Loading...
6 results
Search Results
Now showing 1 - 6 of 6
- MIRAU-Net :An Improved Neural Network Based on U-Net for Gliomas SegmentationPublication . Aboelenein, Nagwa M.; Songhao, Piao; Noor, Alam; Ahmad, Pir NomanGliomas are the largest prevalent and destructive of brain tumors and have crucial parts for the diagnosing and treating of MRI brain tumors during segmentation using computerized methods. Recently, U-Net architecture has achieved impressive brain tumor segmentation, but this role remains challenging due to the differing severity and appearance of gliomas. Therefore, we proposed a novel encoder-decoder architecture called Multi Inception Residual Attention U-Net (MIRAU-Net) in this work. It integrates residual, inception modules with attention gates into U-Net to further enhance brain tumor segmentation performance. Encoderdecoder is connected in this architecture through Inception Residual pathways to decrease the distance between their maps of features. We use the weight crossentropy and generalized Dice (GDL) with focal Tversky loss functions to resolve the class imbalance problem. The evaluation performance of MIRAU-Net checked with Brats 2019 and obtained mean dice similarities of 0.885 for the whole tumor, 0.879 for the core area, and 0.818 for the enhancement tumor. Experiment results reveal that the suggested MIRAU-Net beats its baselines and provides better efficiency than recent techniques for brain tumor segmentation.
- Employing Intelligent Aerial Data Aggregators for Internet of Things: Challenges and SolutionsPublication . Li, Kai; Ni, W.; Noor, Alam; Guizani, MohsenInternet-of-Things (IoT) devices equipped with temperature and humidity sensors, and cameras are increasingly deployed to monitor remote and human-unfriendly areas, e.g., farmlands, forests, rural highways or electricity infrastructures. Aerial data aggregators, e.g., autonomous drones, provide a promising solution for collecting sensory data of the IoT devices in human-unfriendly environments, enhancing network scalability and connectivity. The flexibility of a drone and favourable line-of-sight connection between the drone and IoT devices can be exploited to improve data reception at the drone. This article first discusses challenges of the drone-assisted data aggregation in IoT networks, such as incomplete network knowledge at the drone, limited buffers of the IoT devices, and lossy wireless channels. Next, we investigate the feasibility of onboard deep reinforcement learning-based solutions to allow a drone to learn its cruise control and data collection schedule online. For deep reinforcement learning in a continuous operation domain, deep deterministic policy gradient (DDPG) is suitable to deliver effective joint cruise control and communication decision, using its outdated knowledge of the IoT devices and network states. A case study shows that the DDPG-based framework can take advantage of the continuous actions to substantially outperform existing non-learning-based alternatives.
- An efficient adaptive modulation technique over realistic wireless communication channels based on distance and SINRPublication . Khan, Rahim; Yang, Qiang; NOOR, ALAM; Altaf Khattak, Sohaib Bin; Guo, Liang; Tufail, Ahsan BinA growing trend has been observed in recent research in wireless communication systems. However, several limitations still exist, such as packet loss, limited bandwidth and inefficient use of available bandwidth that needs further investigation and research. In light of the above limitations, this paper uses adaptive modulation under various parameters, such as signal to interference plus noise ratio (SINR), and communication channel 19s distances. The primary goal is to minimize bit error rate (BER), improve throughput and utilize the available bandwidth efficiently. Additionally, the impact of Additive White Gaussian Noise (AWGN), Rayleigh and Rician fading channels on the performance of various modulation schemes are also studied. The simulation results demonstrate that our proposed technique optimally improves the BER and spectral efficiency in the long-range communication as compared to the fixed modulation schemes under the co-channel interference of surrounding base stations. The results indicate that the performance of fixed modulation schemes is suitable only either at high SINR and low distance or at low SINR and high distance values. Moreover, on the other hand, its performance was suboptimal in the entire wireless communication channel due to high distortion and attenuation. Lastly, we also noted that BER performance in the AWGN channel is better than Rayleigh and Rician channels with Rayleigh channel exhibiting poor performance than the Rician channel.
