Hamza Javed - Academia.edu (original) (raw)
Papers by Hamza Javed
Journal of Ayub Medical College Abbottabad
Background: Interstitial Lung Disease (ILD) - an umbrella term encompassing about 100 different p... more Background: Interstitial Lung Disease (ILD) - an umbrella term encompassing about 100 different pathophysiological entities are usually defined as an irreversible, progressive fibrotic changes in the lung parenchyma that leads to difficult breathing and reduced gaseous exchange at the alveolar level. We aimed to quantify the validity of CXR for the diagnosis of ILD taking HRCT as gold standard in the population of Hazara division. Methods: This validation study was conducted during 11 June till 12 Dec 2019 in the radiology department of Ayub Teaching Hospital, Abbottabad on 60 adult patients aged 30–60 years who presented with progressive exertional dyspnoea. The patients were enrolled into the study via non-probability, consecutive sampling technique. All the data was recorded on a self-developed structured questionnaire. Data was analyzed using SPSS version 20. Results: The mean age of study participants was 47.18±6.90 years SD with a range of 36–60years. The mean of time duration...
Internet of Things
The exponential growth of Internet of Things (IoT) has given rise to a new wave of edge computing... more The exponential growth of Internet of Things (IoT) has given rise to a new wave of edge computing due to the need to process data on the edge, closer to where it is being produced and attempting to move away from a cloud-centric architecture. This provides its own opportunity to decrease latency and address data privacy concerns along with the ability to reduce public cloud costs. The serverless computing model provides a potential solution with its event-driven architecture to reduce the need for ever-running servers and convert the backend services to an as-used model. This model is an attractive prospect in edge computing environments with varying workloads and limited resources. Furthermore, its setup on the edge of the network promises reduced latency to the edge devices communicating with it and eliminates the need to manage the underlying infrastructure. In this book chapter, first, we introduce the novel concept of serverless edge computing, then, we analyze the performance of multiple serverless platforms, namely, OpenFaaS, AWS Greengrass, Apache OpenWhisk, when set up on the single-board computers (SBCs) on the edge and compare it with public cloud serverless offerings, namely, AWS Lambda and Azure Functions, to deduce the suitability of serverless architectures on the network edge. These serverless platforms are set up on a cluster of Raspberry Pis and we evaluate their performance by simulating different types of edge workloads. The evaluation results show that OpenFaaS achieves the lowest response time on the SBC edge computing infrastructure while serverless cloud offerings are the most reliable with the highest success rate.
Brazilian Archives of Biology and Technology
The study was conducted to investigate physiochemical, techno-functional, and sensory attributes ... more The study was conducted to investigate physiochemical, techno-functional, and sensory attributes of yogurt supplemented with basil seed gum. Two levels of gum as 0.5% and 1% was used to develop a product. The product was stored for 21 days at 4°C and assessed on each 3rd day for texture properties such as cohesiveness, adhesiveness and stringiness, pH, and sensory evaluation. Proximate analysis showed moisture content 10.76%, protein content 16.93%, fat content 6.93% fiber content 27.25%, ash HIGHLIGHTS • The term 'yoghurt' relates to the Turkish word 'Jughurt' and to yogurmark 'to knead' and yogum 'dense' or 'thick.' • The method of manufacture for different yogurt products is nevertheless quite like yoghurt production. The difference is in the use of specific cultures, incorporation of additives, curd treatment, and method of packaging. • Consumers may seek for low-fat dairy products, which may suffer from a lack of sensory quality • The incorporation of basil seed gum into yogurt is one of the conceivable ways to promote health benefits.
