Cluster-based Classification Research Articles

Vortex-Induced Vibration Performance Analysis of Long-Span Sea-Crossing Bridges Using Unsupervised Clustering

Vortex-induced vibration is a type of wind-induced vibration occurring frequently in large-span sea-crossing bridges under relatively low wind speeds, posing a threat to the structural fatigue performance and driving comfort. Identifying the instantaneous occurrence moments of vortex-induced vibration is a prerequisite for establishing a data-driven prediction model for vortex-induced vibration, and it is of great significance for the monitoring and early warning of vortex-induced vibration performance in bridges. To automatically detect the occurrence moments of vortex-induced vibration and establish a correlation model between vortex-induced vibration amplitude and environmental factors, this study proposes a fuzzy C-means clustering-based classification method. In order to detect the occurrence moments of vortex-induced vibration more finely, only short-term or even instantaneous structural vibration indicators were selected and transformed for distribution as clustering features. The entire detection process could be carried out unsupervised, reducing the manual cost of obtaining vortex-induced vibration information from massive monitoring data. Finally, actual vortex-induced vibration test data from a certain overseas bridge was utilized to verify the feasibility of this method. Based on the classification results, the correlation between vortex-induced vibration amplitude and environmental variables was determined, providing valuable guidance for predicting vortex-induced vibration amplitudes.

Clustering-Based Classification of Polygonal Wheels in a Railway Freight Vehicle Using a Wayside System

Polygonal wheels are one of the most common defects in train wheels, causing a reduction in comfort levels for passengers and a higher degradation of vehicle and track components. With the aim of contributing to the safety and reliability of railway transport, this paper presents the development of an innovative methodology for classifying polygonal wheels based on a wayside system. To achieve that, a numerical train-track interaction model was adopted to simulate the passage of a freight train over a virtual wayside monitoring system composed of a set of accelerometers installed on the rails. Then, the acquired acceleration time series was transformed to a frequency domain using a Fast Fourier transform (FFT), and on this data, damage-sensitive features were extracted. The features based on Principal Component Analysis (PCA) showed great sensitivity to the harmonic order, while the ones based on Continuous Wavelet Transform (CWT) model showed great sensitivity to the defect amplitude. One step further, all features are merged using the Mahalanobis distance in order to obtain a damage index strongly correlated with the polygonal defect. Finally, a cluster analysis allowed the automatic classification of polygonal wheels, according to the harmonic order (harmonic-based) and defect amplitude (amplitude-based). The proposed methodology demonstrated high efficiency in identifying different types of polygonal wheels using a minimum layout of two sensors.

Abstract 3500: Refining diagnosis of renal cell carcinoma subtypes through single-cell resolution transcriptomic signatures

Abstract A remaining challenge in the field of renal cell carcinoma (RCC) is diagnosis of rare or mixed subtypes, which hampers the delivery of the most effective healthcare to patients. While a new classification scheme, integrating molecular characteristics of tumors, is emerging, it requires a deep understanding of the tumor heterogeneity and etiopathogenesis of each subtype. We have generated and analyzed single-cell transcriptome profiles of 38 human RCCs and normal kidneys 16 RCCs with diverse histological subtypes and established gene signatures specific to each cell type. We have applied these gene signatures to bulk RNA-sequencing data of 1000 RCC tumors with different histological subtypes and normal kidneys from The Cancer Genome Atlas (TCGA) to characterize different cancer types and cellular origins. Unsupervised clustering analysis of TCGA data shows diagnostic discrepancies for 9.3% cases and subclassifies each major subtype (clear cell, papillary and chromophobe) into clusters with differential clinical outcomes.[KM1]. The pathological marker expression in misdiagnosed tumors is consistent with clustering-based classification, not their original diagnosis. Notably, using unique and subtype-specific gene signature patterns, we identified clear cell papillary renal cell tumor (ccpRCT), which is a newly classified benign entity and the main tumor type representing the mis-diagnosed tumors. These observations have further been confirmed by reviewing histological images of the tumors by an experienced genitourinary pathologist. Interestingly, our gene signatures reveal that ccpRCT does not originate from proximal tubule cells unlike clear cell and papillary RCCs. Taken together, our approach suggests a potential new classification method connected to clinical behaviors and drug responses based on overall transcriptomic differences. Citation Format: Minjun Kim, Ariel Madrigal, Zohreh Mehrjoo, Kate I. Glennon, Madeleine Arseneault, Morag Park, Fadi Brimo, Simon Tanguay, Hamed S. Najafabadi, Yasser Riazalhosseini. Refining diagnosis of renal cell carcinoma subtypes through single-cell resolution transcriptomic signatures [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3500.

