Features For Classification Research Articles

Cross-attention mechanism-based spectrum sensing in generalized Gaussian noise

Spectrum sensing (SS) technology is essential for cognitive radio (CR) networks to effectively identify and utilize idle spectrum resources. Due to the influence of noise characteristics in the channel, providing accurate sensing results is challenging. In order to improve the performance of SS under non-Gaussian noise and overcome the limitations of existing methods that are mostly based on a single feature, we propose a novel time-frequency cross fusion network (TFCFN). Specifically, we utilize gated recurrent units (GRU) to capture long-term dependencies in the time domain on the original signals, meanwhile, we perform a fast Fourier transform (FFT) on the original signals to obtain the frequency domain information, and subsequently use convolutional neural networks (CNN) to extract the local spatial features in the frequency domain. Ultimately, these time-domain and frequency-domain features are dynamically fused through a cross-attention mechanism to construct more comprehensive and robust features for signal classification. We use generalized Gaussian distribution (GGD) as the noise model and reconstruct the RadioML2016.10a dataset to explore the performance under various noise conditions. The experimental results show that compared with the baseline methods, TFCFN exhibits better detection ability and maintains lower complexity in both Gaussian and non-Gaussian noise environments. Notably, when the shape parameter of GGD is set to 0.5 and the signal-to-noise ratio (SNR) of the received signal is -16dB, it can maintain the probability of false alarm (Pf\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$P_f$$\\end{document}) of 10% while still ensuring the probability of detection (Pd\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$P_d$$\\end{document}) of over 90%.

CRCGAN: Toward robust feature extraction in finger vein recognition

Deep convolutional neural networks (CNNs) have produced remarkable outcomes in finger vein recognition. However, these networks often overfit label information, losing essential image features, and are sensitive to noise, with minor input changes leading to incorrect recognition. To address above problems, this paper presents a new classification reconstruction cycle generative adversarial network (CRCGAN) for finger vein recognition. CRCGAN comprises a feature generator, a feature discriminator, an image generator, and an image discriminator, which are designed for robust feature extraction. Concretely, the feature generator extracts features for classification, while the image generator reconstructs images from these features. Two discriminators provide feedback, guiding the generators to improve the quality of generated data. With this design of bi-directional image-to-feature mapping and cyclic adversarial training, CRCGAN achieves the extraction of essential features and minimizes overfitting. Additionally, precisely due to the extraction of essential features, CRCGAN is not sensitive to noise. Experimental results on three public databases, including THU-FVFDT2, HKPU, and USM, demonstrate CRCGAN’s competitive performance and strong noise resistance, achieving recognition accuracies of 98.36%, 99.17% and 99.49% respectively, with less than 0.5% degradation on HKPU and USM databases under noisy conditions.

EEG Dataset for the Recognition of Different Emotions Induced in Voice-User Interaction

Electroencephalography (EEG)-based open-access datasets are available for emotion recognition studies, where external auditory/visual stimuli are used to artificially evoke pre-defined emotions. In this study, we provide a novel EEG dataset containing the emotional information induced during a realistic human-computer interaction (HCI) using a voice user interface system that mimics natural human-to-human communication. To validate our dataset via neurophysiological investigation and binary emotion classification, we applied a series of signal processing and machine learning methods to the EEG data. The maximum classification accuracy ranged from 43.3% to 90.8% over 38 subjects and classification features could be interpreted neurophysiologically. Our EEG data could be used to develop a reliable HCI system because they were acquired in a natural HCI environment. In addition, auxiliary physiological data measured simultaneously with the EEG data also showed plausible results, i.e., electrocardiogram, photoplethysmogram, galvanic skin response, and facial images, which could be utilized for automatic emotion discrimination independently from, as well as together with the EEG data via the fusion of multi-modal physiological datasets.