Pakistan biomedical journal, Mar 31, 2022
Pseudomonas aeruginosa are Gram-negative, nonfermentative bacteria that may be found in water, se... more Pseudomonas aeruginosa are Gram-negative, nonfermentative bacteria that may be found in water, sediment, and other humid habitats. P. aeruginosa is commonly linked to human illnesses, where it acts as a nosocomial microbial pathogen that uses a functional strategic way to infect nearly any tissue or organ, especially in susceptible people or the elderly [1]. The potential of P. aeruginosa to cause illness is enhanced by the wide variety of resistance mechanisms to the antibiotics, as well as the ability to thrive in a wide range of environmental circumstances and virulence determinants [2]. P. aeruginosa thrives in both normal and low-oxygen settings
2021 IEEE 32nd International Conference on Application-specific Systems, Architectures and Processors (ASAP)
This paper presents novel reconfigurable architectures for reducing the latency of recurrent neur... more This paper presents novel reconfigurable architectures for reducing the latency of recurrent neural networks (RNNs) that are used for detecting gravitational waves. Gravitational interferometers such as the LIGO detectors capture cosmic events such as black hole mergers which happen at unknown times and of varying durations, producing time-series data. We have developed a new architecture capable of accelerating RNN inference for analyzing time-series data from LIGO detectors. This architecture is based on optimizing the initiation intervals (II) in a multi-layer LSTM (Long Short-Term Memory) network, by identifying appropriate reuse factors for each layer. A customizable template for this architecture has been designed, which enables the generation of low-latency FPGA designs with efficient resource utilization using high-level synthesis tools. The proposed approach has been evaluated based on two LSTM models, targeting a ZYNQ 7045 FPGA and a U250 FPGA. Experimental results show that with balanced II, the number of DSPs can be reduced up to 42% while achieving the same IIs. When compared to other FPGA-based LSTM designs, our design can achieve about 4.92 to 12.4 times lower latency.
Healthcare Technology Letters, 2021
The rapid proliferation of wearable devices for medical applications has necessitated the need fo... more The rapid proliferation of wearable devices for medical applications has necessitated the need for automated algorithms to provide labelling of physiological time-series data to identify abnormal morphology. However, such algorithms are less reliable than goldstandard human expert labels (where the latter are typically difficult and expensive to obtain), due to their large inter-and intra-subject variabilities. Actions taken in response to these algorithms can therefore result in sub-optimal patient care. In a typical scenario where only unevenly sampled continuous or numeric estimates are provided, without access to the "ground truth", it is challenging to choose which algorithms to trust and which to ignore, or even how to merge the outputs from multiple algorithms to form a more precise final estimate for individual patients. In this work, the novel application of two previously proposed parametric fully-Bayesian graphical models is demonstrated for fusing labels from (i) independent and (ii) potentially correlated algorithms, validated on two publicly available datasets for the task of respiratory rate (RR) estimation. These unsupervised models aggregate RR labels and estimate jointly the assumed bias and precision of each algorithm. Fusing estimates in this way may then be used to infer the underlying ground truth for individual patients. It is shown that modelling the latent correlations between algorithms improves the RR estimates, when compared to commonly employed strategies in the literature. Finally, it is demonstrated that the adoption of a strongly Bayesian approach to inference using Gibbs sampling results in improved estimation over the current state-ofthe-art (e.g. hierarchical Gaussian processes) in physiological time-series modelling. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020
Cardiovascular diseases (CVDs) remain responsible for millions of deaths annually. Myocardial inf... more Cardiovascular diseases (CVDs) remain responsible for millions of deaths annually. Myocardial infarction (MI) is the most prevalent condition among CVDs. Although datadriven approaches have been applied to predict CVDs from ECG signals, comparatively little work has been done on the use of multiple-lead ECG traces and their efficient integration to diagnose CVDs. In this paper, we propose an end-to-end trainable and joint spectral-longitudinal model to predict heart attack using data-level fusion of multiple ECG leads. The spectral stage transforms the time-series waveforms to stacked spectrograms and encodes the frequency-time characteristics, whilst the longitudinal model helps to utilise the temporal dependency that exists in these waveforms using recurrent networks. We validate the proposed approach using a public MI dataset. Our results show that the proposed spectrallongitudinal model achieves the highest performance compared to the baseline methods.
We describe the new Quartus backend of hls4ml, designed to deploy Neural Networks on Intel FPGAs.... more We describe the new Quartus backend of hls4ml, designed to deploy Neural Networks on Intel FPGAs. We list the supported network components and layer architectures (dense, binary/ternary, and convolutional neural networks) and evaluate its performance on a benchmark problem previously considered to develop the Vivado backend of hls4ml. We also introduce the support for recurrent layers and introduce a new asynchronous calling model to increase performance for larger models. In addition to that, we also demonstrate the use of this new model to optimize large-sparse networks.
