Similarity-based Methods Research Articles

Phishing webpage detection based on global and local visual similarity

In recent years, phishing websites have constantly evolved, causing traditional URL or HTML-based detection methods less effective. This limitation motivated the development of visual similarity-based detection methods. These methods can identify phishing websites in a rapidly changing phishing landscape since the key factor in deceiving users is the high visual similarity between phishing pages and their corresponding legitimate ones. However, existing similarity-based methods often suffer from high false positive rates. To alleviate the problem, this paper proposed a new webpage similarity phishing detection framework. Using a deep learning model, the framework locates a website logo and integrates the logo area with the full webpage to detect phishing pages. Experimental evaluations on multiple datasets demonstrate the model’s ability to achieve a precision of 91% and a recall of 88% in detecting phishing websites. Comparative experiments against existing methods reveal that the proposed model enhances precision and recall by 17% and 21%, respectively, while reducing the false positive rate by 1%.

Similarity-based active learning methods

Active Learning has been a popular method to circumvent the labeling cost in machine learning methods. The majority of active learning approaches can be classified into two categories: representative-based and informative-based methods, with some hybrid methods that combine both. This work presents a naïve query strategy, namely Similarity-Based Active Learning (SBAL), which computes the sum of a row in the similarity matrix at each selection step, and a general optimization framework that can accommodate a broad range of active learning algorithms. The label complexity for different classification metrics is used as a primary criterion for comparing different algorithms. The proposed algorithm’s numerical performance is illustrated using simulated data scenarios and by applying it to the real-world COVID-19 image classification. The results demonstrate that, based on the classification metric, labeling cost and label complexity, SBAL outperforms other hybrid methods, such as Adaptive Active Learning (AAL) and Maximizing Variance for Active Learning (MVAL).

SSGAN: A Semantic Similarity-Based GAN for Small-Sample Image Augmentation

Image sample augmentation refers to strategies for increasing sample size by modifying current data or synthesizing new data based on existing data. This technique is of vital significance in enhancing the performance of downstream learning tasks in widespread small-sample scenarios. In recent years, GAN-based image augmentation methods have gained significant attention and research focus. They have achieved remarkable generation results on large-scale datasets. However, their performance tends to be unsatisfactory when applied to datasets with limited samples. Therefore, this paper proposes a semantic similarity-based small-sample image augmentation method named SSGAN. Firstly, a relatively shallow pyramid-structured GAN-based backbone network was designed, aiming to enhance the model’s feature extraction capabilities to adapt to small sample sizes. Secondly, a feature selection module based on high-dimensional semantics was designed to optimize the loss function, thereby improving the model’s learning capacity. Lastly, extensive comparative experiments and comprehensive ablation experiments were carried out on the “Flower” and “Animal” datasets. The results indicate that the proposed method outperforms other classical GANs methods in well-established evaluation metrics such as FID and IS, with improvements of 18.6 and 1.4, respectively. The dataset augmented by SSGAN significantly enhances the performance of the classifier, achieving a 2.2% accuracy improvement compared to the best-known method. Furthermore, SSGAN demonstrates excellent generalization and robustness.

SEGCECO: Subgraph Embedding of Gene expression matrix for prediction of CEll-cell COmmunication.

Recent advances in single-cell RNA sequencing technology have eased analyses of signaling networks of cells. Recently, cell-cell interaction has been studied based on various link prediction approaches on graph-structured data. These approaches have assumptions about the likelihood of node interaction, thus showing high performance for only some specific networks. Subgraph-based methods have solved this problem and outperformed other approaches by extracting local subgraphs from a given network. In this work, we present a novel method, called Subgraph Embedding of Gene expression matrix for prediction of CEll-cell COmmunication (SEGCECO), which uses an attributed graph convolutional neural network to predict cell-cell communication from single-cell RNA-seq data. SEGCECO captures the latent and explicit attributes of undirected, attributed graphs constructed from the gene expression profile of individual cells. High-dimensional and sparse single-cell RNA-seq data make converting the data into a graphical format a daunting task. We successfully overcome this limitation by applying SoptSC, a similarity-based optimization method in which the cell-cell communication network is built using a cell-cell similarity matrix which is learned from gene expression data. We performed experiments on six datasets extracted from the human and mouse pancreas tissue. Our comparative analysis shows that SEGCECO outperforms latent feature-based approaches, and the state-of-the-art method for link prediction, WLNM, with 0.99 ROC and 99% prediction accuracy. The datasets can be found at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE84133 and the code is publicly available at Github https://github.com/sheenahora/SEGCECO and Code Ocean https://codeocean.com/capsule/8244724/tree.