Dynamic Mode Decomposition-Based Features for Ovarian Cancer Gene Expression Classification Using Machine Learning

Machine learning (ML) algorithms have been deployed in recent years as models for the analysis of complex data. The ubiquity of ML algorithms stems from their ability to learn the patterns and structures inherent in data. Additionally, they are adaptable to a wide range of data types, irrespective of size, which allows them to learn and predict the future pattern of data. In this work, dynamic mode decomposition (DMD), an ML algorithm, is deployed to analyse the pattern of gene expression data from patients with and without ovarian cancer. Ovarian cancer is one of the deadliest gynaecologic cancers worldwide. The obscure nature of the symptoms makes early detection of ovarian cancer difficult. Early diagnosis increases the chances of survival for patients. Furthermore, the modes computed from DMD are used as features and separately fed into three ML classifiers- support vector machine (SVM), decision tree (DecTr), and K- nearest neighbour (KNN) to classify the gene expression into either cancer or non-cancer categories. Multiple metrics- sensitivity, accuracy, precision, and error rate are used to assess the performance of the models, to have a balanced illustration of a model’s performance. The DecTr outperforms the other two classifiersSVM and KNN, across the metrics used in evaluating the performance of the models.

Extraction of Features for Time Series Classification Using Noise Injection

Time series data often display complex, time-varying patterns, which pose significant challenges for effective classification due to data variability, noise, and imbalance. Traditional time series classification techniques frequently fall short in addressing these issues, leading to reduced generalization performance. Therefore, there is a need for innovative methodologies to enhance data diversity and quality. In this paper, we introduce a method for the extraction of features for time series classification using noise injection to address these challenges. By employing noise injection techniques for data augmentation, we enhance the diversity of the training data. Utilizing digital signal processing (DSP), we extract key frequency features from time series data through sampling, quantization, and Fourier transformation. This process enhances the quality of the training data, thereby maximizing the model’s generalization performance. We demonstrate the superiority of our proposed method by comparing it with existing time series classification models. Additionally, we validate the effectiveness of our approach through various experimental results, confirming that data augmentation and DSP techniques are potent tools in time series data classification. Ultimately, this research presents a robust methodology for time series data analysis and classification, with potential applications across a broad spectrum of data analysis problems.

Support vector machine classification of irritable bowel syndrome patients based on whole-brain resting-state functional connectivity features.

Irritable bowel syndrome (IBS) is a disorder characterized by signaling dysregulation between the brain and gut, leading to gastrointestinal dysfunction. Symptoms such as abdominal pain and constipation can manifest periodically or persistently, and negative emotions may exacerbate the symptoms. Previous studies have shown that the pathogenesis of IBS is closely related to the brain-gut axis and brain function, but there are still difficulties in disease diagnosis. Therefore, this study applied a machine-learning approach based on resting-state functional magnetic resonance imaging (rs-fMRI) whole-brain functional connectivity (FC) to distinguish IBS patients from healthy controls (HCs). A total of 176 subjects, comprising 88 consecutive patients with IBS and 88 age-, sex- and education-matched HCs, were enrolled in this study between January 2020 and January 2024 at the First Affiliated Hospital of Shantou University Medical College. All the subjects underwent rs-fMRI and high-resolution anatomical T1-weighted imaging (T1WI) examinations. Following the preprocessing of the rs-fMRI image data, FC matrices between all regions of interest (ROIs) were extracted using automated anatomical labeling (AAL). Subsequently, supervised machine learning was performed using whole-brain FC for classification features to identify the best-performing model. Finally, weights of the optimal model's features were exported to confirm the neuroanatomical regions significantly influencing model establishment. Compared with other supervised learning models, the support vector machine (SVM) model had significantly higher classification accuracy and performed significantly better than the other models (P<0.05) with a classification accuracy of 75% and an area under the curve (AUC) of 0.7788 (95% confidence interval [CI]: 0.6861-0.8715) (P<0.01). In addition, the FC features from the Rolandic operculum (ROL) to the anterior cingulate gyrus (ACG), the calcarine sulcus (CAL) to the triangular part of the inferior frontal gyrus (IFG), the gyrus rectus (REC) to the inferior occipital gyrus (IOG), the lingual gyrus (LING) to the putamen (PUT), and the IOG to the angular gyrus (ANG) were relatively important in the construction of the machine-learning models. The SVM was the optimal machine-learning model for effectively classifying IBS patients and HCs based on whole-brain resting-state FC matrices. The FC features between the emotion-related brain regions significantly affected the construction of the machine-learning models. As a classification feature in machine learning, whole-brain resting-state FC holds the potential to achieve precision medicine in IBS and enhance disease diagnostic efficacy.