Gels, 2022
Ultrasound imaging is a widely used technique in every health care center and hospital. Ultrasoun... more Ultrasound imaging is a widely used technique in every health care center and hospital. Ultrasound gel is used as a coupling medium in all ultrasound procedures to replace air between the transducer and the patient’s skin, as ultrasound waves have trouble in traveling through air. This research was performed to formulate an inexpensive alternative to commercially available ultrasound gel as it is expensive and imported from other countries. Different formulations with different concentrations of carbopol 980 (CAR 980) and methylparaben were prepared with natural ingredients such as aloe vera gel and certain available chemicals that have no harmful effects on the skin. To justify the efficiency of the formulations; necessary physicochemical characteristics such as visual clarity, homogeneity, transparency, skin irritation, antibacterial activity, pH, stability, spreadability, conductivity, acoustic impedance, viscosity, and cost were evaluated. Moreover, a comparison study was also c...
JOURNAL OF WEED SCIENCE RESEARCH, 2021
Tyrosinase is a key enzyme in melanogenesis and its high activity leads to increasedpigmentations... more Tyrosinase is a key enzyme in melanogenesis and its high activity leads to increasedpigmentations causing skin disorder like freckles, melanosoma and black spot. Therefore to search for new tyrosinase inhibitors is desirable. In present study, methanolic (MeOH) extracts from leaves, fruit peel and pulp of Citrus bergamia (CB) and, leaves and fruitof Ficus carica (FC) were prepared which were further process for fractional ethyl alcohol (EA), n-hexane (n-Hx) and chloroform (CHCl3)extractions (total 20 extracts) aiming to test their anti-tyrosinase potential, in-vitro. Our results confirmed that all MeOH FC and CB extracts showed significant anti-oxidant activity with IC50 range of 461.9 ± 16.1µg/ml to 2324.4 ± 116.1 µg/ml. Moreover, CB and FC all 20 extracts have significant anti-tyrosinase activity with IC50 range of 13.9 ± 0.5 µg/ml to 320.5 ± 3.3 µg/ml. Interestingly, CB MeOH-EA peel and leaf extracts showed tyrosinase inhibition (IC50) 13.9 ± 0.5 µg/ml and 17.2 ± 0.8 µg/ml, resp...
Knowledge Management and Acquisition for Intelligent Systems, 2021
Visual inspection of electrocardiograms (ECGs) is a common clinical practice to diagnose heart di... more Visual inspection of electrocardiograms (ECGs) is a common clinical practice to diagnose heart diseases (HDs), which are still responsible for millions of deaths globally every year. In particular, myocardial infarction (MI) is the leading cause of mortality among HDs. ECGs reflect the electrical activity of the heart and provide a quicker process of diagnosis compared to laboratory blood tests. However, still it requires trained clinicians to interpret ECG waveforms, which poses a challenge in low-resourced healthcare systems, such as poor doctorto-patient ratios. Previous works in this space have shown the use of data-driven approaches to predict HDs from ECG signals but focused on domain-specific features that are less generalizable across patient and device variations. Moreover, limited work has been conducted on the use of longitudinal information and fusion of multiple ECG leads. In contrast, we propose an end-to-end trainable solution for MI diagnosis, which (1) uses 12 ECG leads; (2) fuses the leads at data-level by stacking their spectrograms; (3) employs transfer learning to encode features rather than learning representations from scratch; and (4) uses a recurrent neural network to encode temporal dependency in long duration ECGs. Our approach is validated using multiple datasets, including tens of thousands of subjects, and encouraging performance is achieved.
ArXiv, 2021
Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devic... more Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devices and systems are extremely valuable across a broad range of application domains. In scientific domains, real-time near-sensor processing can drastically improve experimental design and accelerate scientific discoveries. We have developed hls4ml, an open-source software-hardware co-design workflow to interpret and translate machine learning algorithms for implementation in FPGAs and ASICs specifically to support domain scientists. In this paper, we describe the essential features of the hls4ml workflow including network optimization techniques— such as pruning and quantization-aware training—which can be incorporated naturally into the device implementations. We expand on previous hls4ml work by extending capabilities and techniques towards low-power implementations and increased usability: new PythonAPIs, quantization-aware pruning, end-to-end FPGAworkflows, long pipeline kernels for l...
