Similar Calculations Research Articles

Improved Collaborative Filtering Recommender System Based on Hybrid Similarity Measures

Recommender Systems (RS) based on collaborative filtering has been successfully applied to provide relevant and personalized recommendations from an enormous amount of data in various domains. To achieve this, similarity measurements, such as the Pearson Correlation Coefficient (PCC), Cosine, and Jaccard, are used to compute the similarity between users or items based on correlations among user preferences from the user-item rating matrix. However, existing similarity metrics suffer from drawbacks emanating from data sparsity caused by insufficient number of transactions and feedback and scalability of the system’s ability to handle increasing amounts of data efficiently. The objective of this study is to improve the recommendation quality and increase the prediction accuracy by addressing the problems of similarity computation in collaborative filtering. This paper presents a hybrid similarity measure that combines Adjusted Triangle similarity, User Rating Preference behavior, and the Jaccard (ATURPJ) coefficient. The proposed hybrid similarity measures were evaluated on four widely used and publicly available datasets, MovieLens, FilmTrust, and CiaoDVD, using the predictive accuracy metrics of Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) and recommendation quality of Precision, Recall, and F-measure. The experimental results show that the proposed hybrid similarity measure significantly outperforms existing approaches with MAE of 0.547 and RMSE of 0.735 compared to the baseline of 0.707 and 0.903 respectively on ML-100k dataset. Overall, this approach has the potential to improve the quality of recommendation and accuracy of the prediction

Bio-Inspired Algorithms in Healthcare

Exploring hidden patterns in medical data sets is made possible by the huge potential of medical data mining. A clinical diagnosis can be made with the help of these patterns. Research on bio-inspired algorithms is a recent development. Its primary benefit is its ability to weave together social behavior, emergence, and connectionism subfields. In a nutshell, it involves modeling live phenomena using computers while studying life to make better computer applications. This chapter describes the application of five bio-inspired algorithms, including metaheuristics, to classify seven distinct real health-related information sets. While the other two of these methods rely on random population creation to create classification rules, the other two rely on the computation of similarity between the data used for training and testing. The outcomes demonstrated that bio-inspired supervised medical data classification methods were incredibly effective.

A computational model for angular velocity integration in a locust heading circuit.

Accurate navigation often requires the maintenance of a robust internal estimate of heading relative to external surroundings. We present a model for angular velocity integration in a desert locust heading circuit, applying concepts from early theoretical work on heading circuits in mammals to a novel biological context in insects. In contrast to similar models proposed for the fruit fly, this circuit model uses a single 360° heading direction representation and is updated by neuromodulatory angular velocity inputs. Our computational model was implemented using steady-state firing rate neurons with dynamical synapses. The circuit connectivity was constrained by biological data, and remaining degrees of freedom were optimised with a machine learning approach to yield physiologically plausible neuron activities. We demonstrate that the integration of heading and angular velocity in this circuit is robust to noise. The heading signal can be effectively used as input to an existing insect goal-directed steering circuit, adapted for outbound locomotion in a steady direction that resembles locust migration. Our study supports the possibility that similar computations for orientation may be implemented differently in the neural hardware of the fruit fly and the locust.

TorchGeo: Deep Learning With Geospatial Data

Remotely sensed geospatial data are critical for applications including precision agriculture, urban planning, disaster monitoring and response, and climate change research, among others. Deep learning methods are particularly promising for modeling many remote sensing tasks given the success of deep neural networks in similar computer vision tasks and the sheer volume of remotely sensed imagery available. However, the variance in data collection methods and handling of geospatial metadata make the application of deep learning methodology to remotely sensed data nontrivial. For example, satellite imagery often includes additional spectral bands beyond red, green, and blue and must be joined to other geospatial data sources that may have differing coordinate systems, bounds, and resolutions. To help realize the potential of deep learning for remote sensing applications, we introduce TorchGeo, a Python library for integrating geospatial data into the PyTorch deep learning ecosystem. TorchGeo provides data loaders for a variety of benchmark datasets, composable datasets for uncurated geospatial data sources, samplers for geospatial data, and transforms that work with multispectral imagery. TorchGeo is also the first library to provide pre-trained models for multispectral satellite imagery (e.g., models that use all bands from the Sentinel-2 satellites), allowing for advances in transfer learning on downstream remote sensing tasks with limited labeled data. We use TorchGeo to create reproducible benchmark results on existing datasets and benchmark our proposed method for preprocessing geospatial imagery on the fly. TorchGeo is open source and available on GitHub: https://github.com/microsoft/torchgeo.

