arXiv subjects

Abdullah Bin Shams

Publications and source records attributed to Abdullah Bin Shams.

16 recordsLinked to original sources

arXiv2026

Binary Contact Sensing for Sitting Posture Recognition Without Pressure Sensors

Prolonged sitting with poor posture results in musculoskeletal injury. Early intervention and prevention methods to monitor posture rely on cameras, wearable devices, and dense pressure arrays. Although effective, these approaches introduce privacy concerns, calibration needs, higher cost, etc. In this paper, we explore the spatial pattern of body contact as a binary posture feature vector for a distinct contact-based sitting posture recognition system without the need for analog signal conditioning and calibration. Our sensing principle uses 10 mechanical contact switches arranged in a 5 x 2 array on the backrest. Each switch encodes local body contact into 10-bit binary posture signatures for four postures: normal sitting, leaning back, leaning left, and leaning right. Decision tree and logistic regression classifiers achieved highest accuracy of 96%. Low correlation amongst the switches indicates that every switch captures complimentary information for successful posture classification. SHAP analysis identified the central contacts as the most informative and significant region for posture discrimination. Our results show that binary contact patterns can capture sufficient spatial information for reliable posture recognition. This sensing strategy offers a simple & low-cost alternative to pressure-based systems to monitor posture without the need for mapping the biomechanical pressure distribution.

eess.SP↗

arXiv2026

Single-Cycle Multidirectional EOG Classification Faster than Human Reaction Time for Wearable Human-Computer Interactions

Electrooculogram (EOG) is a non-invasive bio-signal generated by the potential difference between the retina and cornea during eye movement, and is widely utilized in Human-Computer Interaction (HCI) systems. Expanding the range of detectable eye movements enhances system capability. However, increasing the number of classes typically degrades classification performance. While AI-based approaches can mitigate this limitation, their complexity increases significantly when operating on single-cycle EOG signals. Although single-cycle signals offer advantages such as low latency, reduced power consumption, and improved responsiveness, they are inherently limited by reduced informational content and higher susceptibility to noise. Ensuring low latency remains critical for real-time HCI applications, where system response must remain below human reaction thresholds. In this experimental study, using explainable AI, we address these challenges by developing 1-dimensional (1D) and cascaded ANN and CNN architectures capable of highly accurate classification across ten EOG classes (Stare, Blink, Up, Down, Right, Left, Up-left, Up-right, Down-left, and Down-right) using single-cycle signals, while simultaneously achieving latency substantially lower than human reaction time. The study achieved an accuracy of around 99% for all the models with a latency of 38.6 ms for the 1D ANN, and 82.85 ms for the cascaded CNN. These findings confirm that cascaded neural network architectures, can effectively balance high classification accuracy and low latency for single-cycle, multi-class EOG-based HCI systems under limited data availability.

eess.SP↗

arXiv2023

A Prospective Approach for Human-to-Human Interaction Recognition from Wi-Fi Channel Data using Attention Bidirectional Gated Recurrent Neural Network with GUI Application Implementation

Human Activity Recognition (HAR) research has gained significant momentum due to recent technological advancements, artificial intelligence algorithms, the need for smart cities, and socioeconomic transformation. However, existing computer vision and sensor-based HAR solutions have limitations such as privacy issues, memory and power consumption, and discomfort in wearing sensors for which researchers are observing a paradigm shift in HAR research. In response, WiFi-based HAR is gaining popularity due to the availability of more coarse-grained Channel State Information. However, existing WiFi-based HAR approaches are limited to classifying independent and non-concurrent human activities performed within equal time duration. Recent research commonly utilizes a Single Input Multiple Output communication link with a WiFi signal of 5 GHz channel frequency, using two WiFi routers or two Intel 5300 NICs as transmitter-receiver. Our study, on the other hand, utilizes a Multiple Input Multiple Output radio link between a WiFi router and an Intel 5300 NIC, with the time-series Wi-Fi channel state information based on 2.4 GHz channel frequency for mutual human-to-human concurrent interaction recognition. The proposed Self-Attention guided Bidirectional Gated Recurrent Neural Network (Attention-BiGRU) deep learning model can classify 13 mutual interactions with a maximum benchmark accuracy of 94% for a single subject-pair. This has been expanded for ten subject pairs, which secured a benchmark accuracy of 88% with improved classification around the interaction-transition region. An executable graphical user interface (GUI) software has also been developed in this study using the PyQt5 python module to classify, save, and display the overall mutual concurrent human interactions performed within a given time duration. ...

