Water Supply Pipeline Burr Data Detection Based on Improved LightGBM by Focal Loss

doi:10.3969/j.issn.1006-2475.2024.09.013

Abstract

Abstract: Addressing the issue of low recall in the detection of burrs in water supply pipelines due to data imbalance， this paper proposes an improved method for detecting pipeline burr data by utilizing the Focal Loss function and integrating it with LightGBM. Firstly， considering the characteristics of pipeline burr data， neighborhood-related features are constructed. Secondly， the Focal Loss function is introduced into LightGBM to increase the model’s weight on hard-to-detect burr samples. Different parameter values for Focal Loss are experimented to balance precision and recall. Finally， different parameter settings for Focal Loss are selected for model fusion to further improve the detection performance of the model on imbalanced burr data. Experiments are carried out on a real dataset from a municipal water supply pipeline. The experimental results show that， compared with a single model based on the cross-entropy loss function， the fused model with the improved Focal Loss in this paper achieves 33.3 percentage points increase in recall and 18 percentage points increase in F1 score for burr data. However， the precision of burr data detection still needs further improvement. The method proposed in this paper starts with loss function and dynamically adjusts the weights of difficult and easy samples to effectively improve the detection performance of burr data under unbalanced data.

Key words: anomaly detection, Focal Loss, LightGBM, imbalanced data, burr data

CLC Number:

TP391

XUE Hao, MA Jing, GUO Xiaoyu. Water Supply Pipeline Burr Data Detection Based on Improved LightGBM by Focal Loss[J]. Computer and Modernization, 2024, 0(09): 74-81.

