Search

The neurodegenerative disorder known as Parkinson's disease (PD) affects many people. The objective of this investigation was to examine the relationship between immune system infiltration, ATP-binding cassette transporter subfamily A member 7 (ABCA7) and TBL2 as well as potential therapeutic targets for the identification of PD associated to endoplasmic reticulum (ER) stress. First, we obtained PD data through GEO and divided it into two sets: a training set (GSE8397) plus a set for validation (GSE7621). Functional enrichment analysis was performed on a set of DEGs that overlapped with genes involved in endoplasmic reticulum stress. To identify genes of PD linked with endoplasmic reticulum stress, we employed random forest (RF) along with the least absolute shrinkage and selection operator (LASSO) logistic regression. Spearman's rank correlation analysis was then used to find associations among diagnostic markers with immune cell penetration. A grand total of 2 stress-related endoplasmic reticulum signature transcripts were identified. ABCA7 and TBL2 were shown to have diagnostic potential for PD and immune infiltrating cells have a role in the etiology of the disease. Additionally, resting CD4 memory, plasma cells, and NK cells overall exhibited positive associations with ABCA7, whereas triggered macrophages, T cells with active CD4 memory, activating NK cells, T cells with activated CD4 naive, engaged NK cells, and neutrophils all had adverse interactions with ABCA7. Overall, ABCA7 together with TBL2 have diagnostic utility for PD, and several types of immune cells, especially macrophages, may be involved in the development and progression of the disease., (© 2024. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

We develop a machine learning (ML) model using electrocardiography (ECG) to predict myocardial blood flow reserve (MFR) and assess its prognostic value for major adverse cardiovascular events (MACEs). Using 3,639 ECG-positron emission tomography (PET) and 17,649 ECG-single-photon emission computed tomography (SPECT) data pairs, the ML model is trained with a swarm intelligence approach and support vector regression (SVR). The model achieves a receiver-operator curve (ROC) area under the curve (AUC) of 0.83, with a sensitivity and specificity of 0.75. An ECG-MFR value below 2 is significantly associated with MACE, with hazard ratios (HRs) of 3.85 and 3.70 in the discovery and validation phases, respectively. The model's C-statistic is 0.76, with a net reclassification improvement (NRI) of 0.35. Validated in an independent cohort, the ML model using ECG data offers superior MACE prediction compared to baseline clinical models, highlighting its potential for risk stratification in patients with coronary artery disease (CAD) using the accessible 12-lead ECG., Competing Interests: Declaration of interests The authors declare no competing interests., (Copyright © 2024 The Author(s). Published by Elsevier Inc. All rights reserved.)

With the direct input-output connections, a random vector functional link (RVFL) network is a simple and effective learning algorithm for single-hidden layer feedforward neural networks (SLFNs). RVFL is a universal approximator for continuous functions on compact sets with fast learning property. Owing to its simplicity and effectiveness, RVFL has attracted significant interest in numerous real-world applications. In reality, the performance of RVFL is often challenged by randomly assigned network parameters. In this paper, we propose a novel unsupervised network parameter learning method for RVFL, named sparse pre-trained random vector functional link (SP-RVFL for short) network. The proposed SP-RVFL uses a sparse autoencoder with ℓ 1 -norm regularization to adaptively learn superior network parameters for specific learning tasks. By doing so, the learned network parameters in SP-RVFL are embedded with the valuable information of input data, which alleviate the randomly generated parameter issue and improve the algorithmic performance. Experiments and comparisons on 16 diverse benchmarks from different domains confirm the effectiveness of the proposed SP-RVFL. The corresponding results also demonstrate that RVFL outperforms extreme learning machine (ELM)., (Copyright © 2019 Elsevier Ltd. All rights reserved.)

Based on the fast kurtogram, many previous studies have focused on frequency band selection (FBS) affected by interference due to impulsive noise and varying speed conditions. Recently, machine learning algorithms have been considered effective for bearing diagnosis. However, most of these methods are supervised learning and thus suffer from data imbalance in the practical applications. This study proposes a semi-supervised learning indicator called outlier rate diagram (ORgram) based on the signal changes before and after bearing damage. ORgram is suitable for impulsive noise and varying speed conditions. First, the healthy bearing data is segmented by rotational speed and modeled with one-class support vector machine (SVM) for each frequency band. As bearing defects sprout, the defect response will produce the highest outlier rate in the informative frequency band (IFB). After selecting the IFB, techniques such as envelope analysis and order tracking are used to identify damaged bearing components for an alarm to reduce the losses caused by unplanned downtime. [ABSTRACT FROM AUTHOR]

