arXiv subjects

Arash Mohammadi

Publications and source records attributed to Arash Mohammadi.

At least 55 records · Page 3Linked to original sources

arXiv2022

AKF-SR: Adaptive Kalman Filtering-based Successor Representation

Recent studies in neuroscience suggest that Successor Representation (SR)-based models provide adaptation to changes in the goal locations or reward function faster than model-free algorithms, together with lower computational cost compared to that of model-based algorithms. However, it is not known how such representation might help animals to manage uncertainty in their decision-making. Existing methods for SR learning do not capture uncertainty about the estimated SR. In order to address this issue, the paper presents a Kalman filter-based SR framework, referred to as Adaptive Kalman Filtering-based Successor Representation (AKF-SR). First, Kalman temporal difference approach, which is a combination of the Kalman filter and the temporal difference method, is used within the AKF-SR framework to cast the SR learning procedure into a filtering problem to benefit from the uncertainty estimation of the SR, and also decreases in memory requirement and sensitivity to model's parameters in comparison to deep neural network-based algorithms. An adaptive Kalman filtering approach is then applied within the proposed AKF-SR framework in order to tune the measurement noise covariance and measurement mapping function of Kalman filter as the most important parameters affecting the filter's performance. Moreover, an active learning method that exploits the estimated uncertainty of the SR to form the behaviour policy leading to more visits to less certain values is proposed to improve the overall performance of an agent in terms of received rewards while interacting with its environment.

cs.NE↗

arXiv2022

CAE-Transformer: Transformer-based Model to Predict Invasiveness of Lung Adenocarcinoma Subsolid Nodules from Non-thin Section 3D CT Scans

Lung cancer is the leading cause of mortality from cancer worldwide and has various histologic types, among which Lung Adenocarcinoma (LUAC) has recently been the most prevalent one. The current approach to determine the invasiveness of LUACs is surgical resection, which is not a viable solution to fight lung cancer in a timely fashion. An alternative approach is to analyze chest Computed Tomography (CT) scans. The radiologists' analysis based on CT images, however, is subjective and might result in a low accuracy. In this paper, a transformer-based framework, referred to as the "CAE-Transformer", is developed to efficiently classify LUACs using whole CT images instead of finely annotated nodules. The proposed CAE-Transformer can achieve high accuracy over a small dataset and requires minor supervision from radiologists. The CAE Transformer utilizes an encoder to automatically extract informative features from CT slices, which are then fed to a modified transformer to capture global inter-slice relations and provide classification labels. Experimental results on our in-house dataset of 114 pathologically proven Sub-Solid Nodules (SSNs) demonstrate the superiority of the CAE-Transformer over its counterparts, achieving an accuracy of 87.73%, sensitivity of 88.67%, specificity of 86.33%, and AUC of 0.913, using a 10-fold cross-validation.

eess.IV↗

arXiv2022

ViT-HGR: Vision Transformer-based Hand Gesture Recognition from High Density Surface EMG Signals

Recently, there has been a surge of significant interest on application of Deep Learning (DL) models to autonomously perform hand gesture recognition using surface Electromyogram (sEMG) signals. DL models are, however, mainly designed to be applied on sparse sEMG signals. Furthermore, due to their complex structure, typically, we are faced with memory constraints; require large training times and a large number of training samples, and; there is the need to resort to data augmentation and/or transfer learning. In this paper, for the first time (to the best of our knowledge), we investigate and design a Vision Transformer (ViT) based architecture to perform hand gesture recognition from High Density (HD-sEMG) signals. Intuitively speaking, we capitalize on the recent breakthrough role of the transformer architecture in tackling different complex problems together with its potential for employing more input parallelization via its attention mechanism. The proposed Vision Transformer-based Hand Gesture Recognition (ViT-HGR) framework can overcome the aforementioned training time problems and can accurately classify a large number of hand gestures from scratch without any need for data augmentation and/or transfer learning. The efficiency of the proposed ViT-HGR framework is evaluated using a recently-released HD-sEMG dataset consisting of 65 isometric hand gestures. Our experiments with 64-sample (31.25 ms) window size yield average test accuracy of 84.62 +/- 3.07%, where only 78, 210 number of parameters is utilized. The compact structure of the proposed ViT-based ViT-HGR framework (i.e., having significantly reduced number of trainable parameters) shows great potentials for its practical application for prosthetic control.

