Salvato in:
Dettagli Bibliografici
Autori principali: Zhuoxian, Liu, Tuo, Shi, Xiaofeng, Hu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.06749
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916476876750848
author Zhuoxian, Liu
Tuo, Shi
Xiaofeng, Hu
author_facet Zhuoxian, Liu
Tuo, Shi
Xiaofeng, Hu
contents Police incident data is crucial for public security intelligence, yet grassroots agencies struggle with efficient classification due to manual inefficiency and automated system limitations, especially in telecom and online fraud cases. This research proposes a multichannel neural network model, KLCBL, integrating Kolmogorov-Arnold Networks (KAN), a linguistically enhanced text preprocessing approach (LERT), Convolutional Neural Network (CNN), and Bidirectional Long Short-Term Memory (BiLSTM) for police incident classification. Evaluated with real data, KLCBL achieved 91.9% accuracy, outperforming baseline models. The model addresses classification challenges, enhances police informatization, improves resource allocation, and offers broad applicability to other classification tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06749
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle KLCBL: An Improved Police Incident Classification Model
Zhuoxian, Liu
Tuo, Shi
Xiaofeng, Hu
Artificial Intelligence
Police incident data is crucial for public security intelligence, yet grassroots agencies struggle with efficient classification due to manual inefficiency and automated system limitations, especially in telecom and online fraud cases. This research proposes a multichannel neural network model, KLCBL, integrating Kolmogorov-Arnold Networks (KAN), a linguistically enhanced text preprocessing approach (LERT), Convolutional Neural Network (CNN), and Bidirectional Long Short-Term Memory (BiLSTM) for police incident classification. Evaluated with real data, KLCBL achieved 91.9% accuracy, outperforming baseline models. The model addresses classification challenges, enhances police informatization, improves resource allocation, and offers broad applicability to other classification tasks.
title KLCBL: An Improved Police Incident Classification Model
topic Artificial Intelligence
url https://arxiv.org/abs/2411.06749