Simple Summary: This study presented an artificial intelligence-based classification emphasizing error identification and quantification of cellularity and nuclear morphological features in digital pathological images of common astrocytic tumors. The identification of incorrect predictions was essential for the subsequent development of better techniques. Quantifying cellularity and nuclear morphological features brought deeper insights into neoplastic morphology and paved the way for further development of a scoring system for objective classification and precision diagnosis to improve interobserver variations. Interobserver variations in the pathology of common astrocytic tumors impact diagnosis and subsequent treatment decisions. This study leveraged a residual neural network-50 (ResNet-50) in digital pathological images of diffuse astrocytoma, anaplastic astrocytoma, and glioblastoma to recognize characteristic pathological features and perform classification at the patch and case levels with identification of incorrect predictions. In addition, cellularity and nuclear morphological features, including axis ratio, circularity, entropy, area, irregularity, and perimeter, were quantified via a hybrid task cascade (HTC) framework and compared between different characteristic pathological features with importance weighting. A total of 95 cases, including 15 cases of diffuse astrocytoma, 11 cases of anaplastic astrocytoma, and 69 cases of glioblastoma, were collected in Taiwan Hualien Tzu Chi Hospital from January 2000 to December 2021. The results revealed that an optimized ResNet-50 model could recognize characteristic pathological features at the patch level and assist in diagnosis at the case level with accuracies of 0.916 and 0.846, respectively. Incorrect predictions were mainly due to indistinguishable morphologic overlap between anaplastic astrocytoma and glioblastoma tumor cell area, zones of scant vascular lumen with compact endothelial cells in the glioblastoma microvascular proliferation area mimicking the glioblastoma tumor cell area, and certain regions in diffuse astrocytoma with too low cellularity being misrecognized as the glioblastoma necrosis area. Significant differences were observed in cellularity and each nuclear morphological feature among different characteristic pathological features. Furthermore, using the extreme gradient boosting (XGBoost) algorithm, we found that entropy was the most important feature for classification, followed by cellularity, area, circularity, axis ratio, perimeter, and irregularity. Identifying incorrect predictions provided valuable feedback to machine learning design to further enhance accuracy and reduce errors in classification. Moreover, quantifying cellularity and nuclear morphological features with importance weighting provided the basis for developing an innovative scoring system to achieve objective classification and precision diagnosis among common astrocytic tumors. [ABSTRACT FROM AUTHOR]

In multiple-instance learning (MIL), the existing bag encoding and attention-based pooling approaches assume that the instances in the bag have no relationship among them. This assumption is unsuited, as the instances in the bags are rarely independent in diverse MIL applications. In contrast, the instance relationship assumption-based techniques incorporate the instance relationship information in the classification process. However, in MIL, the bag composition process is complicated, and it may be possible that instances in one bag are related and instances in another bag are not. In present MIL algorithms, this relationship assumption is not explicitly modeled. The learning algorithm is trained based on one of two relationship assumptions (whether instances in all bags have a relationship or not). Hence, it is essential to model the assumption of instance relationships in the bag classification process. This paper proposes a robust approach that generates vector representation for the bag for both assumptions and the representation selection process to determine whether to consider the instances related or unrelated in the bag classification process. This process helps to determine the essential bag representation vector for every individual bag. The proposed method utilizes attention pooling and vision transformer approaches to generate bag representation vectors. Later, the representation selection subnetwork determines the vector representation essential for bag classification in an end-to-end trainable manner. The generalization abilities of the proposed framework are demonstrated through extensive experiments on several benchmark datasets. The experiments demonstrate that the proposed approach outperforms other state-of-the-art MIL approaches in bag classification. [ABSTRACT FROM AUTHOR]

In this paper, we study numerical solution of ruin probability of continuous time model. We develop an effective optimal adaptive particle swarm optimization-triangular neural network (PSO-TNN), which consists of three parts: particle swarm optimization algorithm (PSO) improved trigonometric function, extreme learning machine algorithm with initial conditions (IELM) and improved reduction algorithm. The results obtained that PSO-TNN is superior to triangular neural network (TNN) and physics-informed neural networks (PINNs), and PSO is superior to Aquila Optimizer (AO), Smell Agent Optimization (SAO), African vultures optimization algorithm (AVOA), Arithmetic optimization algorithm (AOA) in the optimization of neural network. Because the relationship between the number of neural networks and the mean square error is uncertain, we propose the adaptive reduction algorithm (AR). Through the comparison of numerical solutions with the analytical solutions and traditional numerical solutions, the PSO-TNN algorithm clearly reduced the mean square error and relative error. The PSO-TNN algorithm shows a clear improvement in terms of accuracy and overall efficiency. [ABSTRACT FROM AUTHOR]

Identifying and managing osteosarcoma pose significant challenges, especially in resource-constrained developing nations. Advanced diagnostic methods involve isolating the nucleus from cancer cells for comprehensive analysis. However, two main challenges persist: mitigating image noise during the capture and transmission of cellular sections, and providing an efficient, accurate, and cost-effective solution for cell nucleus segmentation. To tackle these issues, we introduce the Twin-Self and Cross-Attention Vision Transformer (TSCA-ViT). This pioneering AI-based system employs a directed filtering algorithm for noise reduction and features an innovative transformer architecture with a twin attention mechanism for effective segmentation. The model also incorporates cross-attention-enabled skip connections to augment spatial information. We evaluated our method on a dataset of 1000 osteosarcoma pathology slide images from the Second People's Hospital of Huaihua, achieving a remarkable average precision of 97.7%. This performance surpasses traditional methodologies. Furthermore, TSCA-ViT offers enhanced computational efficiency owing to its fewer parameters, which results in reduced time and equipment costs. These findings underscore the superior efficacy and efficiency of TSCA-ViT, offering a promising approach for addressing the ongoing challenges in osteosarcoma diagnosis and treatment, particularly in settings with limited resources. [ABSTRACT FROM AUTHOR]