References

［1］王飞. iLOF*：一种改进的局部异常检测算法［J］. 计算机系统应用， 2015，24（12）：233-238.
［2］孙梦迪. 基于压力数据的城市供水网络异常事件检测研究［D］. 重庆：重庆邮电大学， 2021.
［3］ HAWKINS D M. Identification of Outliers［M］. London： Chapman and Hall， 1980.
［4］ ISLAM M K， HRIDI P， HOSSAIN M S， et al. Network anomaly detection using LightGBM： A gradient boosting classifier［C］// 2020 30th International Telecommunication Networks and Applications Conference （ITNAC）. IEEE， 2020. DOI: 10.1109/ITNAC50341.2020.9315049.
［5］杨凌凯. 改进的LightGBM算法在汽车销售客户流失预警中的应用［D］. 武汉：华中农业大学， 2022.
［6］李爱华，王迪文，续维佳，等. 基于多数据源融合的创业板上市公司财务造假异常检测［J］. 数据分析与知识发现， 2023，7（5）：33-47.
［7］ LIN M Y， ZHU X F， HUA T， et al. Detection of ionospheric scintillation based on XGBoost model improved by SMOTE-ENN technique［J］. Remote Sensing， 2021，13（13）. DOI: 10.3390/rs13132577.
［8］ LIN T Y， GOYAL P， GIRSHICK R， et al. Focal loss for dense object detection［C］// Proceedings of the 2017 IEEE International Conference on Computer Vision. IEEE， 2017：
2999-3007.
［9］ JOHNSON R A， WICHERN D W. Applied Multivariate Statistical Analysis［M］. Pearson， 2007.
［10］ LI A H， FENG M Y， LI Y R Y， et al. Application of outlier mining in insider identification based on boxplot method［J］. Procedia Computer Science， 2016，91：245-251.
［11］习佳星，沈钢，许承焯. 地铁车辆车轮轮缘异常磨耗检测中的箱线图算法和改进孤立森林算法［J］. 城市轨道交通研究， 2022，25（12）：127-132.
［12］顾国庆，李晓辉. 基于箱线图异常检测的指数加权平滑预测模型［J］. 计算机与现代化， 2021（1）：28-33.
［13］ SHENG B， LI Q， MAO W Z， et al. Outlier detection in sensor networks［C］// Proceedings of the 8th ACM International Symposium on Mobile AD HOC Networking and Computing. ACM， 2007：219-228.
［14］ GOLDSTEIN M， DENGEL A. Histogram-based outlier score （HBOS）： A fast unsupervised anomaly detection algorithm［C］ // KI-2012： Poster and Demo Track. 2012，1：59-63.
［15］ BREUNIG M M， KRIEGEL H P， NG R T， et al. LOF： Identifying density-based local outliers［C］// Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data. ACM， 2000：93-104.
［16］ CHENG Z Y， ZOU C M， DONG J W. Outlier detection using isolation forest and local outlier factor［C］// Proceedings of the 2019 Conference on Research in Adaptive and Convergent Systems. ACM， 2019：161-168.
［17］刘志硕，彭涛，侯娜. 基于局部异常因子算法的首都机场航班延误预警研究［J］. 民航学报， 2022，6（2）：21-25.
［18］陶永辉，王勇. 基于改进的K-means风电机异常数据检测［J］. 国外电子测量技术， 2023，42（4）：141-148.
［19］ CHAWLA S， GIONIS A. K-means–： A unified approach to clustering and outlier detection［C］// Proceedings of the 2013 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics. 2013：189-197.
［20］贾旭超，马迅，刘安磊，等. 基于孤立森林法的电能计量数据异常检测方法［J］. 河北电力技术， 2023，42（2）：41-45.
［21］ ÇELIK M， DADAŞER-ÇELIK F， DOKUZ A Ş. Anomaly detection in temperature data using DBSCAN algorithm［C］// 2011 International Symposium on Innovations in Intelligent Systems and Applications. IEEE， 2011：91-95.
［22］ THANG T M， KIM J. The anomaly detection by using DBSCAN clustering with multiple parameters［C］// 2011 International Conference on Information Science and Applications. IEEE， 2011. DOI: 10.1109/ICISA.2011.5772437.
［23］ SAVE P， TIWAREKAR P， JAIN K N， et al. A novel idea for credit card fraud detection using decision tree［J］. International Journal of Computer Applications， 2017，161（13）:6-9.
［24］ YANG J H， DENG T Q， SUI R. An adaptive weighted one-class SVM for robust outlier detection［C］// Proceedings of the 2015 Chinese Intelligent Systems Conference. Springer， 2016，1：475-484.
［25］ PRIMARTHA R， TAMA B A. Anomaly detection using random forest： A performance revisited［C］// 2017 International Conference on Data and Software Engineering （ICoDSE）.
IEEE，2017. DOI: 10.1109/ICODSE.2017.8285847.
［26］陈适宜. 一种基于XGboost的异常检测算法［J］. 电脑知识与技术， 2021，17（2）：188-189.
［27］ LIU S C， CHEN Z， PAN M C， et al. Magnetic anomaly detection based on full connected neural network［J］. IEEE Access， 2019，7：182198-182206.
［28］ SU Y， ZHAO Y J， SUN M， et al. Detecting outlier machine instances through gaussian mixture variational autoencoder with one dimensional cnn［J］. IEEE Transactions on Computers， 2021，71（4）：892-905.
［29］ NGUYEN H D， TRAN K P， THOMASSEY S， et al. Forecasting and anomaly detection approaches using LSTM and LSTM autoencoder techniques with the applications in supply chain management［J］. International Journal of Information Management， 2021，57. DOI： 10.1016/j.ijinfomgt.2020.
102282.
［30］ WU D， JIANG Z K， XIE X F， et al. LSTM learning with Bayesian and Gaussian processing for anomaly detection in industrial IoT［J］. IEEE Transactions on Industrial Informatics， 2019，16（8）：5244-5253.
［31］ TAN X P， SU S J， HUANG Z P， et al. Wireless sensor networks intrusion detection based on SMOTE and the random forest algorithm［J］. Sensors， 2019，19（1）. DOI： 10.3390/s19010203.
［32］张海宾，肖涵，易灿灿，等. 基于KNN 和深度高斯混合模型的边界过采样方法［J］. 数据分析与知识发现， 2023，7（5）：116-122.
［33］ MUSHAVA J， MURRAY M. A novel XGBoost extension for credit scoring class-imbalanced data combining a generalized extreme value link and a modified focal loss function［J］. Expert Systems with Applications， 2022，202. DOI: 10.1016/j.eswa.2022.117233.

