Nelly Elsayed

Nelly Elsayed, Zag ElSayed, Navid Asadizanjani et al.

Understanding human behavior and monitoring mental health are essential to maintaining the community and society's safety. As there has been an increase in mental health problems during the COVID-19 pandemic due to uncontrolled mental health, early detection of mental issues is crucial. Nowadays, the usage of Intelligent Virtual Personal Assistants (IVA) has increased worldwide. Individuals use their voices to control these devices to fulfill requests and acquire different services. This paper proposes a novel deep learning model based on the gated recurrent neural network and convolution neural network to understand human emotion from speech to improve their IVA services and monitor their mental health.

Victor Adewopo, Nelly Elsayed, Zag ElSayed et al.

Action detection and public traffic safety are crucial aspects of a safe community and a better society. Monitoring traffic flows in a smart city using different surveillance cameras can play a significant role in recognizing accidents and alerting first responders. The utilization of action recognition (AR) in computer vision tasks has contributed towards high-precision applications in video surveillance, medical imaging, and digital signal processing. This paper presents an intensive review focusing on action recognition in accident detection and autonomous transportation systems for a smart city. In this paper, we focused on AR systems that used diverse sources of traffic video capturing, such as static surveillance cameras on traffic intersections, highway monitoring cameras, drone cameras, and dash-cams. Through this review, we identified the primary techniques, taxonomies, and algorithms used in AR for autonomous transportation and accident detection. We also examined data sets utilized in the AR tasks, identifying the main sources of datasets and features of the datasets. This paper provides potential research direction to develop and integrate accident detection systems for autonomous cars and public traffic safety systems by alerting emergency personnel and law enforcement in the event of road accidents to minimize human error in accident reporting and provide a spontaneous response to victims

Victor Adewopo, Nelly Elsayed, Zag Elsayed et al.

Accident detection and traffic analysis is a critical component of smart city and autonomous transportation systems that can reduce accident frequency, severity and improve overall traffic management. This paper presents a comprehensive analysis of traffic accidents in different regions across the United States using data from the National Highway Traffic Safety Administration (NHTSA) Crash Report Sampling System (CRSS). To address the challenges of accident detection and traffic analysis, this paper proposes a framework that uses traffic surveillance cameras and action recognition systems to detect and respond to traffic accidents spontaneously. Integrating the proposed framework with emergency services will harness the power of traffic cameras and machine learning algorithms to create an efficient solution for responding to traffic accidents and reducing human errors. Advanced intelligence technologies, such as the proposed accident detection systems in smart cities, will improve traffic management and traffic accident severity. Overall, this study provides valuable insights into traffic accidents in the US and presents a practical solution to enhance the safety and efficiency of transportation systems.

Saleh Abunajm, Nelly Elsayed, Zag ElSayed et al.

Lung cancer is the leading cause of death among different types of cancers. Every year, the lives lost due to lung cancer exceed those lost to pancreatic, breast, and prostate cancer combined. The survival rate for lung cancer patients is very low compared to other cancer patients due to late diagnostics. Thus, early lung cancer diagnostics is crucial for patients to receive early treatments, increasing the survival rate or even becoming cancer-free. This paper proposed a deep-learning model for early lung cancer prediction and diagnosis from Computed Tomography (CT) scans. The proposed mode achieves high accuracy. In addition, it can be a beneficial tool to support radiologists' decisions in predicting and detecting lung cancer and its stage.

Victor Adewopo, Nelly Elsayed

The dynamic and unpredictable nature of road traffic necessitates effective accident detection methods for enhancing safety and streamlining traffic management in smart cities. This paper offers a comprehensive exploration study of prevailing accident detection techniques, shedding light on the nuances of other state-of-the-art methodologies while providing a detailed overview of distinct traffic accident types like rear-end collisions, T-bone collisions, and frontal impact accidents. Our novel approach introduces the I3D-CONVLSTM2D model architecture, a lightweight solution tailored explicitly for accident detection in smart city traffic surveillance systems by integrating RGB frames with optical flow information. Our experimental study's empirical analysis underscores our approach's efficacy, with the I3D-CONVLSTM2D RGB + Optical-Flow (Trainable) model outperforming its counterparts, achieving an impressive 87\% Mean Average Precision (MAP). Our findings further elaborate on the challenges posed by data imbalances, particularly when working with a limited number of datasets, road structures, and traffic scenarios. Ultimately, our research illuminates the path towards a sophisticated vision-based accident detection system primed for real-time integration into edge IoT devices within smart urban infrastructures.

