Deep Residual Networks (ResNets) are prone to overfitting in problems with uncertainty, such as intrusion detection problems. To alleviate this problem, we proposed a method that combines the Adaptive Neuro-fuzzy Inference System (ANFIS) and the ResNet algorithm. This method can make use of the advantages of both the ANFIS and ResNet, and alleviate the overfitting problem of ResNet. Compared with the original ResNet algorithm, the proposed method provides overlapped intervals of continuous attributes and fuzzy rules to ResNet, improving the fuzziness of ResNet. To evaluate the performance of the proposed method, the proposed method is realized and evaluated on the benchmark NSL-KDD dataset. Also, the performance of the proposed method is compared with the original ResNet algorithm and other deep learning-based and ANFIS-based methods. The experimental results demonstrate that the proposed method is better than that of the original ResNet and other existing methods on various metrics, reaching a 98.88% detection rate and 1.11% false alarm rate on the KDDTrain+ dataset.
For generating an interpretable deep architecture for identifying deep intrusion patterns, this study proposes an approach that combines ANFIS (Adaptive Network-based Fuzzy Inference System) and DT (Decision Tree) for interpreting the deep pattern of intrusion detection. Meanwhile, for improving the efficiency of training and predicting, Pearson Correlation analysis, standard deviation, and a new adaptive K-means are used to select attributes and make fuzzy interval decisions. The proposed algorithm was trained, validated, and tested on the NSL-KDD (National security lab-knowledge discovery and data mining) dataset. Using 22 attributes that highly related to the target, the performance of the proposed method achieves a 99.86% detection rate and 0.14% false alarm rate on the KDDTrain+ dataset, a 77.46% detection rate on the KDDTest+ dataset, which is better than many classifiers. Besides, the interpretable model can help us demonstrate the complex and overlapped pattern of intrusions and analyze the pattern of various intrusions.
BACKGROUND: Intra-articular hyaluronic acid (HA) injection is used in management of knee, hand and hip osteoarthritis. While HA injection is included in the list of evaluated therapies, its efficacy and optimum dosing still have no consensus. This study was conducted to explore the possibility of using single injection HA to increase patient convenience while maintaining the therapeutic efficacy.
METHODS: We present a prospective, open label, non-blinded, randomized controlled trial performed in accordance with guidelines in principles of good clinical practice. Block randomization was done for patients to receive either single 5 ml GO-ON injection or the conventional three injections of 2.5 ml GO-ON at weekly interval. Baseline Western Ontario McMaster University Osteoarthritis (WOMAC) scores were evaluated and recorded. All subjects were re-evaluated at 3 months and the WOMAC score recorded again as primary end points. Data analyses were performed with IBM SPSS Statistics for Windows software (version 21.0, IBM Corp, Armonk, New York, USA).
RESULTS: In the cohort of 127 patients, 33 were males and 94 females. The mean age was 59.1 years (standard deviation (SD) = 7.25) in single injection arm and 60.1 years (SD = 7.72) in triple injection arm. The two groups were recorded to have no significant difference in age ( p = 0.46) and Kellgren-Lawrence radiological grade ( p = 0.694). There was significant increase in the WOMAC scores from the baseline (pre-injection) to that recorded 3 months after injection ( p < 0.001) in patients of both groups. However, there was no statistically significant difference noticed in this clinical improvement between the two arms ( p = 0.889).
CONCLUSION: The study shows single 5 ml dose regime comparing well with conventional three doses of 2.5 ml of intra-articular GO-ON HA injected at weekly intervals and confirms good efficacy, tolerability and safety of single larger dose of GO-ON knee intra-articular injection.