Deep learning techniques for quality of transmission estimation in optical networks

A large body of research has recently examined the estimation of the quality of transmission (QoT) in optical networks with deep learning. This paper discusses a lightpath’s quality of transmission to design fiber-optic communication and networks using deep learning algorithms. We need different major estimation parameters for advanced optical fiber communication and networks, i.e., modulation formats, baud rate, and code rate. Currently, the quality of transmission for unspecified optical paths depends on different estimation techniques i.e., (1) analytical models estimating physical layer impairments (PLIs) and (2) margined formulas. This paper focuses on deep-learning techniques that can be applied to optimization and complex systems. The deep learning algorithms contain different classifiers that can simulate results and estimate the bit-error rate, and signal-to-noise ratio of unspecified optical paths with threshold values, traffic volume, and modulation format. We must train and test the datasets for various classifiers, and classification features using Korean network topology. The classifier accuracy and Area Under the ROC Curve (AUC) simulation results are carried out using MATLAB.

PTE: Prompt tuning with ensemble verbalizers

Prompt tuning has achieved remarkable success in facilitating the performance of Pre-trained Language Models (PLMs) across various downstream NLP tasks, particularly in scenarios with limited downstream data. Reframing tasks as fill-in-the-blank questions represents an effective approach within prompt tuning. However, this approach necessitates the mapping of labels through a verbalizer consisting of one or more label tokens, constrained by manually crafted prompts. Furthermore, most existing automatic crafting methods either introduce external resources or rely solely on discrete or continuous optimization strategies. To address this issue, we have proposed a methodology for optimizing discrete verbalizers based on gradient descent, which we refer to this approach as PTE. This method integrates discrete tokens into verbalizers that can be continuously optimized, combining the distinct advantages of both discrete and continuous optimization strategies. In contrast to prior approaches, ours eschews reliance on prompts generated by other models or prior knowledge, merely augmenting a matrix. This approach boasts remarkable simplicity and flexibility, enabling prompt optimization while preserving the interpretability of output label tokens without constraints imposed by discrete vocabularies. Finally, employing this method in text classification tasks, we observe that PTE achieves results comparable to, if not surpassing, previous methods even under extreme conciseness. This furnishes a simple, intuitive, and efficient solution for automatically constructing verbalizers. Moreover, through quantitative analysis of optimized verbalizers, we uncover that language models likely rely not only on semantic information but also on other features for text classification. This revelation unveils new avenues for future research and model enhancements.

ADCMDES: Design of an augmented cross-domain collaborative recommendation model using novel distance metric and ensemble stratification

Collaborative recommendation involves leveraging information from one entity to suggest attributes of other entities through pattern analysis. These models are invaluable for understanding data behaviour’s impact on related entities. Researchers propose various pattern recognition and correlation models, employing distance metrics like Jaccard, Cosine, etc., to estimate correlations between user queries and recommendation datasets. However, these models become less efficient as dataset size increases due to exponential correlation estimation delays. To enhance scalability while retaining recommendation quality, a new approach is introduced: ADCMDES. This novel augmented cross-domain collaborative model employs a hybrid distance metric and ensemble stratification for dataset pruning. It operates semi-supervisedly, requiring information about the entities being collaborated upon. This data is used to cluster similar collaborative entities, producing a condensed cluster with greater relevancy to user queries. Utilizing word2vec, records are transformed into features for an ensemble classification engine. The resultant model categorizes user input, directing it to the most relevant cluster. Entries within this cluster are ranked using a hybrid metric amalgamating 18 distance measures, enhancing correlation between input queries and recommendations. In testing, ADCMDES exhibited 15% better accuracy, 8% better precision, 9% better recall, and 3% lower RMSE compared to standard models across datasets. While some delay is introduced due to ensemble classification and augmented feature pooling, this doesn't considerably affect long-term recommendation performance and can be mitigated through parallel processing and redundancy reduction techniques.