An ensemble method with a hybrid of genetic algorithm and K-prototypes algorithm for mixed data classification

Due to challenges posed by mixed data clustering, this study aims to introduce an innovative clustering-based classification algorithm that possesses the advantages of both classification and clustering techniques for mixed data analysis. The proposed algorithm employs the K-prototypes algorithm with a genetic algorithm to optimize weights and centroids and utilizes the bagging method to build multiple classifiers, thereby enhancing classification performance. Furthermore, it incorporates four mutation mechanisms, including Gaussian, Cauchy, Levy, and single-point mutations, to explore optimal solutions. This study suggests using a 20% sampling ratio for the bootstrap sampling in the proposed algorithm. This ratio has been proven to be sufficient for achieving good classification performance while reducing computational time. Experimental results indicate that the proposed algorithm outperforms benchmark classifiers, demonstrating superior classification performance across five performance indicators. In addition, the loan eligibility case study offers valuable insights into applying the proposed algorithm in real-world scenarios, demonstrating that the proposed algorithm can achieve superior classification performance compared to other algorithms. It also offers managerial implications to help different industries and fields understand the appropriate timing and scenarios for implementing the algorithm.

Multispectral Image Processing System for Precision Detection of Reheated Coconut Oil

In the pursuit of enhancing food safety protocols, this article explores a cutting-edge approach to quality control in the coconut oil industry. We present a multispectral image processing system designed specifically for the detection of reheated coconut oil, leveraging advancements in machine learning. Machine learning algorithms, fused with image classification techniques, provide a robust framework for accurately identifying reheated coconut oil. It is proposed to develop a spectral clustering-based classifier to determine the effect of reheating and reuse of coconut oil. Post-processing methods refine classification results, while validation ensures the system's adaptability to diverse datasets.

Quantifying multi-dimensional services of water ecosystems and breakpoint-based spatial radiation of typical regulating services considering the hierarchical clustering-based classification

This study proposes a set of water ecosystem services (WES) research system, including classification, benefit quantification and spatial radiation effect, with the goal of promoting harmonious coexistence between humans and nature, as well as providing a theoretical foundation for optimizing water resources management. Hierarchical cluster analysis was applied to categorize WES taking in to account the four nature constraints of product nature, energy flow relationships, circularity, and human social utility. A multi-dimensional benefit quantification methodology system for WES was constructed by combining the emergy theory with multidisciplinary methods of ecology, economics, and sociology. Based on the theories of spatial autocorrelation and breaking point, we investigated the spatial radiation effects of typical services in the cyclic regulation category. The proposed methodology has been applied to Luoyang, China. The results show that the Resource Provisioning (RP) and Cultural Addition (CA) services change greatly over time, and drive the overall WES to increase and then decrease. The spatial and temporal distribution of water resources is uneven, with WES being slightly better in the southern region than the northern region. Additionally, spatial radiation effects of typical regulating services are most prominent in S County. This finding suggests the establishment of scientific and rational intra-basin or inter-basin water management systems to expand the beneficial impacts of water-rich areas on neighboring regions.

Idiographic assessment of attachment relationships: Construction and validation of scales for use in narrative psychotherapy

In this study the focus was on the development and validation of scales that can be used in an attachment-based narrative form of psychotherapy/counseling. One hundred and six participants completed an online survey, in which they were asked to select one significant troublesome relationship (past or present), to describe the nature of this relationship in a couple of sentences and to characterize the relationship by means of the list of 49 attachment items. By employing exploratory and confirmatory factor analysis (N = 106), a six-factor model emerged covering four classical attachment prototypes: (I) security; (II) anxiety (preoccupation with relationships, fear of rejection); (III) dismissive avoidance (i.e., defensive separation/denial of attachment need; and (IV) fearful avoidance (avoidance/alienation, threat). In two validation studies, the interpersonal and affective meaning of these scales were examined by using instruments that accentuate agentic and communal interpersonal orientations in human contact. In a subsequent qualitative study, we used a cluster-based classification into attachment groups for the exhaustive screening of the content of (a selection of) 40 texts of 40 persons. This hermeneutic approach disclosed characteristic themes for each of the secure, preoccupied, dismissive-avoidant and fearful-avoidant prototypes which are discussed in detail. In narrative psychotherapy a thematic overview according to the attachment typology may be helpful in fine-tuning the therapeutic process, in that it may increase a client’s awareness of attachment issues and associated (dysfunctional) emotional reactions.

