Similarity Algorithm Research Articles

Toward a Context-Aware Course-Planning Model in Pervasive Learning Environments

This article proposes a context-aware course-planning model for pervasive learning environments. The model considers learners’ preferences, including their learning styles, locations, activities, and devices. The model generates four-dimensional contexts based on these preferences, each dimension being a weighted vector of visual, aural, read/write, and kinesthetic (VARK) features. Using a content-based similarity algorithm, the model adapts the course content to each learner’s context. The courses are created in a sequence of rings, each containing all possible learning materials (LMs) that have the same content in different formats. Each LM is represented by a vector with weights like those of the learners’ context dimensions. The model generates all possible plans based on the predefined contexts of the learner, detects the learner’s actual context, and adapts the content accordingly. The goal of the model is to enable learners to learn what they want, in the way they prefer, and to complete courses efficiently, at any time, place, and during any activity, in the appropriate format.

IMPLEMENTATION OF STRING SIMILARITY ALGORITHM IN PUBLIC COMPLAINT APPLICATIONS TO MINIMIZE SIMILAR COMPLAINTS

Presently, the complaining service in Kartasura local government relies on manual recording where people must come to the government office, write their complaints and submit them to the office staff. This situation causes inefficiency since people have to travel from their places to the local government office. Moreover, the manual recording makes the complaints cannot be managed properly since the same complaints can be submitted more than one time. Additionally, it also causes some confusion to the government staff since they need to carefully check whether it has been submitted previously and approve the complaints accordingly. To solve the issue, a web-based application complaint system is developed to reduce the number of the same complaints from the citizen as well as to help staff manage the complaints data. The Jaro-Winkler String Similarity algorithm is adopted to check the similarity of newly submitted complaints with existing complaints data. The algorithm detects similarities of newly submitted complaints by determining the level of string equality to the existing complaints. Experimental results using one month period of complaints data in December 2022 show that the application is able to detect the similarity between the newly submitted complaints to the existing complaints. As the value of similarity threshold is higher, the number of rejected complaints also increases. Meanwhile, the test results of the system using the System Usability Scale Score obtained an average value of 76.5, which means the system is included in the Acceptable category and can be used for daily activity.

Bubble nucleation and jetting inside a millimetric droplet

In this work we present experiments and simulations on the nucleation and successive dynamics of laser-induced bubbles inside liquid droplets in free-fall motion, i.e. a case where the bubbles are subjected to the influence of a free boundary in all directions. Within this spherical millimetric droplet, we have investigated the nucleation of secondary bubbles induced by the rarefaction wave that is produced when the shock wave emitted by the laser-induced plasma reflects at the drop surface. Interestingly, three-dimensional clusters of cavitation bubbles are observed. Their shape is compared with the negative pressure distribution computed with a computational fluid dynamics model and allows us to estimate a cavitation threshold value. In particular, we observed that the focusing of the waves in the vicinity of the free surface can give rise to explosive cavitation events that end up in fast liquid ejections. High-speed recordings of the drop/bubble dynamics are complemented by the velocity and pressure fields simulated for the same initial conditions. The effect of the proximity of a curved free surface on the jetting dynamics of the bubbles was qualitatively assessed by classifying the cavitation events using a non-dimensional stand-off parameter ${\Upsilon\hskip -1,05em -\,}$ that depends on the drop size, the bubble maximum radius and the relative position of the bubble inside the drop. Additionally, we studied the role of the drop's curvature by implementing a structural similarity algorithm to compare cases with bubbles produced near a flat surface to the bubbles inside the drop. Interestingly, this quantitative comparison method indicated the existence of equivalent stand-off distances at which bubbles influenced by different boundaries behave in a very similar way. The oscillation of the laser-induced bubbles promotes the onset of Rayleigh–Taylor and Rayleigh–Plateau instabilities, observed on the drop's surface. This phenomenon was studied by varying the ratio of the maximum radii of the bubble and the drop. The specific mechanisms leading to the destabilisation of the droplet surface were identified.