Sample-Level Cross-View Similarity Learning for Incomplete Multi-View Clustering

Incomplete multi-view clustering has attracted much attention due to its ability to handle partial multi-view data. Recently, similarity-based methods have been developed to explore the complete relationship among incomplete multi-view data. Although widely applied to partial scenarios, most of the existing approaches are still faced with two limitations. Firstly, fusing similarities constructed individually on each view fails to yield a complete unified similarity. Moreover, incomplete similarity generation may lead to anomalous similarity values with column sum constraints, affecting the final clustering results. To solve the above challenging issues, we propose a Sample-level Cross-view Similarity Learning (SCSL) method for Incomplete Multi-view Clustering. Specifically, we project all samples to the same dimension and simultaneously construct a complete similarity matrix across views based on the inter-view sample relationship and the intra-view sample relationship. In addition, a simultaneously learning consensus representation ensures the validity of the projection, which further enhances the quality of the similarity matrix through the graph Laplacian regularization. Experimental results on six benchmark datasets demonstrate the ability of SCSL in processing incomplete multi-view clustering tasks. Our code is publicly available at https://github.com/Tracesource/SCSL.

CFSSynergy: Combining Feature-Based and Similarity-Based Methods for Drug Synergy Prediction.

Drug synergy prediction plays a vital role in cancer treatment. Because experimental approaches are labor-intensive and expensive, computational-based approaches get more attention. There are two types of computational methods for drug synergy prediction: feature-based and similarity-based. In feature-based methods, the main focus is to extract more discriminative features from drug pairs and cell lines to pass to the task predictor. In similarity-based methods, the similarities among all drugs and cell lines are utilized as features and fed into the task predictor. In this work, a novel approach, called CFSSynergy, that combines these two viewpoints is proposed. First, a discriminative representation is extracted for paired drugs and cell lines as input. We have utilized transformer-based architecture for drugs. For cell lines, we have created a similarity matrix between proteins using the Node2Vec algorithm. Then, the new cell line representation is computed by multiplying the protein-protein similarity matrix and the initial cell line representation. Next, we compute the similarity between unique drugs and unique cells using the learned representation for paired drugs and cell lines. Then, we compute a new representation for paired drugs and cell lines based on the similarity-based features and the learned features. Finally, these features are fed to XGBoost as a task predictor. Two well-known data sets were used to evaluate the performance of our proposed method: DrugCombDB and OncologyScreen. The CFSSynergy approach consistently outperformed existing methods in comparative evaluations. This substantiates the efficacy of our approach in capturing complex synergistic interactions between drugs and cell lines, setting it apart from conventional similarity-based or feature-based methods.

ISoLIM: a similarity-based spatial prediction software for the big data era

ABSTRACT Spatial prediction software is a valuable tool for predicting the spatial distribution of geographic variables and have a wide applicability with numerous non-expert users. However, as the input data to spatial prediction tasks gets more various in sources and larger in volume in the big data era, existing software are faced with challenges when processing such data on personal computers, which is one of the main platforms for running the software. This study uses the design and implementation of a similarity-based spatial prediction desktop software, the intelligent Soil Land Inference Model (iSoLIM), as an example to enable existing software to easily execute spatial prediction tasks with multi-source and large-volume data. The implemented similarity-based method was originally designed for digital soil mapping and has been applied to many other geographic variables. In the presented software, an expandable knowledge representation schema is adopted to intelligently manage multi-source knowledge data and enable knowledge integration; block division-based parallelization is adopted for intelligent computation arrangement on large-volume data. Experiments attest that, compared to existing software, iSoLIM can achieve higher accuracy from multi-source knowledge data by knowledge integration; and shows higher efficiency when processing data in large volume.

