Search

Identifying the abnormal samples from a data set and determining their type are two key tasks of anomaly detection. However, the existing anomaly detection algorithms are generally faced with the defects of weak generalization ability and insufficient interpretation, the core reason of which is that they cannot mine specific features for different abnormal types. In this paper, a new anomaly detection algorithm aiming at feature selection for different abnormal types is developed. Inspired by self-supervised learning, we take the stationarity of variance changes of abnormal score similarity as a pretext task and combine it with wrapped search method. Then, the features and the corresponding parameters for different abnormal types can be screened to apply to the downstream task of anomaly integration detection. To verify the efficiency of the new algorithm, we conduct two sets of experiments to compare the new algorithm with 11 classical anomaly detection and 3 clustering anomaly detection algorithms on the data sets WDBC, WPBC and Wilt from DAMI database with the evaluation measures P@n , Adj- P@n , AP, Adj-AP and AUC. The experiment results show that, both in the identification and classification on abnormal samples, all performance measures of the new algorithm are explicitly better than that of the contrastive algorithms. Also, we apply the new algorithm to the Chinese auto insurance market, and find that the results can help managers to identify the main patterns of fraudulent claims and to summarize the feature combinations of fraud behaviors. In general, the new algorithm developed in this paper has the following advantages compared with traditional algorithms: 1) It can directly capture abnormal features and realize effective recognition of abnormal types, which effectively bridge the gap between abnormal judgement and feature screening. 2) Automatic screening of abnormal features can be completed under the condition of self-updating learning optimal strategy. 3) Only a few features are extracted from all features to reveal the abnormal characteristics, which significantly improves the interpretability and generalization ability of the algorithm and its results. In a word, through the novel self-supervised design method, feature screening is skillfully integrated into the anomaly detection task, which may provide a new way for anomaly detection research. [ABSTRACT FROM AUTHOR]

Feature extraction is one of the fundamental problems in pattern recognition research. For image recognition, extracting effective image features is the key to accomplish the recognition task. In this paper, a partial differential equations-based multi-rank two-dimensional canonical correlation analysis (PDEs-MR2DC2A) is proposed for multi-view feature extraction and pattern classification. Unlike most of the previous researches on multi-view algorithms that work directly on the original 2D representation, in our approach, we first utilize the evolution process of PDEs to extract the feature matrix of per-view. In addition, we employ multi-rank left and right projecting matrices to maximize the correlation. The computational complexity of PDEs-MR2DC2A is also analyzed. To evaluate the effectiveness of the proposed algorithm, we conducted a series of performance comparisons with some existing methods on several popular datasets. The experimental results showed that our proposed algorithm performed very well on these datasets and outperformed the existing related methods on some metrics. • A novel multi-rank multi-view algorithm based on PDEs is proposed. • This approach can extract rotation and translation invariant features. • Numerous experimental results demonstrate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Feature extraction networks play a crucial role in classification algorithms. However, most convolutional neural networks use the form of residual block stacking to extract downstream features of images, and this simple form is not sufficient to obtain better classification performance. Therefore, this paper proposes a YOLOX detection framework based on an improved ConvNeXt which incorporates many advantages of Swin-Transformer with efficient classification performance. To address the problems of unstable IOU convergence and inaccurate regression coordinates of the algorithm, this paper adopts Manhattan distance as the new penalty term, and the new loss function combines the advantages of Euclidean distance and Manhattan distance, which has no gradient explosion in the early training period and can drop smoothly to a stable point in the late training period. The proposed algorithm is robust to negative effects such as dust, light, shadows, and occlusions, and is well-suited for masked-face detection in industrial and public scenarios. The proposed model is tested on the VOC dataset and the AIZOO open-source masked-face dataset, obtaining 5.58% AP improvement on the VOC dataset and reaching 96.665% AP on the masked-face dataset, which is better than other algorithms. • Designing a deep neural network to use for masked-face detection. • Anchor-free model is used to avoid time-consuming post-processing. • The improved ConvNeXt network improves classification performance. • Adopting Manhattan distance-based localization loss makes training stable. • The Mosaic data augmentation strategy alleviates the overfitting problem. [ABSTRACT FROM AUTHOR]