Enhanced cancer classification and critical feature visualization using Raman spectroscopy and convolutional neural networks

Cell misuse and cross-contamination pose a significant threat to the accuracy of cell research outcomes, often leading to the wasteful expenditure of time, manpower, and material resources. Consequently, the accurate identification of cell lines is paramount. However, traditional identification methods, which often involve staining and culturing procedures, are not only time-consuming but also laborious. This underscores the need for a novel approach that enables rapid and automated cell line identification, thereby enhancing research efficiency and accuracy. Raman spectroscopy, renowned for its label-free, rapid, and noninvasive nature, offers invaluable molecular insights into samples, making it a widely utilized technique in the biological field. In this study, the identification of one normal and five cancer cell lines was achieved using a sparrow search algorithm-convolutional neural networks (SSA-CNN), considering both the full spectra and fingerprint region perspectives. The SSA-CNN model demonstrated exceptional performance, not just in binary classification, but also in accurately distinguishing among six cell lines. It achieved the highest accuracy (around 95 %), and the lowest standard error (≤3%), for both the full spectra and fingerprint region. Based on the highly accurate SSA-CNN model, proposed the application of gradient-weighted class activation mapping (Grad-CAM) to visualize the Raman feature peaks. Upon comparing the visualized Raman features with reported biomarkers, found that not only were common biomolecules such as glucose, proteins, and liquids visualized, but specific feature peaks also aligned with reported biomarkers. The aforementioned results clearly demonstrated that the proposed strategy not only classifies cancer cell lines with remarkable accuracy but also served as a valuable tool for the discovery of novel biomarkers.

STMixer: A One-Stage Sparse Action Detector.

Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract actor-specific features for action recognition. This detection paradigm requires multi-stage training and inference, and the feature sampling is only constrained inside the box, failing to effectively leverage richer context information outside. Recently, several query-based action detectors have been proposed to predict action instances in an end-to-end manner. However, they still lack adaptability in feature sampling and decoding, thus suffering from the issues of inferior performance or slower convergence. In this paper, we propose two core designs for a more flexible one-stage sparse action detector. First, we present a query-based adaptive feature sampling module, which endows the detector with the flexibility of mining a group of discriminative features from the entire spatio-temporal domain. Second, we devise a decoupled feature mixing module, which dynamically attends to and mixes video features along the spatial and temporal dimensions respectively for better feature decoding. Based on these designs, we instantiate two detection pipelines, that is, STMixer-K for keyframe action detection and STMixer-T for action tubelet detection. Without bells and whistles, our STMixer detectors obtain the state-of-the-art results on five challenging spatio-temporal action detection benchmarks for keyframe action detection or action tube detection.

Deep learning-assisted detection of psychoactive water pollutants using behavioral profiling of zebrafish embryos

Water pollution poses a significant risk to the environment and human health, necessitating the development of innovative detection methods. In this study, a series of representative psychoactive compounds were selected as model pollutants, and a new approach combining zebrafish embryo behavioral phenotyping with deep learning was used to identify and classify water pollutants. Zebrafish embryos were exposed to 17 psychoactive compounds at environmentally relevant concentrations (1 and 10 μg/L), and their locomotor behavior was recorded at 5 and 6 days post-fertilization (dpf). We constructed six distinct zebrafish locomotor track datasets encompassing various observation times and developmental stages and evaluated multiple deep learning models on these datasets. The results demonstrated that the ResNet101 model performed optimally on the 1-min track dataset at 6 dpf, achieving an accuracy of 65.35 %. Interpretability analyses revealed that the model effectively focused on the relevant locomotor track features for classification. These findings suggest that the integration of zebrafish embryo behavioral analysis with deep learning can serve as an environmentally friendly and economical method for detecting water pollutants. This approach offers a new perspective for water quality monitoring and has the potential to assist existing chemical analytical techniques in detection, thereby advancing environmental toxicology research and water pollution control efforts.

Preoperative CT-based radiomics and deep learning model for predicting risk stratification of gastric gastrointestinal stromal tumors.