Complex hybrid weighted pruning method for accelerating convolutional neural networks

The increasing interest in filter pruning of convolutional neural networks stems from its inherent ability to effectively compress and accelerate these networks. Currently, filter pruning is mainly divided into two schools: norm-based and relation-based. These methods aim to selectively remove the least important filters according to predefined rules. However, the limitations of these methods lie in the inadequate consideration of filter diversity and the impact of batch normalization (BN) layers on the input of the next layer, which may lead to performance degradation. To address the above limitations of norm-based and similarity-based methods, this study conducts empirical analyses to reveal their drawbacks and subsequently introduces a groundbreaking complex hybrid weighted pruning method. By evaluating the correlations and norms between individual filters, as well as the parameters of the BN layer, our method effectively identifies and prunes the most redundant filters in a robust manner, thereby avoiding significant decreases in network performance. We conducted comprehensive and direct pruning experiments on different depths of ResNet using publicly available image classification datasets, ImageNet and CIFAR-10. The results demonstrate the significant efficacy of our approach. In particular, when applied to the ResNet-50 on the ImageNet dataset, achieves a significant reduction of 53.5% in floating-point operations, with a performance loss of only 0.6%.

Collaborative Filtering-based Fast Delay-aware algorithm for joint VNF deployment and migration in edge networks

As Network Function Virtualization (NFV) continues to advance, Virtual Network Functions (VNFs) such as firewalls are increasingly used. Service Function Chains (SFCs) are formed by combining specific VNFs in a particular order, which are then deployed on the physical network to provide dedicated services to end users. Occasionally, partial VNF migration is employed to maintain service and network stability. However, decision-making times and system delays may become unacceptable due to the heterogeneous resource requirements of VNFs and the massive state migration of VNFs, especially in Multi-access Edge Computing (MEC) networks where resources are scarce and demand fluctuations are frequent. To solve these challenges, we first formulate the problem of Minimizing decision Time and system Latency for joint VNF Deployment and Migration (MTLDM) as a multi-objective optimization problem. Then, we propose a Collaborative Filtering-based Fast Delay-aware algorithm (CFFD) to solve this problem. In this algorithm, we introduce an innovative approach, referred to as the collaborative filtering-based method, which utilizes the preference information of deployed/migrated VNFs to assist the current VNF deployment/migration in reducing decision-making time. Additionally, we design a similarity-based method in CFFD to search for suitable hosts for the current VNF, thereby reducing the complexity caused by heterogeneity and minimizing system latency. Furthermore, we implement a heuristic method in CFFD to increase the number of accepted requests. In the end, extensive simulations are conducted to evaluate the performance of CFFD in comparison with baseline algorithms and to select the suitable similarity algorithm. The results of the selection simulation show that Manhattan distance and cosine similarity are superior to Pearson’s correlation. Moreover, the comparison simulation results indicate that CFFD outperforms the baseline algorithms in terms of delay optimization and decision time by up to 22.08% and 99%, respectively.

Diversity, Characterization, and Potential Applications of Bacterial Endophytes Isolated from the Halophyte Limonium axillare