cs.CV↗

arXiv2022

Lung-Originated Tumor Segmentation from Computed Tomography Scan (LOTUS) Benchmark

Lung cancer is one of the deadliest cancers, and in part its effective diagnosis and treatment depend on the accurate delineation of the tumor. Human-centered segmentation, which is currently the most common approach, is subject to inter-observer variability, and is also time-consuming, considering the fact that only experts are capable of providing annotations. Automatic and semi-automatic tumor segmentation methods have recently shown promising results. However, as different researchers have validated their algorithms using various datasets and performance metrics, reliably evaluating these methods is still an open challenge. The goal of the Lung-Originated Tumor Segmentation from Computed Tomography Scan (LOTUS) Benchmark created through 2018 IEEE Video and Image Processing (VIP) Cup competition, is to provide a unique dataset and pre-defined metrics, so that different researchers can develop and evaluate their methods in a unified fashion. The 2018 VIP Cup started with a global engagement from 42 countries to access the competition data. At the registration stage, there were 129 members clustered into 28 teams from 10 countries, out of which 9 teams made it to the final stage and 6 teams successfully completed all the required tasks. In a nutshell, all the algorithms proposed during the competition, are based on deep learning models combined with a false positive reduction technique. Methods developed by the three finalists show promising results in tumor segmentation, however, more effort should be put into reducing the false positive rate. This competition manuscript presents an overview of the VIP-Cup challenge, along with the proposed algorithms and results.

eess.IV↗

arXiv2022

DF-SSmVEP: Dual Frequency Aggregated Steady-State Motion Visual Evoked Potential Design with Bifold Canonical Correlation Analysis

Recent advancements in Electroencephalography (EEG) sensor technologies and signal processing algorithms have paved the way for further evolution of Brain Computer Interfaces (BCI). When it comes to Signal Processing (SP) for BCI, there has been a surge of interest on Steady-State motion-Visual Evoked Potentials (SSmVEP), where motion stimulation is utilized to address key issues associated with conventional light-flashing/flickering. Such benefits, however, come with the price of having less accuracy and less Information Transfer Rate (ITR). In this regard, the paper focuses on the design of a novel SSmVEP paradigm without using resources such as trial time, phase, and/or number of targets to enhance the ITR. The proposed design is based on the intuitively pleasing idea of integrating more than one motion within a single SSmVEP target stimuli, simultaneously. To elicit SSmVEP, we designed a novel and innovative dual frequency aggregated modulation paradigm, referred to as the Dual Frequency Aggregated steady-state motion Visual Evoked Potential (DF-SSmVEP), by concurrently integrating "Radial Zoom" and "Rotation" motions in a single target without increasing the trial length. Compared to conventional SSmVEPs, the proposed DF-SSmVEP framework consists of two motion modes integrated and shown simultaneously each modulated by a specific target frequency. The paper also develops a specific unsupervised classification model, referred to as the Bifold Canonical Correlation Analysis (BCCA), based on two motion frequencies per target. The proposed DF-SSmVEP is evaluated based on a real EEG dataset and the results corroborate its superiority. The proposed DF-SSmVEP outperforms its counterparts and achieved an average ITR of 30.7 +/- 1.97 and an average accuracy of 92.5 +/- 2.04.

eess.SP↗

arXiv2021

BP-Net: Cuff-less, Calibration-free, and Non-invasive Blood Pressure Estimation via a Generic Deep Convolutional Architecture