Victor Adewopo, Nelly Elsayed, Kelly Anderson

Humans are able to intuitively deduce actions that took place between two states in observations via deductive reasoning. This is because the brain operates on a bidirectional communication model, which has radically improved the accuracy of recognition and prediction based on features connected to previous experiences. During the past decade, deep learning models for action recognition have significantly improved. However, deep neural networks struggle with these tasks on a smaller dataset for specific Action Recognition (AR) tasks. As with most action recognition tasks, the ambiguity of accurately describing activities in spatial-temporal data is a drawback that can be overcome by curating suitable datasets, including careful annotations and preprocessing of video data for analyzing various recognition tasks. In this study, we present a novel lightweight framework combining transfer learning techniques with a Conv2D LSTM layer to extract features from the pre-trained I3D model on the Kinetics dataset for a new AR task (Smart Baby Care) that requires a smaller dataset and less computational resources. Furthermore, we developed a benchmark dataset and an automated model that uses LSTM convolution with I3D (ConvLSTM-I3D) for recognizing and predicting baby activities in a smart baby room. Finally, we implemented video augmentation to improve model performance on the smart baby care task. Compared to other benchmark models, our experimental framework achieved better performance with less computational resources.

Nelly Elsayed, Zag ElSayed, Anthony S. Maida

Long short-term memory (LSTM) is one of the robust recurrent neural network architectures for learning sequential data. However, it requires considerable computational power to learn and implement both software and hardware aspects. This paper proposed a novel LiteLSTM architecture based on reducing the LSTM computation components via the weights sharing concept to reduce the overall architecture computation cost and maintain the architecture performance. The proposed LiteLSTM can be significant for processing large data where time-consuming is crucial while hardware resources are limited, such as the security of IoT devices and medical data processing. The proposed model was evaluated and tested empirically on three different datasets from the computer vision, cybersecurity, speech emotion recognition domains. The proposed LiteLSTM has comparable accuracy to the other state-of-the-art recurrent architecture while using a smaller computation budget.

Shrish Pellakur, Nelly Elsayed, Zag ElSayed et al.

Alzheimer's disease is a degenerative brain disease. Being the primary cause of Dementia in adults and progressively destroys brain memory. Though Alzheimer's disease does not have a cure currently, diagnosing it at an earlier stage will help reduce the severity of the disease. Thus, early diagnosis of Alzheimer's could help to reduce or stop the disease from progressing. In this paper, we proposed a deep convolutional neural network-based model for learning model using to determine the stage of Dementia in adults based on the Magnetic Resonance Imaging (MRI) images to detect the early onset of Alzheimer's.

Gargi Desai, Nelly Elsayed, Zag Elsayed et al.

The world is still overwhelmed by the spread of the COVID-19 virus. With over 250 Million infected cases as of November 2021 and affecting 219 countries and territories, the world remains in the pandemic period. Detecting COVID-19 using the deep learning method on CT scan images can play a vital role in assisting medical professionals and decision authorities in controlling the spread of the disease and providing essential support for patients. The convolution neural network is widely used in the field of large-scale image recognition. The current method of RT-PCR to diagnose COVID-19 is time-consuming and universally limited. This research aims to propose a deep learning-based approach to classify COVID-19 pneumonia patients, bacterial pneumonia, viral pneumonia, and healthy (normal cases). This paper used deep transfer learning to classify the data via Inception-ResNet-V2 neural network architecture. The proposed model has been intentionally simplified to reduce the implementation cost so that it can be easily implemented and used in different geographical areas, especially rural and developing regions.

Zag ElSayed, Murat Ozer, Nelly Elsayed et al.

Brain Computer Interface (BCI) has great potential for solving many brain signal analysis limitations, mental disorder resolutions, and restoring missing limb functionality via neural-controlled implants. However, there is no single available, and safe implant for daily life usage exists yet. Most of the proposed implants have several implementation issues, such as infection hazards and heat dissipation, which limits their usability and makes it more challenging to pass regulations and quality control production. The wireless implant does not require a chronic wound in the skull. However, the current complex clustering neuron identification algorithms inside the implant chip consume a lot of power and bandwidth, causing higher heat dissipation issues and draining the implant's battery. The spike sorting is the core unit of an invasive BCI chip, which plays a significant role in power consumption, accuracy, and area. Therefore, in this study, we propose a low-power adaptive simplified VLSI architecture, "Zydeco-Style," for BCI spike sorting that is computationally less complex with higher accuracy that performs up to 93.5% in the worst-case scenario. The architecture uses a low-power Bluetooth Wireless communication module with external IoT medical ICU devices. The proposed architecture was implemented and simulated in Verilog. In addition, we are proposing an implant conceptual design.

