- Award ID(s):
- 1924112
- PAR ID:
- 10158120
- Date Published:
- Journal Name:
- Proceedings of the 6th IEEE World Forum on Internet of Things (WF-IoT)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
The modeling of the brain as a three-dimensional spatial object, similar to a geographical landscape, has the paved way for the successful application of Kriging methods in solving the seizure detection problem with good performance but in cubic computational time complexity. The Deep Neural Network (DNN) has been widely used for seizure detection due to its effectiveness in classification tasks, although at the cost of a protracted training time. While Kriging exploits the spatial correlation between data locations, DNN relies on its capacity to learn intrinsic representations within the dataset from the basest unit parts. This paper presents a Distributed Kriging-Bootstrapped Deep Neural Network (DNN) model as a twofold solution for fast and accurate seizure detection using brain signals collected with the electroencephalogram (EEG) from healthy subjects and patients of epilepsy. The proposed model parallelizes the Kriging computation into different cores in a machine and then produces a strongly correlated, unified quasi-output data which serves as an input to the Deep Neural Network. Experimental results validate the proposed model as superior to conventional Kriging methods and DNN by training in 91% less time than the basic DNN and about three times as fast as the ordinary Kriging-Bootstrapped Deep Neural Network (DNN) model while maintaining good performance in terms of sensitivity, specificity and testing accuracy compared to other models and existing works.more » « less
-
Epileptic seizures are dangerous. They render patients unconscious and can lead to death within seconds of onset. There is, therefore, the need for a very fast and accurate seizure detection mechanism. Kriging methods have been used extensively in geostatistics for spatial prediction and are known for very high accuracy. By modeling the brain as a spatial map, we demonstrate the effectiveness of Kriging Methods for efficient seizure detection in an edge computing paradigm. We explore three different types of Kriging - Simple Kriging, Ordinary Kriging and Universal Kriging. Results from various experiments with electroencephalogram (EEG) signals of both healthy and diseased patients show that all three Kriging methods have good performance in terms of accuracy, sensitivity and detection latency. However, Simple Kriging emerged as the slight favorite for seizure detection with a mean detection latency of 0.81 sec, an accuracy of 97.50%, a sensitivity of 94.74% and a perfect specificity. Simple Kriging is at least 5% better than Ordinary Kriging and Universal Kriging when evaluated at 68.2% confidence interval. The results obtained in this paper compare favorably with other seizure detection models in the literature.more » « less
-
Traditional network intrusion detection approaches encounter feasibility and sustainability issues to combat modern, sophisticated, and unpredictable security attacks. Deep neural networks (DNN) have been successfully applied for intrusion detection problems. The optimal use of DNN-based classifiers requires careful tuning of the hyper-parameters. Manually tuning the hyperparameters is tedious, time-consuming, and computationally expensive. Hence, there is a need for an automatic technique to find optimal hyperparameters for the best use of DNN in intrusion detection. This paper proposes a novel Bayesian optimization-based framework for the automatic optimization of hyperparameters, ensuring the best DNN architecture. We evaluated the performance of the proposed framework on NSL-KDD, a benchmark dataset for network intrusion detection. The experimental results show the framework’s effectiveness as the resultant DNN architecture demonstrates significantly higher intrusion detection performance than the random search optimization-based approach in terms of accuracy, precision, recall, and f1-score.more » « less
-
Purpose The purpose of this study is to develop a deep learning framework for additive manufacturing (AM), that can detect different defect types without being trained on specific defect data sets and can be applied for real-time process control.
Design/methodology/approach This study develops an explainable artificial intelligence (AI) framework, a zero-bias deep neural network (DNN) model for real-time defect detection during the AM process. In this method, the last dense layer of the DNN is replaced by two consecutive parts, a regular dense layer denoted (L1) for dimensional reduction, and a similarity matching layer (L2) for equal weight and non-biased cosine similarity matching. Grayscale images of 3D printed samples acquired during printing were used as the input to the zero-bias DNN.
Findings This study demonstrates that the approach is capable of successfully detecting multiple types of defects such as cracks, stringing and warping with high accuracy without any prior training on defective data sets, with an accuracy of 99.5%.
Practical implications Once the model is set up, the computational time for anomaly detection is lower than the speed of image acquisition indicating the potential for real-time process control. It can also be used to minimize manual processing in AI-enabled AM.
Originality/value To the best of the authors’ knowledge, this is the first study to use zero-bias DNN, an explainable AI approach for defect detection in AM.
-
Deep learning is being incorporated in many modern software systems. Deep learning approaches train a deep neural network (DNN) model using training examples, and then use the DNN model for prediction. While the structure of a DNN model as layers is observable, the model is treated in its entirety as a monolithic component. To change the logic implemented by the model, e.g. to add/remove logic that recognizes inputs belonging to a certain class, or to replace the logic with an alternative, the training examples need to be changed and the DNN needs to be retrained using the new set of examples. We argue that decomposing a DNN into DNN modules-akin to decomposing a monolithic software code into modules-can bring the benefits of modularity to deep learning. In this work, we develop a methodology for decomposing DNNs for multi-class problems into DNN modules. For four canonical problems, namely MNIST, EMNIST, FMNIST, and KMNIST, we demonstrate that such decomposition enables reuse of DNN modules to create different DNNs, enables replacement of one DNN module in a DNN with another without needing to retrain. The DNN models formed by composing DNN modules are at least as good as traditional monolithic DNNs in terms of test accuracy for our problems.more » « less