Objective: The paper focuses on development of robust and accurate processing solutions for continuous and cuff-less blood pressure (BP) monitoring. In this regard, a robust deep learning-based framework is proposed for computation of low latency, continuous, and calibration-free upper and lower bounds on the systolic and diastolic BP. Method: Referred to as the BP-Net, the proposed framework is a novel convolutional architecture that provides longer effective memory while achieving superior performance due to incorporation of casual dialated convolutions and residual connections. To utilize the real potential of deep learning in extraction of intrinsic features (deep features) and enhance the long-term robustness, the BP-Net uses raw Electrocardiograph (ECG) and Photoplethysmograph (PPG) signals without extraction of any form of hand-crafted features as it is common in existing solutions. Results: By capitalizing on the fact that datasets used in recent literature are not unified and properly defined, a benchmark dataset is constructed from the MIMIC-I and MIMIC-III databases obtained from PhysioNet. The proposed BP-Net is evaluated based on this benchmark dataset demonstrating promising performance and shows superior generalizable capacity. Conclusion: The proposed BP-Net architecture is more accurate than canonical recurrent networks and enhances the long-term robustness of the BP estimation task. Significance: The proposed BP-Net architecture addresses key drawbacks of existing BP estimation solutions, i.e., relying heavily on extraction of hand-crafted features, such as pulse arrival time (PAT), and; Lack of robustness. Finally, the constructed BP-Net dataset provides a unified base for evaluation and comparison of deep learning-based BP estimation algorithms.

cs.LG↗

arXiv2021

Multi-Agent Reinforcement Learning via Adaptive Kalman Temporal Difference and Successor Representation

Distributed Multi-Agent Reinforcement Learning (MARL) algorithms has attracted a surge of interest lately mainly due to the recent advancements of Deep Neural Networks (DNNs). Conventional Model-Based (MB) or Model-Free (MF) RL algorithms are not directly applicable to the MARL problems due to utilization of a fixed reward model for learning the underlying value function. While DNN-based solutions perform utterly well when a single agent is involved, such methods fail to fully generalize to the complexities of MARL problems. In other words, although recently developed approaches based on DNNs for multi-agent environments have achieved superior performance, they are still prone to overfiting, high sensitivity to parameter selection, and sample inefficiency. The paper proposes the Multi-Agent Adaptive Kalman Temporal Difference (MAK-TD) framework and its Successor Representation-based variant, referred to as the MAK-SR. Intuitively speaking, the main objective is to capitalize on unique characteristics of Kalman Filtering (KF) such as uncertainty modeling and online second order learning. The proposed MAK-TD/SR frameworks consider the continuous nature of the action-space that is associated with high dimensional multi-agent environments and exploit Kalman Temporal Difference (KTD) to address the parameter uncertainty. By leveraging the KTD framework, SR learning procedure is modeled into a filtering problem, where Radial Basis Function (RBF) estimators are used to encode the continuous space into feature vectors. On the other hand, for learning localized reward functions, we resort to Multiple Model Adaptive Estimation (MMAE), to deal with the lack of prior knowledge on the observation noise covariance and observation mapping function. The proposed MAK-TD/SR frameworks are evaluated via several experiments, which are implemented through the OpenAI Gym MARL benchmarks.

cs.LG↗

arXiv2021

Human-level COVID-19 Diagnosis from Low-dose CT Scans Using a Two-stage Time-distributed Capsule Network

