Cosine Similarity Research Articles

Residual cosine similar attention and bidirectional convolution in dual-branch network for skin lesion image classification

Skin cancer is one of the most serious threats to human health among skin lesions. Computer-aided diagnosis methods can assist patients in identifying and detecting skin lesion types early, thereby enabling corresponding treatments. In this paper, we propose a dual-branch neural network model Conformer with Residual Cosine Similarity Attention and Bidirectional Convolutional fusion strategy, named RCSABC-Conformer. The core of this network structure comprises three parts: a Convolutional Neural Network (CNN) branch with Residual Cosine Similarity Attention (RCSA), a Transformer branch, and a Feature Couple Unit with Bidirectional Convolutional strategy (BC-FCU). The RCSA module calculates the cosine similarity value between the feature map generated by the convolutional operation and the feature map of the residual edge to assess whether their semantic information is similar. The semantic information of similar parts is weighted by exponential normalization to enhance the network's memory of similar features of the same type of skin lesion. The BC-FCU module interactively fuses local features and global representations of skin lesion images with different resolutions in the two branches. Specifically, when the global representations is integrated into local features, we introduce a new bidirectional convolution strategy to extract the feature map from both forward and backward directions, and then select the element with the smaller feature value from the two directions to fuse into local features. In this way, we can minimize the interference of the artifact features extracted by the Transformer branch on the CNN branch. In addition, taking advantage of the Transformer branch's capacity to construct global representations, our model can learn contextual semantic information of normal skin and lesion areas to enhance model robustness. We conducted experiments on three datasets, consisting of clinical and dermoscopic skin lesion images, as well as a hybrid of both. The experimental results show that RCSABC-Conformer outperforms both advanced and classical classification methods in terms of classification accuracy across all three datasets, without requiring an increase in the number of parameters and computational complexity. Compared with the baseline model, the classification accuracy of our proposed method improves by 2.40%, 5.39%, and 4.44% on the three datasets, respectively. To the best of our knowledge, this is the first study to apply an interactive fusion dual-branch network for multi-disease classification on different modalities of skin lesion databases. Code will be available at https://github.com/AlenLi817/RCSABC-Conformer.

Hybrid Approach to Improve Recommendation of Cloud Services for Personalized QoS Requirements

Cloud-service recommendation systems make suggestions based on ratings provided by cloud users. These ratings may contain sparse data, which makes it difficult to speculate on suitable cloud services. Moreover, new cloud users often suffer from cold-start difficulties. Therefore, in this study, we attempt to better overcome these two challenges, i.e., cold start and data sparsity, using a hybrid approach incorporating neural matrix factorization, deep autoencoders, and suitable questionnaires. The proposed approach provides a list of the top N cloud service providers for old cloud users based on the predicted preferences using quality of service data and asymmetrically weighted cosine similarity. To address the cold start problem, we design a questionnaire to survey new user preferences and suggest personalized cloud providers accordingly. The experiments based on the Cloud Armor database demonstrate that our approach outperforms other models. The proposed approach has a precision of 85% and achieves a mean absolute error (MAE) of 0.05 and root-mean-square error (RMSE) of 0.14 for the differences between the input and predicted values. We also receive a satisfaction level of nearly 78.5% for recommendation lists provided to new cloud service customers.

Web Application for Retrieval-Augmented Generation: Implementation and Testing

The purpose of this paper is to explore the implementation of retrieval-augmented generation (RAG) technology with open-source large language models (LLMs). A dedicated web-based application, PaSSER, was developed, integrating RAG with Mistral:7b, Llama2:7b, and Orca2:7b models. Various software instruments were used in the application’s development. PaSSER employs a set of evaluation metrics, including METEOR, ROUGE, BLEU, perplexity, cosine similarity, Pearson correlation, and F1 score, to assess LLMs’ performance, particularly within the smart agriculture domain. The paper presents the results and analyses of two tests. One test assessed the performance of LLMs across different hardware configurations, while the other determined which model delivered the most accurate and contextually relevant responses within RAG. The paper discusses the integration of blockchain with LLMs to manage and store assessment results within a blockchain environment. The tests revealed that GPUs are essential for fast text generation, even for 7b models. Orca2:7b on Mac M1 was the fastest, and Mistral:7b had superior performance on the 446 question–answer dataset. The discussion is on technical and hardware considerations affecting LLMs’ performance. The conclusion outlines future developments in leveraging other LLMs, fine-tuning approaches, and further integration with blockchain and IPFS.

