoencoder to avoid bias, and it also could reduce the cross-imputation between variables to learn more robust representations. Lastly, extensive experiments conducted on two classical tasks demonstrate the superiority of our model over the state-of-the-art ones.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"690 ","pages":"Article 121576"},"PeriodicalIF":8.1,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538570","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}

引用次数: 0

Light sensor based covert channels on mobile devices 基于光传感器的移动设备隐蔽信道

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-10-23 DOI: 10.1016/j.ins.2024.121581

Mila Dalla Preda , Claudia Greco , Michele Ianni , Francesco Lupia , Andrea Pugliese

The widespread adoption of light sensors in mobile devices has enabled functionalities that range from automatic brightness control to environmental monitoring. However, these sensors also present significant security and privacy risks within the Android ecosystem due to unrestricted access permissions. This paper explores how light sensor data can be used for covert communication through a novel, light-based out-of-band channel. We develop two approaches–Baseline and ResetBased–that use luminance values to encode and decode data. These methods tackle challenges that arise from data variability and the unpredictability of sensor event timings. To enhance data transmission accuracy, our methods employ a novel strategy for selecting luminance reference sequences and leverage mean-squared-error-based distance for decoding. Experimental results validate the effectiveness of our approaches and their potential for real-world applications.

光传感器在移动设备中的广泛应用实现了从自动亮度控制到环境监测的各种功能。然而，由于不受限制的访问权限，这些传感器在安卓生态系统中也存在重大的安全和隐私风险。本文探讨了如何通过新颖的基于光的带外信道将光传感器数据用于隐蔽通信。我们开发了两种使用亮度值对数据进行编码和解码的方法--基线法和基于重置法。这些方法可以应对数据变化和传感器事件时间不可预测性带来的挑战。为了提高数据传输的准确性，我们的方法采用了一种新颖的策略来选择亮度参考序列，并利用基于均方误差的距离来进行解码。实验结果验证了我们方法的有效性及其在实际应用中的潜力。

引用次数: 0

Unveiling diagnostic information for type 2 diabetes through interpretable machine learning 通过可解释的机器学习揭示 2 型糖尿病的诊断信息

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-10-22 DOI: 10.1016/j.ins.2024.121582

Xiang Lv , Jiesi Luo , Yonglin Zhang , Hui Guo , Ming Yang , Menglong Li , Qi Chen , Runyu Jing

The interpretability of disease prediction models is often crucial for their trustworthiness and usability among medical practitioners. Existing methods in interpretable artificial intelligence improve model transparency but fall short in identifying precise, disease-specific primal information. In this work, an interpretable deep learning-based algorithm called the data space landmark refiner was developed, which not only enhances both global interpretability and local interpretability but also reveals the intrinsic information of the data distribution. Using the proposed method, a type 2 diabetes mellitus diagnostic model with high interpretability was constructed on the basis of the electronic health records from two hospitals. Moreover, effective diagnostic information was directly derived from the model’s internal parameters, demonstrating strong alignment with current clinical knowledge. Compared with conventional interpretable machine learning approaches, the proposed method offered more precise and specific interpretability, increasing clinical practitioners’ trust in machine learning-supported diagnostic models.

疾病预测模型的可解释性往往对其在医疗从业者中的可信度和可用性至关重要。现有的可解释人工智能方法提高了模型的透明度，但在识别精确的特定疾病原始信息方面存在不足。在这项工作中，开发了一种基于可解释深度学习的算法--数据空间地标提炼器，它不仅增强了全局可解释性和局部可解释性，还揭示了数据分布的内在信息。利用所提出的方法，以两家医院的电子病历为基础，构建了具有高可解释性的 2 型糖尿病诊断模型。此外，有效的诊断信息直接来自模型的内部参数，与当前的临床知识非常吻合。与传统的可解释机器学习方法相比，所提出的方法提供了更精确、更具体的可解释性，提高了临床医师对机器学习支持的诊断模型的信任度。

{"title":"Unveiling diagnostic information for type 2 diabetes through interpretable machine learning","authors":"Xiang Lv , Jiesi Luo , Yonglin Zhang , Hui Guo , Ming Yang , Menglong Li , Qi Chen , Runyu Jing","doi":"10.1016/j.ins.2024.121582","DOIUrl":"10.1016/j.ins.2024.121582","url":null,"abstract":"<div><div>The interpretability of disease prediction models is often crucial for their trustworthiness and usability among medical practitioners. Existing methods in interpretable artificial intelligence improve model transparency but fall short in identifying precise, disease-specific primal information. In this work, an interpretable deep learning-based algorithm called the data space landmark refiner was developed, which not only enhances both global interpretability and local interpretability but also reveals the intrinsic information of the data distribution. Using the proposed method, a type 2 diabetes mellitus diagnostic model with high interpretability was constructed on the basis of the electronic health records from two hospitals. Moreover, effective diagnostic information was directly derived from the model’s internal parameters, demonstrating strong alignment with current clinical knowledge. Compared with conventional interpretable machine learning approaches, the proposed method offered more precise and specific interpretability, increasing clinical practitioners’ trust in machine learning-supported diagnostic models.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"690 ","pages":"Article 121582"},"PeriodicalIF":8.1,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530661","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}