Reverse transcription-polymerase chain reaction (RT-PCR) is currently the gold standard in COVID-19 diagnosis. It can, however, take days to provide the diagnosis, and false negative rate is relatively high. Imaging, in particular chest computed tomography (CT), can assist with diagnosis and assessment of this disease. Nevertheless, it is shown that standard dose CT scan gives significant radiation burden to patients, especially those in need of multiple scans. In this study, we consider low-dose and ultra-low-dose (LDCT and ULDCT) scan protocols that reduce the radiation exposure close to that of a single X-Ray, while maintaining an acceptable resolution for diagnosis purposes. Since thoracic radiology expertise may not be widely available during the pandemic, we develop an Artificial Intelligence (AI)-based framework using a collected dataset of LDCT/ULDCT scans, to study the hypothesis that the AI model can provide human-level performance. The AI model uses a two stage capsule network architecture and can rapidly classify COVID-19, community acquired pneumonia (CAP), and normal cases, using LDCT/ULDCT scans. The AI model achieves COVID-19 sensitivity of 89.5% +\- 0.11, CAP sensitivity of 95% +\- 0.11, normal cases sensitivity (specificity) of 85.7% +\- 0.16, and accuracy of 90% +\- 0.06. By incorporating clinical data (demographic and symptoms), the performance further improves to COVID-19 sensitivity of 94.3% +\- pm 0.05, CAP sensitivity of 96.7% +\- 0.07, normal cases sensitivity (specificity) of 91% +\- 0.09 , and accuracy of 94.1% +\- 0.03. The proposed AI model achieves human-level diagnosis based on the LDCT/ULDCT scans with reduced radiation exposure. We believe that the proposed AI model has the potential to assist the radiologists to accurately and promptly diagnose COVID-19 infection and help control the transmission chain during the pandemic.

eess.IV↗

arXiv2021

TEDGE-Caching: Transformer-based Edge Caching Towards 6G Networks

As a consequence of the COVID-19 pandemic, the demand for telecommunication for remote learning/working and telemedicine has significantly increased. Mobile Edge Caching (MEC) in the 6G networks has been evolved as an efficient solution to meet the phenomenal growth of the global mobile data traffic by bringing multimedia content closer to the users. Although massive connectivity enabled by MEC networks will significantly increase the quality of communications, there are several key challenges ahead. The limited storage of edge nodes, the large size of multimedia content, and the time-variant users' preferences make it critical to efficiently and dynamically predict the popularity of content to store the most upcoming requested ones before being requested. Recent advancements in Deep Neural Networks (DNNs) have drawn much research attention to predict the content popularity in proactive caching schemes. Existing DNN models in this context, however, suffer from longterm dependencies, computational complexity, and unsuitability for parallel computing. To tackle these challenges, we propose an edge caching framework incorporated with the attention-based Vision Transformer (ViT) neural network, referred to as the Transformer-based Edge (TEDGE) caching, which to the best of our knowledge, is being studied for the first time. Moreover, the TEDGE caching framework requires no data pre-processing and additional contextual information. Simulation results corroborate the effectiveness of the proposed TEDGE caching framework in comparison to its counterparts.

cs.NI↗

arXiv2021

DQLEL: Deep Q-Learning for Energy-Optimized LoS/NLoS UWB Node Selection

Recent advancements in Internet of Things (IoTs) have brought about a surge of interest in indoor positioning for the purpose of providing reliable, accurate, and energy-efficient indoor navigation/localization systems. Ultra Wide Band (UWB) technology has been emerged as a potential candidate to satisfy the aforementioned requirements. Although UWB technology can enhance the accuracy of indoor positioning due to the use of a wide-frequency spectrum, there are key challenges ahead for its efficient implementation. On the one hand, achieving high precision in positioning relies on the identification/mitigation Non Line of Sight (NLoS) links, leading to a significant increase in the complexity of the localization framework. On the other hand, UWB beacons have a limited battery life, which is especially problematic in practical circumstances with certain beacons located in strategic positions. To address these challenges, we introduce an efficient node selection framework to enhance the location accuracy without using complex NLoS mitigation methods, while maintaining a balance between the remaining battery life of UWB beacons. Referred to as the Deep Q-Learning Energy-optimized LoS/NLoS (DQLEL) UWB node selection framework, the mobile user is autonomously trained to determine the optimal set of UWB beacons to be localized based on the 2-D Time Difference of Arrival (TDoA) framework. The effectiveness of the proposed DQLEL framework is evaluated in terms of the link condition, the deviation of the remaining battery life of UWB beacons, location error, and cumulative rewards. Based on the simulation results, the proposed DQLEL framework significantly outperformed its counterparts across the aforementioned aspects.

