Browsing by Author "Hosseinabadi, Fahimeh Aghaei"

Now showing 1 - 4 of 4

Open Access
Comparative characterization of indoor VLC and MMW communications via ray tracing simulations
(IEEE, 2023) Hosseinabadi, Fahimeh Aghaei; Eldeeb, H. B.; Bariah, L.; Muhaidat, S.; Uysal, Murat; Electrical & Electronics Engineering; UYSAL, Murat; Hosseinabadi, Fahimeh Aghaei
The demand for ultra-high-speed indoor wireless connectivity is ever-increasing, which poses unique challenges for the next generation wireless communication system design. This has prompted the exploration of higher frequency bands including millimeter wave (MMW) and visible light bands in addition to the conventional sub-6 GHz band. This paper provides a comprehensive comparison of the propagation channels of these frequency bands under the same indoor environment and scenarios. We adopt ray tracing techniques for site-specific channel modeling, which enables the consideration of the three-dimensional models of the indoor environment and objects inside. It allows us to take into account different frequencies, i.e., 2.4 GHz, 6 GHz, 28 GHz, 60 GHz, 100 GHz, and visible light band as well as different transmitter types, i.e., omnidirectional/directional antennas for radio frequency systems and indoor luminaries for visible light communications (VLC). For different frequencies under consideration, we obtain channel impulse responses (CIRs) and present the channel path losses for various user trajectories in indoor environments. Furthermore, we propose closed-form expressions for the cumulative distribution functions (CDFs) of received power levels for all frequency bands under consideration. Our results demonstrate that VLC channels exhibit lower path loss than that in MMW bands but higher than that of 2.4 GHz band. In addition, it is observed that VLC systems exhibit more sensitivity to shadowing and blockage effects. Our findings further indicate that the characteristics of the propagation channel are greatly influenced by the antenna type. For instance, using omnidirectional and rectangular patch antennas results in lower path loss compared to horn antennas, and this difference becomes more significant as the transmission distance decreases.
Metadata only
A comparative evaluation of propagation characteristics of vehicular VLC and MMW channels
(IEEE, 2023) Hosseinabadi, Fahimeh Aghaei; Eldeeb, H. B.; Uysal, Murat; Electrical & Electronics Engineering; UYSAL, Murat; Hosseinabadi, Fahimeh Aghaei
Vehicle-to-vehicle (V2V) communication is an underlying key technology to realize future intelligent transportation systems. Both millimeter wave (MMW) communication and visible light communication (VLC) are strong candidates to address V2V connectivity. Most of the earlier literature focuses on an individual technology. In an effort to better highlight the differences and relative advantages of these two competing technologies, we provide a comprehensive one-to-one comparison between vehicular VLC and MMW channels in this paper. For this purpose, we utilize ray tracing simulations which enable the consideration of three-dimensional modeling of the propagation environment and allow the study of various system parameters and road conditions in both line-of-sight and non-line-of-sight conditions. Under the same settings, we present the received signal strengths for both systems and investigate the channel characteristics for communication between two vehicles in the same lane as well as in different lanes with a lateral shift. We also analyze the impact of low, medium, and high density of neighbor vehicles as well as partial and complete blockage.
Metadata only
Graph convolutional network-based deep feature learning for cardiovascular disease recognition from heart sound signals
(Wiley, 2022-12) Rezaee, K.; Khosravi, M. R.; Jabari, M.; Hesari, S.; Anari, M. S.; Hosseinabadi, Fahimeh Aghaei; Hosseinabadi, Fahimeh Aghaei
The high mortality rate and prevalence of cardiovascular disease (CVD) make early detection of the disease essential. Due to its simplicity and low cost, the phonocardiogram (PCG) system is widely used in healthcare applications for the recognition of CVD in multiclass problems. On the basis of the PCG signal, this paper proposes a hybrid method for classifying cardiac sounds with deep extracted features through two-step learning. For fine-grained features in Graph Convolutional Networks (GCNs), sampling and prior layers are employed. A PCG signal is divided into equal parts with overlap using the windowing process. L-spectrograms extract frequency-domain information from signals to figure out their power spectrum. Furthermore, the deep GCN tries to determine the association between CVD and spectrogram images to recognize CVD signals better. Combining retrieved features with convolutional neural network (CNN) characteristics reveals an image's intrinsic associations. To generate relational feature representations, correlations between clusters and GCN are visualized using a graph structure. CNN's discriminative ability has been enhanced by incorporating GCN attributes. Using Michigan Heart Sound and Murmur Database and PhysioNet/CinC 2016 Challenge results, we are 99.44% and 96.16% accurate, respectively. Through a combination of GCN architecture, CNN design, and deep features, the hybrid model significantly improves CVD classification accuracy. Measuring metrics demonstrate that the proposed approach detects CVD more effectively than previous approaches.
Metadata only
PDM: Privacy-aware deployment of machine-learning applications for industrial cyber–physical cloud systems
(IEEE, 2021-08) Xu, X.; Mo, R.; Yin, X.; Khosravi, M. R.; Hosseinabadi, Fahimeh Aghaei; Chang, V.; Li, G.; Hosseinabadi, Fahimeh Aghaei
The cyber-physical cloud systems (CPCSs) release powerful capability in provisioning the complicated industrial services. Due to the advances of machine learning (ML) in attack detection, a wide range of ML applications are involved in industrial CPCSs. However, how to ensure the implementation efficiency of these applications, and meanwhile avoid the privacy disclosure of the datasets due to data acquisition by different operators, remain challenging for the design of the CPCSs. To fill this gap, in this article a privacy-aware deployment method (PDM), named PDM, is devised for hosting the ML applications in the industrial CPCSs. In PDM, the ML applications are partitioned as multiple computing tasks with certain execution order, like workflows. Specifically, the deployment problem is formulated as a multiobjective problem for improving the implementation performance and resource utility. Then, the most balanced and optimal strategy is selected by leveraging an improved differential evolution technique. Finally, through comprehensive experiments and comparison analysis, PDM is fully evaluated.