cs.LG↗

arXiv2023

Development of a Risk-Free COVID-19 Screening Algorithm from Routine Blood Tests Using Ensemble Machine Learning

The Reverse Transcription Polymerase Chain Reaction (RTPCR)} test is the silver bullet diagnostic test to discern COVID infection. Rapid antigen detection is a screening test to identify COVID positive patients in little as 15 minutes, but has a lower sensitivity than the PCR tests. Besides having multiple standardized test kits, many people are getting infected and either recovering or dying even before the test due to the shortage and cost of kits, lack of indispensable specialists and labs, time-consuming result compared to bulk population especially in developing and underdeveloped countries. Intrigued by the parametric deviations in immunological and hematological profile of a COVID patient, this research work leveraged the concept of COVID-19 detection by proposing a risk-free and highly accurate Stacked Ensemble Machine Learning model to identify a COVID patient from communally available-widespread-cheap routine blood tests which gives a promising accuracy, precision, recall and F1-score of 100%. Analysis from R-curve also shows the preciseness of the risk-free model to be implemented. The proposed method has the potential for large scale ubiquitous low-cost screening application. This can add an extra layer of protection in keeping the number of infected cases to a minimum and control the pandemic by identifying asymptomatic or pre-symptomatic people early.

cs.LG↗

arXiv2022

Telehealthcare and Telepathology in Pandemic: A Noninvasive, Low-Cost Micro-Invasive and Multimodal Real-Time Online Application for Early Diagnosis of COVID-19 Infection

To contain the spread of the virus and stop the overcrowding of hospitalized patients, the coronavirus pandemic crippled healthcare facilities, mandating lockdowns and promoting remote work. As a result, telehealth has become increasingly popular for offering low-risk care to patients. However, the difficulty of preventing the next potential waves of infection has increased by constant virus mutation into new forms and a general lack of test kits, particularly in developing nations. In this research, a unique cloud-based application for the early identification of individuals who may have COVID-19 infection is proposed. The application provides five modes of diagnosis from possible symptoms (f1), cough sound (f2), specific blood biomarkers (f3), Raman spectral data of blood specimens (f4), and ECG signal paper-based image (f5). When a user selects an option and enters the information, the data is sent to the cloud server. The deployed machine learning (ML) and deep learning (DL) models classify the data in real time and inform the user of the likelihood of COVID-19 infection. Our deployed models can classify with an accuracy of 100%, 99.80%, 99.55%, 95.65%, and 77.59% from f3, f4, f5, f2, and f1 respectively. Moreover, the sensitivity for f2, f3, and f4 is 100%, which indicates the correct identification of COVID positive patients. This is significant in limiting the spread of the virus. Additionally, another ML model, as seen to offer 92% accuracy serves to identify patients who, out of a large group of patients admitted to the hospital cohort, need immediate critical care support by estimating the mortality risk of patients from blood parameters. The instantaneous multimodal nature of our technique offers multiplex and accurate diagnostic methods, highlighting the effectiveness of telehealth as a simple, widely available, and low-cost diagnostic solution, even for future pandemics.

cs.LG↗

arXiv2022

ABO3 Perovskites' Formability Prediction and Crystal Structure Classification using Machine Learning

Renewable energy sources are of great interest to combat global warming, yet promising sources like photovoltaic (PV) cells are not efficient and cheap enough to act as an alternative to traditional energy sources. Perovskite has high potential as a PV material but engineering the right material for a specific application is often a lengthy process. In this paper, ABO3 type perovskites' formability is predicted and its crystal structure is classified using machine learning with high accuracy, which provides a fast screening process. Although the study was done with solar-cell application in mind, the prediction framework is generic enough to be used for other purposes. Formability of perovskite is predicted and its crystal structure is classified with an accuracy of 98.57% and 90.53% respectively using Random Forest after 5-fold cross-validation. Our machine learning model may aid in the accelerated development of a desired perovskite structure by providing a quick mechanism to get insight into the material's properties in advance.