Rev1 overexpression accelerates N-methyl-N-nitrosourea (MNU)-induced thymic lymphoma by increasing mutagenesis.

Rev1 has two important functions in the translesion synthesis pathway, including dCMP transferase activity, and acts as a scaffolding protein for other polymerases involved in translesion synthesis. However, the role of Rev1 in mutagenesis and tumorigenesis invivo remains unclear. We previously generated Rev1-overexpressing (Rev1-Tg) mice and reported that they exhibited a significantly increased incidence of intestinal adenoma and thymic lymphoma (TL) after N-methyl-N-nitrosourea (MNU) treatment. In this study, we investigated mutagenesis of MNU-induced TL tumorigenesis in wild-type (WT) and Rev1-Tg mice using diverse approaches, including whole-exome sequencing (WES). In Rev1-Tg TLs, the mutation frequency was higher than that in WT TL in most cases. However, no difference in the number of nonsynonymous mutations in the Catalogue of Somatic Mutations in Cancer (COSMIC) genes was observed, and mutations involved in Notch1 and MAPK signaling were similarly detected in both TLs. Mutational signature analysis of WT and Rev1-Tg TLs revealed cosine similarity with COSMIC mutational SBS5 (aging-related) and SBS11 (alkylation-related). Interestingly, the total number of mutations, but not the genotypes of WT and Rev1-Tg, was positively correlated with the relative contribution of SBS5 in individual TLs, suggesting that genetic instability could be accelerated in Rev1-Tg TLs. Finally, we demonstrated that preleukemic cells could be detected earlier in Rev1-Tg mice than in WT mice, following MNU treatment. In conclusion, Rev1 overexpression accelerates mutagenesis and increases the incidence of MNU-induced TL by shortening the latency period, which may be associated with more frequent DNA damage-induced genetic instability.

Development of Moodle-based Plugin for Automated Essay-Type Grading

The essay is an exam requiring a more profound understanding of answering and evaluating the answers. However, if the number of questions and participants increases, this will result in a decrease in the quality of the lecturer's assessment. This prompted the development of a software based on the Moodle plugin named Essay Similarity to assess essay answers based on the similarity between the two documents, namely the answers given and the answer key provided. Moodle was chosen because, after the Covid-19 pandemic, many sectors have shifted to working remotely, including the education sector. This resulted in an LMS like Moodle experiencing an increase in users. As of 2020 yesterday, Moodle users have exceeded 190 million users on more than 145,000 websites. In developing this plugin, the method used is the waterfall method using the PHP programming language. The algorithm used to find similarities between the two documents is cosine similarity. Testing the level of similarity between manual and automatic grading was carried out on four models of essay questions. Based on the test results, the average similarity between automatic grading compared to manual grading is 45.44%.

Code Comments: A Way of Identifying Similarities in the Source Code

This study investigates whether analyzing the code comments available in the source code can effectively reveal functional similarities within software. The authors explore how both machine-readable comments (such as linter instructions) and human-readable comments (in natural language) can contribute towards measuring the code similarity. For the former, the work is relying on computing the cosine similarity over the one-hot encoded representation of the machine-readable comments, while for the latter, the focus is on detecting similarities in English comments, using threshold-based computations against the similarity measurements obtained using models based on Levenshtein distances (for form-based matches), Word2Vec (for contextual word representations), as well as deep learning models, such as Sentence Transformers or Universal Sentence Encoder (for semantic similarity). For evaluation, this research has analyzed the similarities between different source code versions of the open-source code editor, VSCode, based on existing ESlint-specific directives, as well as applying natural language processing techniques on incremental releases of Kubernetes, an open-source system for automating containerized application management. The experiments outlines the potential for detecting code similarities solely based on comments, and observations indicate that models like Universal Sentence Encoder are providing a favorable balance between recall and precision. This research is integrated into Project Martial, an open-source project for automatic assistance in detecting plagiarism in software.