A Chinese Short Text Similarity Method Integrating Sentence-Level and Phrase-Level Semantics

Short text similarity, as a pivotal research domain within Natural Language Processing (NLP), has been extensively utilized in intelligent search, recommendation systems, and question-answering systems. Most existing short-text similarity models focus on aligning the overall semantic content of an entire sentence, often ignoring the semantic associations between individual phrases in the sentence. It is particular in the Chinese context, as synonyms and near-synonyms can cause serious interference in the computation of text similarity. To overcome these limitations, a novel short text similarity computation method integrating both sentence-level and phrase-level semantics was proposed. By harnessing vector representations of Chinese words/phrases as external knowledge, this approach amalgamates global sentence characteristics with local phrase features to compute short text similarity from diverse perspectives, spanning from the global to the local level. Experimental results demonstrate that the proposed model outperforms previous methods in the Chinese short text similarity task. Specifically, the model achieves an accuracy of 90.16% in LCQMC, which is 2.23% and 1.46%, respectively, better than ERNIE and Glyce + BERT.

Simignore: Exploring and enhancing multimodal large model complex reasoning via similarity computation.

Recently, the field of multimodal large language models (MLLMs) has grown rapidly, with many Large Vision-Language Models (LVLMs) relying on sequential visual representations. In these models, images are broken down into numerous tokens before being fed into the Large Language Model (LLM) alongside text prompts. However, the opaque nature of these models poses significant challenges to their interpretability, particularly when dealing with complex reasoning tasks. To address this issue, we utilized Grad-CAM to investigate the interaction dynamics between images and text within complex reasoning processes. Our information flow analysis revealed a distinct pattern: it tends to converge in the initial layers and then disperse as it progresses through deeper layers. This pattern suggests that the early stages of processing focus on the interaction between visual and textual elements, while later stages engage in deeper reasoning. We developed Simignore, a novel image token reduction technique based on this insight. Simignore enhances the model's complex reasoning capabilities by calculating the similarity between image and text embeddings, thereby ignoring tokens that are not semantically relevant. Extensive experiments across different MLLM architectures have shown that our approach consistently improves performance in complex reasoning tasks. This work not only contributes to the advancement of MLLM interpretability but also provides a robust framework for future research in this area. The paper's source code can be accessed from https://github.com/FanshuoZeng/Simignore.

Deep Learning Approaches for Similarity Computation: A Survey

Deep Learning Approaches for Similarity Computation: A Survey

Molecular modeling of cellulose tosylate immobilized α-amylases: An in silico case study through MD simulation and refinement.

The use of enzymes as catalysts in industrial processes has been studied, and they offer more ecologically friendly options for chemical reactions. In the current work, we investigated the potential of molecular modeling to solve the ordinarily difficult problem of identifying the amino acids involved in the covalent mode of immobilization by in silico investigations. The immobilized α-Amylase on Cellulose tosylate (henceforth referred to as Celltos) shows extra peaks of OH and NH2, CN, SO, C-O-C, and CS. Celltos exhibits distinct ether, imine, and CS peaks, indicating the potential contribution of α-Amylase's hydroxyl, amino, and thiol groups towards immobilization with cellulose's tosylate group. The native amylase was processed for Molecular Dynamics simulation. The simulated amylase was found to be the root mean squarely deviated to 1.16 Å. Autodock Vina, GOLD, SwissDock, and iGemdock generate output averages of 6.164, 6.549, 9.313 & 137.811 and 5.903, 7.656, 9.752 & 132.218 for an unrefined and refined dataset, respectively. The catalytic site intactness values for unrefined and refined SAT9, SAT13, and LAT21 were 83.3 %, 100 %, 100 %, and 8.33 %, 0 %, and 0 %, respectively. Our findings were additionally confirmed by bond distance similarity computations.