PLOS ONE, 2021
Background Delays in patient flow and a shortage of hospital beds are commonplace in hospitals du... more Background Delays in patient flow and a shortage of hospital beds are commonplace in hospitals during periods of increased infection incidence, such as seasonal influenza and the COVID-19 pandemic. The objective of this study was to develop and evaluate the efficacy of machine learning methods at identifying and ranking the real-time readiness of individual patients for discharge, with the goal of improving patient flow within hospitals during periods of crisis. Methods and performance Electronic Health Record data from Oxford University Hospitals was used to train independent models to classify and rank patients’ real-time readiness for discharge within 24 hours, for patient subsets according to the nature of their admission (planned or emergency) and the number of days elapsed since their admission. A strategy for the use of the models’ inference is proposed, by which the model makes predictions for all patients in hospital and ranks them in order of likelihood of discharge within...
Journal of Ayub Medical College, Abbottabad : JAMC, 2020
Background Anaplastic thyroid carcinoma is a high-grade tumour with poor prognosis. Most of the c... more Background Anaplastic thyroid carcinoma is a high-grade tumour with poor prognosis. Most of the cases are easily diagnosed on cytology and some of these are associated with increased neutrophils in cytology specimen as well as in the blood. The objective of the study is to determine the frequency of neutrophilia with fever in anaplastic thyroid carcinoma. Methods This descriptive cross-sectional study was performed in the Department of Pathology Ayub Teaching Hospital Abbottabad as well as in association with Advance lab Abbottabad. All the cases diagnosed as anaplastic thyroid carcinoma on cytology were included, histopathological examination was done only in 5 cases. The duration of study was from October 2016 to October 2019 were included in the study. Results Out of 150 cases of thyroid cytology 09 were diagnosed as anaplastic thyroid carcinoma. The mean age of patients was 65.7±6.96. Gender distribution was 5/9 (55.6%) males and 4/9 (44.4%) were females. Out of which 05 were co...
Journal of Ayub Medical College, Abbottabad : JAMC, 2021
BACKGROUND Evaluation of the educational environment is key to the delivery of high-quality medic... more BACKGROUND Evaluation of the educational environment is key to the delivery of high-quality medical education. Especially, when an institute is in the transition phase of curriculum. In curriculum transformation phase of Ayub Medical College Abbottabad, no such evaluation has been done. This study aimed to find the direction of Educational environment in the transition phase curriculum of Ayub Medical College Abbottabad and compare different domains of educational environment with gender, residency, pre-medical education's medium of instruction, and doctors among sibling or parents. Methods This descriptive cross-sectional survey was conducted among students of integrated and traditional curriculum of Ayub Medical College, Abbottabad from 1st December 2019 to 29th February 2020. By Non-probability convenience sampling technique, pre-validated Dundee Ready Educational Environment Measure questionnaire was used. Descriptive and inferential statistics were calculated in SPSS v22. R...
Artificial Intelligence in Medicine, 2021
Myocardial Infarction (MI) has the highest mortality of all cardiovascular diseases (CVDs). Detec... more Myocardial Infarction (MI) has the highest mortality of all cardiovascular diseases (CVDs). Detection of MI and information regarding its occurrence-time in particular, would enable timely interventions that may improve patient outcomes, thereby reducing the global rise in CVD deaths. Electrocardiogram (ECG) recordings are currently used to screen MI patients. However, manual inspection of ECGs is time-consuming and prone to subjective bias. Machine learning methods have been adopted for automated ECG diagnosis, but most approaches require extraction of ECG beats or consider leads independently of one another. We propose an end-to-end deep learning approach, DeepMI, to classify MI from normal cases as well as identifying the time-occurrence of MI (defined as acute, recent and old), using a collection of fusion strategies on 12 ECG leads at data-, feature-, and decision-level. In order to minimise computational overhead, we employ transfer learning using existing computer vision networks. Moreover, we use recurrent neural networks to encode the longitudinal information inherent in ECGs. We validated DeepMI on a dataset collected from 17,381 patients, in which over 323,000 samples were extracted per ECG lead. We were able to classify normal cases as well as acute, recent and old onset cases of MI, with AUROCs of 96.7%, 82.9%, 68.6% and 73.8%, respectively. We have demonstrated a multi-lead fusion approach to detect the presence and occurrence-time of MI. Our end-to-end framework provides flexibility for different levels of multi-lead ECG fusion and performs feature extraction via transfer learning.
