Sudden cardiac arrest among young people is a recent worldwide risk, and it is noticed that people with cardiac arrhythmia are more susceptible to various heart diseases. Manual classification can be error-prone, and certainly, there is a need for automation to classify ECG signals to predict cardiac arrhythmia accurately. The proposed self-attention artificial intelligence auto-encoder algorithm proved an effective cardiac arrhythmia classification strategy with a novel modified Kalman filter pre-processing. We achieved 24.00 SNRimp, 0.055 RMSE, 22.1 PRD% for -5db, 20.4 SNRimp, 0.0245 RMSE, 12 PRD% whereas 14.05 SNRimp, 0.010 RMSE, and 7.25 PRD%, which reduces the ECG signal noise during the pre-processing and improves the visibility of the QRS complex and R-R peaks of ECG waveform. The extracted features were used in network of neurons to execute the classification for MIT-BIH arrhythmia databases using the newly developed self-attention autoencoder (AE) algorithm. The results are compared with existing models, revealing that the proposed system outperforms the classification and prediction of cardiac arrhythmia with a precision of 99.91%, recall of 99.86%, and accuracy of 99.71%. It is confirmed that self-attention-AE training results are promising, and it benefits the diagnosis of ECGs for complex cardiac conditions to solve real-world heart problems.
Attacks on IoT devices are increasing day by day. Since IoT devices nowadays have become an integral part of our daily lives, the data gathered from IoT devices benefits intruders in many ways. Financial and Healthcare institutions also allow their customers to use their services by using handheld IoT devices. Smart homes and autonomous vehicles use many IoT devices to gather data through the built-in sensors and send it to the Edge server for further processing. The computation result on the Edge server determines the decision to fulfill the user-specific needs. As these data are vital in the future cycle of execution of an intelligent algorithm of IoT device software program, hence the data are not just of temporary use, but it is transferred to a Cloud server for permanent storage. The data flows from IoT sensors to the Edge server, then from the Edge server to the Cloud server. Here the riskiest part for data to stay is on the Edge server. To counter such a security risk, we proposed and implemented the Adaptive Epsilon Greedy Reinforcement Learning (AEGRL) method which is the extension of the traditional Epsilon (ℇ) greedy reinforcement learning method. The proposed method works efficiently for both static and dynamic environments. Experimental results show that our proposed security method outperforms the recent similar security approaches in terms of scalability, robustness, and accuracy.
1 August 2022 in Journal of Physics: Conference Series
The limited resource and computation capacity of an IoT device always being a target vector for intruders to use to steal sensitive data from the device. Computational problems later solved by the engineers by introducing an edge server near to IoT device network boundary, but still it is not secure from the hands of intruders. IoT device vulnerabilities still can allow Edge server to give the control of the device to the intruders. Hence both the Edge server and the connected IoT device may fall under the control of an intruder for a misuse. In this paper we study how IoT devices in case of Edge computing falls under security threats. We have used NS2 simulator to identify a malicious node that behaves inconsistent in terms of Packet Delivery Ratio, End-to-End Delay, and Throughput.
9 September 2025 in International Journal of Applied Mathematics
Intrusion Detection Systems (IDS) are very important for keeping networks safe from online dangers, especially when there are a lot of different classes of data and duplicate features that can slow things down. This work presents a new way to improve the performance of IDS by mixing the K-Best and Random Forest Importance methods for feature extraction. Before Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Independent Component Analysis (ICA), and the suggested blend method were used on the IoT-23 dataset, features were normalized and labeled. The combination method picked out important factors like flow time, packet length, protocol type, and response numbers, which led to better classification results. We used an 80-20 split for train and test to check how well three models (XGBoost, Random Forest, and Naive Bayes) worked. Comparative research showed that the combined method was better, as it achieved 99% accuracy and big gains in precision, memory, and F1-score measures. In particular, XGBoost proved to be the best model, showing impressive speed with its mixed feature set. PCA, LDA, and ICA, on the other hand, gave average results. This shows how important it is to combine different feature selection methods. The results show that the mix method can deal with feature duplication and improve IDS performance, which makes it a good choice for real-world use. To make this method even better, more study could look into how it works with bigger datasets and more models.