cond-mat.mtrl-sci↗

arXiv2021

Prediction Model for Mortality Analysis of Pregnant Women Affected With COVID-19

COVID-19 pandemic is an ongoing global pandemic which has caused unprecedented disruptions in the public health sector and global economy. The virus, SARS-CoV-2 is responsible for the rapid transmission of coronavirus disease. Due to its contagious nature, the virus can easily infect an unprotected and exposed individual from mild to severe symptoms. The study of the virus effects on pregnant mothers and neonatal is now a concerning issue globally among civilians and public health workers considering how the virus will affect the mother and the neonates health. This paper aims to develop a predictive model to estimate the possibility of death for a COVID-diagnosed mother based on documented symptoms: dyspnea, cough, rhinorrhea, arthralgia, and the diagnosis of pneumonia. The machine learning models that have been used in our study are support vector machine, decision tree, random forest, gradient boosting, and artificial neural network. The models have provided impressive results and can accurately predict the mortality of pregnant mothers with a given input.The precision rate for 3 models(ANN, Gradient Boost, Random Forest) is 100% The highest accuracy score(Gradient Boosting,ANN) is 95%,highest recall(Support Vector Machine) is 92.75% and highest f1 score(Gradient Boosting,ANN) is 94.66%. Due to the accuracy of the model, pregnant mother can expect immediate medical treatment based on their possibility of death due to the virus. The model can be utilized by health workers globally to list down emergency patients, which can ultimately reduce the death rate of COVID-19 diagnosed pregnant mothers.

cs.LG↗

arXiv2021

Impact of Receiver Antenna Polarization and Resource Scheduler on the Downlink Performance of High Velocity Users in 5G Millimeter Wave Small Cell Technology

With the occupancy of the existing frequency spectrum the demands of the skyrocketing data traffic paved the path for 5G millimeter Wave (mmWave) technology. The wide frequency spectrum and high directivity can elevate the mean data rate. This performance gain comes at the cost of a higher pathloss which limits the use of mmWave technology to small cells. Also at such high frequencies the multipath components and blockages appear as persistent barriers leading to alteration of antenna polarization, affecting resource scheduler performance and throughput degradation. The impact of these barriers for high velocity user equipments (UEs) in mmWave network is still left to be studied. Using closed loop spatial multiplexing transmission scheme this study analyses the effect of receiver antenna polarization and types of resource scheduler used in base station on the downlink performance of mobile users (0-120kmph) in the mmWave small cell network. Thorough investigation has been conducted to infer which antenna combination should be advantageous under different scheduling algorithms for high mobility UEs. Our results indicate that the scheduler performance is complimented by the receiver antenna polarization, and by appropriate selection a better downlink performance can be sustained. Also reception under linear polarization performs better over circular polarization for high velocity UEs.

eess.SP↗

arXiv2021

Survival Prediction of Heart Failure Patients using Stacked Ensemble Machine Learning Algorithm

Cardiovascular disease, especially heart failure is one of the major health hazard issues of our time and is a leading cause of death worldwide. Advancement in data mining techniques using machine learning (ML) models is paving promising prediction approaches. Data mining is the process of converting massive volumes of raw data created by the healthcare institutions into meaningful information that can aid in making predictions and crucial decisions. Collecting various follow-up data from patients who have had heart failures, analyzing those data, and utilizing several ML models to predict the survival possibility of cardiovascular patients is the key aim of this study. Due to the imbalance of the classes in the dataset, Synthetic Minority Oversampling Technique (SMOTE) has been implemented. Two unsupervised models (K-Means and Fuzzy C-Means clustering) and three supervised classifiers (Random Forest, XGBoost and Decision Tree) have been used in our study. After thorough investigation, our results demonstrate a superior performance of the supervised ML algorithms over unsupervised models. Moreover, we designed and propose a supervised stacked ensemble learning model that can achieve an accuracy, precision, recall and F1 score of 99.98%. Our study shows that only certain attributes collected from the patients are imperative to successfully predict the surviving possibility post heart failure, using supervised ML algorithms.