Class-Wise Classifier Design Capable of Continual Learning Using Adaptive Resonance Theory-Based Topological Clustering

This paper proposes a supervised classification algorithm capable of continual learning by utilizing an Adaptive Resonance Theory (ART)-based growing self-organizing clustering algorithm. The ART-based clustering algorithm is theoretically capable of continual learning, and the proposed algorithm independently applies it to each class of training data for generating classifiers. Whenever an additional training data set from a new class is given, a new ART-based clustering will be defined in a different learning space. Thanks to the above-mentioned features, the proposed algorithm realizes continual learning capability. Simulation experiments showed that the proposed algorithm has superior classification performance compared with state-of-the-art clustering-based classification algorithms capable of continual learning.

Left Atrial Strain in the Assessment of Diastolic Function in Heart Failure: A Machine Learning Approach.

Diastolic dysfunction (DD) assessment in heart failure is still challenging. Peak atrial longitudinal strain (PALS) is strongly related to end-diastolic pressure and prognosis, but it is still not part of standard DD assessment. We tested the hypothesis that a machine learning approach would be useful to include PALS in DD classification and refine prognostic stratification. In a derivation cohort of 864 heart failure patients in sinus rhythm (age, 66.6±12 years; heart failure with reduced ejection fraction, n=541; heart failure with mildly reduced ejection fraction, n=129; heart failure with preserved ejection fraction, n=194), machine learning techniques were retrospectively applied to PALS and guideline-recommended diastolic variables. Outcome (death/heart failure rehospitalization) of the identified DD-clusters was compared with that by guidelines-based classification. To identify the best combination of variables able to classify patients in one of the identified DD-clusters, classification and regression tree analysis was applied (with DD-clusters as dependent variable and PALS plus guidelines-recommended diastolic variables as explanatory variables). The algorithm was subsequently validated in a prospective cohort of 189 heart failure outpatients (age, 65±13 years). Three distinct echocardiographic DD-clusters were identified (cluster-1, n=212; cluster-2, n=376; cluster-3 DD, n=276), with modest agreement with guidelines-recommended classification (kappa=0.40; P<0.001). DD-clusters were predicted by a simple algorithm including E/A ratio, left atrial volume index, E/e' ratio, and PALS. After 36.5±29.4 months follow-up, 318 events occurred. Compared to guideline-based classification, DD-clusters showed a better association with events in multivariable models (C-index 0.720 versus 0.733, P=0.033; net reclassification improvement 0.166 [95% CI, 0.035-0.276], P=0.013), without interaction with ejection fraction category. In the validation cohort (median follow-up: 18.5 months), cluster-based classification better predicted outcome than guideline-based classification (C-index 0.80 versus 0.78, P=0.093). Integrating PALS by machine learning algorithm in DD classification improves risk stratification over recommended current criteria, regardless of ejection fraction status. This proof of concept study needs further validation of the proposed algorithm to assess generalizability to other populations.

Deep Instance Segmentation With Automotive Radar Detection Points

Automotive radar provides reliable environmental perception in all-weather conditions with affordable cost, but it hardly supplies semantic and geometry information due to the sparsity of radar detection points. With the development of automotive radar technologies in recent years, instance segmentation becomes possible by using automotive radar. Its data contain contexts such as radar cross section and micro-Doppler effects, and sometimes can provide detection when the field of view is obscured. The outcome from instance segmentation could be potentially used as the input of trackers for tracking targets. The existing methods often utilize a clustering-based classification framework, which fits the need of real-time processing but has limited performance due to minimum information provided by sparse radar detection points. In this paper, we propose an efficient method based on clustering of estimated semantic information to achieve instance segmentation for the sparse radar detection points. In addition, we show that the performance of the proposed approach can be further enhanced by incorporating the visual multi-layer perceptron. The effectiveness of the proposed method is verified by experimental results on the popular RadarScenes dataset, achieving 89.53% mean coverage and 86.97% mean average precision with the IoU threshold of 0.5, which is superior to other approaches in the literature. More significantly, the consumed memory is around 1MB, and the inference time is less than 40 ms, indicating that our proposed algorithm is storage and time efficient. These two criteria ensure the practicality of the proposed method in real-world systems.