Hyperparameter optimization plays a significant role in the overall performance of machine learning algorithms. However, the computational cost of algorithm evaluation can be extremely high for complex algorithm or large dataset. In this paper, we propose a model-based reinforcement learning with experience variable and meta-learning optimization method to speed up the training process of hyperparameter optimization. Specifically, an RL agent is employed to select hyperparameters and treat the k-fold cross-validation result as a reward signal to update the agent. To guide the agent's policy update, we design an embedding representation called "experience variable" and dynamically update it during the training process. Besides, we employ a predictive model to predict the performance of machine learning algorithm with the selected hyperparameters and limit the model rollout in short horizon to reduce the impact of the inaccuracy of the model. Finally, we use the meta-learning technique to pre-train the model for fast adapting to a new task. To prove the advantages of our method, we conduct experiments on 25 real HPO tasks and the experimental results show that with the limited computational resources, the proposed method outperforms the state-of-the-art Bayesian methods and evolution method. [ABSTRACT FROM AUTHOR]

The identification of biomarkers plays a crucial role in personalized medicine, both in the clinical and research settings. However, the contrast between predictive and prognostic biomarkers can be challenging due to the overlap between the two. A prognostic biomarker predicts the future outcome of cancer, regardless of treatment, and a predictive biomarker predicts the effectiveness of a therapeutic intervention. Misclassifying a prognostic biomarker as predictive (or vice versa) can have serious financial and personal consequences for patients. To address this issue, various statistical and machine learning approaches have been developed. The aim of this study is to present an in-depth analysis of recent advancements, trends, challenges, and future prospects in biomarker identification. A systematic search was conducted using PubMed to identify relevant studies published between 2017 and 2023. The selected studies were analyzed to better understand the concept of biomarker identification, evaluate machine learning methods, assess the level of research activity, and highlight the application of these methods in cancer research and treatment. Furthermore, existing obstacles and concerns are discussed to identify prospective research areas. We believe that this review will serve as a valuable resource for researchers, providing insights into the methods and approaches used in biomarker discovery and identifying future research opportunities. [ABSTRACT FROM AUTHOR]

Traditional congestion control protocols may fail to achieve consistently-high performance over a wide range of networking environments as their hardwired policies are optimized over specific network conditions. In this paper, we depart from conventional wisdom and propose Glider, a new congestion control protocol that uses deep reinforcement learning to be more versatile and adaptive to dynamic environments. In particular, Glider uses a framework based on Deep Q-Network, that a sender keeps adapting its congestion control strategies by continuously interacting with the network environment. In addition, the sender constantly sends data, making it challenging to apply reinforcement learning algorithms that require step-by-step state computation to congestion control. Therefore, we design a Dynamic Bisection Division Algorithm (DBDA) to discretize the packet transmission process into steps to ensure Glider's feasibility on congestion control. We have used an extensive array of experiments on Pantheon to show that Glider can adapt well to varying buffer sizes and is resilient to random loss. Moreover, on wide-area inter-data center links, it can achieve 6.4 × and 1.4 × higher throughput than TCP CUBIC and BBR, respectively, and comparable performance as other learning-based congestion control protocols in the literature. [ABSTRACT FROM AUTHOR]

Network embedding aims to generate an embedding for each node in a network, which facilitates downstream machine learning tasks such as node classification and link prediction. Current work mainly focuses on transductive network embedding, i.e. generating fixed node embeddings, which is not suitable for real-world applications. This paper proposes a novel continual temporal network embedding method called ConMNCI by mining neighborhood and community influences inductively. We propose an aggregator function that integrates neighborhood influence with community influence to generate node embeddings at any time, and introduce the idea from continual learning to enhance inductive learning. We conduct extensive experiments on several real-world datasets and compare ConMNCI with several state-of-the-art baseline methods on various tasks, including node classification and network visualization. The experimental results show that ConMNCI significantly outperforms the state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