引用次数: 0

Discounted fully probabilistic design of decision rules 决策规则的全概率贴现设计

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-10-22 DOI: 10.1016/j.ins.2024.121578

Miroslav Kárný, Soňa Molnárová

Axiomatic fully probabilistic design (FPD) of optimal decision rules strictly extends the decision making (DM) theory represented by Markov decision processes (MDP). This means that any MDP task can be approximated by an explicitly found FPD task whereas many FPD tasks have no MDP equivalent. MDP and FPD model the closed loop — the coupling of an agent and its environment — via a joint probability density (pd) relating the involved random variables, referred to as behaviour. Unlike MDP, FPD quantifies agent's aims and constraints by an ideal pd. The ideal pd is high on the desired behaviours, small on undesired behaviours and zero on forbidden ones. FPD selects the optimal decision rules as the minimiser of Kullback-Leibler's divergence of the closed-loop-modelling pd to its ideal twin. The proximity measure choice follows from the FPD axiomatics.

MDP minimises the expected total loss, which is usually the sum of discounted partial losses. The discounting reflects the decreasing importance of future losses. It also diminishes the influence of errors caused by:

the imperfection of the employed environment model;

roughly-expressed aims;

the approximate learning and decision-rules design.

The established FPD cannot currently account for these important features. The paper elaborates the missing discounted version of FPD. This non-trivial filling of the gap in FPD also employs an extension of dynamic programming, which is of an independent interest.

最优决策规则的公理全概率设计（FPD）严格扩展了马尔可夫决策过程（MDP）所代表的决策（DM）理论。这意味着任何 MDP 任务都可以用明确找到的 FPD 任务来近似，而许多 FPD 任务却没有与 MDP 相对应的任务。马尔可夫决策过程和 FPD 通过相关随机变量的联合概率密度 (pd) 对闭环（即代理与其环境的耦合）进行建模，并将其称为行为。与 MDP 不同，FPD 通过理想 pd 量化代理的目标和约束。理想 pd 在期望行为上为高，在不期望行为上为小，在禁止行为上为零。FPD 根据闭环建模 pd 与理想 pd 的库尔巴克-莱伯勒发散值的最小值来选择最优决策规则。MDP 最小化预期总损失，通常是折现部分损失之和。贴现反映了未来损失重要性的递减。它还能减少以下因素造成的误差：所使用环境模型的不完善；目标表达粗糙；近似学习和决策规则设计。本文阐述了 FPD 的缺失折扣版本。对 FPD 缺陷的这一非同小可的填补，还采用了动态编程的扩展，这也是本文的另一个关注点。

{"title":"Discounted fully probabilistic design of decision rules","authors":"Miroslav Kárný, Soňa Molnárová","doi":"10.1016/j.ins.2024.121578","DOIUrl":"10.1016/j.ins.2024.121578","url":null,"abstract":"<div><div>Axiomatic fully probabilistic design (FPD) of optimal decision rules strictly extends the decision making (DM) theory represented by Markov decision processes (MDP). This means that any MDP task can be approximated by an explicitly found FPD task whereas many FPD tasks have no MDP equivalent. MDP and FPD model the closed loop — the coupling of an agent and its environment — via a joint probability density (pd) relating the involved random variables, referred to as behaviour. Unlike MDP, FPD quantifies agent's aims and constraints by an <em>ideal pd</em>. The ideal pd is high on the desired behaviours, small on undesired behaviours and zero on forbidden ones. FPD selects the optimal decision rules as the minimiser of Kullback-Leibler's divergence of the closed-loop-modelling pd to its ideal twin. The proximity measure choice follows from the FPD axiomatics.</div><div>MDP minimises the expected total loss, which is usually the sum of discounted partial losses. The discounting reflects the decreasing importance of future losses. It also diminishes the influence of errors caused by:</div><div><figure><img></figure> the imperfection of the employed environment model;</div><div><figure><img></figure> roughly-expressed aims;</div><div><figure><img></figure> the approximate learning and decision-rules design.</div><div>The established FPD cannot currently account for these important features. The paper elaborates the missing discounted version of FPD. This non-trivial filling of the gap in FPD also employs an extension of dynamic programming, which is of an independent interest.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"690 ","pages":"Article 121578"},"PeriodicalIF":8.1,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530657","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}