cs.NI↗

arXiv2021

Hand Gesture Recognition Using Temporal Convolutions and Attention Mechanism

Advances in biosignal signal processing and machine learning, in particular Deep Neural Networks (DNNs), have paved the way for the development of innovative Human-Machine Interfaces for decoding the human intent and controlling artificial limbs. DNN models have shown promising results with respect to other algorithms for decoding muscle electrical activity, especially for recognition of hand gestures. Such data-driven models, however, have been challenged by their need for a large number of trainable parameters and their structural complexity. Here we propose the novel Temporal Convolutions-based Hand Gesture Recognition architecture (TC-HGR) to reduce this computational burden. With this approach, we classified 17 hand gestures via surface Electromyogram (sEMG) signals by the adoption of attention mechanisms and temporal convolutions. The proposed method led to 81.65% and 80.72% classification accuracy for window sizes of 300ms and 200ms, respectively. The number of parameters to train the proposed TC-HGR architecture is 11.9 times less than that of its state-of-the-art counterpart.

cs.LG↗

arXiv2021

Data Shapley Value for Handling Noisy Labels: An application in Screening COVID-19 Pneumonia from Chest CT Scans

A long-standing challenge of deep learning models involves how to handle noisy labels, especially in applications where human lives are at stake. Adoption of the data Shapley Value (SV), a cooperative game theoretical approach, is an intelligent valuation solution to tackle the issue of noisy labels. Data SV can be used together with a learning model and an evaluation metric to validate each training point's contribution to the model's performance. The SV of a data point, however, is not unique and depends on the learning model, the evaluation metric, and other data points collaborating in the training game. However, effects of utilizing different evaluation metrics for computation of the SV, detecting the noisy labels, and measuring the data points' importance has not yet been thoroughly investigated. In this context, we performed a series of comparative analyses to assess SV's capabilities to detect noisy input labels when measured by different evaluation metrics. Our experiments on COVID-19-infected of CT images illustrate that although the data SV can effectively identify noisy labels, adoption of different evaluation metric can significantly influence its ability to identify noisy labels from different data classes. Specifically, we demonstrate that the SV greatly depends on the associated evaluation metric.

eess.IV↗

arXiv2021

Q-Net: A Quantitative Susceptibility Mapping-based Deep Neural Network for Differential Diagnosis of Brain Iron Deposition in Hemochromatosis

Brain iron deposition, in particular deep gray matter nuclei, increases with advancing age. Hereditary Hemochromatosis (HH) is the most common inherited disorder of systemic iron excess in Europeans and recent studies claimed high brain iron accumulation in patient with Hemochromatosis. In this study, we focus on Artificial Intelligence (AI)-based differential diagnosis of brain iron deposition in HH via Quantitative Susceptibility Mapping (QSM), which is an established Magnetic Resonance Imaging (MRI) technique to study the distribution of iron in the brain. Our main objective is investigating potentials of AI-driven frameworks to accurately and efficiently differentiate individuals with Hemochromatosis from those of the healthy control group. More specifically, we developed the Q-Net framework, which is a data-driven model that processes information on iron deposition in the brain obtained from multi-echo gradient echo imaging data and anatomical information on T1-Weighted images of the brain. We illustrate that the Q-Net framework can assist in differentiating between someone with HH and Healthy control (HC) of the same age, something that is not possible by just visualizing images. The study is performed based on a unique dataset that was collected from 52 subjects with HH and 47 HC. The Q-Net provides a differential diagnosis accuracy of 83.16% and 80.37% in the scan-level and image-level classification, respectively.

cs.LG↗

arXiv2021

Online Dynamic Window (ODW) Assisted Two-stage LSTM Frameworks for Indoor Localization