Hybrid cluster based classification model for high dimensional disease prediction databases

As biomedical databases continue to expand, it becomes increasingly difficult to identify a crucial feature for a classification task due to big data size and sparsity issues. Traditional feature subset models rely on fixed-sized dimensions for the feature ranking and classification process, which is not suitable for addressing concerns with sparsity, missing values, and imbalance in the selection of crucial features for the data classification process. To enhance disease prediction effectiveness, this article proposes a hybrid ensemble feature selection method that employs an advanced cluster-based classification model. The model uses an ensemble of rated features to classify the disease with high accuracy and true positive rate. To improve the effectiveness of tree pruning and classification, we introduce a novel cluster-based classification model. We simulated experimental results using various training datasets to predict accuracy. Our proposed results demonstrate that the gene-chemical disease clustering-based classification framework outperforms traditional methods, statistical metrics, and classification models in terms of optimization.

Detecting Sarcopenia Risk by Diabetes Clustering: A Japanese Prospective Cohort Study.

Previous studies have assessed the usefulness of data-driven clustering for predicting complications in patients with diabetes mellitus. However, whether the diabetes clustering is useful in predicting sarcopenia remains unclear. To evaluate the predictive power of diabetes clustering for the incidence of sarcopenia in a prospective Japanese cohort. Three-year prospective cohort study. We recruited Japanese patients with type 1 or type 2 diabetes mellitus (n = 659) between January 2018 and February 2020 from the Fukushima Diabetes, Endocrinology, and Metabolism cohort. Kaplan-Meier and Cox proportional hazards models were used to measure the predictive values of the conventional and clustering-based classification of diabetes mellitus for the onset of sarcopenia. Sarcopenia was diagnosed according to the Asian Working Group for Sarcopenia (AWGS) 2019 consensus update. Onset of sarcopenia. Cluster analysis of a Japanese population revealed 5 diabetes clusters: cluster 1 [severe autoimmune diabetes (SAID)], cluster 2 [severe insulin-deficient diabetes (SIDD)], cluster 3 (severe insulin-resistant diabetes, cluster 4 (mild obesity-related diabetes), and cluster 5 (mild age-related diabetes). At baseline, 38 (6.5%) patients met the AWGS sarcopenia criteria, and 55 had newly developed sarcopenia within 3 years. The SAID and SIDD clusters were at high risk of developing sarcopenia after correction for known risk factors. This study reveals that among the 5 diabetes clusters, the SAID and SIDD clusters are at a high risk for developing sarcopenia. Clustering-based stratification may be beneficial for predicting and preventing sarcopenia in patients with diabetes.

Clinical Characteristicsof Inpatients With New-Onset Diabetes Mellitus in Eastern China: Based on Novel Clustering Analysis.

IntroductionThis study aimed to explore the novel classification of inpatients with new-onset diabetes in Eastern China by the cluster-based classification method and compare the clinical characteristics among the different subgroups.MethodsA total of 1017 Inpatients with new-onset diabetes of five hospitals in Eastern China were included in the study. Clustering analysis was used to cluster the data into five subgroups according to six basic variables. The differences in clinical characteristics, treatments, and the prevalence of diabetes-related diseases among the five subgroups were analyzed by multiple groups comparisons and pairwise comparisons. The risk of diabetes-related diseases in the five subgroups was compared by calculating odd ratio (OR). P value < 0.05 was considered significant.ResultsFive subgroups were obtained by clustering analysis with the highest proportion of patients with severe insulin-deficient diabetes (SIDD) 451 (44.35%), followed by patients with mild age-related diabetes (MARD) 236 (23.21%), patients with mild obesity-related diabetes (MOD) 207 (20.35%), patients with severe insulin-resistant diabetes (SIRD) 81 (7.96%), and patients with severe autoimmune diabetes (SAID) 42 (4.13%). Five subtypes had their own unique characteristics and treatments. The prevalence and risk of diabetes-related complications and comorbidities were also significantly different among the five subtypes. Diabetic kidney disease (DKD) was the most common in SIRD group. Patients in SIDD, SIRD, and MARD groups were more likely to develop cardiovascular disease (CVD) and/or stroke, diabetic peripheral vascular disease (DPVD), and diabetic distal symmetric polyneuropathy (DSPN). The prevalence and risk of metabolic syndrome (MS) were the highest in MOD and SIRD groups. Patients in SAID group had the highest prevalence and risk of diabetic ketoacidosis (DKA). Patients with MOD were more likely to develop non-alcoholic fatty liver disease (NAFLD).ConclusionsThe inpatients with new-onset diabetes in Eastern China had the unique clustering distribution. The clinical characteristics, treatments, and diabetes-related complications and comorbidities of the five subgroups were different, which may provide the basis for precise treatments of diabetes.