A Sound Similarity Algorithm Based on Human Intuition

In this work, we describe some characteristics of human timbre perception. We propose the concept of harmony function to quantify how harmonious two pitches are perceived to be and apply these psychoacoustics theories to build a comparison algorithm. To examine the algorithm, some audio samples are chosen to take the test and get a natural result as expected. As the title suggests, the calculation result of this algorithm is in line with human intuition.

Similar Questions Identification on Indonesian Language Subject Using Machine Learning

Question similarity is carried out to evaluate similarities between questions in a collection of questions in the question and answer forum and on other platforms. This is done to improve the performance of the question-and-answer forum so that new questions submitted by users can be identified as similar to existing questions in the database. Currently, research related to question similarity is still being carried out on foreign language datasets. The purpose of this research is to identify the similarity of questions in a collection of questions in Indonesian. The method used is Support Vector Machine and IndoBERT. For feature extraction, we evaluate the lexical features and syntax features of each question. For lexical feature extraction, we use the cosine similarity algorithm to calculate the distance between two objects which are represented as vectors. For syntax feature extraction we use the Indonesian part of speech tagger (POS Tag). The dataset used is a collection of questions on Indonesian subjects at the primary and secondary school levels. The results of this study show that the best performance of the Support Vector Machine is obtained from the use of the cosine similarity feature with an accuracy of 85%. While the use of the POS Tag feature or the combination of POS Tag and cosine similarity causes the model to be overfitted and the accuracy decreases to 77%. Meanwhile, for the IndoBERT model, an accuracy of 95% was obtained.

English-Chinese translation strategies based on BERT and multi-similarity fusion of English and American literature

Abstract Under the background of big data development, more intelligent technologies make work and life convenient, and the traditional English-US literature translation methods and means are difficult to adapt to the fast-paced era of big data, so this paper conducts research and analysis on this problem. In terms of the English-Chinese translation strategy based on BERT and multi-similarity fusion of English and American literature, the article first introduces the concept and principle of BERT, and multi-similarity fusion algorithm then constructs the model of BERT and multi-similarity algorithm fusion, analyzes and discusses the English and American literature translation dataset respectively, and compares it with three different similarity algorithms in terms of three indicators. The data shows that BERT has the greatest effect on the accuracy rate, followed by BLEU value and Manhattan distance. Compared with the fusion of the three methods, the data analysis of a single method is better, and the three selected index values all remain above 90%, and this study is conducive to improving the accuracy and efficiency of English and American literature work, which is of great historical significance for international literary communication.

Sistem Rekomendasi Pemilihan Program MSIB Bagi Mahasiswa Pendidikan Informatika

This study discusses a recommendation system using a content-based filtering method with cosine similarity to help informatics education students choose the right Certified Independent Study and Internship Program (MSIB). The data used is data based on student interests, program and course data available on the MSIB web portal. The content-based filtering method is used to consider the suitability between student preferences and the MSIB program curriculum, while the cosine similarity algorithm is used to calculate the similarity score between different contents. The development of this recommendation system can assist informatics education students in choosing the MSIB program that is in accordance with the preferences of the student's interest profile. The results of the system evaluation obtained an average precision level of 89.4%, indicating that the list of recommendations provided by the system is very good and very relevant according to user preferences.

Analysis of Pharmaceutical Processes in Chinese Medicine Based on Quantity and Measure Value Transfer: A Case of Salvia miltiorrhiza Purified Extract Preparation

