With the wide application of wireless sensor networks in military and environmental monitoring, security issues have become increasingly prominent. Data exchanged over wireless sensor networks is vulnerable to malicious attacks due to the lack of physical defense equipment. Therefore, corresponding schemes of intrusion detection are urgently needed to defend against such attacks. Considering the serious class imbalance of the intrusion dataset, this paper proposes a method of using the synthetic minority oversampling technique (SMOTE) to balance the dataset and then uses the random forest algorithm to train the classifier for intrusion detection. The simulations are conducted on a benchmark intrusion dataset, and the accuracy of the random forest algorithm has reached 92.39%, which is higher than other comparison algorithms. After oversampling the minority samples, the accuracy of the random forest combined with the SMOTE has increased to 92.57%. This shows that the proposed algorithm provides an effective solution to solve the problem of class imbalance and improves the performance of intrusion detection.
With the wide application of wireless sensor networks in military and environmental monitoring, security issues have become increasingly prominent. Data exchanged over wireless sensor networks is vulnerable to malicious attacks due to the lack of physical defense equipment. Therefore, corresponding schemes of intrusion detection are urgently needed to defend against such attacks. Considering the serious class imbalance of the intrusion dataset, this paper proposes a method of using the synthetic minority oversampling technique (SMOTE) to balance the dataset and then uses the random forest algorithm to train the classifier for intrusion detection. The simulations are conducted on a benchmark intrusion dataset, and the accuracy of the random forest algorithm has reached 92.39%, which is higher than other comparison algorithms. After oversampling the minority samples, the accuracy of the random forest combined with the SMOTE has increased to 92.57%. This shows that the proposed algorithm provides an effective solution to solve the problem of class imbalance and improves the performance of intrusion detection.
Shukui Qin,1 Rui-Hua Xu,2 Lin Shen,3 Jianming Xu,4 Yuxian Bai,5 Lei Yang,6 Yanhong Deng,7 Zhen-dong Chen,8 Haijun Zhong,9 Hongming Pan,10 Weijian Guo,11 Yongqian Shu,12 Ying Yuan,13 Jianfeng Zhou,14 Nong Xu,15 Tianshu Liu,16 Dong Ma,17 Changping Wu,18 Ying Cheng,19 Donghui Chen,20 Wei Li,21 Sanyuan Sun,22 Zhuang Yu,23 Peiguo Cao,24 Haihui Chen,25 Jiejun Wang,26 Shubin Wang,27 Hongbing Wang,28 Ning Wang,29 Bin Zhang,29 Qiang Zhang,29 Weiguo Su,30 Xiaojun Guo,30 Jin Li31 1Cancer Center, Jinling Hospital, Nanjing, People's Republic of China; 2Department of Medical Oncology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Guangzhou, People's Republic of China; 3Department of Gastrointestinal Oncology, Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Peking University Cancer Hospital & Institute, Beijing, People's Republic of China; 4Department of Medical Oncology, The Fifth Medical Center of Chinese PLA General Hospital, Beijing, People's Republic of China; 5Department of Medical Oncology, Harbin Medical University Cancer Hospital, Harbin, People's Republic of China; 6Department of Medical Oncology, Nantong Cancer Hospital, Nantong, People's Republic of China; 7Department of Medical Oncology, The Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou, People's Republic of China; 8Department of Medical Oncology, The Second Hospital of Anhui Medical University, Hefei, People's Republic of China; 9Department of Medical Oncology, Zhejiang Cancer Hospital, Hangzhou, People's Republic of China; 10Department of Medical Oncology, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University, Hangzhou, People's Republic of China; 11Department of Medical Oncology, Shanghai Medical College, Fudan University Shanghai Cancer Center, Shanghai, People's Republic of China; 12Department of Medical Oncology, Jiangsu Provincial Hospital, Nanjing, People's Republic of China; 13Department of Medical Oncology, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, People's