Household Electricity Consumer Classification Using Novel Clustering Approach, Review, and Case Study

There is an increasing demand for electricity on a global level. Thus, the utility companies are looking for the effective implementation of demand response management (DRM). For this, utility companies should know the energy demand and optimal household consumer classification (OHCC) of the end users. In this regard, data mining (DM) techniques can give better insights and support. This work proposes a DM-technique-based novel methodology for OHCC in the Indian context. This work uses the household electricity consumption (HEC) of 225 houses from three districts of Maharashtra, India. The data sets used are namely questionnaire survey (QS), monthly energy consumption (MEC), and tariff orders. This work addresses the challenges for OHCC in energy meter data sets of the conventional grid and smart grid (SG). This work uses expert classification and clustering-based classification methods for OHCC. The expert classification method provides four new classes for OHCC. The clustering method is employed to develop eight different classification models. The two-stage clustering model, using K-means (KM) and the self-organizing map (SOM), is the best fit among the eight models. The result shows that the two-stage clustering of the SOM with the KM model provides 88% of overlap-free samples and 0.532 of the silhouette score (SS) mean compared to the expert classification method. This study can be beneficial to the electricity distribution companies for OHCC and can offer better services to consumers.

Improving Recognition of Overlapping Activities with Less Interclass Variations in Smart Homes through Clustering-Based Classification.

The systems of sensing technology along with machine learning techniques provide a robust solution in a smart home due to which health monitoring, elderly care, and independent living take advantage. This study addresses the overlapping problem in activities performed by the smart home resident and improves the recognition performance of overlapping activities. The overlapping problem occurs due to less interclass variations (i.e., similar sensors used in more than one activity and the same location of performed activities). The proposed approach overlapping activity recognition using cluster-based classification (OAR-CbC) that makes a generic model for this problem is to use a soft partitioning technique to separate the homogeneous activities from nonhomogeneous activities on a coarse-grained level. Then, the activities within each cluster are balanced and the classifier is trained to correctly recognize the activities within each cluster independently on a fine-grained level. We examine four partitioning and classification techniques with the same hierarchy for a fair comparison. The OAR-CbC evaluates on smart home datasets Aruba and Milan using threefold and leave-one-day-out cross-validation. We used evaluation metrics: precision, recall, F score, accuracy, and confusion matrices to ensure the model's reliability. The OAR-CbC shows promising results on both datasets, notably boosting the recognition rate of all overlapping activities more than the state-of-the-art studies.

Clustering-Based Semi-Supervised Cross-Modal Retrieval Using Scene Graph

In this paper, we propose a clustering-based semi-supervised cross-modal retrieval method to relieve the problem of insufficient annotation in cross-modal datasets. First, we reconstruct cross-modal data as scene graph structure to filter meaningless information. Second, we extract embedding representation features of images and texts to put them into a common space. Finally, we propose a clustering-based classification method with modality-independent constraint to discriminate samples. According to our experimental results, significant improvement on performance shows the accuracy of our method in terms of three widely used cross-modal datasets compared with the state-of-the-art methods.