cs.LG↗

arXiv2021

Identification of the Resting Position Based on EGG, ECG, Respiration Rate and SpO2 Using Stacked Ensemble Learning

Rest is essential for a high-level physiological and psychological performance. It is also necessary for the muscles to repair, rebuild, and strengthen. There is a significant correlation between the quality of rest and the resting posture. Therefore, identification of the resting position is of paramount importance to maintain a healthy life. Resting postures can be classified into four basic categories: Lying on the back (supine), facing of the left / right sides and free-fall position. The later position is already considered to be an unhealthy posture by researchers equivocally and hence can be eliminated. In this paper, we analyzed the other three states of resting position based on the data collected from the physiological parameters: Electrogastrogram (EGG), Electrocardiogram (ECG), Respiration Rate, Heart Rate, and Oxygen Saturation (SpO2). Based on these parameters, the resting position is classified using a hybrid stacked ensemble machine learning model designed using the Decision tree, Random Forest, and Xgboost algorithms. Our study demonstrates a 100% accurate prediction of the resting position using the hybrid model. The proposed method of identifying the resting position based on physiological parameters has the potential to be integrated into wearable devices. This is a low cost, highly accurate and autonomous technique to monitor the body posture while maintaining the user privacy by eliminating the use of RGB camera conventionally used to conduct the polysomnography (sleep Monitoring) or resting position studies.

cs.LG↗

arXiv2021

Downlink Performance Enhancement of High Velocity Users in 5G Networks by Configuring Antenna System

A limitation of bandwidth in the wireless network and the exponential rise in the high data rate requirement prompted the development of Massive Multiple-Input-Multiple-Output (MIMO) technique in 5G. Using this method the ever rising data rate can be met with the increment of the number of antennas. This comes at the price of energy consumption of higher amount, complex network setups and maintenance. Moreover a high-velocity user experiences unpredictable fluctuations in the channel condition that deteriorates the downlink performance. Therefore a proper number of antenna selection is of paramount importance. This issue has been addressed using different categories of algorithms but only for static users. In this study we proffer to implement antenna diversity in closed loop spatial multiplexing MIMO transmission scheme by operating more number of reception antennas than the number of transmission antennas for ameliorating the downlink performance of high-velocity users in case of single user MIMO technology. In general our results can be interpreted for large scale antenna systems like Massive MIMO even though a 4x4 MIMO system has been executed to carry out this study here. Additionally it shows great prospects for solving practical life problems like low data rate and call drops during handover to be experienced by cellular users traveling by high-speed transportation systems like Dhaka Metro Rail. The cell edge users are anticipated to get benefits from this method in case of SU-MIMO technology. The proposed method is expected to be easily implemented in the existing network structures with nominal difficulties.

eess.SP↗

arXiv2021

Configuring Antenna System to Enhance the Downlink Performance of High Velocity Users in 5G MU-MIMO Networks

An exponential increase in the data rate demand prompted several technical innovations. Multi User Multiple Input Multiple Output (MU-MIMO) is one of the most promising schemes. This has been evolved into Massive MIMO technology in 5G to further stretch the network throughput. Massive MIMO tackles the rising data rate with the increase in the number of antenna. This comes at the price of a higher energy consumption. Moreover the high velocity users in MU-MIMO scheme experiences a frequent unpredictable change in the channel condition that degrade its downlink performance. Therefore a proper number of antenna selection is of paramount importance. This issue has been addressed using machine learning techniques and Channel State Information (CSI) but only for static users. In this study we propose to introduce antenna diversity in spatial multiplexing MU-MIMO transmission scheme by operating more number of reception antenna compare to the number of transmission antenna. The diversity improves the downlink performance of high velocity users. In general our results can be interpreted for large scale antenna systems like Massive MIMO. The proposed method can be easily implemented in the existing network architectures with minimal complexity. Also it has the potential for solving real-life problems like call drops and low data rate to be experienced by cellular users traveling through high-speed transportation systems like Dhaka MRT project

eess.SP↗

arXiv2020

Trust Concerns in Health Apps collecting Personally Identifiable Information during COVID-19-like Zoonosis