Background: Psychogenic erectile dysfunction (pED) patients who are under their 40s in China consist of a major component of erectile dysfunction. Existing neuroimaging studies have demonstrated that pED is a functional disorder with aberrant neural representations on the local level, the regional level, and the global level, respectively. Therefore, it is reasonable to incorporate brain information from all these levels simultaneously into consideration when identifying neuroimaging biomarkers for pED. However, no such endeavors have been made in previous studies to fully disclose the central mechanism of pED. Method: To incorporate multi‐level brain features to fully explore the neural representation of pED, a novel machine learning framework was proposed in the current study. Specifically, we used amplitude of low‐frequency fluctuation, regional homogeneity, and degree centrality as indices for local, regional, and global brain activity, respectively. A fully data‐driven method, that is, support vector machine (SVM) with recursive feature elimination analyses, was used to investigate discriminative brain map between 48 pED patients and 39 healthy control subjects for resting state functional magnetic resonance imaging (rs‐fMRI) data. Results: By fusing multi‐level brain features, our method led to a superb classification accuracy of 95.12% between two groups. Interestingly, the right anterior cingulate gyrus and the left precuneus showed abnormal representations at different levels simultaneously in pED patients, which also explicated highest discriminative power between groups. Moreover, the right insular, the left fusiform gyrus, the right inferior temporal gyrus, the right superior frontal gyrus, the right precentral gyrus, the bilateral parahippocampal gyrus, and the bilateral inferior frontal gyrus were discriminative for pED. Also, correlation analysis explicated that several core brain regions were associated with the clinical manifestations in pED patients. Conclusion: This is one of the first study investigating brain alterations on different levels simultaneously in pED patients. Our results suggested that pED involves multi‐level aberrant brain representations in multi‐dimensional neurobehavioral components, which closely interrelated with cognitive and psychosocial factors, that is, attention, appraisal, emotion, and sensorimotor. Our findings are likely to help foster new insights into the pathophysiological mechanisms of pED and the aberrant brain regions may serve as potential therapeutic targets for targeted therapy for brain. [ABSTRACT FROM AUTHOR]

Coronary artery disease (CAD) is a global health issue. Lipid peroxidation produces various by-products that associate with CAD, such as 4-hydroxynonenal (HNE) and malondialdehyde (MDA). The autoantibodies against HNE and MDA-modified peptides may be useful in the diagnosis of CAD. This study included 41 healthy controls (HCs) and 159 CAD patients with stenosis rates of <30%, 30–70%, and >70%. The plasma level of autoantibodies against four different unmodified and HNE-modified peptides were measured in this study, including CFAH1211–1230, HPT78–108, IGKC2–19, and THRB328–345. Furthermore, feature ranking, feature selection, and machine learning models have been utilized to exploit the diagnostic performance. Also, we combined autoantibodies against MDA and HNE-modified peptides to improve the models' performance. The eXtreme Gradient Boosting (XGBoost) model received a sensitivity of 78.6% and a specificity of 90.4%. Our study demonstrated the combination of autoantibodies against oxidative modification may improve the model performance. [ABSTRACT FROM AUTHOR]

Radiological imaging is an integral component of cancer care, including diagnosis, staging, and treatment response monitoring. It contains rich information about tumor phenotypes that are governed not only by cancer cellintrinsic biological processes but also by the tumor microenvironment, such as the composition and function of tumor-infiltrating immune cells. By analyzing the radiological scans using a quantitative radiomics approach, robust relations between specific imaging and molecular phenotypes can be established. Indeed, a number of studies have demonstrated the feasibility of radiogenomics for predicting intrinsic molecular subtypes and gene expression signatures in breast cancer based on MRI. In parallel, promising results have been shown for inferring the amount of tumor-infiltrating lymphocytes, a key factor for the efficacy of cancer immunotherapy, from standard-of-care radiological images. Compared with the biopsy-based approach, radiogenomics offers a unique avenue to profile the molecular makeup of the tumor and immune microenvironment as well as its evolution in a noninvasive and holistic manner through longitudinal imaging scans. Here, we provide a systematic review of the state of the art radiogenomics studies in the era of immunotherapy and discuss emerging paradigms and opportunities in AI and deep learning approaches. These technical advances are expected to transform the radiogenomics field, leading to the discovery of reliable imaging biomarkers. This will pave the way for their clinical translation to guide precision cancer therapy. [ABSTRACT FROM AUTHOR]

Osteosarcoma is a bone tumor which is malignant. There are many difficulties when doctors manually identify patients' MRI images to complete the diagnosis. The osteosarcoma in MRI images is very complex, making its recognition and segmentation resource-consuming. Automatic osteosarcoma area segmentation can solve these problems to a certain extent. However, existing studies usually fail to balance segmentation accuracy and efficiency. They are either sensitive to noise with low accuracy or time-consuming. So we propose an auxiliary segmentation method based on denoising and local enhancement. The method first optimizes the osteosarcoma images, including removing noise using the Edge Enhancement based Transformer for Medical Image Denoising (Eformer) and using a non-parameter method to localize and enhance the tumor region in MRI images. Osteosarcoma was then segmented by Deep Feature Aggregation for Real-Time Semantic Segmentation (DFANet). Our method achieves impressive segmentation accuracy. Moreover, it is efficient in both time and space. It can provide information about the location and extent of the osteosarcoma as a basis for further diagnosis. [ABSTRACT FROM AUTHOR]