Quantity and measure value transfer is widely used to examine the correlation between the quality of Chinese herbs, Chinese herbal intermediates, and Chinese patent medicines. This study performed a quantity and measure value transfer analysis to assess the total solids yield, phenolic component yield, and phenolic component purity in the Salvia miltiorrhiza purified extract (SMPE) preparation process. The amount of extracted total solids was between 45–250 mg/g following the processes of reflux extraction, vacuum concentration, lime–sulfuric acid refining, first ethanol precipitation, second ethanol precipitation, first acidification, alkalization, thermal hydrolysis, and second acidification. Regarding yield and purity, Danshensu ranked first among all phenolic components. Additionally, a quantitative index defined as the total variation (TV) value was proposed to describe the consistency of the SMPE preparation process. The batch-to-batch variation in the SMPE came from the variable in herb quality and the preparation process, and the latter contributed more. The contribution of individual processes to the total variation (TVP) was proposed as an index to measure the impact of processes on batch-to-batch consistency. According to the TVP value, the lime–sulfuric acid refining process, the first ethanol precipitation process, and the second acidification process were all deemed crucial. When the similarity algorithms for the composition of the intermediates and SMPE were examined, the Euclidean distance outperformed the Pearson correlation coefficient, Spearman correlation coefficient, and cosine of the pinch angles. Based on the variation in the average Euclidean distance (ΔDj¯) during the process, the second ethanol precipitation, alkalization, and thermal hydrolysis processes were determined to be critical. This study clarified the primary causes of extract quality fluctuation, identified the critical processes, and examined the pharmaceutical process of traditional Chinese medicine (TCM) from the standpoint of quantity and measure value transfer. The method can be used as a reference for the analysis of other TCM pharmaceutical processes.

A detector for Android repackaged applications with layout-fingerprint

Some existing methods for detecting repackaged apps use layout files to generate a global layout tree, but this can result in node positions affecting feature accuracy and repeated layout matching affecting model accuracy. In our paper, we propose ReHunter, a detection method for repackaged apps based on layout fingerprint. ReHunter uses a weight-based layout similarity algorithm to eliminate the influence of node position on features, and applies rules to prevent layout matching between applications, addressing the detection interference caused by repeated layout matching. Our experiments demonstrate that ReHunter achieves higher accuracy, with a false positive rate of 1.8% and a false negative rate of 1.7%.

MA-STS-Based Social Intimacy Analysis Algorithm Using Real Campus Network Data

In recent years, the widespread availability of Wi-Fi in various settings, including universities, enterprises, and large shopping centers, has become increasingly prevalent. The user’s time and location information embedded in wireless network systems can reveal individual and group social relationships, which indirectly reflect each person’s psychological well-being. However, due to challenges in obtaining complete data, the high complexity of related data, and the absence of suitable data analysis models, few studies have analyzed student social behavior using data from university campus networks. This paper employs real-world data from a renowned Chinese university’s wireless campus network for in-depth analysis and introduces a novel multiangle semantic trajectory similarity (MA-STS) algorithm to infer the intimacy and relationship types (such as teacher-student, friends, classmates, or romantic partners) between users. The experiments demonstrate that the proposed algorithm achieves an accuracy of over 95%.

SIMMER employs similarity algorithms to accurately identify human gut microbiome species and enzymes capable of known chemical transformations.

Bacteria within the gut microbiota possess the ability to metabolize a wide array of human drugs, foods, and toxins, but the responsible enzymes for these chemical events remain largely uncharacterized due to the time-consuming nature of current experimental approaches. Attempts have been made in the past to computationally predict which bacterial species and enzymes are responsible for chemical transformations in the gut environment, but with low accuracy due to minimal chemical representation and sequence similarity search schemes. Here, we present an in silico approach that employs chemical and protein Similarity algorithms that Identify MicrobioMe Enzymatic Reactions (SIMMER). We show that SIMMER accurately predicts the responsible species and enzymes for a queried reaction, unlike previous methods. We demonstrate SIMMER use cases in the context of drug metabolism by predicting previously uncharacterized enzymes for 88 drug transformations known to occur in the human gut. We validate these predictions on external datasets and provide an in vitro validation of SIMMER's predictions for metabolism of methotrexate, an anti-arthritic drug. After demonstrating its utility and accuracy, we made SIMMER available as both a command-line and web tool, with flexible input and output options for determining chemical transformations within the human gut. We present SIMMER as a computational addition to the microbiome researcher's toolbox, enabling them to make informed hypotheses before embarking on the lengthy laboratory experiments required to characterize novel bacterial enzymes that can alter human ingested compounds.