JOURNAL OF WEED SCIENCE RESEARCH, 2021
-Tyrosinase is a key enzyme of melanogenesis which determines the mammalian skin, hair and eye co... more -Tyrosinase is a key enzyme of melanogenesis which determines the mammalian skin, hair and eye colour. Hyper-pigmentation leads to various skin disorders like melasma, sunspots, age spots and freckles. Moreover, abnormal skin pigmentation is a serious aesthetic concern which leads to psychosocial problems. Thus to achieve melanin inhibition, inhibition of tyrosinase might be an effective approach. To this end we prepared methanolic (MeOH) extracts from leaves and roots of Allium sativum (AS) and Mentha piperita (MP), which were further processed for 1:1 fractional distillation to prepare methanolic n-hexane (MeOH_n-Hx), methanolic ethyl acetate (MeOH_EA) and methanolic chloroform (MeOH_CHCl3) extracts, aiming to evaluate tyrosinase and anti-oxidant activities in-vitro. Our results confirmed that all MeOH-crude AS and MP extracts showed significant anti-oxidant activity with IC50 values ranging from 0.05 ± 0.2 mg/ml to 4.3 ± 2.3mg/ml. Moreover, AS and MP all 16 extracts have significant anti-tyrosinase activity with IC50 range from 0.014 ± 0mg/ml to 1.205 ± 0.07mg/ml. Interestingly, AS leaf MetOH_EA, AS leaf MetOH_CHCl3, AS root MetOH_EA and MP leaf MetOH_CHCl3 showed significant anti-tyrosinase activity even higher than positive control kojic acid. AS leaf MetOH_CHCl3 extract being the most potent among all tested extracts is proposed as potential candidate to treat tyrosinase rooted hyper-pigmentation in future.
Pure and Applied Biology, 2020
Bacterial infections and their increasing resistance to common antibiotics is posing serious thre... more Bacterial infections and their increasing resistance to common antibiotics is posing serious threat to global public health. To this end, finding new alternatives and evaluating their antibacterial efficacy is always desirable. Therefore, in the present study we used methanol (MeOH), n-hexane (n-Hex), ethyl acetate (ETAC) and chloroform (CHCl3) to prepared four different types of extracts from Moringa oleifera (M. oliefera) leaves aiming to inhibit five selected bacteria. Initially, agar well diffusion methods was used, and zones of inhibition were measured as an indicator of bacterial susceptibility. MeOH, n-Hex, ETAC and CHCl3 leaf extracts showed highest zone of inhibition against E. coli, B. cereus, S. pyogenes, S. aureus and S. enterica, respectively. Moreover, highest zones of inhibition were observed at lowest incubation (24hr) and lowest zones were observed at highest incubation period (72hr) for all tested concentrations. Later, macrodilution method was used to access the antibacterial susceptibility in liquid medium. Results confirmed the susceptibility of all test bacteria with different level of IC50 values ranging from 7.07 ± 0.44 to10.91 ± 0.10 mg/ml for MeOH extract, 1.66 ± 0.08 to 2.11 ± 0.11 mg/ml for n-Hex extract, 2.58 ± 0.13 to 3.84 ± 0.21 mg/ml for ETAC extract and 3.73 ± 0.75 to 8.36 ± 0.20 mg/ml for CHCl3 extract. Interestingly, none of the tested bacteria showed resistance against any of the tested extract in well diffusion or macrodilution method expressing the M. oliefera leaves extracts as potent candidates to kill bacteria in semisolid or in liquid medium to fulfill medical needs in future.