Heterogeneous Graph Neural Networks (HGNNs) have demonstrated significant success in capturing complex interactions within heterogeneous graphs to learn graph representations. However, designing effective HGNN architecture is a challenging task that demands substantial domain knowledge and human effort. Fortunately, the advent of Heterogeneous Graph Architecture Search (HGNAS) has automated this process and yielded networks surpassing those designed by humans. Nonetheless, conventional HGNAS approaches are limited in their ability to generalize to unseen or diverse task types. To address these limitations, we propose an efficient method called Contrastive Meta-reinforcement learning-based Heterogeneous Graph Neural Architecture Search (CM-HGNAS). Our approach aims to produce high-performance networks tailored to different types of tasks. Firstly, we use gradient-based meta-learning to rapidly adapt to new tasks by leveraging the knowledge acquired from meta-training tasks. Secondly, since our meta-training tasks encompass various types of tasks, including node classification and link prediction, we employ contrastive learning to unify the evaluation metric across all tasks. This unification enhances the generalization capabilities of our model across diverse tasks. Experimental results demonstrate that our method successfully generalizes to unseen tasks and surpasses existing HGNN baselines and HGNAS techniques in terms of performance. [ABSTRACT FROM AUTHOR]

Simple Summary: Distinguishing between chronic lymphocytic leukemia (CLL), accelerated CLL (aCLL), and full-blown transformation to diffuse large B-cell lymphoma (Richter transformation; RT) has significant clinical implications. Identifying cellular phenotypes via unsupervised clustering provides the most robust analytic performance in analyzing digitized pathology slides. This study serves as a proof of concept that using an unsupervised machine learning scheme can enhance diagnostic accuracy. Identifying the progression of chronic lymphocytic leukemia (CLL) to accelerated CLL (aCLL) or transformation to diffuse large B-cell lymphoma (Richter transformation; RT) has significant clinical implications as it prompts a major change in patient management. However, the differentiation between these disease phases may be challenging in routine practice. Unsupervised learning has gained increased attention because of its substantial potential in data intrinsic pattern discovery. Here, we demonstrate that cellular feature engineering, identifying cellular phenotypes via unsupervised clustering, provides the most robust analytic performance in analyzing digitized pathology slides (accuracy = 0.925, AUC = 0.978) when compared to alternative approaches, such as mixed features, supervised features, unsupervised/mixed/supervised feature fusion and selection, as well as patch-based convolutional neural network (CNN) feature extraction. We further validate the reproducibility and robustness of unsupervised feature extraction via stability and repeated splitting analysis, supporting its utility as a diagnostic aid in identifying CLL patients with histologic evidence of disease progression. The outcome of this study serves as proof of principle using an unsupervised machine learning scheme to enhance the diagnostic accuracy of the heterogeneous histology patterns that pathologists might not easily see. [ABSTRACT FROM AUTHOR]

[Display omitted] • A context helps the agent to learn knowledge from previous tasks. • A simple multi-task objective meta-training procedure is proposed to run faster. • A quadratic penalty technique is used to preserve the historical experience. • A predictive model is applied to further accelerate the adaptation phase. In this paper, we present a context-based meta-reinforcement learning approach to tackle the challenging data-inefficiency problem of Hyperparameter Optimization (HPO). Specifically, we design an agent which sequentially selects hyperparameters to maximize the expected accuracy of the machine learning algorithm on the validation set. First, we design a context variable that learns the latent embedding of prior experience, and the agent can solve the new tasks efficiently conditioned on it. Second, we employ a multi-task objective method that aims to maximize the average reward across all the meta-training tasks to meta-train the agent. Third, in the adaptation phase, we introduce a quadratic penalty technique to achieve better performance of the agent. Finally, to further improve the efficiency in the adaptation phase, we use a predictive model to evaluate the accuracy of machine learning algorithm instead of training it. We evaluate our approach on 18 real-world datasets and the results demonstrate that our approach outperforms other state-of-the-art optimization methods in terms of test set accuracy and runtime performance. [ABSTRACT FROM AUTHOR]

Vehicular ad hoc networks (VANETs) and the services they support are an essential part of intelligent transportation. Through physical technologies, applications, protocols, and standards, they help to ensure traffic moves efficiently and vehicles operate safely. This article surveys the current state of play in VANETs development. The summarized and classified include the key technologies critical to the field, the resource-management and safety applications needed for smooth operations, the communications and data transmission protocols that support networking, and the theoretical and environmental constructs underpinning research and development, such as graph neural networks and the Internet of Things. Additionally, we identify and discuss several challenges facing VANETs, including poor safety, poor reliability, non-uniform standards, and low intelligence levels. Finally, we touch on hot technologies and techniques, such as reinforcement learning and 5G communications, to provide an outlook for the future of intelligent transportation systems. [ABSTRACT FROM AUTHOR]