Optimization of traditional methods for determining the similarity of project names and purchases using large language models

The subject of the study is the analysis and improvement of methods for determining the relevance of project names to the information content of purchases using large language models. The object of the study is a database containing the names of projects and purchases in the field of electric power industry, collected from open sources. The author examines in detail such aspects of the topic as the use of TF-IDF and cosine similarity metrics for primary data filtering, and also describes in detail the integration and evaluation of the effectiveness of large language models such as GigaChat, GPT-3.5, and GPT-4 in text data matching tasks. Special attention is paid to the methods of clarifying the similarity of names based on reflection introduced into the prompta of large language models, which makes it possible to increase the accuracy of data comparison. The study uses TF-IDF and cosine similarity methods for primary data analysis, as well as large GigaChat, GPT-3.5 and GPT-4 language models for detailed verification of the relevance of project names and purchases, including reflection in model prompta to improve the accuracy of results. The novelty of the research lies in the development of a combined approach to determining the relevance of project names and purchases, combining traditional methods of processing text information (TF-IDF, cosine similarity) with the capabilities of large language models. A special contribution of the author to the research of the topic is the proposed methodology for improving the accuracy of data comparison by clarifying the results of primary selection using GPT-3.5 and GPT-4 models with optimized prompta, including reflection. The main conclusions of the study are confirmation of the prospects of using the developed approach in the tasks of information support for procurement processes and project implementation, as well as the possibility of using the results obtained for the development of text data mining systems in various sectors of the economy. The study showed that the use of language models makes it possible to improve the value of the F2 measure to 0.65, which indicates a significant improvement in the quality of data comparison compared with basic methods.

Evolved Massive Stars at Low Metallicity. VII. The Lower Mass Limit of the Red Supergiant Population in the Large Magellanic Cloud

The precise definition of the lower mass limit of red supergiant stars (RSGs) is an open question in astrophysics and does not attract much attention. Here, we assemble a spectroscopic evolved cool star sample with 6602 targets, including RSGs, asymptotic giant branch stars, and red giant branch stars, in the Large Magellanic Cloud based on Gaia DR3 and Sloan Digital Sky Survey IV/APOGEE-2. The reference spectrum of each stellar population is built according to the quantile range of relative intensity (1% ∼ 99%). Five different methods, e.g., χ 2, cosine similarity, machine learning (ML), equivalent width, and line ratio, are used in order to separate different stellar populations. ML and χ 2 provide the best and relatively consistent prediction of a certain population. The derived lower limit of the RSG population is able to reach the K s -band tip of the red giant branch (K s ≈12.0 mag), indicating a luminosity as low as about 103.5 L ⊙, which corresponds to a stellar radius of only about 100 R ⊙. Given the mass–luminosity relation of L/L⊙=f(M/M⊙)3 with f ≈ 15.5 ± 3 and taking into account the mass loss of faint RSGs up to now, the minimal initial mass of the RSG population would be about 6.1 ± 0.4 M ⊙, which is much lower than the traditional threshold of 8 M ⊙ for the massive stars. This is the first spectroscopic evidence, indicating that the lower mass limit of the RSG population is around 6 M ⊙. However, the destinies of such faint RSGs are still elusive and may have a large impact on stellar evolutionary and supernova models.

Exploring hidden pathways to sustainable manufacturing for cyber-physical production systems

Future manufacturing scenarios will likely be built around cyber-physical production systems. To succeed, this new manufacturing paradigm will also have to comply with the golden rule of sustainability. However, the concept of sustainability as defined in a number of high-level policy documents and recommendations requires disambiguation. The paper introduces HITECS, a novel, context-independent text analytics methodology for hidden correlation analysis in documents. HITECS is based on the assumption that there is a strong link between a concept and the words implicitly chosen to explain it. The analysis is based on the combination of bare words frequency and cosine similarity, excluding trivial, first-level terms (titles, keywords, and definitions). Processing a corpus of generally accepted documents related to various definitions and requirements of sustainability unfolded their hidden correlations and some common key concepts. These results indicate that terms like access, inclusion, global, change, together with others like resource, share, and integration, are among leading concepts in the high-level documents discussing the requirements of sustainability. A similar analysis in the domain of cyber-physical production systems shows strong conceptual overlaps but also gaps indicating pathways for future research and actions.