Nelly Elsayed

AI-driven speech-to-text (STT) documentation systems are increasingly adopted in clinical settings to reduce documentation burden and improve workflow efficiency. However, adoption has outpaced systematic evaluation of socio-technical risks related to transparency, reliability, patient autonomy, and organizational accountability. This study develops a socio-technical framework for identifying and governing risks associated with clinical STT systems. We synthesize interdisciplinary evidence from automatic speech recognition research, clinical workflow and human factors studies, ethical guidance on consent and autonomy, and regulatory and organizational sources. Using a structured narrative synthesis, literature was iteratively reviewed and thematically analyzed to identify recurring socio-technical risk mechanisms and inform a layered conceptual framework. Findings show that clinical STT systems operate within tightly coupled socio-technical environments where model performance, audio conditions, clinician oversight, patient understanding, workflow design, and institutional governance are interdependent. Key risks include inconsistent consent practices, performance disparities for accented speech and speech disorders, accuracy degradation in real clinical settings, automation complacency, and unclear accountability across vendors and healthcare organizations. These risks inform a six-layer governance model spanning technical, human/workflow, ethical, organizational, regulatory, and sociocultural dimensions. We propose a governance framework and implementation roadmap to support responsible deployment of clinical STT systems, emphasizing transparency, patient autonomy, documentation integrity, and accountable oversight.

Rob Sullivan, Nelly Elsayed

The performance of Large language models (LLMs) across a broad range of domains has been impressive but have been critiqued as not being able to reason about their process and conclusions derived. This is to explain the conclusions draw, and also for determining a plan or strategy for their approach. This paper explores the current research in investigating symbolic reasoning and LLMs, and whether an LLM can inherently provide some form of reasoning or whether supporting components are necessary, and, if there is evidence for a reasoning capability, is this evident in a specific domain or is this a general capability? In addition, this paper aims to identify the current research gaps and future trends of LLM explainability, presenting a review of the literature, identifying current research into this topic and suggests areas for future work.

Victor Adewopo, Nelly Elsayed, Zag Elsayed et al.

In the dynamic urban landscape, where the interplay of vehicles and pedestrians defines the rhythm of life, integrating advanced technology for safety and efficiency is increasingly crucial. This study delves into the application of cutting-edge technological methods in smart cities, focusing on enhancing public safety through improved traffic accident detection. Action recognition plays a pivotal role in interpreting visual data and tracking object motion such as human pose estimation in video sequences. The challenges of action recognition include variability in rapid actions, limited dataset, and environmental factors such as (Weather, Illumination, and Occlusions). In this paper, we present a novel comprehensive dataset for traffic accident detection. This datasets is specifically designed to bolster computer vision and action recognition systems in predicting and detecting road traffic accidents. We integrated datasets from wide variety of data sources, road networks, weather conditions, and regions across the globe. This approach is underpinned by empirical studies, aiming to contribute to the discourse on how technology can enhance the quality of life in densely populated areas. This research aims to bridge existing research gaps by introducing benchmark datasets that leverage state-of-the-art algorithms tailored for traffic accident detection in smart cities. These dataset is expected to advance academic research and also enhance real-time accident detection applications, contributing significantly to the evolution of smart urban environments. Our study marks a pivotal step towards safer, more efficient smart cities, harnessing the power of AI and machine learning to transform urban living.

Nelly Elsayed, Constantinos L. Zekios, Navid Asadizanjani et al.

Ensemble modeling has been widely used to solve complex problems as it helps to improve overall performance and generalization. In this paper, we propose a novel TemporalAugmenter approach based on ensemble modeling for augmenting the temporal information capturing for long-term and short-term dependencies in data integration of two variations of recurrent neural networks in two learning streams to obtain the maximum possible temporal extraction. Thus, the proposed model augments the extraction of temporal dependencies. In addition, the proposed approach reduces the preprocessing and prior stages of feature extraction, which reduces the required energy to process the models built upon the proposed TemporalAugmenter approach, contributing towards green AI. Moreover, the proposed model can be simply integrated into various domains including industrial, medical, and human-computer interaction applications. Our proposed approach empirically evaluated the speech emotion recognition, electrocardiogram signal, and signal quality examination tasks as three different signals with varying complexity and different temporal dependency features.