The continuous malicious software (malware) attacks on smartphones pose a serious threat to the security of users, especially the dominant platform Android. Data-driven methods based on machine learning algorithms are a promising way to defend against that. In this paper, we explore the limitations of this kind of methods in improving the performance of malware detection, e.g., considering each feature in isolation and relying on balanced class data, and propose a multi-model ensemble framework MEFDroid by combining individual predictors, where hybrid deep learning based feature extraction methods are adopted to learn meaningful features from raw data. Besides, a novel fusion scheme is exploited to fuse multi-level representations and mine their correlations to maximize the utilization of original information. To evaluate the effectiveness of the MEFDroid framework, we conduct a step-by-step model justification experiment to investigate how the proposed algorithms (i.e., ESAES, EDAES and EDAFS) enhance the malware detection performance gradually. We also compare the proposed algorithms with classical machine learning methods, conventional sampling solutions for the imbalance problem. Besides, we investigate the reliability of our proposed methods using another public dataset. Our extensive experimental results demonstrate that the target model EDAFS in MEFDroid outperforms others in terms of most metrics, which means that it is an effective alternative solution to detect Android malware. [ABSTRACT FROM AUTHOR]

Non-contact identification of cattle is the basis for cattle management, insurance claims, and traceability of milk sources and meat products. In order to lower the threshold of deep learning technology in practical application and improve the recognition accuracy, this paper uses the localization and classification paradigm, fills the image and proposes the LKA (Locate Key Area) module, which further improves the identification accuracy of cattle without using any labeling information. To avoid the impact of different collection devices, we use three brands of mobile phones and two cameras to collect data. Due to the fact that CNN features do not have scale invariance, the image is filled as a square, and the filling value is discussed. Finally, (0,0,0) is selected for filling. In order to reduce the labeling of new data, the face, torso, and body of the cattle are first detected, and then automatically trimmed to build a classification dataset. In order to further improve the accuracy of classification, LKA module is proposed. This module locates key areas based on the results of class activation map and uses shallow features for monitoring. Thereby completing fine-grained feature extraction without supervision information. Finally, the features of different parts are adjusted for fusion recognition. Experiments were conducted on the head, torso, and whole of cattle. Based on the ResNet50 network architecture, after filling the image into a square, the recognition accuracy has been improved by 0.30%, 0.21%, and 0.43%, respectively. After further adding LKA modules, the accuracy rates were improved by 0.59%, 0.59%, and 0.45%, respectively. In the fusion experiment, ResNet50_LKA and MobileNetV3_LKA achieves 100% accuracy. Experiments have realized dataset construction and fine-grained feature extraction without labeled information, and achieved high recognition accuracy, proving the effectiveness of our method. [ABSTRACT FROM AUTHOR]

This aims to propose a collaborative filtering algorithm based on embedding representation and word embedding techniques, namely UI2vec. According to the joint feature extraction network designed in this paper, UI2vec embeds users and items on the potential space at the same time, and uses the item similarity between them to predict the user's content of interest. Then a generative model VUI2vec with more stable performance is proposed based on UI2vec, which maps users and items as independent Gaussian distributions and obtains the approximate posterior distribution of both by variational inference. The recommendation performance of UI2vec and VUI2vec is evaluated on TaFeng, Movielens, and Netflix datasets. The impact of important superparameters within the model on performance is investigated. The experimental results show that compared with the baseline model, the proposed methods performs consistently well. • UI2vec and VUI2vec as collaborative filtering-based recommendation systems. • It is based on embedding representation of users or items. • Performance is competitive with the state of the art on real-world datasets. • Results encourage integrating collaborative filtering with deep learning. [ABSTRACT FROM AUTHOR]

• 3 layer neural networks outperform other ML algorithms in automated assessments. • In subjective assignments, deep neural networks can improve score prediction. • Word embeddings and linguistic feature results in more precise text mining models. • Extraction and selection of appropriate features can improve results. Machine learning (ML) has recently gained popularity in a variety of domains for automating tasks. This has also been used in the evaluation of student responses/ assignments. This paper presents a qualitatively enhanced methodology for automated score prediction of subjective assignments. To consider all the major aspects of a human grader, 21 linguistic features related to syntactical, grammatical, sentimental, and readability are analyzed from the assignments. This study makes use of the ASAP competition dataset from Kaggle. The evaluation metric used is Quadratic Weighted Kappa (QWK), which measures the agreement between the human graded score and the predicted score. The effect of appropriate feature selection has been observed using Mutual Information Regression. Four ML algorithms are investigated on identified linguistic features. 3 Layer Neural Network with feature selection performed well among all chosen ML algorithms with average QWK of 0.678. To include the benefits of deep learning, a new hybrid model (LF-BiLSTM-att-FS) is proposed that combines a higher level deep neural network (DNN) with the selected features. Pre-trained Glove embedding is used to include contextual information of the text. The proposed model results demonstrated an improvement in overall accuracy, with an average QWK value of 0.768. [ABSTRACT FROM AUTHOR]