Healthcare Technology Letters, 2020
IEEE Journal of Biomedical and Health Informatics, 2020
In low and middle income countries, infectious diseases continue to have a significant impact, pa... more In low and middle income countries, infectious diseases continue to have a significant impact, particularly amongst the poorest in society. Tetanus and hand foot and mouth disease (HFMD) are two such diseases and, in both, death is associated with autonomic nervous system dysfunction (ANSD). Currently, photoplethysmogram or electrocardiogram monitoring is used to detect deterioration in these patients, however expensive clinical monitors are often required. In this study, we employ low-cost and mobile wearable devices to collect patient vital signs unobtrusively; and we develop machine learning algorithms for automatic and rapid triage of patients that provide efficient use of clinical resources. Existing methods are mainly dependent on the prior detection of clinical features with limited exploitation of multi-modal physiological data. Moreover, the latest developments in deep learning (e.g. cross-domain transfer learning) have not been sufficiently applied for infectious disease diagnosis. In this paper, we present a fusion of multi-modal physiological data to predict the severity of ANSD with a hierarchy of resourceaware decision making. First, an on-site triage process is performed using a simple classifier. Second, personalised longitudinal modelling is employed that takes the previous states of the patient into consideration. We have also employed a spectrogram representation of the physiological waveforms to exploit existing networks for cross-domain transfer learning, which avoids the laborious and data intensive process of training a network from scratch. Results show that the proposed framework has promising potential in supporting severity grading of infectious diseases in low-resources settings, such as in the developing world.
Journal of Ayub Medical College Abbottabad
Background: Interstitial Lung Disease (ILD) - an umbrella term encompassing about 100 different p... more Background: Interstitial Lung Disease (ILD) - an umbrella term encompassing about 100 different pathophysiological entities are usually defined as an irreversible, progressive fibrotic changes in the lung parenchyma that leads to difficult breathing and reduced gaseous exchange at the alveolar level. We aimed to quantify the validity of CXR for the diagnosis of ILD taking HRCT as gold standard in the population of Hazara division. Methods: This validation study was conducted during 11 June till 12 Dec 2019 in the radiology department of Ayub Teaching Hospital, Abbottabad on 60 adult patients aged 30–60 years who presented with progressive exertional dyspnoea. The patients were enrolled into the study via non-probability, consecutive sampling technique. All the data was recorded on a self-developed structured questionnaire. Data was analyzed using SPSS version 20. Results: The mean age of study participants was 47.18±6.90 years SD with a range of 36–60years. The mean of time duration...
Internet of Things
The exponential growth of Internet of Things (IoT) has given rise to a new wave of edge computing... more The exponential growth of Internet of Things (IoT) has given rise to a new wave of edge computing due to the need to process data on the edge, closer to where it is being produced and attempting to move away from a cloud-centric architecture. This provides its own opportunity to decrease latency and address data privacy concerns along with the ability to reduce public cloud costs. The serverless computing model provides a potential solution with its event-driven architecture to reduce the need for ever-running servers and convert the backend services to an as-used model. This model is an attractive prospect in edge computing environments with varying workloads and limited resources. Furthermore, its setup on the edge of the network promises reduced latency to the edge devices communicating with it and eliminates the need to manage the underlying infrastructure. In this book chapter, first, we introduce the novel concept of serverless edge computing, then, we analyze the performance of multiple serverless platforms, namely, OpenFaaS, AWS Greengrass, Apache OpenWhisk, when set up on the single-board computers (SBCs) on the edge and compare it with public cloud serverless offerings, namely, AWS Lambda and Azure Functions, to deduce the suitability of serverless architectures on the network edge. These serverless platforms are set up on a cluster of Raspberry Pis and we evaluate their performance by simulating different types of edge workloads. The evaluation results show that OpenFaaS achieves the lowest response time on the SBC edge computing infrastructure while serverless cloud offerings are the most reliable with the highest success rate.
Brazilian Archives of Biology and Technology
The study was conducted to investigate physiochemical, techno-functional, and sensory attributes ... more The study was conducted to investigate physiochemical, techno-functional, and sensory attributes of yogurt supplemented with basil seed gum. Two levels of gum as 0.5% and 1% was used to develop a product. The product was stored for 21 days at 4°C and assessed on each 3rd day for texture properties such as cohesiveness, adhesiveness and stringiness, pH, and sensory evaluation. Proximate analysis showed moisture content 10.76%, protein content 16.93%, fat content 6.93% fiber content 27.25%, ash HIGHLIGHTS • The term 'yoghurt' relates to the Turkish word 'Jughurt' and to yogurmark 'to knead' and yogum 'dense' or 'thick.' • The method of manufacture for different yogurt products is nevertheless quite like yoghurt production. The difference is in the use of specific cultures, incorporation of additives, curd treatment, and method of packaging. • Consumers may seek for low-fat dairy products, which may suffer from a lack of sensory quality • The incorporation of basil seed gum into yogurt is one of the conceivable ways to promote health benefits.