引用次数: 0

Evidence combination with multi-granularity belief structure for pattern classification 利用多粒度信念结构进行证据组合以实现模式分类

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-10-22 DOI: 10.1016/j.ins.2024.121577

Kezhu Zuo , Xinde Li , Le Yu , Tao Shen , Yilin Dong , Jean Dezert

Belief function (BF) theory provides a framework for effective modeling, quantifying uncertainty, and combining evidence, rendering it a potent tool for tackling uncertain decision-making problems. However, with the expansion of the frame of discernment, the increasing number of focal elements processed during the fusion procedure leads to a rapid increase in computational complexity, which limits the practical application of BF theory. To overcome this issue, a novel multi-granularity belief structure (MGBS) method was proposed in this study. The construction of MGBS reduced the number of focal elements and preserved crucial information in the basic belief assignment. This effectively reduced the computational complexity of fusion while ensuring the highest possible classification accuracy. We applied the proposed MGBS algorithm to a human activity recognition task and verified its effectiveness using the University of California, Irvine mHealth, PAMAP2, and Smartphone datasets.

信念函数（BF）理论为有效建模、量化不确定性和组合证据提供了一个框架，使其成为解决不确定决策问题的有力工具。然而，随着判别框架的扩大，融合过程中处理的焦点要素数量不断增加，导致计算复杂度迅速上升，从而限制了信念函数理论的实际应用。为了克服这一问题，本研究提出了一种新颖的多粒度信念结构（MGBS）方法。MGBS 的构建减少了焦点元素的数量，保留了基本信念分配中的关键信息。这有效降低了融合的计算复杂度，同时确保了尽可能高的分类精度。我们将提出的 MGBS 算法应用于人类活动识别任务，并使用加州大学欧文分校的 mHealth、PAMAP2 和智能手机数据集验证了该算法的有效性。

引用次数: 0

Decomposition of pseudo-uninorms with continuous underlying functions via ordinal sum 通过序数和分解具有连续基础函数的伪无穷级数

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-10-22 DOI: 10.1016/j.ins.2024.121573

Juraj Kalafut , Andrea Mesiarová-Zemánková

The decomposition of all pseudo-uninorms with continuous underlying functions, defined on the unit interval, via Clifford's ordinal sum is described. It is shown that each such pseudo-uninorm can be decomposed into representable and trivial semigroups, and special semigroups defined on two points, where the corresponding semigroup operation is the projection to one of the coordinates. Linear orders, for which the ordinal sum of such semigroups yields a pseudo-uninorm, are also characterized.

本文描述了通过克利福德序数和对所有在单位区间上定义的具有连续底函数的伪无穷期的分解。结果表明，每一个这样的伪不等式都可以分解为可表示的三元半群，以及定义在两点上的特殊半群，其中相应的半群运算是对其中一个坐标的投影。此外，还描述了线性阶，对于线性阶，这些半群的序和产生一个伪统一矩。

引用次数: 0

Improving two-dimensional linear discriminant analysis with L1 norm for optimizing EEG signal 利用 L1 准则改进二维线性判别分析，优化脑电信号

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-10-22 DOI: 10.1016/j.ins.2024.121585

Bin Lu , Fuwang Wang , Junxiang Chen , Guilin Wen , Rongrong Fu

Dimensionality reduction is a critical factor in processing high-dimensional datasets. The L1 norm-based Two-Dimensional Linear Discriminant Analysis (L1-2DLDA) is widely used for this purpose, but it remains sensitive to outliers and classes with large deviations, which deteriorates its performance. To address this limitation, the present study proposed Pairwise Sample Distance Two-Dimensional Linear Discriminant Analysis (PSD2DLDA), a novel method that modeled L1-2DLDA using pair-wise sample distances. To improve computational effectiveness, this study also introduced a streamlined variant, Pairwise Class Mean Distance Two-Dimensional Linear Discriminant Analysis (PCD2DLDA), which was based on distances between class mean pairs. Different from previous studies, this study utilized the projected sub-gradient method to optimize these two improved methods. Meanwhile, this study explored the interrelationship, limitations, and applicability of these two improved methods. The comparative experimental results on three datasets validated the outstanding performance of PSD2DLDA and PCD2DLDA methods. In particular, PSD2DLDA exhibited superior robustness compared to PCD2DLDA. Furthermore, applying these two methods to optimize electroencephalogram (EEG) signals effectively enhanced the decoding accuracy of motor imagery neural patterns, which offered a promising strategy for optimizing EEG signals processing in brain-computer interface (BCI) applications.