Enhancing Plant Species Retrieval in Flora Through Language Model Integration

Traditionally, textual data storage and retrieval systems were designed primarily for human reading, mainly relying on paper records. However, as information technology has advanced, computerized searches have become common. However, Boolean logic-based data retrieval systems often struggle to handle data's diversity and richness effectively. These systems rely on strict matching rules, which can lead to either too few or too many results. For example, when searching for plant species descriptions, a query like "circle" AND "ellipse" may exclude relevant records that describe these traits using slightly different terms (e.g., "round" or "oval"). Conversely, broader queries like "oblong" may return an overwhelming number of irrelevant results. This rigidity limits the system's ability to adapt to the nuanced and varied ways users describe data. With the advent of advanced semantic models such as SBERT (Sentence-Bidirectional Encoder Representations from Transformers) (Reimers and Gurevych 2019), we can now delve deeper into the semantic relationships within textual data. Unlike general-purpose large language models, SBERT is specifically designed for efficient semantic similarity computation. In plant taxonomy, records in Flora, such as Flora of Taiwan or Flora of China, play a crucial role in understanding plant diversity in specific regions. These records provide critical information on plant growth environments, morphological characteristics, and economic values. Our research aims to enhance the efficiency of retrieving plant data using language models. Specifically, we transform textual descriptions from Flora and user queries into vector representations (Fig. 2) and calculate their cosine similarity to determine the relevance between user inputs and species records. Cosine similarity, a metric commonly used in text mining and information retrieval, quantifies the similarity between two vectors by measuring the cosine of the angle between them. The similarity score ranges from -1 (completely dissimilar) to 1 (identical), where higher scores indicate greater similarity. By applying this method, we can provide users with ranked scores of plant species related to their queries (Fig. 1). This approach not only streamlines data retrieval but also introduces new perspectives for botanical research and data management, fostering a more efficient exploration of plant diversity. Our results demonstrate the potential of language models to facilitate biodiversity research and data management, especially in retrieving plant taxonomy information. Our approach provides a novel tool for future biodiversity data analysis and retrieval, thereby contributing to the progress of biodiversity conservation.

SAMFL: Secure Aggregation Mechanism for Federated Learning with Byzantine-robustness by functional encryption

Federated learning (FL) enables collaborative model training without sharing private data, thereby potentially meeting the growing demand for data privacy protection. Despite its potentials, FL also poses challenges in achieving privacy-preservation and Byzantine-robustness when handling sensitive data. To address these challenges, we present a novel Secure Aggregation Mechanism for Federated Learning with Byzantine-Robustness by Functional Encryption (SAMFL). Our approach designs a novel dual-decryption multi-input functional encryption (DD-MIFE) scheme, which enables efficient computation of cosine similarities and aggregation of encrypted gradients through a single ciphertext. This innovative scheme allows for dual decryption, producing distinct results based on different keys, while maintaining high efficiency. We further propose TF-Init, integrating DD-MIFE with Truth Discovery (TD) to eliminate the reliance on a root dataset. Additionally, we devise a secure cosine similarity calculation aggregation protocol (SC2AP) using DD-MIFE, ensuring privacy-preserving and Byzantine-robust FL secure aggregation. To enhance FL efficiency, we employ single instruction multiple data (SIMD) to parallelize encryption and decryption processes. Concurrently, to preserve accuracy, we incorporate differential privacy (DP) with selective clipping of model layers within the FL framework. Finally, we integrate TF-Init, SC2AP, SIMD, and DP to construct SAMFL. Extensive experiments demonstrate that SAMFL successfully defends against both inference attacks and poisoning attacks, while improving efficiency and accuracy compared to existing methods. SAMFL provides a comprehensive integrated solution for FL with efficiency, accuracy, privacy-preservation, and robustness.