Coronavirus disease 2019, or COVID-19 in short, is a zoonosis, i.e., a disease that spreads from animals to humans. Due to its highly epizootic nature, it has compelled the public health experts to deploy smartphone applications to trace its rapid transmission pattern along with the infected persons as well by utilizing the persons' personally identifiable information. However, these information may summon several undesirable provocations towards the technical experts in terms of privacy and cyber security, particularly the trust concerns. If not resolved by now, the circumstances will affect the mass level population through inadequate usage of the health applications in the smartphones and thus liberate the forgery of a catastrophe for another COVID-19-like zoonosis to come. Therefore, an extensive study was required to address this severe issue. This paper has fulfilled the study mentioned above needed by not only discussing the recently designed and developed health applications all over the regions around the world but also investigating their usefulness and limitations. The trust defiance is identified as well as scrutinized from the viewpoint of an end-user. Several recommendations are suggested in the later part of this paper to leverage awareness among the ordinary individuals.

cs.CR↗

arXiv2020

Overview of digital health surveillance system during COVID-19 pandemic: public health issues and misapprehensions

Without proper medication and vaccination for the COVID-19, many governments are using automated digital healthcare surveillance system to prevent and control the spread. There is not enough literature explaining the concerns and privacy issues; hence, we have briefly explained the topics in this paper. We focused on digital healthcare surveillance system's privacy concerns and different segments. Further research studies should be conducted in different sectors. This paper provides an overview based on the published articles, which are not focusing on the privacy issues that much. Artificial intelligence and 5G networks combine the advanced digital healthcare surveillance system; whereas Bluetooth-based contact tracing systems have fewer privacy concerns. More studies are required to find the appropriate digital healthcare surveillance system, which would be ideal for monitoring, controlling, and predicting the COVID-19 trajectory.

cs.CY↗

arXiv2020

Digital Surveillance Systems for Tracing COVID-19: Privacy and Security Challenges with Recommendations

Coronavirus disease 2019, i.e. COVID-19 has imposed the public health measure of keeping social distancing for preventing mass transmission of COVID-19. For monitoring the social distancing and keeping the trace of transmission, we are obligated to develop various types of digital surveillance systems, which include contact tracing systems and drone-based monitoring systems. Due to the inconvenience of manual labor, traditional contact tracing systems are gradually replaced by the efficient automated contact tracing applications that are developed for smartphones. However, the commencement of automated contact tracing applications introduces the inevitable privacy and security challenges. Nevertheless, unawareness and/or lack of smartphone usage among mass people lead to drone-based monitoring systems. These systems also invite unwelcomed privacy and security challenges. This paper discusses the recently designed and developed digital surveillance system applications with their protocols deployed in several countries around the world. Their privacy and security challenges are discussed as well as analyzed from the viewpoint of privacy acts. Several recommendations are suggested separately for automated contact tracing systems and drone-based monitoring systems, which could further be explored and implemented afterwards to prevent any possible privacy violation and protect an unsuspecting person from any potential cyber attack.

cs.CR↗

arXiv2018

PV-Powered CoMP-Based Green Cellular Networks with a Standby Grid Supply

This paper proposes a novel framework for PV-powered cellular networks with a standby grid supply and an essential energy management technique for achieving envisaged green networks. The proposal considers an emerging cellular network architecture employing two types of coordinated multipoint (CoMP) transmission techniques for serving the subscribers. Under the proposed framework, each base station (BS) is powered by an individual PV solar energy module having an independent storage device. BSs are also connected to the conventional grid supply for meeting additional energy demand. We also propose a dynamic inter-BS solar energy sharing policy through a transmission line for further greening the proposed network by minimizing the consumption from the grid supply. An extensive simulation-based study in the downlink of a Long-Term Evolution (LTE) cellular system is carried out for evaluating the energy efficiency performance of the proposed framework. System performance is also investigated for identifying the impact of various system parameters including storage factor, storage capacity, solar generation capacity, transmission line loss, and different CoMP techniques.

eess.SP↗