THE USE OF ROUGH CLASSIFICATION AND TWO THRESHOLD TWO DIVISORS FOR DEDUPLICATION

The data deduplication technique efficiently reduces and removes redundant data in big data storage systems. The main issue is that the data deduplication requires expensive computational effort to remove duplicate data due to the vast size of big data. The paper attempts to reduce the time and computation required for data deduplication stages. The chunking and hashing stage often requires a lot of calculations and time. This paper initially proposes an efficient new method to exploit the parallel processing of deduplication systems with the best performance. The proposed system is designed to use multicore computing efficiently. First, The proposed method removes redundant data by making a rough classification for the input into several classes using the histogram similarity and k-mean algorithm. Next, a new method for calculating the divisor list for each class was introduced to improve the chunking method and increase the data deduplication ratio. Finally, the performance of the proposed method was evaluated using three datasets as test examples. The proposed method proves that data deduplication based on classes and a multicore processor is much faster than a single-core processor. Moreover, the experimental results showed that the proposed method significantly improved the performance of Two Threshold Two Divisors (TTTD) and Basic Sliding Window BSW algorithms.

Application of an Improved Link Prediction Algorithm Based on Complex Network in Industrial Structure Adjustment

For a healthy industrial structure (IS) and stable economic development in China, this study proposes an improved link prediction algorithm (LP) based on complex networks. The algorithm calculates the similarity by constructing a mixed similarity index. A regional IS network model is built in the study, and the direction of IS adjustment is calculated with the mixed similarity indicators. In this study, the prediction accuracy of the proposed improved LP algorithm in the real network dataset is up to 0.944, which is significantly higher than that of the other algorithms. In the reality of IS optimization, industries of high similarity could be obtained through similarity algorithms, and reasonable coordinated development strategies are proposed. In addition, the simulated IS adjustment strategy in this study shows that it is highly sustainable in development, which is reflected in its lower carbon emissions. The optimization of IS adjustment could be achieved through IS network model and the improved LP algorithm. This study provides valuable suggestions for China’s regional industrial structure adjustment.

Research on Automatic Design of Substation Secondary Circuit Based on Improved SPCD Model and Knowledge Graph

In view of the lack of automatic design research of the physical circuit of the substation secondary system, and the digital design and handover level that the substation urgently needs to improve, this paper proposes the following solutions. First of all, an improvement plan is proposed for the existing SPCD model, adding all design related information such as external function grouping and logical interface of the panel cabinet. Secondly, extract the function group elements and secondary cabinet elements of the improved SPCD model as knowledge graph nodes, and abstract the relationship between function group’s interfaces as knowledge graph relationships. Based on the Neo4j graph database, a typical bay knowledge graph for secondary design is conFstructed. Furthermore, the electric power secondary field data set is mined, the Word2vec model is trained by the secondary field data set, and the text similarity algorithm model in the secondary design field is established. Finally, based on the above research, a method for automatic design of substation secondary physical circuits and automatic generation of SPCD model file based on word2vec text similarity is proposed.

Global Path Link Prediction Method Based on Improved Resource Allocation

Link prediction is a basic method to study complex networks, which has important practical application value. This paper proposes a global path link prediction method based on resource allocation for complex network topology information. Firstly, we improve the current quantization method of node resource transmission capability, and then consider the global path information in the network structure comprehensively. Finally, the link prediction method is defined based on the quantized resource transmission capability and global path information. Compared with 11 classical similarity algorithms, the experimental results show that the link prediction accuracy of this method has been improved to some extent, among which the highest improvement is 22.85%.

Recommendation System for Prospective Bride and Groom Using Cosine Similarity Algorithm

Ta'aruf is an introductory process intended for getting to know each other between two individuals which is expected to continue at the marriage level. Forum ta'aruf Padi Melati is an institution under the Regional Leadership of Muhammadiyah Bantul that aims to become a medium for cadres Nasyi'atul Aisyiyah and Muhammadiyah Youth in finding a life partner. The ta'aruf process carried out by the current Forum ta'aruf Padi Melati is still carried out using information exchange via WhatsApp through forum leaders where the candidates will send biodata and criteria for the desired partner. The purpose of this study was to design a website prototype to help the managers of the Ta'aruf Padi Melati Forum to do matching Potential Pairing with the Application of the Cosine Similarity Algorithm. The application of the Cosine Similarity algorithm aims to compare the degree of fit of several candidates. The research method is carried out in several stages starting in stages, namely interviews with the managers of the jasmine rice ta'aruf forum, then conducting by applying the Cosine similarity method to create a classification of category pairs into groups according to the degree of similarity of the criteria. The final result is the degree of match of the pair criteria expected by each participant.