Background: It is difficult to identify pancreatic ductal adenocarcinoma (PDAC) and mass-forming chronic pancreatitis (MFCP) lesions through conventional CT or MR examination. As an innovative image analysis method, radiomics may possess potential clinical value in identifying PDAC and MFCP. To develop and validate radiomics models derived from multiparametric MRI to distinguish pancreatic ductal adenocarcinoma (PDAC) and mass-forming chronic pancreatitis (MFCP) lesions. Methods: This retrospective study included 119 patients from two independent institutions. Patients from one institution were used as the training cohort (51 patients with PDAC and 13 patients with MFCP), and patients from the other institution were used as the testing cohort (45 patients with PDAC and 10 patients with MFCP). All the patients had pathologically confirmed results, and preoperative MRI was performed. Four feature sets were extracted from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and the artery (A) and portal (P) phases of dynamic contrast-enhanced MRI, and the corresponding radiomics models were established. Several clinical characteristics were used to discriminate PDAC and MFCP lesions, and clinical model was established. The results of radiologists' evaluation were compared with pathology and radiomics models. Univariate analysis and the least absolute shrinkage and selection operator algorithm were performed for feature selection, and a support vector machine was used for classification. The receiver operating characteristic (ROC) curve was applied to assess the model discrimination. Results: The areas under the ROC curves (AUCs) for the T1WI, T2WI, A and, P and clinical models were 0.893, 0.911, 0.958, 0.997 and 0.516 in the primary cohort, and 0.882, 0.902, 0.920, 0.962 and 0.649 in the validation cohort, respectively. All radiomics models performed better than clinical model and radiologists' evaluation both in the training and testing cohorts by comparing the AUC of various models, all P<0.050. Good calibration was achieved. Conclusions: The radiomics models based on multiparametric MRI have the potential ability to classify PDAC and MFCP lesions. [ABSTRACT FROM AUTHOR]

Hyperparameter tuning is critical for the performance of machine learning algorithms. However, a noticeable limitation is the high computational cost of algorithm evaluation for complex models or for large datasets, which makes the tuning process highly inefficient. In this paper, we propose a novel model-based method for efficient hyperparameter optimization. Firstly, we frame this optimization process as a reinforcement learning problem and then employ an agent to tune hyperparameters sequentially. In addition, a model that learns how to evaluate an algorithm is used to speed up the training. However, model inaccuracy is further exacerbated by long-term use, resulting in collapse performance. We propose a novel method for controlling the model use by measuring the impact of the model on the policy and limiting it to a proper range. Thus, the horizon of the model use can be dynamically adjusted. We apply the proposed method to tune the hyperparameters of the extreme gradient boosting and convolutional neural networks on 101 tasks. The experimental results verify that the proposed method achieves the highest accuracy on 86.1% of the tasks, compared with other state-of-the-art methods and the average ranking of runtime is significant lower than all methods by using the predictive model. [ABSTRACT FROM AUTHOR]

Data stream classification becomes a promising prediction work with relevance to many practical environments. However, under the environment of concept drift and noise, the research of data stream classification faces lots of challenges. Hence, a new incremental ensemble model is presented for classifying nonstationary data streams with noise. Our approach integrates three strategies: incremental learning to monitor and adapt to concept drift; ensemble learning to improve model stability; and a microclustering procedure that distinguishes drift from noise and predicts the labels of incoming instances via majority vote. Experiments with two synthetic datasets designed to test for both gradual and abrupt drift show that our method provides more accurate classification in nonstationary data streams with noise than the two popular baselines. [ABSTRACT FROM AUTHOR]

We considers a distributionally robust optimization problem when the ambiguity set specifies the support as well as the mean and the covariance matrix of the uncertain parameters. After deriving a general deterministic reformulation for the distributionally robust optimization problem, we obtain tractable optimization reformulations when the support set is the whole space and when it is a convex polyhedral set. A hybrid method of Gurobi and a smoothing Newton conjugate gradient method is suggested to solve the tractable optimization problems and numerical results of the hybrid method for solving an illustrative example are reported. [ABSTRACT FROM AUTHOR]

Multi-instance learning (MIL) is commonly used to classify a set of instances, also known as a bag, where labels for the training set are only available for each bag. Many MIL methods exist, but they often suffer from high computation complexity and the key information from MIL being ignored, which deteriorates the classification performance. Recently, locality-sensitive hashing (LSH), with its high scalability, has shown the ability in enhancing MIL performance. However, for these LSH-based methods, the fixed number of bits is used to represent each projected dimension, resulting in subtle information loss and the algorithm performance reduction. In this paper, we propose a self-adaptive LSH encoding method for MIL, termed as SALE. SALE uses LSH to generate the primary batches, followed by a self-adaptive process for reconstruction. Reconstructed bags are transformed into random super histograms (RSH) using an incomplete coding method, and then weighted through a scheme that takes advantage of key instances. These weighted RSHs are used to train the learning model. SALE efficiently deals with large MIL problems, due to its low complexity and RSH’s ability to exploit key information of MIL. Experiments demonstrate SALE’s good performance compared to state-of-the-art MIL methods. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) is a popular machine learning method which can flexibly simulate the relationships of real-world classification applications. When facing problems ( i.e. , data sets) with a smaller number of samples ( i.e. , instances), ELM may often result in the overfitting trouble. In this paper, we propose a new Instance Cloned Extreme Learning Machine (IC-ELM for short) which can handle numerous different classification problems. IC-ELM uses an instance cloning method to balance the input data’s distribution and extend the training data set, which alleviates the overfitting issue and enhances the testing classification accuracy. Experiments and comparisons on 20 UCI data sets, and validations on image and text classification applications, demonstrate that IC-ELM is able to achieve superior results compared to the original ELM algorithm and its variants, as well as several other classical machine learning algorithms. [ABSTRACT FROM AUTHOR]