An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring

Continuous monitoring of trained ML models to determine when their predictions should and should not be trusted is essential for their safe deployment. Such a framework ought to be high-performing, explainable, post-hoc and actionable. We propose TRUST-LAPSE, a “mistrust” scoring framework for continuous model monitoring. We assess the trustworthiness of each input sample's model prediction using a sequence of latent-space embeddings. Specifically, (a) our latent-space mistrust score estimates mistrust using distance metrics (Mahalanobis distance) and similarity metrics (cosine similarity) in the latent-space and (b) our sequential mistrust score determines deviations in correlations over the sequence of past input representations in a non-parametric, sliding-window based algorithm for actionable continuous monitoring. We evaluate TRUST-LAPSE via two downstream tasks: (1) distributionally shifted input detection, and (2) data drift detection. We evaluate across diverse domains– audio and vision using public datasets and further benchmark our approach on challenging, real-world electroencephalograms (EEG) datasets for seizure detection. Our latent-space mistrust scores achieve state-of-the-art results with AUROCs of 84.1 (vision), 73.9 (audio), and 77.1 (clinical EEGs), outperforming baselines by over 10 points. We expose critical failures in popular baselines that remain insensitive to input semantic content, rendering them unfit for real-world model monitoring. We show that our sequential mistrust scores achieve high drift detection rates; over 90% of the streams show <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$&lt; 20\%$</tex-math></inline-formula> error for all domains. Through extensive qualitative and quantitative evaluations, we show that our mistrust scores are more robust and provide explainability for easy adoption into practice.

A smart filtering-based adaptive optimized link state routing protocol in flying ad hoc networks for traffic monitoring

Nowadays, the use of drones as a fundamental element of smart cities has attracted the attention of many researchers to monitor and control the traffic of vehicles. Because of the high flexibility of multi-drone systems, like flying ad hoc networks (FANETs), they provide various services and improve modern life in smart cities. However, due to the unique features of FANET, especially the high speed of drones and rapid changes in network topology, communication reliability is a serious challenge in this network. Hence, traditional routing protocols, such as optimized link state routing (OLSR) scheme, cannot work well in these networks. In this paper, a smart filtering-based adaptive optimized link state routing (SFA-OLSR) scheme is proposed in FANETs. To increase adaptability to the FANET environment, SFA-OLSR provides a new solution to adjust the hello broadcast period so that each flying node specifies its broadcast period based on a new scale called cosine similarity between real and predicted positions. Furthermore, in SFA-OLSR, each flying node develops a filtering algorithm based on two parameters, namely link lifetime and remaining energy. The purpose of this algorithm is to reduce the size of the single-hop neighboring set of each flying node and minimize the search space when finding multi-point relays (MPRs). This increases the convergence speed of the algorithm. Then, SFA-OLSR exploits the sparrow search algorithm (SSA) to single out the best MPRs. This algorithm introduces a multi-objective function by focusing on three components, including energy, link lifespan, and neighbor degree. Lastly, the simulation process of SFA-OLSR is performed by the NS3 simulator. This process evaluates the performance of the proposed method and three schemes, namely Gangopadhyay et al., P-OLSR, and OLSR-ETX. These evaluations show that SFA-OLSR has a good performance in terms of three scales, namely packet delivery ratio, delay, and throughput, but its overhead is more than other methods.

Medical nearest-word embedding technique implemented using an unsupervised machine learning approach for Bengali language

Abstract The rapid growth of natural language processing (NLP) applications, such as text summarization, speech recognition, information extraction, and machine translation, has led to the development of structured query language (SQL) for extracting information from structured data. However, due to limited resources, converting Natural Language (NL) queries to SQL in Bengali is challenging. This article proposes an unsupervised machine learning model to find semantically Bengali closed words that can generate SQL from NL queries in Bengali. The main objective of the proposed system is to provide support in the creation of patient-oriented explanations and educational resources by simplifying intricate medical terminology. The major findings of the proposed system are as follows: The use of machine translation in the field of medicine facilitates the dissemination of healthcare information to a diverse international audience and improves the performance of entity recognition tasks, including the identification of medical conditions, drugs, or procedures within clinical notes or electronic health data. This system allows a naive user to extract health-related information from a healthcare-structured database without any knowledge of SQL. The system accepts a query and generates a response according to the query in Bengali language. Query tokenization and stop word removal are carried out in the preprocessing stage, and unsupervised machine learning techniques are implemented to process the input query sentence. Tokenized words are converted into vectors using the skip-gram model, with noise-contrastive estimation (NCE) applied to discriminate between actual and irrelevant words. Stochastic gradient descent (SGD) optimizes the model by randomly choosing a small amount of data from the dataset and using cosine similarity to measure closer words. The semantically closer words are found using an unsupervised learning method to generate the SQL.