Republic of China; 14Department of Medical Oncology, Peking Union Medical College Hospital, Beijing, People's Republic of China; 15Department of Medical Oncology, The First Affiliated Hospital of Zhejiang University College of Medicine, Hangzhou, People's Republic of China; 16Department of Medical Oncology, Fudan University Zhongshan Hospital, Shanghai Medical College, Shanghai, People's Republic of China; 17Department of Medical Oncology, Guangdong Provincial People's Hospital, Guangzhou, People's Republic of China; 18Department of Medical Oncology, The First People's Hospital of Changzhou, Changzhou, People's Republic of China; 19Department of Medical Oncology, Jilin Province Cancer Hospital, Changchun, People's Republic of China; 20Department of Medical Oncology, Shanghai Jiaotong University Affiliated First People's Hospital, Shanghai, People's Republic of China; 21Department of Medical Oncology, The First Hospital of Jilin University, Changchun, People's Republic of China; 22Department of Medical Oncology, Xuzhou Central Hospital, Xuzhou, People's Republic of China; 23Department of Medical Oncology, The Affiliated Hospital of Medical College Qingdao University, Qingdao, People's Republic of China; 24Department of Medical Oncology, The Third Xiangya Hospital of Central South University, Changsha, People's Republic of China; 25Department of Medical Oncology, Liuzhou Worker's Hospital, Liuzhou, People's Republic of China; 26Department of Medical Oncology, Shanghai Changzheng Hospital, The Second Military Medical University, Shanghai, People's Republic of China; 27Department of Medical Oncology, Peking University Shenzhen Hospital, Beijing University, Shenzhen, People's Republic of China; 28Department of Medical Oncology, The Affiliated Hospital of Xuzhou Medical College, Xuzhou Medical College, Xuzhou, People's Republic of China; 29Eli Lilly and Company, Shanghai, People's Republic of China; 30Hutchison MediPharma Limited, Shanghai, People's Republic of China; 31Department of Medical Oncology, Tongji University Shanghai East Hospital, Shanghai, People's Republic of ChinaCorrespondence: Jin LiDepartment of Medical Oncology, Tongji University Shanghai East Hospital, Shanghai, People's Republic of ChinaTel +8613761222111Email lijin@csco.org.cnObjective: The aim of the present subgroup analysis of the FRESCO trial is to determine the efficacy and hepatotoxicity of fruquintinib in Chinese patients with metastatic CRC with liver metastasis (CRLM) who were receiving third-line or posterior-line therapy.Methods: Overall survival (OS) and progression-free survival (PFS) were evaluated by Kaplan–Meier method. Hazard ratio (HR) was estimated through Cox proportional hazards model. Hepatotoxicity was coded using the standardized MedDRA queries of hepatic failure, fibrosis, cirrhosis, and other liver injury-related conditions and graded using the Common Terminology Criteria Adverse Events grades. The efficacy of fruquintinib in patients with CRLM was evaluated in various subgroups.Results: A total of 287 (69.0%) patients with metastatic CRC had liver metastasis (LM, fruquintinib: 185 and placebo: 102). Median OS in patients with CRLM was significantly prolonged with fruquintinib compared with placebo (8.61 months vs 5.98 months; HR=0.59, 95% CI, 0.45– 0.77, P< 0.001). In patients with CRLM, the incremental median PFS for patients in the fruquintinib-treated group was significantly higher than in the placebo group (median PFS: 3.71 vs.1.84 months; HR=0.22, 95% CI: 0.17– 0.30; P< 0.001). Compared with placebo, significant improvements in OS were observed with fruquintinib in LM patients regardless of lung metastasis, prior target therapy, and K-RAS status. In patients with CRLM, treatment-emergent hepatotoxicities of any grade occurred in 7 (3.8%) patients in the fruquintinib group vs 2 (2.0%) in the placebo group.Conclusion: Fruquintinib demonstrated a statistically significant increase in OS and PFS as compared with placebo in Chinese patients with CRLM. The hepatotoxicity of fruquintinib was less reported, and comparable with placebo in patients with CRLM.ClinicalTrials.gov Identifier: NCT02314819.Keywords: colorectal cancer, FRESCO trial, fruquintinib, liver metastasis