In distance metric learning, recent work has shown that value difference metric (VDM) with a strong attribute independence assumption outperforms other existing distance metrics. However, an open question is whether VDM with a less restrictive assumption can perform even better. Many approaches have been proposed to improve VDM by weakening the assumption. In this paper, we make a comprehensive survey on the existing improved approaches and then propose a new approach to improve VDM by attribute weighting. We name the proposed new distance function as attribute-weighted value difference metric (AWVDM). Moreover, we propose a modified attribute-weighted value difference metric (MAWVDM) by incorporating the learned attribute weights into the conditional probability estimates of AWVDM. AWVDM and MAWVDM significantly outperform VDM and inherit the computational simplicity of VDM simultaneously. Experimental results on a large number of UCI data sets validate the performance of AWVDM and MAWVDM. [ABSTRACT FROM AUTHOR]

In this paper, we combine context-based Meta-Reinforcement Learning with task-aware representation to efficiently overcome data-inefficiency and limited generalization in the hyperparameter optimization problem. First, we propose a new context-based meta-RL model that disentangles task inference and control, which improves the meta-training efficiency and accelerates the learning process for unseen tasks. Second, the task properties are inferred on-line, which includes not only the dataset representation but also the task-solving experience, thus encouraging the agent to explore in a much smarter fashion. Third, we employ amortized meta-learning to meta-train the agent, which is simple and runs faster than the gradient-based meta-training method. Experimental results suggest that our method can search for the optimal hyperparameter configuration with limited computational cost in a reasonable time. [Display omitted] • A task encoder is proposed to achieve the task inference. • The rich task-specific information allows the agent to make better decision. • An amortized meta-learning approach is proposed to accelerate the meta-training. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) is a promising model for training single-hidden layer feedforward networks (SLFNs) and has been widely used for classification. However, ELM faces the challenge of arbitrarily selected parameters, e.g. , the network weights and hidden biases. Therefore, many efforts have been made to enhance the performance of ELM, such as using evolutionary algorithms to explore promising areas of the solution space. Although evolutionary algorithms can explore promising areas of the solution space, they are not able to locate global optimum efficiently. In this paper, we present a new Memetic Algorithm (MA)-based Extreme Learning Machine (M-ELM for short). M-ELM embeds the local search strategy into the global optimization framework to obtain optimal network parameters. Experiments and comparisons on 46 UCI data sets validate the performance of M-ELM. The corresponding results demonstrate that M-ELM significantly outperforms state-of-the-art ELM algorithms. [ABSTRACT FROM AUTHOR]

Graph classification aims to learn models to classify structure data. To date, all existing graph classification methods are designed to target one single learning task and require a large number of labeled samples for learning good classification models. In reality, each real-world task may only have a limited number of labeled samples, yet multiple similar learning tasks can provide useful knowledge to benefit all tasks as a whole. In this paper, we formulate a new multi-task graph classification (MTG) problem, where multiple graph classification tasks are jointly regularized to find discriminative subgraphs shared by all tasks for learning. The niche of MTG stems from the fact that with a limited number of training samples, subgraph features selected for one single graph classification task tend to overfit the training data. By using additional tasks as evaluation sets, MTG can jointly regularize multiple tasks to explore high quality subgraph features for graph classification. To achieve this goal, we formulate an objective function which combines multiple graph classification tasks to evaluate the informativeness score of a subgraph feature. An iterative subgraph feature exploration and multi-task learning process is further proposed to incrementally select subgraph features for graph classification. Experiments on real-world multi-task graph classification datasets demonstrate significant performance gain. [ABSTRACT FROM PUBLISHER]

Classification on structure data, such as graphs, has drawn wide interest in recent years. Due to the lack of explicit features to represent graphs for training classification models, extensive studies have been focused on extracting the most discriminative subgraphs features from the training graph dataset to transfer graphs into vector data. However, such filter-based methods suffer from two major disadvantages: (1) the subgraph feature selection is separated from the model learning process, so the selected most discriminative subgraphs may not best fit the subsequent learning model, resulting in deteriorated classification results; (2) all these methods rely on users to specify the number of subgraph features K , and suboptimally specified K values often result in significantly reduced classification accuracy. In this paper, we propose a new graph classification paradigm which overcomes the above disadvantages by formulating subgraph feature selection as learning a K -dimensional feature space from an implicit and large subgraph space, with the optimal K value being automatically determined. To achieve the goal, we propose a regularized loss minimization-driven (RLMD) feature selection method for graph classification. RLMD integrates subgraph selection and model learning into a unified framework to find discriminative subgraphs with guaranteed minimum loss w.r.t . the objective function. To automatically determine the optimal number of subgraphs K from the exponentially large subgraph space, an effective elastic net and a subgradient method are proposed to derive the stopping criterion, so that K can be automatically obtained once RLMD converges. The proposed RLMD method enjoys gratifying property including proved convergence and applicability to various loss functions. Experimental results on real-life graph datasets demonstrate significant performance gain. [ABSTRACT FROM AUTHOR]