降维是处理高维数据集的一个关键因素。基于 L1 准则的二维线性判别分析（L1-2DLDA）在这方面得到了广泛应用，但它对异常值和偏差较大的类仍然很敏感，从而降低了其性能。针对这一局限性，本研究提出了成对样本距离二维线性判别分析（PSD2DLDA），这是一种利用成对样本距离对 L1-2DLDA 进行建模的新方法。为了提高计算效率，本研究还引入了一种基于类均值对之间距离的简化变体--成对类均值距离二维线性判别分析（PCD2DLDA）。与以往研究不同的是，本研究利用投影子梯度法对这两种改进方法进行了优化。同时，本研究探讨了这两种改进方法的相互关系、局限性和适用性。三个数据集的对比实验结果验证了 PSD2DLDA 和 PCD2DLDA 方法的卓越性能。特别是，与 PCD2DLDA 相比，PSD2DLDA 表现出更高的鲁棒性。此外，应用这两种方法优化脑电图（EEG）信号，有效提高了运动图像神经模式的解码精度，为优化脑机接口（BCI）应用中的脑电信号处理提供了一种前景广阔的策略。

{"title":"Improving two-dimensional linear discriminant analysis with L1 norm for optimizing EEG signal","authors":"Bin Lu , Fuwang Wang , Junxiang Chen , Guilin Wen , Rongrong Fu","doi":"10.1016/j.ins.2024.121585","DOIUrl":"10.1016/j.ins.2024.121585","url":null,"abstract":"<div><div>Dimensionality reduction is a critical factor in processing high-dimensional datasets. The L1 norm-based Two-Dimensional Linear Discriminant Analysis (L1-2DLDA) is widely used for this purpose, but it remains sensitive to outliers and classes with large deviations, which deteriorates its performance. To address this limitation, the present study proposed Pairwise Sample Distance Two-Dimensional Linear Discriminant Analysis (PSD2DLDA), a novel method that modeled L1-2DLDA using pair-wise sample distances. To improve computational effectiveness, this study also introduced a streamlined variant, Pairwise Class Mean Distance Two-Dimensional Linear Discriminant Analysis (PCD2DLDA), which was based on distances between class mean pairs. Different from previous studies, this study utilized the projected sub-gradient method to optimize these two improved methods. Meanwhile, this study explored the interrelationship, limitations, and applicability of these two improved methods. The comparative experimental results on three datasets validated the outstanding performance of PSD2DLDA and PCD2DLDA methods. In particular, PSD2DLDA exhibited superior robustness compared to PCD2DLDA. Furthermore, applying these two methods to optimize electroencephalogram (EEG) signals effectively enhanced the decoding accuracy of motor imagery neural patterns, which offered a promising strategy for optimizing EEG signals processing in brain-computer interface (BCI) applications.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"690 ","pages":"Article 121585"},"PeriodicalIF":8.1,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538694","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}

引用次数: 0

Efficiency analysis in bi-level on fuzzy input and output 关于模糊输入和输出的双层效率分析

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-10-22 DOI: 10.1016/j.ins.2024.121551

Kh. Ghaziyani , F. Hosseinzadeh Lotfi , Sohrab Kordrostami , Alireza Amirteimoori

To enhance the conventional framework of data envelope analysis (DEA), a novel hybrid bi-level model is proposed, integrating fuzzy logic with triangular fuzzy numbers to effectively address data uncertainty. This model innovatively departs from the traditional DEA’s ’black box’ approach by incorporating inter-organizational relationships and the internal dynamics of decision-making units (DMUs). Utilizing a modified Russell’s method, it provides a nuanced efficiency analysis in scenarios of ambiguous data. The study aims to enhance the accuracy and applicability of Data Envelopment Analysis in uncertain data environments. To achieve this, a novel hybrid bi-level model integrating fuzzy logic is presented. Validated through a case study involving 15 branches of a private Iranian bank, the model demonstrates improved accuracy in efficiency assessments and paves the way for future research in operational systems uncertainty management. The results indicated that, among the 15 branches of a private Iranian bank analyzed for the year 2022, branches 1, 10, and 11 demonstrated leader-level efficiency, while branch 3 exhibited follower-level efficiency, and branch 1 achieved overall efficiency. These branches attained an efficiency rating of

E^{+ +}

, signifying a high level of efficiency within the model’s parameters.