Research on positive and negative sample sampling strategies in contrastive learning

Abstract. Contrastive learning is an important technique in the field of machine learning for learning data representations. In the field of self-supervised visual representation learning, the strategy of positive and negative sample selection is key to improving the efficiency and effectiveness of model learning. Traditional self-supervised learning methods often employ random sampling strategies to select positive and negative samples, but this approach may result in uneven sample quality when dealing with complex datasets, thereby affecting the learning outcomes. To alleviate this problem, this study is dedicated to exploring more effective strategies for positive and negative sample selection and processing to optimize the self-supervised learning process. To this end, we propose an improved method of self-supervised learning called contrastive learning with enhanced diversity. On the one hand, this method utilizes the weight parameters of the DINO pre-trained model to initialize the feature extraction network of SimCLR, providing more accurate calculations of feature similarity. On the other hand, by setting a threshold on the feature similarity matrix and penalizing (subtracting 0.5 from) similarity scores that do not exceed this threshold, we reduce the excessive impact of high similarity scores on model training, thereby helping the model better distinguish between positive and negative samples. In downstream image classification tasks, we conducted detailed evaluations of the improved model, specifically including fine-tuning and linear evaluation aspects. Experiments show that the proposed approach improves the performance of the loss functions and improves the accuracy of the proposed SimCLR model.

Application of Binary Image Quality Assessment Methods to Predict the Quality of Optical Character Recognition Results

One of the continuous challenges related to the growing popularity of mobile devices and embedded systems with limited memory and computational power is the development of relatively fast methods for real-time image and video analysis. One such example is Optical Character Recognition (OCR), which is usually too complex for such devices. Considering that images captured by cameras integrated into mobile devices may be acquired in uncontrolled lighting conditions, some quality issues related to non-uniform illumination may affect the image binarization results and further text recognition results. The solution proposed in this paper is related to a significant reduction in the computational burden, preventing the necessity of full text recognition. Conducting only the initial image binarization using various thresholding methods, the computation of the mutual similarities of binarization results is proposed, making it possible to build a simple model of binary image quality for a fast prediction of the OCR results’ quality. The experimental results provided in the paper obtained for the dataset of 1760 images, as well as the additional verification for a larger dataset, confirm the high correlation of the proposed quality model with text recognition results.

More Interpretable Graph Similarity Computation via Maximum Common Subgraph Inference

More Interpretable Graph Similarity Computation via Maximum Common Subgraph Inference

UAV Geo-Localization Dataset and Method Based on Cross-View Matching.

The stable flight of drones relies on Global Navigation Satellite Systems (GNSS). However, in complex environments, GNSS signals are prone to interference, leading to flight instability. Inspired by cross-view machine learning, this paper introduces the VDUAV dataset and designs the VRLM network architecture, opening new avenues for cross-view geolocation. First, to address the limitations of traditional datasets with limited scenarios, we propose the VDUAV dataset. By leveraging the virtual-real mapping of latitude and longitude coordinates, we establish a digital twin platform that incorporates 3D models of real-world environments. This platform facilitates the creation of the VDUAV dataset for cross-view drone localization, significantly reducing the cost of dataset production. Second, we introduce a new baseline model for cross-view matching, the Virtual Reality Localization Method (VRLM). The model uses FocalNet as its backbone and extracts multi-scale features from both drone and satellite images through two separate branches. These features are then fused using a Similarity Computation and Feature Fusion (SCFF) module. By applying a weighted fusion of multi-scale features, the model preserves critical distinguishing features in the images, leading to substantial improvements in both processing speed and localization accuracy. Experimental results demonstrate that the VRLM model outperforms FPI on the VDUAV dataset, achieving an accuracy increase to 83.35% on the MA@20 metric and a precision of 74.13% on the RDS metric.

A graph similarity measurement algorithm combining global and local fine-grained features

Graph Similarity Computation (GSC) is not only a basic operation of graph similarity search, but also plays an important role in many application fields, including drug design, program analysis and social group identification. Since calculating the exact distance or similarity between two graphs is usually an NP-hard problem, the tradeoff between precision and speed needs to be addressed. In this paper, a pooling-based graph neural network method is proposed, which effectively integrates the coarse-grained interaction features of the two graph data and the fine -grained interaction features of the nodes between the subgraphs, and further reduce the computational cost while ensuring the accuracy. The experimental results show that the proposed method has good performance on real graph data sets. Compared with previous methods, the proposed method not only improves the accuracy but also improves the computational efficiency.

Cross-Lingual Short-Text Semantic Similarity for Kannada–English Language Pair

Analyzing the semantic similarity of cross-lingual texts is a crucial part of natural language processing (NLP). The computation of semantic similarity is essential for a variety of tasks such as evaluating machine translation systems, quality checking human translation, information retrieval, plagiarism checks, etc. In this paper, we propose a method for measuring the semantic similarity of Kannada–English sentence pairs that uses embedding space alignment, lexical decomposition, word order, and a convolutional neural network. The proposed method achieves a maximum correlation of 83% with human annotations. Experiments on semantic matching and retrieval tasks resulted in promising results in terms of precision and recall.