Research about recommender systems emerges over the last decade and comprises valuable services to increase different companies' revenue. While most existing recommender systems rely either on a content-based approach or a collaborative approach, there are hybrid approaches that can improve recommendation accuracy using a combination of both approaches. Even though many algorithms are proposed using such methods, it is still necessary for further improvement. This paper proposes a recommender system method using a graph-based model associated with the similarity of users' ratings in combination with users' demographic and location information. By utilizing the advantages of Autoencoder feature extraction, we extract new features based on all combined attributes. Using the new set of features for clustering users, our proposed approach (GHRS) outperformed many existing recommendation algorithms on recommendation accuracy. Also, the method achieved significant results in the cold-start problem. All experiments have been performed on the MovieLens dataset due to the existence of users' side information. • We propose a recommendation system using graph-based features and Autoencoders. • We investigate and analyze each step of the method to find the best setup. • We examine the method with the most popular evaluation metrics and datasets. • Results show an improvement in comparison with basic and state of the art methods. [ABSTRACT FROM AUTHOR]

[Display omitted] • SentiWordNet lexicon is used for generating sentiment features of email data. • Probabilistic Latent Semantic Analysis algorithm is used for clustering. • The sentiment sequence of thread and thread size are identified. • Evaluated the proposed model using accuracy, precision, recall and F-measure. Email messaging is the most common way of providing effective communication between internauts. Consequently, the total sent and received emails count will be increased. But, the internaut can't remember all such emails. Even though email thread identification approaches give satisfactory benefits to the internauts, but they may fail to alert them for a cause to identify the sentiments behind an email thread. To address, this issue Probabilistic Latent Semantic Analysis clustering algorithm has been used in this paper to identify the email sentiment thread sequence. The sentiment and the thread sequence within the emails have been discovered as clustering sentiment polarity and temporal categories with the help of PLSA clusters. At the initial stage, we used three feature extraction methods, latent semantic analysis (LDA), bag of words (BoW), TF-IDF and SentiWordNet (SWN) lexicon for generating sentiment features of email. Next, Probabilistic Latent Semantic Analysis algorithm is used to form email clusters based on sentiment features. Thus, it helps to identify thread sentiment and sequence of sentiment threads. Email threads give a mechanism by which any user will be able to find out the sequence in the thread on the basis of sentiment analysis of email related to a specific set of communication during a specific time period. Various parameters evaluation measures have been considered in this work to evaluate the proposed model such as accuracy, precision, recall and F-measure, and the proposed algorithm is compared with other standard algorithms. Furthermore, a statistical test has also been performed. [ABSTRACT FROM AUTHOR]

Feature selection in real-world data mining problems is essential to make the learning task efficient and more accurate. Identifying the best feature selection algorithm, among the many available, is a complex activity that still relies heavily on human experts or some random trial-and-error procedure. Thus, the automated machine learning community has taken some steps towards the automation of this process. In this paper, we address the metalearning challenge of recommending feature selection algorithms by proposing a novel meta-feature engineering model. Our model considers a broad collection of meta-features that enable the study of the relationship between the dataset properties and the feature selection algorithm performance in terms of several criteria. We arrange the input meta-features into eight categories: (i) simple, (ii) statistical, (iii) information-theoretical, (iv) complexity, (v) landmarking, (vi) based on symbolic models, (vii) based on images, and (viii) based on complex networks (graphs). The target meta-features emerge from a multi-criteria performance measure, based on five individual performance indexes, that assesses feature selection methods grounded in information, distance, dependence, consistency, and precision measures. We evaluate our proposal using a recently developed framework that extracts the input meta-features from 213 benchmark datasets, and ranks the assessed feature selection algorithms, to fill in the target meta-features in meta-bases. This evaluation uses five state-of-the-art classification methods to induce recommendation models from meta-bases: C4.5, Random Forest, XGBoost, ANN, and SVM. The results showed that it is possible to reach an average accuracy of up to 90% applying our meta-feature engineering model. This work is the first to use an extensive empirical evaluation to provide a careful discussion of the strengths and limitations of more than 160 meta-features. These meta-features, while designed to aid the task of feature selection algorithm recommendation, can readily be employed in other metalearning scenarios. Therefore, we believe our findings are a valuable contribution to the fields of automated machine learning and data mining, as well as to the feature extraction and pattern recognition communities. • A novel meta-feature engineering model recommends feature selection algorithms. • The proposal obtains promising results from 213 datasets with hit rates of up to 90%. • Some simple, landmarking, image, and graph-based input meta-features highlighted. • A multi-criteria performance measure rigorously assesses candidate algorithms. • Chains of binary or multiclass classifiers can efficiently rank candidate algorithms. [ABSTRACT FROM AUTHOR]