Recently, there has been a worldwide call to explore nature-friendly compounds, which could enhance plant growth and substitute for chemically synthesized products. Endophytes are a group of microorganisms that lives in the plants and algae symbiotically. In this research, endophytes were isolated from leaves of the halophyte, Limonium axillare. A total of 280 bacterial isolates were obtained from the leaves of L. axillare. Strains displaying similarities in terms of morphology and biochemical reactions were categorized into 48 groups. One representative from each group was identified and subjected to enzymatic and plant growth-promoting tests. Forty-eight isolates were identified using a sequence similarity-based method based on the 16S rDNA gene. The identified strains were categorized into two genera: Bacillus and Staphylococcus. Our investigation uncovered 44 isolates from the Bacillus genus, representing 10 different species, including Bacillus sp., B. pseudomycoides, B. cereus, B. paramycoides, B. velezensis, B. subtilis, B. thuringiensis, B. wiedmannii, B. anthracis, and B. bacterium. Furthermore, we observed that only 4 isolates belonged to the Staphylococcus genus, encompassing 3 distinct species: S. bacterium, S. succinus, and S. saprophyticus. The isolated bacteria were screened for extracellular enzymes, plant growth promoting traits, antifungal activity, and salinity tolerance. From the previous screening, diverse responses were obtained. Most of the isolates were secreted at least one of the hydrolysis enzymes (protease, lipase and amylase). (93.8%) of the strains showed phosphate solubilization activity. (33.3%) produce (IAA). Siderophore production potential was present in 91.7% of isolates, while ACC deaminase and HCN production activities were identified in 52.1 and 41.7% of strains, respectively. Additionally, DNase activity was evident in 27.1%, and ammonia production was observed in 31.3% of the isolates. The isolates Bacillus velezensis (AL4QUA) strain showed positive effect in the greenhouse experiment in terms of plant growth promoter agent and biocontrol agent against Fusarium oxysporum pathogen of tomato seedling. Thus, endophytes have the potential to reduce chemical inputs in conventional agricultural practices, increase nutrient uptake and improve plant stress resilience.

Neurosurgical literature classification – Evaluation of three automated methods and time trend analysis of the literature

BackgroundAutomated supervised text classification methods require preclassified training data. Their application in scenarios that a large amount of preclassified data is not accessible is challenging. Neurosurgical literature classification into subspecialties is an example of this situation. We have introduced an automated similarity-based text classification method, evaluated it along with two other automated methods and applied the introduced method in neurosurgical literature classification. MethodsPerformance of an introduced similarity-based text classification method along with two other automated methods (Lbl2Vec and keyword counting-based methods) was compared with performance of two senior neurosurgery registrars in classification of neurosurgical literature to 5 subspecialties. The Kappa-statistic measure of interrater agreement, overall marginal homogeneity using the Stuart-Maxwell test, marginal homogeneity relative to individual categories using McNemar tests and the sensitivity and specificity of each of the three methods were calculated.The introduced method was used to classify 211617 neurosurgical publications indexed in Pubmed to different subspecialties based on keywords extracted from subspecialty sections of a neurosurgery textbook. ResultsThe introduced similarity-based method showed the highest agreement with the registrars (raw agreement and Kappa value) followed by the Lbl2Vec and the counting-based method. Classifications of the English neurosurgical publications indexed in Pubmed into categories of Oncology, Vascular, Spine and functional using the introduced similarity-based method were more reliable (closer to the registrars’ classifications) than Cranial trauma. The classifications and future forecast showed highest publications in Oncology, followed by Cranial trauma, Vascular, spine and functional neurosurgery. ConclusionThe classification of the English neurosurgical publications indexed in Pubmed to different subspecialties, using the introduced method, shows that Oncology and tumour has been the main battleground for the neurosurgeons over years and probably in the near future. The performance of the introduced classification method in comparison with the human performance shows its potential application in the situations that enough preclassified data are not accessible for automated text classification.

ScEM: A New Ensemble Framework for Predicting Cell Type Composition Based on scRNA-Seq Data.

With the advent of single-cell RNA sequencing (scRNA-seq) technology, many scRNA-seq data have become available, providing an unprecedented opportunity to explore cellular composition and heterogeneity. Recently, many computational algorithms for predicting cell type composition have been developed, and these methods are typically evaluated on different datasets and performance metrics using diverse techniques. Consequently, the lack of comprehensive and standardized comparative analysis makes it difficult to gain a clear understanding of the strengths and weaknesses of these methods. To address this gap, we reviewed 20 cutting-edge unsupervised cell type identification methods and evaluated these methods comprehensively using 24 real scRNA-seq datasets of varying scales. In addition, we proposed a new ensemble cell-type identification method, named scEM, which learns the consensus similarity matrix by applying the entropy weight method to the four representative methods are selected. The Louvain algorithm is adopted to obtain the final classification of individual cells based on the consensus matrix. Extensive evaluation and comparison with 11 other similarity-based methods under real scRNA-seq datasets demonstrate that the newly developed ensemble algorithm scEM is effective in predicting cellular type composition.