Naive Bayes (NB) is a popular machine learning tool for classification, due to its simplicity, high computational efficiency, and good classification accuracy, especially for high dimensional data such as texts. In reality, the pronounced advantage of NB is often challenged by the strong conditional independence assumption between attributes, which may deteriorate the classification performance. Accordingly, numerous efforts have been made to improve NB, by using approaches such as structure extension, attribute selection, attribute weighting, instance weighting, local learning and so on. In this paper, we propose a new Artificial Immune System (AIS) based self-adaptive attribute weighting method for Naive Bayes classification. The proposed method, namely AISWNB, uses immunity theory in Artificial Immune Systems to search optimal attribute weight values, where self-adjusted weight values will alleviate the conditional independence assumption and help calculate the conditional probability in an accurate way. One noticeable advantage of AISWNB is that the unique immune system based evolutionary computation process, including initialization, clone, section, and mutation, ensures that AISWNB can adjust itself to the data without explicit specification of functional or distributional forms of the underlying model. As a result, AISWNB can obtain good attribute weight values during the learning process. Experiments and comparisons on 36 machine learning benchmark data sets and six image classification data sets demonstrate that AISWNB significantly outperforms its peers in classification accuracy, class probability estimation, and class ranking performance. [ABSTRACT FROM AUTHOR]

This paper formulates a multi-graph learning task. In our problem setting, a bag contains a number of graphs and a class label. A bag is labeled positive if at least one graph in the bag is positive, and negative otherwise. In addition, the genuine label of each graph in a positive bag is unknown, and all graphs in a negative bag are negative. The aim of multi-graph learning is to build a learning model from a number of labeled training bags to predict previously unseen test bags with maximum accuracy. This problem setting is essentially different from existing multi-instance learning (MIL), where instances in MIL share well-defined feature values, but no features are available to represent graphs in a multi-graph bag. To solve the problem, we propose a Multi-Graph Feature based Learning ( gMGFL) algorithm that explores and selects a set of discriminative subgraphs as features to transfer each bag into a single instance, with the bag label being propagated to the transferred instance. As a result, the multi-graph bags form a labeled training instance set, so generic learning algorithms, such as decision trees, can be used to derive learning models for multi-graph classification. Experiments and comparisons on real-world multi-graph tasks demonstrate the algorithm performance. [ABSTRACT FROM AUTHOR]

Abstract: Both transcription factors (TFs) and microRNAs (miRNAs) regulate gene expression. TFs activate or suppress the initiation of the transcription process and miRNAs regulate mRNAs post-transcriptionally, thus forming a temporally ordered regulatory event. Ectopic expression of key transcriptional regulators and/or miRNAs has been shown to be involved in various tumors. Therefore, uncovering the coregulation of TFs and miRNAs in human cancers may lead to the discovery of novel therapeutics. We introduced a two-stage learning fuzzy method to model TF–miRNA coregulation using both genomic data and verified regulatory relationships. In Stage 1, a learning (adaptive) fuzzy inference system (ANFIS) combines two sequence alignment features of TF and target by learning from verified TF–target pairs into a sequence matching score. Next, a non-learning FIS incorporates a sequence alignment score and a correlation score from paired TF–target gene expression to output a Stage 1 fuzzy score to infer whether a TF–target regulation exists. For significant TF–target pairs, in Stage 2, similar to Stage 1, we first infer whether a miRNA regulates each common target by an ANFIS, which incorporates their sequences and known miRNA–target relationships to output a sequence score. Next, an FIS incorporates the Stage 1 fuzzy score, Stage 2 sequence score and gene expression correlation score of a miRNA–target pair to determine whether TF–miRNA coregulation exists. We collected 54 (8) TF–miRNA–target triples validated in ER-positive (ER-negative) breast cancer cell lines in the same article, and they were used as positives. Negative examples were constructed for Stage 1 (Stage 2) by pairing TFs (miRNAs) with human housekeeping genes found in the literature; both positives and negatives were used to train ANFISs in the training step. This two-stage fizzy algorithm was applied to predict 54 (8) TF–miRNA coregulation triples in ER-positive (ER-negative) human breast cancer cell lines, and resulted in true-positive rates of 0.55 (0.74) and 0.57 (0.75) using 3-fold and n-fold cross validations (CVs), respectively. False-positive rate bound was 0.07 (0.13) for ER-positive (ER-negative) breast cancer using both 3-fold and n-fold CVs. Interestingly, among the 62 coregulatroy triples from ER-positive/negative breast cancer cells, about 72% have TF- and coregulatory miRNA expression simultaneously greater or less than the corresponding medians, while in the remaining 28% of TFs and their coregulatory miRNAs are conversely expressed. The proposed fuzzy algorithm performed well in identification of TF–miRNA coregulation triples in human breast cancer. After being trained by the corresponding verified coregulatory triples and genomic data, this algorithm can be applied to uncover novel coregulation in other cancers in the future. [Copyright &y& Elsevier]