Gastrointestinal stromal tumors (GISTs) are clinically heterogeneous with various malignant potential in different individuals. It is crucial to explore a reliable method for preoperative risk stratification of gastric GISTs noninvasively. To establish and evaluate a machine learning model using the combination of computed tomography (CT) morphology, radiomics, and deep learning features to predict the risk stratification of primary gastric GISTs preoperatively. The 193 gastric GISTs lesions were randomly divided into training set, validation set, and test set in a ratio of 6:2:2. The qualitative and quantitative CT morphological features were assessed by two radiologists. The tumors were segmented manually, and then radiomic features were extracted using PyRadiomics and the deep learning features were extracted using pre-trained Resnet50 from arterial phase and venous phase CT images, respectively. Pearson correlation analysis and recursive feature elimination were used for feature selection. Support vector machines were employed to build a classifier for predicting the risk stratification of GISTs. This study compared the performance of models using different pre-trained convolutional neural networks (CNNs) to extract deep features for classification, as well as the performance of modeling features from single-phase and dual-phase images. The arterial phase, venous phase and dual-phase machine learning models were built, respectively, and the morphological features were added to the dual-phase machine learning model to construct a combined model. Receiver operating characteristic (ROC) curves were used to evaluate the efficacy of each model. The clinical application value of the combined model was determined through the decision curve analysis (DCA) and the net reclassification index (NRI) was analyzed. The area under the curve (AUC) of the dual-phase machine learning model was 0.876, which was higher than that of the arterial phase model or venous phase model (0.813, 0.838, respectively). The combined model had best predictive performance than the above models with an AUC of 0.941 (95% CI: 0.887-0.974) (p=0.012, Delong test). DCA demonstrated that the combined model had good clinical application value with an NRI of 0.575 (95% CI: 0.357-0.891). In this study, we established a combined model that incorporated dual-phase morphology, radiomics, and deep learning characteristics, which can be used to predict the preoperative risk stratification of gastric GISTs.

The case classification and their development for would-be mathematics teachers’ training

Abstract The article looks into the issue of the case classification for the training of Mathematics teachers. The analysis, which was carried out, and the survey of 47 University teachers of methodical disciplines allowed to highlight the classification features of cases in the process of teaching methodical disciplines: the amount of time to complete, the way of presentation, the level of complexity and the breadth of the covered problem. Classifying cases by the amount of time for their implementation contributed to the separation of mini-cases, medium-term cases, and long-term cases. Classification by the method of presentation of cases in the process of studying methodical disciplines ensured their use in printed (handwritten) form, multimedia presentation of cases, and video cases. According to the level of complexity, the cases were divided into reproductive-training, partial-research, and creative-innovative cases. Thematic and integrated cases ensured the breadth of coverage of the problem during the teaching of methodical disciplines. The article presents general requirements for the selection and development of cases in the process of studying methodical disciplines. These requirements are based on the principles of accessibility, scientificity, contextuality, systematicity, methodological expediency, and practical orientation. The classification and specific requirements became the basis for the development of cases that can be used in the process of teaching methodological disciplines of would-be Mathematics teachers.

Transformer based on multi-scale local feature for colon cancer histopathological image classification

Colon cancer histopathological image recognition is an important method in the early screening of colon cancer. At present, most whole slide images (WSIs) classification models only consider the features of a single patch, and do not consider the features of the WSIs region. To expand the receptive field of the patches and obtain its surrounding pathological information, this paper proposes a transformer based on multi-scale local feature for colon cancer histopathological image classification model. The model samples patches based on farthest point sampling (FPS). A multi-scale grouping scheme is also proposed to capture WSI local regions. Then the classification labels, feature information and local area information of sampled patches are embedded into the transformer encoder. In addition, the focal loss function is adopted to solve the problem of unbalanced categories of colon cancer histopathological images. Experimental results demonstrate that our model surpasses competing methods in performance on both hospital colon cancer datasets and The Cancer Genome Atlas(TCGA) colon cancer datasets.

Feature selection via robust weighted score for high dimensional binary class-imbalanced gene expression data

In this paper, a robust weighted score for unbalanced data (ROWSU) is proposed for selecting the most discriminative features for high dimensional gene expression binary classification with class-imbalance problem. The method addresses one of the most challenging problems of highly skewed class distributions in gene expression datasets that adversely affect the performance of classification algorithms. First, the training dataset is balanced by synthetically generating data points from minority class observations. Second, a minimum subset of genes is selected using a greedy search approach. Third, a novel weighted robust score, where the weights are computed by support vectors, is introduced to obtain a refined set of genes. The highest scoring genes based on this approach are combined with the minimum subset of genes selected by the greedy search approach to form the final set of genes. The novel method ensures the selection of the most discriminative genes, even in the presence of skewed class distribution, thereby improving the performance of the classifiers. The performance of the proposed ROWSU method is evaluated on 7 gene expression datasets. Classification accuracy, sensitivity and F1-score are used as performance metrics to compare the proposed ROWSU algorithm with several other state-of-the-art methods. Boxplots and stability plots are also constructed for a better understanding of the results. The results show that the proposed method outperforms the existing feature selection procedures based on classification performance from k nearest neighbors (kNN) and random forest (RF) classifiers.