A novel IFN-CSM-CoCoSo approach for multiple-attribute group decision-making with intuitionistic fuzzy sets: An application in assessing corporate social responsibility performance

With the rapid growth of the economy, enterprises have encountered a series of problems while pursuing economic benefits, such as food safety and environmental pollution issues, resource shortages and energy consumption issues, which affect the sustainable development of enterprises. Establishing a corporate performance evaluation system from the perspective of social responsibility, based on stakeholder theory and the importance of overall goals reflected in the weight of social responsibility indicators, is a very effective measure to achieve corporate social responsibility (CSR) goals through CSR motivation and stakeholders. The performance evaluation of CSR from the perspective of environmental accounting is a MAGDM. Recently, the CoCoSo technique and cosine similarity measure (CSM) technique was utilized to conduct the MAGDM. The intuitionistic fuzzy sets (IFSs) are utilized as a technique for conducting uncertain information during the performance evaluation of CSR from the perspective of environmental accounting. In this study, the intuitionistic fuzzy CoCoSo based on the CSM (IFN-CSM-CoCoSo) technique is built for MAGDM with IFSs. Finally, a numerical example for performance evaluation of CSR from the perspective of environmental accounting is conducted to verify the IFN-CSM-CoCoSo technique.

A novel deviation measurement for scheduled intelligent transportation system via comparative spatial-temporal path networks

Transit managers can use Intelligent Transportation System technologies to access large amounts of data to monitor network status. However, the presentation of the data lacks structural information. Existing single-network description technologies are ineffective in representing the temporal and spatial characteristics simultaneously. Therefore, there is a need for complementary methods to address these deficiencies. To address these limitations, this paper proposes an approach that combines Network Snapshots and Temporal Paths for the scheduled system. A dual information network is constructed to assess the degree of operational deviation considering the planning tasks. To validate the effectiveness, discussions are conducted through a modified cosine similarity calculation on theoretical analysis, delay level description, and the ability to identify abnormal dates. Compared to some state-of-the-art methods, the proposed method achieves an average Spearman delay correlation of 0.85 and a relative distance of 3.47. Furthermore, case analyses are invested in regions of China's Mainland, Europe, and the United States, investigating both the overall and sub-regional network fluctuations. To represent the impact of network fluctuations in sub-regions, a response loss value was developed. The times that are prone to fluctuations are also discussed through the classification of time series data. The research can offer a novel approach to system monitoring, providing a research direction that utilizes individual data combined to represent macroscopic states. Our code will be released at https://github.com/daozhong/STPN.git.

Bidirectional recommendation in HR analytics through text summarization

For over a decade, online job portals have been providing their services to both job seekers and employers in search of hiring opportunities. Because of the high demand for recruitment, it is insufficient to use conventional hiring methods to find a suitable candidate to fill the position. Validating resumes online is challenging due to the potential for manual errors, making the process inherently risky. The bidirectional method comprises named entity recognition (NER) for extracting the required resumes for recruiters. Cosine similarity shows the match percentage of resumes for the job requirements and vice versa. In an attempt to tackle an issue of unregistered words, a solution called decoder attention with pointer network (DA-PN) has been introduced. This method incorporates the use of coverage mechanism to prevent word repetition through generated text summary. DA-PN+Cover method with mixed learning objective (MLO) (DA-PN+Cover+MLO) is utilized for protecting grow of increasing faults in generated text summary. Performance of proposed method is estimated using evaluation indicator recall oriented understudy for gisting evaluation (ROUGE) and attains an average of 27.47 which is comparatively higher than existing methods.

Strong Prediction: Language Model Surprisal Explains Multiple N400 Effects.

Theoretical accounts of the N400 are divided as to whether the amplitude of the N400 response to a stimulus reflects the extent to which the stimulus was predicted, the extent to which the stimulus is semantically similar to its preceding context, or both. We use state-of-the-art machine learning tools to investigate which of these three accounts is best supported by the evidence. GPT-3, a neural language model trained to compute the conditional probability of any word based on the words that precede it, was used to operationalize contextual predictability. In particular, we used an information-theoretic construct known as surprisal (the negative logarithm of the conditional probability). Contextual semantic similarity was operationalized by using two high-quality co-occurrence-derived vector-based meaning representations for words: GloVe and fastText. The cosine between the vector representation of the sentence frame and final word was used to derive contextual cosine similarity estimates. A series of regression models were constructed, where these variables, along with cloze probability and plausibility ratings, were used to predict single trial N400 amplitudes recorded from healthy adults as they read sentences whose final word varied in its predictability, plausibility, and semantic relationship to the likeliest sentence completion. Statistical model comparison indicated GPT-3 surprisal provided the best account of N400 amplitude and suggested that apparently disparate N400 effects of expectancy, plausibility, and contextual semantic similarity can be reduced to variation in the predictability of words. The results are argued to support predictive coding in the human language network.

