B.3. Communication/Networking and Information Technology
Roya Morshedi; S. Mojtaba Matinkhah; Mohammad Taghi Sadeghi
Abstract
IoT devices has witnessed a substantial increase due to the growing demand for smart devices. Intrusion Detection Systems (IDS) are critical components for safeguarding IoT networks against cyber threats. This study presents an advanced approach to IoT network intrusion detection, leveraging deep learning ...
Read More
IoT devices has witnessed a substantial increase due to the growing demand for smart devices. Intrusion Detection Systems (IDS) are critical components for safeguarding IoT networks against cyber threats. This study presents an advanced approach to IoT network intrusion detection, leveraging deep learning techniques and pristine data. We utilize the publicly available CICIDS2017 dataset, which enables comprehensive training and testing of intrusion detection models across various attack scenarios, such as Distributed Denial of Service (DDoS) attacks, port scans, botnet activity, and more. Our goal is to provide a more effective method than the previous methods. Our proposed deep learning model incorporates dense transition layers and LSTM architecture, designed to capture both spatial and temporal dependencies within the data. We employed rigorous evaluation metrics, including sparse categorical cross-entropy loss and accuracy, to assess model performance. The results of our approach show outstanding accuracy, reaching a peak of 0.997 on the test data. Our model demonstrates stability in loss and accuracy metrics, ensuring reliable intrusion detection capabilities. Comparative analysis with other machine learning models confirms the effectiveness of our approach. Moreover, our study assesses the model's resilience to Gaussian noise, revealing its capacity to maintain accuracy in challenging conditions. We provide detailed performance metrics for various attack types, offering insights into the model's effectiveness across diverse threat scenarios.
F. Salimian Najafabadi; M. T. Sadeghi
Abstract
An important sector that has a significant impact on the economies of countries is the agricultural sector. Researchers are trying to improve this sector by using the latest technologies. One of the problems facing farmers in the agricultural activities is plant diseases. If a plant problem is diagnosed ...
Read More
An important sector that has a significant impact on the economies of countries is the agricultural sector. Researchers are trying to improve this sector by using the latest technologies. One of the problems facing farmers in the agricultural activities is plant diseases. If a plant problem is diagnosed soon, the farmer can treat the disease more effectively. This study introduces a new deep artificial neural network called AgriNet which is suitable for recognizing some types of agricultural diseases in a plant using images from the plant leaves. The proposed network makes use of the channel shuffling technique of ShuffleNet and the channel dependencies modeling technique of SENet. One of the factors influencing the effectiveness of the proposed network architecture is how to increase the flow of information in the channels after explicitly modelling interdependencies between channels. This is in fact, an important novelty of this research work. The dataset used in this study is PlantVillage, which contains 14 types of plants in 24 groups of healthy and diseased. Our experimental results show that the proposed method outperforms the other methods in this area. AgriNet leads to accuracy and loss of 98% and 7%, respectively on the experimental data. This method increases the recognition accuracy by about 2% and reduces the loss by 8% compared to the ShuffleNetV2 method.
H.3. Artificial Intelligence
T. Zare; M. T. Sadeghi; H. R. Abutalebi; J. Kittler
Abstract
Machine-learning solutions to classification, clustering and matching problems critically depend on the adopted metric, which in the past was selected heuristically. In the last decade, it has been demonstrated that an appropriate metric can be learnt from data, resulting in superior performance as compared ...
Read More
Machine-learning solutions to classification, clustering and matching problems critically depend on the adopted metric, which in the past was selected heuristically. In the last decade, it has been demonstrated that an appropriate metric can be learnt from data, resulting in superior performance as compared with traditional metrics. This has recently stimulated a considerable interest in the topic of metric learning, especially using kernel functions, which map data to feature spaces with enhanced class separability, and implicitly define a new metric in the original feature space. The formulation of the problem of metric learning depends on the supervisory information available for the task. In this paper, we focus on semi-supervised kernel based distance metric learning where the training data set is unlabelled, with the exception of a small subset of pairs of points labelled as belonging to the same class (cluster) or different classes (clusters). The proposed method involves creating a pool of kernel functions. The corresponding kernels matrices are first clustered to remove redundancy in representation. A composite kernel constructed from the kernel clustering result is then expanded into an orthogonal set of basis functions. The mixing parameters of this expansion are then optimised using point similarity and dissimilarity information conveyed by the labels. The proposed method is evaluated on synthetic and real data sets. The results show the merit of using similarity and dissimilarity information jointly as compared to using just the similarity information, and the superiority of the proposed method over all the recently introduced metric learning approaches.