Transformer-Based Regression Models for Assessing Reading Passage Complexity: A Deep Learning Approach in Natural Language Processing

Natural Language Processing (NLP) is a vital area in deep learning, widely applied in tasks like text classification, virtual assistants, speech recognition, and autocorrect features in digital devices. It allows machines to understand and generate human language, enhancing user interactions with software. This paper presents a deep learning model using the Transformer architecture for a regression task to predict the complexity of reading passages based on text excerpts. By leveraging the Transformer’s capability to identify complex patterns in text, the model achieves a relative error rate of about 10%. The paper also examines how different architectural choices influence model performance, focusing on one-hot encoding and embeddings. While one-hot encoding provides a simple text representation, embeddings offer a richer, more nuanced understanding of word relationships. The findings highlight the significance of model design and data representation in optimizing NLP tasks, providing insights for future advancements in the field.

Automated Classification and Segmentation and Feature Extraction from Breast Imaging Data

Automated Classification and Segmentation and Feature Extraction from Breast Imaging Data

Rural anthroponyms in the shchuchin dialect of the Voronezh region

INTRODUCTION. The study is carried out in the context of the anthropocentric paradigm and is devoted to the topic of “Man”. Nickname nominations and their unique characteristics are considered. The relevance of studying the thematic group is associated with the observed processes of decreasing the number of dialect speakers, interest in the study of folk speech and the importance of registering the information available to villagers to build a certain linguistic picture. The aim of the study is to analyze unofficial anthroponyms of the small village of Shchuchye in the Liski district of the Voronezh region, reflected in the local dialect.MATERIALS AND METHODS. The field material is used to study the names of village people, functioning in the sphere of informal communication in the Voronezh dialect. Experimental (survey and observation) and descriptive (description and comparison) linguistic research methods are used.RESULTS AND DISCUSSION. The rural nomenclature includes groups of nickname units, the classification feature of which is the method of nomination, motivational feature and the nature of the derivative base. The emergence of unofficial anthroponyms is associated with the established norms of village communication. The Shchuchin mosaic of onomastic units includes male, female and family nicknames. Male anthroponyms predominate. It is postulated that productive ways of forming names are suffixal, truncation and substantiation.CONCLUSION. The customs of interpersonal provincial communication are quite strong. The original village nomenclature of the Shchuchintsy, depicted through folk speech combining southern Russian and Ukrainian features, is presented by 100 nickname units and represented by 21 groups. It demonstrates the original linguistic imagination of rural residents and is important not only for the dialectal anthroponymy of the 21st century, but also for Russian onomastics in general. The study may be continued by features reflecting other characteristics of unofficial names and their motivational features.

A Study on Novel Amino Acid Pair Features for Protein Evolutionary Classifications

Protein evolutionary classification from amino acid sequence is one of the hot research topics in computational biology and bioinformatics. The amino acid composition and arrangement in a protein sequence embed the hints to its evolutionary origins. The feature extraction from an amino acid sequence to a numerical vector is still a challenging problem. Traditional feature methods extract protein sequence information either from individual amino acids or kmers aspects, which have general performance with limitations in classification accuracy. To further improve the accuracy in protein evolutionary classifications, six new features defined on separated amino acid pairs are proposed for protein evolutionary classification analysis, where composition and arrangement as well as physical properties are considered for the different combinations of separated amino acid pairs. Different from general consideration of amino acid pairs, the new features account for the features of separated amino acid pairs with spatial intervals in the sequence, which may deeper reflect the spatial relationships and characters between the amino acid in pairs. In test of the performances of the new features, five standard protein evolutionary classification examples are employed, where the new features proposed are compared with classical protein sequence features such as averaged property factors (APF), natural vector (NV) and pseudo amino acid composition (PseAAC) as well as kmer versions of these features. The area under precision-recall curve (AUPRC) analysis shows that the new features are efficient in evolutionary classifications, which outperform traditional protein sequence features that are based on individual amino acids and kmers. Parameter analysis on the novel separated amino acid pair features and kmer features show that the features of some medium or longer length of amino acid pair intervals and kmers may achieve higher classification accuracy in evolutionary classifications. From this analysis, the newly proposed separated amino acid pairs with spacial intervals are proved to be efficient units in extracting protein sequences features, which may interpret richer evolutionary information of protein sequences than individual amino acids and kmers.