- Poisoning federated learning with graph neural networks in Internet of DronesPublication . Li, Kai; NOOR, ALAM; Ni, Wei; Tovar, Eduardo; Fu, Xiaoming; Akan, Ozgur B.Internet of Drones (IoD) is an innovative technology that integrates mobile computing capabilities with drones, enabling them to process data at or near the location where it is collected. Federated learning can significantly enhance the efficiency and effectiveness of data processing and decision-making in IoD. Since federated learning relies on aggregating updates from multiple drones, a malicious drone can generate poisoning local model updates that involves erroneous information, leading to incorrect decisions or even dangerous situations. In this paper, a new data-independent model poisoning attack is developed to manipulate federated learning accuracy, which does not rely on training data at drones. The proposed attack leverages an adversarial graph neural network (A-GNN) to generate poisoning local model updates based on the benign local models overheard. Particularly, the A-GNN discerns the graph structural correlations between the benign local models and the features of the training data that underpin these models. The graph structural correlations are reconstructively manipulated at the malicious drone to crafts poisoning local model updates, where the training loss of the federated learning is maximized.
- Deep Graph-based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet-of-Things (EdgeIoT)Publication . Li, Kai; Ni, Wei; Yuan, Xin; Noor, Alam; Jamalipour, AbbasThis paper puts forth an aerial edge Internet-of-Things (EdgeIoT) system, where an unmanned aerial vehicle (UAV) is employed as a mobile edge server to process mission-critical computation tasks of ground Internet-of-Things (IoT) devices. When the UAV schedules an IoT device to offload its computation task, the tasks buffered at the other unselected devices could be outdated and have to be cancelled. We investigate a new joint optimization of UAV cruise control and task offloading allocation, which maximizes tasks offloaded to the UAV, subject to the IoT device’s computation capacity and battery budget, and the UAV’s speed limit. Since the optimization contains a large solution space while the instantaneous network states are unknown to the UAV, we propose a new deep graph-based reinforcement learning framework. An advantage actor-critic (A2C) structure is developed to train the real-time continuous actions of the UAV in terms of the flight speed, heading, and the offloading schedule of the IoT device. By exploring hidden representations resulting from the network feature correlation, our framework takes advantage of graph neural networks (GNN) to supervise the training of UAV’s actions in A2C. The proposed GNN-A2C framework is implemented with Google Tensorflow. The performance analysis shows that GNN-A2C achieves fast convergence and reduces considerably the task missing rate in aerial EdgeIoT.
- 3D convolutional neural networks based automatic modulation classification in the presence of channel noisePublication . Khan, Rahim; Yang, Qiang; Ullah, Inam; Rehman, Ateeq Ur; Tufail, Ahsan Bin; NOOR, ALAM; Rehman, Abdul; Cengiz, KorhanAutomatic modulation classification is a task that is essentially required in many intelligent communication systems such as fibre-optic, next-generation 5G or 6G systems, cognitive radio as well as multimedia internet-ofthings networks etc. Deep learning (DL) is a representation learning method that takes raw data and finds representations for different tasks such as classification and detection. DL techniques like Convolutional Neural Networks (CNNs) have a strong potential to process and analyse large chunks of data. In this work, we considered the problem of multiclass (eight classes) classification of modulated signals, which are, Binary Phase Shift Keying, Quadrature Phase Shift Keying, 16 and 64 Quadrature Amplitude Modulation corrupted by Additive White Gaussian Noise, Rician and Rayleigh fading channels using 3D-CNN architectures in both frequency and spatial domains while deploying three approaches for data augmentation, which are, random zoomed in/out, random shift and random weak Gaussian blurring augmentation techniques with a cross-validation (CV) based hyperparameter selection statistical approach. Simulation results testify the performance of 10-fold CV without augmentation in the spatial domain to be the best while the worst performing method happens to be 10-fold CV without augmentation in the frequency domain and we found learning in the spatial domain to be better than learning in the frequency domain.