Determining dense velocity fields for fluid images based on affine motion.

In this article, we address the problem of estimating fluid flows between two adjacent images containing fluid and non-fluid objects. Typically, traditional optical flow estimation methods lack accuracy, because of the highly deformable nature of fluid, the lack of definitive features, and the motion differences between fluid and non-fluid objects. Our approach captures fluid motions using an affine motion model for each small patch of an image. To obtain robust patch matches, we propose a best-buddies similarity-based method to address the lack of definitive features but many similar features in fluid phenomena. A dense set of affine motion models was then obtained by performing nearest-neighbor interpolation. Finally, dense fluid flow was recovered by applying the affine transformation to each patch and was improved by minimizing a variational energy function. Our method was validated using different types of fluid images. Experimental results show that the proposed method achieves the best performance.

Fuzzy-based video compression using bilinear fuzzy relation equations

We present a novel color video compression method using the greatest solution of a system of bilinear fuzzy relation equations to assess the similarity between frames. The frames in each band are treated separately and each frame is classified as an Intra frame or a Predictive frame. A frame is labelled as Predictive frame, and compressed more than an Intra-frame, if the similarity value with the previous Intra frame is higher than a selected threshold; A pre-processing activity is performed to select the optimal threshold value of the similarity between frames. The proposed method allows to supply a high quality of the reconstructed frames and has the advantage of not requiring high CPU time and memory storage for its execution; it was tested on color videos of the Fast-Moving Objects dataset; the results show that it produces better performances than the Lukasiewicz similarity-based video compression method and comparable with those achieved by MPEG-4 and the deep learning video compression method DVC_pro. The results show that the quality of the reconstructed frames obtained with BFRE is comparable with that of DVC Pro, but has a lower computational complexity, providing better performances in terms of video encoding speed.

DeTox: a pipeline for the detection of toxins in venomous organisms.

Venomous organisms have independently evolved the ability to produce toxins 101 times during their evolutionary history, resulting in over 200000 venomous species. Collectively, these species produce millions of toxins, making them a valuable resource for bioprospecting and understanding the evolutionary mechanisms underlying genetic diversification. RNA-seq is the preferred method for characterizing toxin repertoires, but the analysis of the resulting data remains challenging. While early approaches relied on similarity-based mapping to known toxin databases, recent studies have highlighted the importance of structural features for toxin detection. The few existing pipelines lack an integration between these complementary approaches, and tend to be difficult to run for non-experienced users. To address these issues, we developed DeTox, a comprehensive and user-friendly tool for toxin research. It combines fast execution, parallelization and customization of parameters. DeTox was tested on published transcriptomes from gastropod mollusks, cnidarians and snakes, retrieving most putative toxins from the original articles and identifying additional peptides as potential toxins to be confirmed through manual annotation and eventually proteomic analysis. By integrating a structure-based search with similarity-based approaches, DeTox allows the comprehensive characterization of toxin repertoire in poorly-known taxa. The effect of the taxonomic bias in existing databases is minimized in DeTox, as mirrored in the detection of unique and divergent toxins that would have been overlooked by similarity-based methods. DeTox streamlines toxin annotation, providing a valuable tool for efficient identification of venom components that will enhance venom research in neglected taxa.

Association of the PageRank algorithm with similarity-based methods for link prediction in complex networks

Link prediction is an axial field in complex network analysis as it aims to infer new connections between nodes in a given network. Many applications of this task include: the reference system, the suggestion of friends in the social network and the prediction of interactions between proteins in biological networks. Several methods have been developed in the link prediction task, especially the similarity-based methods which are widely used due to their low complexity and good performance. In this paper, we propose a novel link prediction approach that combines the PageRank algorithm with local information-based methods to improve performance while retaining the advantage of low complexity of local methods. We conducted a series of experimental studies on eleven data sets where we compared our new combined methods with six well-known local methods. The results obtained show a significant gain in terms of performance in almost all data sets. In addition to this and to confirm the superiority of the proposed methods, another comparative study is performed, formed of nine local and global methods. According to the experimental results, our approach outperforms all other compared methods with linear complexity.