Internet of Things (IoT)-based indoor localization has gained significant popularity recently to satisfy the ever-increasing requirements of indoor Location-based Services (LBS). In this context, Inertial Measurement Unit (IMU)-based localization is of interest as it provides a scalable solution independent of any proprietary sensors/modules. Existing IMU-based methodologies, however, are mainly developed based on statistical heading and step length estimation techniques that suffer from cumulative error issues and have extensive computational time requirements limiting their application for real-time indoor positioning. To address the aforementioned issues, we propose the Online Dynamic Window (ODW)-assisted two-stage Long Short Term Memory (LSTM) localization framework. Three ODWs are proposed, where the first model uses a Natural Language Processing (NLP)-inspired Dynamic Window (DW) approach, which significantly reduces the required computational time. The second framework is developed based on a Signal Processing Dynamic Windowing (SP-DW) approach to further reduce the required processing time of the two-stage LSTM-based model. The third ODW, referred to as the SP-NLP, combines the first two windowing mechanisms to further improve the overall achieved accuracy. Compared to the traditional LSTM-based positioning approaches, which suffer from either high tensor computation requirements or low accuracy, the proposed ODW-assisted models can perform indoor localization in a near-real time fashion with high accuracy. Performances of the proposed ODW-assisted models are evaluated based on a real Pedestrian Dead Reckoning (PDR) dataset. The results illustrate potentials of the proposed ODW-assisted techniques in achieving high classification accuracy with significantly reduced computational time, making them applicable for near real-time implementations.

cs.LG↗

arXiv2021

TEMGNet: Deep Transformer-based Decoding of Upperlimb sEMG for Hand Gestures Recognition

There has been a surge of recent interest in Machine Learning (ML), particularly Deep Neural Network (DNN)-based models, to decode muscle activities from surface Electromyography (sEMG) signals for myoelectric control of neurorobotic systems. DNN-based models, however, require large training sets and, typically, have high structural complexity, i.e., they depend on a large number of trainable parameters. To address these issues, we developed a framework based on the Transformer architecture for processing sEMG signals. We propose a novel Vision Transformer (ViT)-based neural network architecture (referred to as the TEMGNet) to classify and recognize upperlimb hand gestures from sEMG to be used for myocontrol of prostheses. The proposed TEMGNet architecture is trained with a small dataset without the need for pre-training or fine-tuning. To evaluate the efficacy, following the-recent literature, the second subset (exercise B) of the NinaPro DB2 dataset was utilized, where the proposed TEMGNet framework achieved a recognition accuracy of 82.93% and 82.05% for window sizes of 300ms and 200ms, respectively, outperforming its state-of-the-art counterparts. Moreover, the proposed TEMGNet framework is superior in terms of structural capacity while having seven times fewer trainable parameters. These characteristics and the high performance make DNN-based models promising approaches for myoelectric control of neurorobots.

cs.LG↗

arXiv2021

TB-ICT: A Trustworthy Blockchain-Enabled System for Indoor COVID-19 Contact Tracing

Recently, as a consequence of the COVID-19 pandemic, dependence on Contact Tracing (CT) models has significantly increased to prevent spread of this highly contagious virus and be prepared for the potential future ones. Since the spreading probability of the novel coronavirus in indoor environments is much higher than that of the outdoors, there is an urgent and unmet quest to develop/design efficient, autonomous, trustworthy, and secure indoor CT solutions. Despite such an urgency, this field is still in its infancy. The paper addresses this gap and proposes the Trustworthy Blockchain-enabled system for Indoor Contact Tracing (TB-ICT) framework. The TB-ICT framework is proposed to protect privacy and integrity of the underlying CT data from unauthorized access. More specifically, it is a fully distributed and innovative blockchain platform exploiting the proposed dynamic Proof of Work (dPoW) credit-based consensus algorithm coupled with Randomized Hash Window (W-Hash) and dynamic Proof of Credit (dPoC) mechanisms to differentiate between honest and dishonest nodes. The TB-ICT not only provides a decentralization in data replication but also quantifies the node's behavior based on its underlying credit-based mechanism. For achieving high localization performance, we capitalize on availability of Internet of Things (IoT) indoor localization infrastructures, and develop a data driven localization model based on Bluetooth Low Energy (BLE) sensor measurements. The simulation results show that the proposed TB-ICT prevents the COVID-19 from spreading by implementation of a highly accurate contact tracing model while improving the users' privacy and security.