[1]	LYU Meijing1, NIAN Mei1, ZHANG Jun1, 2, FU Lusen1. Anomaly Detection of Network Traffic Based on Autoencoder [J]. Computer and Modernization, 2024, 0(12): 40-44.
[2]	ZHOU Chuanhua1, 2, REN Taijiao1, LUO Lan1, ZHOU Hao1. Boundary Mixed Resampling Based on Joint Entropy for Imbalanced Data [J]. Computer and Modernization, 2024, 0(09): 95-100.
[3]	LIU Jing-le, LUO Xiang, GONG Cheng-rong, ZHANG Guo-peng. Prediction of Diabetes Mellitus Using LightGBM Classifier with RF-RFECV [J]. Computer and Modernization, 2023, 0(11): 36-43.
[4]	PAN Yu-qing, ZHANG Su-ning, FENG Ren-jun, JING Dong-sheng. Intrusion Detection Method Based on Particle Swarm Optimization Combined with LightGBM [J]. Computer and Modernization, 2023, 0(04): 123-126.
[5]	LIU Fu-qian, QIN Hua-ni, LAI Hui-hui. Person-post Matching Adj-LightGBM Algorithm Based on SMOTE and Bayesian Optimization [J]. Computer and Modernization, 2023, 0(03): 90-95.
[6]	GUO Teng-fei, ZHANG Ze-yan, FU Hong-cai, WANG Ji-xuan, NIU Tian-bao. Lightweight Infrared HV Bushing Identification Algorithm Based on Attention Mechanism [J]. Computer and Modernization, 2022, 0(01): 70-76.
[7]	YAN Rui-an, ZHANG Li-chen. Intrusion Detection Based on Focal Loss and Convolutional Neural Network [J]. Computer and Modernization, 2021, 0(01): 65-69.
[8]	SHI Fei, QIU Zhen, HAN Qin, LI Jin-geng, QIAN Hui-min, XIANG Wen-bo. An Improved Algorithm of Faster R-CNN Based on Variable Weight Loss Function and OHEM [J]. Computer and Modernization, 2020, 0(08): 56-62.
[9]	ZHOU Xing, CHEN Li-fu. Object Detection of Remote Sensing Image Based on Dual Attention Mechanism [J]. Computer and Modernization, 2020, 0(08): 1-7.
[10]	SHI Ming-hua, WU Guang-chao. An Imbalanced Data Classification of Hybrid Sampling Based on Clustering [J]. Computer and Modernization, 2020, 0(05): 34-.
[11]	XIONG Su-sheng1，2. Identifying Transportation Mode Based on Improved LightGBM Algorithm [J]. Computer and Modernization, 2018, 0(10): 68-.
[12]	YI Wei1, MAO Li1, SUN Jun1, WU Lin-hai2,3. Research on Classification of Improved Smote Algorithm on Imbalanced Datasets [J]. Computer and Modernization, 2018, 0(03): 83-.
[13]	HUO Xu1, WU Tao 1,2. A Forecasting Method of Fuzzy Time Series for Imbalanced Data [J]. Computer and Modernization, 2017, 0(12): 108-110.
[14]	QIU Hai-bo1， QIAN Zhong-min1， QIAN Mo-shu2. Used-car Recommendation Based on Synthetic Minority Over-sampling Technique Filter [J]. Computer and Modernization, 2016, 251(07): 118-123.
[15]	GUO Wen-feng1， WANG Yong2. Classifier Ensemble for Imbalanced Data Stream Classification Based on Accumulated Minorities [J]. Computer and Modernization, 2015, 0(3): 41-47.