为了改进传统的数据包络分析（DEA）框架，我们提出了一种新颖的混合双层模型，将模糊逻辑与三角模糊数相结合，以有效解决数据的不确定性问题。该模型创新性地摆脱了传统 DEA 的 "黑箱 "方法，纳入了组织间关系和决策单元（DMU）的内部动态。利用改进的罗素方法，该模型可在数据模糊的情况下提供细致入微的效率分析。本研究旨在提高数据包络分析法在不确定数据环境中的准确性和适用性。为此，研究提出了一种融合模糊逻辑的新型混合双层模型。通过对伊朗一家私人银行的 15 家分行进行案例研究验证，该模型提高了效率评估的准确性，并为运营系统不确定性管理的未来研究铺平了道路。结果表明，在分析的伊朗一家私营银行的 15 家分行中，2022 年，1、10 和 11 分行的效率达到了领导者水平，3 分行的效率达到了追随者水平，1 分行的效率达到了整体水平。这些分行的效率评级为 E++，表明在模型参数范围内具有较高的效率水平。

{"title":"Efficiency analysis in bi-level on fuzzy input and output","authors":"Kh. Ghaziyani , F. Hosseinzadeh Lotfi , Sohrab Kordrostami , Alireza Amirteimoori","doi":"10.1016/j.ins.2024.121551","DOIUrl":"10.1016/j.ins.2024.121551","url":null,"abstract":"<div><div>To enhance the conventional framework of data envelope analysis (DEA), a novel hybrid bi-level model is proposed, integrating fuzzy logic with triangular fuzzy numbers to effectively address data uncertainty. This model innovatively departs from the traditional DEA’s ’black box’ approach by incorporating inter-organizational relationships and the internal dynamics of decision-making units (DMUs). Utilizing a modified Russell’s method, it provides a nuanced efficiency analysis in scenarios of ambiguous data. The study aims to enhance the accuracy and applicability of Data Envelopment Analysis in uncertain data environments. To achieve this, a novel hybrid bi-level model integrating fuzzy logic is presented. Validated through a case study involving 15 branches of a private Iranian bank, the model demonstrates improved accuracy in efficiency assessments and paves the way for future research in operational systems uncertainty management. The results indicated that, among the 15 branches of a private Iranian bank analyzed for the year 2022, branches 1, 10, and 11 demonstrated leader-level efficiency, while branch 3 exhibited follower-level efficiency, and branch 1 achieved overall efficiency. These branches attained an efficiency rating of <span><math><mrow><msup><mi>E</mi><mrow><mo>+</mo><mo>+</mo></mrow></msup></mrow></math></span>, signifying a high level of efficiency within the model’s parameters.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"690 ","pages":"Article 121551"},"PeriodicalIF":8.1,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530615","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}

引用次数: 0

GKF-PUAL: A group kernel-free approach to positive-unlabeled learning with variable selection GKF-PUAL：带变量选择的无组核正向无标记学习方法

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-10-22 DOI: 10.1016/j.ins.2024.121574

Xiaoke Wang , Rui Zhu , Jing-Hao Xue

Variable selection is important for classification of data with many irrelevant predicting variables, but it has not yet been well studied in positive-unlabeled (PU) learning, where classifiers have to be trained without labelled-negative instances. In this paper, we propose a group kernel-free PU classifier with asymmetric loss (GKF-PUAL) to achieve quadratic PU classification with group-lasso regularisation embedded for variable selection. We also propose a five-block algorithm to solve the optimization problem of GKF-PUAL. Our experimental results reveal the superiority of GKF-PUAL in both PU classification and variable selection, improving the baseline PUAL by more than 10% in F1-score across four benchmark datasets and removing over 70% of irrelevant variables on six benchmark datasets. The code for GKF-PUAL is at https://github.com/tkks22123/GKF-PUAL.

变量选择对于具有许多不相关预测变量的数据分类非常重要，但在正向无标记（PU）学习中还没有得到很好的研究，在这种学习中，分类器必须在没有标记负实例的情况下进行训练。在本文中，我们提出了一种具有非对称损失的无组核 PU 分类器（GKF-PUAL），通过嵌入用于变量选择的组-拉索正则化来实现二次 PU 分类。我们还提出了一种五块算法来解决 GKF-PUAL 的优化问题。我们的实验结果表明，GKF-PUAL 在 PU 分类和变量选择方面都具有优越性，在四个基准数据集上的 F1 分数比基准 PUAL 提高了 10%以上，并在六个基准数据集上去除了 70% 以上的无关变量。GKF-PUAL 的代码见 https://github.com/tkks22123/GKF-PUAL。

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Information Sciences

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