Towards Mapping Place Semantics: A Geosocial Media Data Approach for Geo-Semantic Analysis and Place Similarity Computation

Towards Mapping Place Semantics: A Geosocial Media Data Approach for Geo-Semantic Analysis and Place Similarity Computation

Dual-neighbourhood information aggregation and feature fusion for prediction of miRNA–disease association

Studying the intricate relationship between miRNAs and diseases is crucial to prevent and treat miRNA-related disorders. Existing computational methods often overlook the importance of features of different nodes and the propagation of features among heterogeneous nodes. Many prediction models focus only on the feature coding of miRNA and diseases and ignore the importance of feature aggregation. We propose a prediction method via dual-neighbourhood feature aggregation and feature fusion, which uses multiple sources of information, aggregates information on homogeneous and heterogeneous nodes and fuses learned features to predict multiple representations of disease nodes. We constructed similarity networks of multiple homogeneous nodes based on different similarity computation methods respectively, and fused the attention mechanism by using graph convolutional networks to obtain information of different levels of importance. To alleviate the problem of sparse connectivity in the dataset, we built a two-neighbourhood heterogeneous graph neural network model to integrate the homogeneous similarity network into a miRNA-disease heterogeneous network by using known miRNA–disease association information. We used the neighbourhood information associated with the nodes in the network to perform feature aggregation. In addition, we used a feature fusion module to learn the importance of different types of nodes to predict miRNA–disease associations. Our experimental results on the Human microRNA Disease Database (HMDD v3.2) show that the model demonstrates superior performance. This work demonstrates the capability of our model to identify potential miRNAs associated with diseases through a case study of two common cancers.

Secure similar patients query with homomorphically evaluated thresholds

Patient-centric precision medicine requires the analysis of large volumes of genomic data to tailor treatments and medications based on individual-level characteristics. Because the amount of data held by a single institution is limited, researchers may want access to genomic data held by other institutions. Owing to the inherent privacy implications of genomic data, performing comparisons on encrypted data is preferable in certain settings. The Similar patient query (SPQ) is an application that enables a secure search across genomic databases for patients with similar genetic makeup. Query results can be used to draw meaningful conclusions regarding suitable therapies.However, existing protocols either reveal intermediate computations, such as similarity scores, which can lead to membership-inference attacks, or they realize the ideal Boolean output (similar/not similar) through multiple protocol rounds, requiring the database owners to stay online throughout.This paper introduces a two-party privacy-preserving approach to perform SPQs across encrypted genomic databases based on secure function extensions of additively homomorphic encryption. In contrast to related works, our scheme enables secure computation of genomic data similarity without an external party in a single round. This is achieved for more than 1000 positions of a genome in a single public key operation of 256-bit security level in the integer factorization setting.

Feature Enhanced Spatial–Temporal Trajectory Similarity Computation

AbstractTrajectory similarity computation is a fundamental function in many applications of urban data analysis, such as trajectory clustering, trajectory compression, and route planning. In this paper, we study trajectory similarity computation on the road network. However, existing methods have been designed primarily for road network trajectories with spatial information, while ignoring the important temporal information in the real world. To solve this problem, we propose a Feature Enhanced Spatial–Temporal trajectory similarity computation framework FEST, which is a graph neural network (GNN) and sequence model pipeline. We first use the GNN model to capture global information on the road network. In particular, we enhance the process with multi-graph to learn multiple signals from the road network on different aspects. In addition to the original road network topology signal, we also take into account the content signal to learn spatial–temporal features from trajectory traffic, as well as the adaptive similarity signal of the road network to learn hidden features. From these three signals, we construct a multi-graph and use GCN to learn road intersection embedding jointly. Next, we propose a feature-enhanced Transformer with spatial–temporal information to learn correlation within the trajectory, and we further use mean-pooling to get the final trajectory embedding. We compare FEST with six trajectory similarity computation methods on two real-world datasets. The results show that FEST consistently outperforms all baselines and can improve the accuracy of the best-performing baseline.