Summarization of Video using Audio

Abstract: Online education has emerged as a highly effective means of delivering quality education to students. Its popularity has increased due to the high-quality visual and graphical content, delivered by subject matter experts, and the convenience of learning anytime and anywhere. However, students may face time constraints that prevent them from fully engaging with the course content. To address this issue, video transcript summarizers have gained popularity. These tools extract the most important topics from a video, allowing students to understand the essence of the class without having to watch the entire video. Our system focuses on developing a module using txtai.pipeline with Python to summarize online class videos. We use Whisper, a general-purpose speech recognition model, to train our model on a large dataset of diverse audio. The model takes the URL of a video as input and uses two algorithms to summarize the content: TF-IDF and Gensim. The summarization process is subjective, and we have incorporated two prominent methods: cosine similarity and ROUGE score. The former does not require a human-generated summary for reference, while the latter does. Our results show that the efficiency obtained using cosine similarity is greater than 90% in both TF-IDF and Gensim cases. The efficiency obtained in the case of ROUGE score is between 40-50%.

IMAI: A short text matching model integrating multi-angle information

The short text matching models can be roughly divided into representation-based and interaction-based approaches. However, current representation-based text matching models often lack the ability to handle sentence pairs and typically only perform feature interactions at the network’s top layer, which can lead to a loss of semantic focus. The interactive text matching model has significant shortcomings in extracting differential information between sentences and may ignore global information. To address these issues, this article proposes a model structure that combines a dual-tower architecture with an interactive component, which compensates for their respective weaknesses in extracting sentence semantic information. Simultaneously, a method for integrating semantic information is proposed, enabling the model to capture both the interactive information between sentence pairs and the differential information between sentences, thereby addressing the issues with the aforementioned approaches. In the process of network training, a combination of cross-entropy and cosine similarity is used to calculate the model loss. The model is optimized to a stable state. Experiments on the commonly used datasets of QQP and MRPC validate the effectiveness of the proposed model, and its performance is stably improved.

Aiding ICD-10 Encoding of Clinical Health Records Using Improved Text Cosine Similarity and PLM-ICD

The International Classification of Diseases, 10th edition (ICD-10), has been widely used for the classification of patient diagnostic information. This classification is usually performed by dedicated physicians with specific coding training, and it is a laborious task. Automatic classification is a challenging task for the domain of natural language processing. Therefore, automatic methods have been proposed to aid the classification process. This paper proposes a method where Cosine text similarity is combined with a pretrained language model, PLM-ICD, in order to increase the number of probably useful suggestions of ICD-10 codes, based on the Medical Information Mart for Intensive Care (MIMIC)-IV dataset. The results show that a strategy of using multiple runs, and bucket category search, in the Cosine method, improves the results, providing more useful suggestions. Also, the use of a strategy composed by the Cosine method and PLM-ICD, which was called PLM-ICD-C, provides better results than just the PLM-ICD.

A Random Particle Swarm Optimization Based on Cosine Similarity for Global Optimization and Classification Problems.

In today's fast-paced and ever-changing environment, the need for algorithms with enhanced global optimization capability has become increasingly crucial due to the emergence of a wide range of optimization problems. To tackle this issue, we present a new algorithm called Random Particle Swarm Optimization (RPSO) based on cosine similarity. RPSO is evaluated using both the IEEE Congress on Evolutionary Computation (CEC) 2022 test dataset and Convolutional Neural Network (CNN) classification experiments. The RPSO algorithm builds upon the traditional PSO algorithm by incorporating several key enhancements. Firstly, the parameter selection is adapted and a mechanism called Random Contrastive Interaction (RCI) is introduced. This mechanism fosters information exchange among particles, thereby improving the ability of the algorithm to explore the search space more effectively. Secondly, quadratic interpolation (QI) is incorporated to boost the local search efficiency of the algorithm. RPSO utilizes cosine similarity for the selection of both QI and RCI, dynamically updating population information to steer the algorithm towards optimal solutions. In the evaluation using the CEC 2022 test dataset, RPSO is compared with recent variations of Particle Swarm Optimization (PSO) and top algorithms in the CEC community. The results highlight the strong competitiveness and advantages of RPSO, validating its effectiveness in tackling global optimization tasks. Additionally, in the classification experiments with optimizing CNNs for medical images, RPSO demonstrated stability and accuracy comparable to other algorithms and variants. This further confirms the value and utility of RPSO in improving the performance of CNN classification tasks.