A hybrid k-prototypes clustering approach with improved sine-cosine algorithm for mixed-data classification

When dealing a classification problem with mixed data, most of conventional supervised learning algorithms cannot perform well due to their numerical characteristics. However, some clustering algorithms, such as k-prototypes algorithm, show their potential in clustering mixed data. Therefore, the current study intends to develop a novel clustering-based classification algorithm for mixed data to have both merits of classification and clustering. The proposed algorithm employs a sine-cosine algorithm (SCA) to find attribute weights and initial centroids for a k-prototypes algorithm. The objective function of the algorithm is formulated as a sum-up purity. To have better performance for SCA, a mutation strategy, containing Gaussian mutation, Cauchy mutation, Levy mutation, and single-point mutation, is embedded into the original SCA. The proposed algorithm is compared with some metaheuristic-based classification algorithms and existing classification algorithms. Based on the 10 data sets from UCI, the experimental results indicated that the proposed algorithm can achieve superior classification performance in terms of accuracy and Cohen's Kappa. In addition, mutation mechanism can make SCA have better performance.

A semi-supervised clustering-based classification model for classifying imbalanced data streams in the presence of scarcely labelled data

Data streams are potentially infinite in length, fast changing and scarcely labelled. It is practically impossible to label all the observed instances. Online frameworks for classifying data streams are generally supervised in nature assuming the availability of labelled data and hence cannot be used for data streams. Semi-supervised learning (SSL) addresses this problem of scarcely labelled data by using large amount of unlabelled data together with labelled data to build classifiers. Data streams may also suffer from the problem of imbalanced data. Previous works in learning from data streams have analysed problems of imbalanced data. But to the best of our knowledge no work has applied semi-supervised learning approaches for classifying imbalanced data streams so far. This paper proposes a model using a semi-supervised clustering technique to classify an imbalanced data stream in the presence of scarcely labelled data. The results prove that the model outperforms many state-of-the-art techniques.

An Innovative Perceptual Pigeon Galvanized Optimization (PPGO) Based Likelihood Naïve Bayes (LNB) Classification Approach for Network Intrusion Detection System

ABSTRACTIntrusion detection and classification have gained significant attention recently due to the increased utilization of networks. For this purpose, there are different types of Network Intrusion Detection System (NIDS) approaches developed in the conventional works, which mainly focus on identifying the intrusions from the datasets with the help of classification techniques. Still, it is limited by the significant problems of inefficiency in handling large dimensional datasets, high computational complexity, false detection, and more time consumption for training the models. To solve these problems, this research intends to develop an innovative clustering-based classification methodology to precisely detect intrusions from the different types of IDS datasets. Here, the most recent and extensively used IDS datasets such as NSL-KDD, CICIDS, and Bot-IoT have been employed for detecting intrusions. Data preprocessing has been performed to normalize the dataset to eliminate irrelevant attributes and organize the features. Then, the data separation is applied by forming the clusters by using an intelligent Anticipated Distance-based Clustering (ADC) incorporated with the Density-Based Spatial clustering of applications with noise (DBScan) algorithm. It helps to find the distance and density measures for grouping the attributes into the clusters, which increases the efficiency of classification. Here, the most suitable optimal parameters are selected using the Perpetual Pigeon Galvanized Optimization (PPGO) technique. The extracted features are used for training and testing the dataset samples.Consequently, the Likelihood Naove Bayes (LNB) classification approach is implemented to accurately predict the classified label as to whether normal or attack. During the evaluation, the performance of the proposed IDS framework is validated and compared using various evaluation metrics. Theresults show that the proposed ADC-DBScan-LNB model outperforms the other techniques with improved performance outcomes.

CruParamer: Learning on Parameter-Augmented API Sequences for Malware Detection

Learning on execution behaviour, i.e., sequences of API calls, is proven to be effective in malware detection. In this paper, we present CruParamer, a deep neural network based malware detection approach for Windows platform that performs learning on sequences of parameter-augmented APIs. It first employs rule-based and clustering-based classification to assess the sensitivity of a parameter to malicious behaviour, and further labels the API following the run-time parameters with varying degrees of sensitivities. Then, it encodes the APIs by concatenating the native embedding and the sensitive embedding of labelled APIs, for characterizing the relationship between successive labelled APIs and their correspondence in terms of security semantics. Finally, it feeds the sequences of API embedding into the deep neural network for training a binary classifier to detect malware. In addition to presenting the design, we have implemented CruParamer and evaluated it on two datasets. The results demonstrate that CruParamer outperforms naïve models when taking raw APIs as input, proving the effectiveness of CruParamer. Moreover, we have evaluated the impact of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">mimicry</i> and adversarial attacks on our model, and the results verify the robustness of CruParamer.