Building A Web-Based Final Project Detection Information System with Incremental Method and Jaccard Similarity Algorithm

Thesis is a scientific work and one of the graduation requirements for students in tertiary institutions. The process of implementing the thesis at the Information Technology Study Program at the University of Timor is still done manually, starting from submitting titles to data processing which allows for duplicate titles, difficulty finding data and losing data. For this reason, a system is needed to avoid the risk of duplicate titles and difficulty finding the data. So in this study an information system will be built to detect the similarity of the title of the final project (Thesis) using the incremental method and the Jaccard similarity algorithm as a plagiarism detection algorithm. The application of the incremental method is due to its flexible nature and less risk of failure than other development methods. System testing is carried out on the functional system and using the User Acceptance Test. Based on the test results, this system facilitates Study Programs in submitting final assignment titles, finding final assignment data, minimizing the risk of duplicate titles through the Title Similarity Percentage testing feature to find out the highest level of similarity based on thesis title category and avoiding data loss.

Real-Time Multi-Vehicle Multi-Camera Tracking with Graph-Based Tracklet Features

An essential application in intelligent transportation systems is multi-target multi-camera tracking (MTMCT), where the target’s activity is tracked from different cameras. Although the tracking-by-detection scheme is the primary paradigm in MTMCT, the object association information from the video frames is lost. This is mainly because the multi-camera multi-object matching uses the information from the video frames separately. To solve this problem and leverage this association information, we propose an MTMCT framework, where features are built in the form of a graph and a graph similarity algorithm is used to match multi-camera objects. In this paper, we focus on the real-time scenario, where only the past images are used to match an object. Our method achieves an IDF1 score (the ratio of the number of correctly identified objects to the number of ground truth and average objects) of 0.75 with a rate of 14 frames per second (fps).

Quantum-based Detection of Higly Semantically Similar Social bot

Social bot often publish content that has a high degree of similarity in text or semantics. Combining this feature, this paper designs a method to detect social bot. First, the user-published text is used as the input to use sentiment analysis and data cleaning to predict the content. Processing and classification, and then adding the quantum similarity algorithm in the emerging quantum discipline in recent years to the structural system of social bot detection to perform similarity clustering, which greatly improves the operating efficiency of the system, and then obtains the corresponding user attribute characteristics for artificial intelligence. Intelligent algorithm classification, on the collected real dataset, marked two social bot groups for machine learning classification and detection, and listed two traditional similarity algorithms for comparison, the results show that the quantum similarity results Compared with the two traditional similarity algorithms, it has improved, and the average accuracy improvement was about 2%.

Fast screening and identification of illegal adulteration in dietary supplements and herbal medicines using molecular networking with deep-learning-based similarity algorithms.

Liquid chromatography-high-resolution mass spectrometry (LC-HRMS) is a powerful analytical tool used for adulteration inspection. Nevertheless, it is a challenging task to identify illegal adulterants that are not included in the library or are unexpected from large MS data. Molecular networking is a good tool for exploring, visualizing, and organizing MS/MS spectra, and moreover, it employs shifted peak match to calculate spectral similarity, making it capable of identifying adulteration that is not included in the library. The key of molecular networking is spectral similarity algorithms, and therefore, in this study, we compared the performance of four cutting-edge similarity algorithms, modified cosine similarity (shifted peak match), entropy similarity, and two deep-learning-based algorithms, MS2DeepScore and Spec2Vec, in building molecular networking for identification of adulteration that is not included in the library. We conducted an analysis of excluded-query-compound on all MS/MS spectra in test library and performed a large-scale false discovery rate estimation to investigate whether the spectral similarity calculated by each algorithm could represent the actual structural similarity well. The obtained results demonstrated Spec2Vec exhibited good performance in both detection capability and false discovery rate. Further comprehensive evaluation of the performance of Spec2Vec in the identification of adulteration that is not included in the library or is unexpected in different matrices and in application to real samples proved the approach studied here is a promising and powerful tool for adulterant inspection and improved the capability of analyzing large MS data.