An Effective Fuzzy Clustering of Crime Reports Embedded by a Universal Sentence Encoder Model

被引:3
|
作者
Pramanik, Aparna [1 ]
Das, Asit Kumar [1 ]
Pelusi, Danilo [2 ]
Nayak, Janmenjoy [3 ]
机构
[1] Indian Inst Engn Sci & Technol, Dept Comp Sci & Technol, Sibpur 711103, West Bengal, India
[2] Univ Teramo, Dept Commun Sci, I-64100 Teramo, Italy
[3] Maharaja Sriram Chandra Bhanja Deo MSCB Univ, Post Grad Dept Comp Sci, Baripada 757003, Orissa, India
关键词
crime report analysis; named entity recognition; universal encoder-based feature embedding; graph-based clustering; overlapping clusters; fuzzy theory; COMMUNITY DETECTION; GRAPH;
D O I
10.3390/math11030611
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Crime reports clustering is crucial for identifying and preventing criminal activities that frequently happened in society. In the proposed work, named entities in a report are recognized to extract the crime-related phrases and subsequently, the phrases are preprocessed by applying stopword removal and lemmatization operations. Next, the module of the universal encoder model, called the transformer, is applied to extract phrases of the report to get a sentence embedding for each associated sentence, aggregation of which finally provides the vector representation of that report. An innovative and efficient graph-based clustering algorithm consisting of splitting and merging operations has been proposed to get the cluster of crime reports. The proposed clustering algorithm generates overlapping clusters, which indicates the existence of reports of multiple crime types. The fuzzy theory has been used to provide a score to the report for expressing its membership into different clusters, and accordingly, the reports are labelled by multiple categories. The efficiency of the proposed method has been assessed by taking into account different datasets and comparing them with other state-of-the-art approaches with the help of various performance measure metrics.
引用
收藏
页数:18
相关论文
共 12 条
  • [1] Universal Fuzzy Clustering Model
    Sato-Ilic, Mika
    2014 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE), 2014, : 2071 - 2078
  • [2] MathUSE: Mathematical information retrieval system using universal sentence encoder model
    Dadure, Pankaj
    Pakray, Partha
    Bandyopadhyay, Sivaji
    JOURNAL OF INFORMATION SCIENCE, 2024, 50 (01) : 66 - 84
  • [3] MULTILINGUAL TEXT CLASSIFIER USING PRE-TRAINED UNIVERSAL SENTENCE ENCODER MODEL
    Orlovskiy, O., V
    Sohrab, Khalili
    Ostapov, S. E.
    Hazdyuk, K. P.
    Shumylyak, L. M.
    RADIO ELECTRONICS COMPUTER SCIENCE CONTROL, 2022, (03) : 102 - 108
  • [4] An Effective Crowdsourced Test Report Clustering Model Based on Sentence Embedding
    Chen, Hao
    Huang, Song
    Liu, Yuchan
    Luo, Run
    Xie, Yifei
    2021 IEEE 21ST INTERNATIONAL CONFERENCE ON SOFTWARE QUALITY, RELIABILITY AND SECURITY (QRS 2021), 2021, : 888 - 899
  • [5] Deep Embedded Fuzzy Clustering Model for Collaborative Filtering Recommender System
    Binbusayyis, Adel
    INTELLIGENT AUTOMATION AND SOFT COMPUTING, 2022, 33 (01): : 501 - 513
  • [6] Event Pattern Analysis and Prediction at Sentence Level using Neuro-Fuzzy Model for Crime Event Detection
    A. Vadivel
    S. G. Shaila
    Pattern Analysis and Applications, 2016, 19 : 679 - 698
  • [7] Event Pattern Analysis and Prediction at Sentence Level using Neuro-Fuzzy Model for Crime Event Detection
    Vadivel, A.
    Shaila, S. G.
    PATTERN ANALYSIS AND APPLICATIONS, 2016, 19 (03) : 679 - 698
  • [8] Effective fuzzy clustering algorithm with Bayesian model and mean template for image segmentation
    Zhang, Hui
    Wu, Qing Ming Jonathan
    Zheng, Yuhui
    Thanh Minh Nguyen
    Wang, Dingcheng
    IET IMAGE PROCESSING, 2014, 8 (10) : 571 - 581
  • [9] HIFCF: An effective hybrid model between picture fuzzy clustering and intuitionistic fuzzy recommender systems for medical diagnosis
    Nguyen Tho Thong
    Le Hoang Son
    EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (07) : 3682 - 3701
  • [10] A new and effective method for human retina optic disc segmentation with fuzzy clustering method based on active contour model
    Ahmad S. Abdullah
    Javad Rahebi
    Yasa Ekşioğlu Özok
    Mohanad Aljanabi
    Medical & Biological Engineering & Computing, 2020, 58 : 25 - 37