Community-enhanced Link Prediction in Dynamic Networks

The growing popularity of online social networks is quite evident nowadays and provides an opportunity to allow researchers in finding solutions for various practical applications. Link prediction is the technique of understanding network structure and identifying missing and future links in social networks. One of the well-known classes of methods in link prediction is a similarity-based method, which uses local and global topological information of the network to predict missing links. Some methods also exist based on quasi-local features to achieve a trade-off between local and global information on static networks. These quasi-local similarity-based methods are not best suited for considering community information in dynamic networks, failing to balance accuracy and efficiency. Therefore, a community-enhanced framework is presented in this article to predict missing links on dynamic social networks. First, a link prediction framework is presented to predict missing links using parameterized influence regions of nodes and their contribution in community partitions. Then, a unique feature set is generated using local, global, and quasi-local similarity-based as well as community information-based features. This feature set is further optimized using scoring-based feature selection methods to select only the most relevant features. Finally, four machine learning-based classification models are used for link prediction. The experiments are performed on six well-known dynamic networks and three performance metrics, and the results demonstrate that the proposed method outperforms the state-of-the-art methods.

An Overview of Similarity-Based Methods in Predicting Social Network Links: A Comparative Analysis

An Overview of Similarity-Based Methods in Predicting Social Network Links: A Comparative Analysis

A vector projection similarity-based method for miRNA-disease association prediction

[S U M M A R Y] Many miRNA-disease association prediction models incorporate Gaussian interaction profile kernel similarity (GIPS). However, the GIPS fails to consider the specificity of the miRNA-disease association matrix, where matrix elements with a value of 0 represent miRNA and disease relationships that have not been discovered yet. To address this issue and better account for the impact of known and unknown miRNA-disease associations on similarity, we propose a method called vector projection similarity-based method for miRNA-disease association prediction (VPSMDA). In VPSMDA, we introduce three projection rules and combined with logistic functions for the miRNA-disease association matrix and propose a vector projection similarity measure for miRNAs and diseases. By integrating the vector projection similarity matrix with the original one, we obtain the improved miRNA and disease similarity matrix. Additionally, we construct a weight matrix using different numbers of neighbors to reduce the noise in the similarity matrix. In performance evaluation, both LOOCV and 5-fold CV experiments demonstrate that VPSMDA outperforms seven other state-of-the-art methods in AUC. Furthermore, in a case study, VPSMDA successfully predicted 10, 9, and 10 out of the top 10 associations for three important human diseases, respectively, and these predictions were confirmed by recent biomedical resources.

Modeling of small molecule's affinity to phospholipids using IAM-HPLC and QSRR approach enhanced by similarity-based machine algorithms

Immobilized artificial membrane chromatography (IAM) has been proposed as a more biosimilar alternative to classical lipophilicity measurement. Determination of small molecule's affinity to phospholipids can be supported for predicting their behavior in the human body. Therefore, a better understanding of the molecular interaction mechanism between small xenobiotics and phospholipids can accelerate drug discovery. Here, the quantitative structure-retention relationships (QSRR) approach was integrated with mechanistic descriptors calculated using Chemicalize software to propose an easy-to-interpretation QSRR model. Considering the heterogeneous character of the data set, locally weighted least squares kernel regression belonging to similarity-based machine learning methods have been applied. The results showed that lipophilicity, charge, and maximum projection area determine molecule binding to phospholipids. Full validation of the obtained model based on OECD recommendations has been performed and the applicability domain was defined using the probability-oriented distance-based approach. The high values of predictive squared correlation coefficient (Q2), and small root mean square error of prediction (RMSEP), 0.812 and 6.739, respectively, confirmed that the obtained QSRR model is not well-fitted to the training data but also showed prediction power. Additionally, only 1.5% of molecules from the training set and 2.8% from the validation test are outside the applicability domain, confirming great predictive abilities.