cs.CR↗

arXiv2021

Joint Transmission Scheme and Coded Content Placement in Cluster-centric UAV-aided Cellular Networks

Recently, as a consequence of the COVID-19 pandemic, dependence on telecommunication for remote working and telemedicine has significantly increased. In cellular networks, incorporation of Unmanned Aerial Vehicles (UAVs) can result in enhanced connectivity for outdoor users due to the high probability of establishing Line of Sight (LoS) links. The UAV's limited battery life and its signal attenuation in indoor areas, however, make it inefficient to manage users' requests in indoor environments. Referred to as the Cluster centric and Coded UAV-aided Femtocaching (CCUF) framework, the network's coverage in both indoor and outdoor environments increases via a two-phase clustering for FAPs' formation and UAVs' deployment. First objective is to increase the content diversity. In this context, we propose a coded content placement in a cluster-centric cellular network, which is integrated with the Coordinated Multi-Point (CoMP) to mitigate the inter-cell interference in edge areas. Then, we compute, experimentally, the number of coded contents to be stored in each caching node to increase the cache-hit ratio, Signal-to-Interference-plus-Noise Ratio (SINR), and cache diversity and decrease the users' access delay and cache redundancy for different content popularity profiles. Capitalizing on clustering, our second objective is to assign the best caching node to indoor/outdoor users for managing their requests. In this regard, we define the movement speed of ground users as the decision metric of the transmission scheme for serving outdoor users' requests to avoid frequent handovers between FAPs and increase the battery life of UAVs. Simulation results illustrate that the proposed CCUF implementation increases the cache hit-ratio, SINR, and cache diversity and decrease the users' access delay, cache redundancy and UAVs' energy consumption.

cs.IT↗

arXiv2021

COVID19-HPSMP: COVID-19 Adopted Hybrid and Parallel Deep Information Fusion Framework for Stock Price Movement Prediction

The novel of coronavirus (COVID-19) has suddenly and abruptly changed the world as we knew at the start of the 3rd decade of the 21st century. Particularly, COVID-19 pandemic has negatively affected financial econometrics and stock markets across the globe. Artificial Intelligence (AI) and Machine Learning (ML)-based prediction models, especially Deep Neural Network (DNN) architectures, have the potential to act as a key enabling factor to reduce the adverse effects of the COVID-19 pandemic and future possible ones on financial markets. In this regard, first, a unique COVID-19 related PRIce MOvement prediction (COVID19 PRIMO) dataset is introduced in this paper, which incorporates effects of social media trends related to COVID-19 on stock market price movements. Afterwards, a novel hybrid and parallel DNN-based framework is proposed that integrates different and diversified learning architectures. Referred to as the COVID-19 adopted Hybrid and Parallel deep fusion framework for Stock price Movement Prediction (COVID19-HPSMP), innovative fusion strategies are used to combine scattered social media news related to COVID-19 with historical mark data. The proposed COVID19-HPSMP consists of two parallel paths (hence hybrid), one based on Convolutional Neural Network (CNN) with Local/Global Attention modules, and one integrated CNN and Bi-directional Long Short term Memory (BLSTM) path. The two parallel paths are followed by a multilayer fusion layer acting as a fusion centre that combines localized features. Performance evaluations are performed based on the introduced COVID19 PRIMO dataset illustrating superior performance of the proposed framework.

q-fin.ST↗