Nelly Elsayed, Zag ElSayed, Murat Ozer

Suicide is recognized as one of the most serious concerns in the modern society. Suicide causes tragedy that affects countries, communities, and families. There are many factors that lead to suicidal ideations. Early detection of suicidal ideations can help to prevent suicide occurrence by providing the victim with the required professional support, especially when the victim does not recognize the danger of having suicidal ideations. As technology usage has increased, people share and express their ideations digitally via social media, chatbots, and other digital platforms. In this paper, we proposed a novel, simple deep learning-based model to detect suicidal ideations in digital content, mainly focusing on chatbots as the primary data source. In addition, we provide a framework that employs the proposed suicide detection integration with a chatbot-based support system.

Zag ElSayed, Murat Ozer, Nelly Elsayed et al.

A seizure tracking system is crucial for monitoring and evaluating epilepsy treatments. Caretaker seizure diaries are used in epilepsy care today, but clinical seizure monitoring may miss seizures. Monitoring devices that can be worn may be better tolerated and more suitable for long-term ambulatory use. Many techniques and methods are proposed for seizure detection; However, simplicity and affordability are key concepts for daily use while preserving the accuracy of the detection. In this study, we propose a versal, affordable noninvasive based on a simple real-time k-Nearest-Neighbors (kNN) machine learning that can be customized and adapted to individual users in less than four seconds of training time; the system was verified and validated using 500 subjects, with seizure detection data sampled at 178 Hz, the operated with a mean accuracy of (94.5%).

Nelly Elsayed, Zag ElSayed, Murat Ozer

Diabetes is one of the chronic diseases that has been discovered for decades. However, several cases are diagnosed in their late stages. Every one in eleven of the world's adult population has diabetes. Forty-six percent of people with diabetes have not been diagnosed. Diabetes can develop several other severe diseases that can lead to patient death. Developing and rural areas suffer the most due to the limited medical providers and financial situations. This paper proposed a novel approach based on an extreme learning machine for diabetes prediction based on a data questionnaire that can early alert the users to seek medical assistance and prevent late diagnoses and severe illness development.

Nelly Elsayed, Zag ElSayed, Anthony S. Maida

Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware aspects. This paper proposes a novel LiteLSTM architecture based on reducing the computation components of the LSTM using the weights sharing concept to reduce the overall architecture cost and maintain the architecture performance. The proposed LiteLSTM can be significant for learning big data where time-consumption is crucial such as the security of IoT devices and medical data. Moreover, it helps to reduce the CO2 footprint. The proposed model was evaluated and tested empirically on two different datasets from computer vision and cybersecurity domains.

Nelly Elsayed, Anthony S. Maida, Magdy Bayoumi

Hybrid LSTM-fully convolutional networks (LSTM-FCN) for time series classification have produced state-of-the-art classification results on univariate time series. We show that replacing the LSTM with a gated recurrent unit (GRU) to create a GRU-fully convolutional network hybrid model (GRU-FCN) can offer even better performance on many time series datasets. The proposed GRU-FCN model outperforms state-of-the-art classification performance in many univariate and multivariate time series datasets. In addition, since the GRU uses a simpler architecture than the LSTM, it has fewer training parameters, less training time, and a simpler hardware implementation, compared to the LSTM-based models.

Nelly Elsayed, Anthony S. Maida, Magdy Bayoumi

Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame(s) video prediction using a deep-learning-based predictive coding framework that uses convolutional, long short-term memory (convLSTM) modules. We introduce a novel reduced-gate convolutional LSTM(rgcLSTM) architecture that requires a significantly lower parameter budget than a comparable convLSTM. By using a single multi-function gate, our reduced-gate model achieves equal or better next-frame(s) prediction accuracy than the original convolutional LSTM while using a smaller parameter budget, thereby reducing training time and memory requirements. We tested our reduced gate modules within a predictive coding architecture on the moving MNIST and KITTI datasets. We found that our reduced-gate model has a significant reduction of approximately 40 percent of the total number of training parameters and a 25 percent reduction in elapsed training time in comparison with the standard convolutional LSTM model. The performance accuracy of the new model was also improved. This makes our model more attractive for hardware implementation, especially on small devices. We also explored a space of twenty different gated architectures to get insight into how our rgcLSTM fit into that space.