Pakistan biomedical journal, Mar 31, 2022
Pseudomonas aeruginosa are Gram-negative, nonfermentative bacteria that may be found in water, se... more Pseudomonas aeruginosa are Gram-negative, nonfermentative bacteria that may be found in water, sediment, and other humid habitats. P. aeruginosa is commonly linked to human illnesses, where it acts as a nosocomial microbial pathogen that uses a functional strategic way to infect nearly any tissue or organ, especially in susceptible people or the elderly [1]. The potential of P. aeruginosa to cause illness is enhanced by the wide variety of resistance mechanisms to the antibiotics, as well as the ability to thrive in a wide range of environmental circumstances and virulence determinants [2]. P. aeruginosa thrives in both normal and low-oxygen settings
2021 IEEE 32nd International Conference on Application-specific Systems, Architectures and Processors (ASAP)
This paper presents novel reconfigurable architectures for reducing the latency of recurrent neur... more This paper presents novel reconfigurable architectures for reducing the latency of recurrent neural networks (RNNs) that are used for detecting gravitational waves. Gravitational interferometers such as the LIGO detectors capture cosmic events such as black hole mergers which happen at unknown times and of varying durations, producing time-series data. We have developed a new architecture capable of accelerating RNN inference for analyzing time-series data from LIGO detectors. This architecture is based on optimizing the initiation intervals (II) in a multi-layer LSTM (Long Short-Term Memory) network, by identifying appropriate reuse factors for each layer. A customizable template for this architecture has been designed, which enables the generation of low-latency FPGA designs with efficient resource utilization using high-level synthesis tools. The proposed approach has been evaluated based on two LSTM models, targeting a ZYNQ 7045 FPGA and a U250 FPGA. Experimental results show that with balanced II, the number of DSPs can be reduced up to 42% while achieving the same IIs. When compared to other FPGA-based LSTM designs, our design can achieve about 4.92 to 12.4 times lower latency.
Healthcare Technology Letters, 2021
The rapid proliferation of wearable devices for medical applications has necessitated the need fo... more The rapid proliferation of wearable devices for medical applications has necessitated the need for automated algorithms to provide labelling of physiological time-series data to identify abnormal morphology. However, such algorithms are less reliable than goldstandard human expert labels (where the latter are typically difficult and expensive to obtain), due to their large inter-and intra-subject variabilities. Actions taken in response to these algorithms can therefore result in sub-optimal patient care. In a typical scenario where only unevenly sampled continuous or numeric estimates are provided, without access to the "ground truth", it is challenging to choose which algorithms to trust and which to ignore, or even how to merge the outputs from multiple algorithms to form a more precise final estimate for individual patients. In this work, the novel application of two previously proposed parametric fully-Bayesian graphical models is demonstrated for fusing labels from (i) independent and (ii) potentially correlated algorithms, validated on two publicly available datasets for the task of respiratory rate (RR) estimation. These unsupervised models aggregate RR labels and estimate jointly the assumed bias and precision of each algorithm. Fusing estimates in this way may then be used to infer the underlying ground truth for individual patients. It is shown that modelling the latent correlations between algorithms improves the RR estimates, when compared to commonly employed strategies in the literature. Finally, it is demonstrated that the adoption of a strongly Bayesian approach to inference using Gibbs sampling results in improved estimation over the current state-ofthe-art (e.g. hierarchical Gaussian processes) in physiological time-series modelling. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020
Cardiovascular diseases (CVDs) remain responsible for millions of deaths annually. Myocardial inf... more Cardiovascular diseases (CVDs) remain responsible for millions of deaths annually. Myocardial infarction (MI) is the most prevalent condition among CVDs. Although datadriven approaches have been applied to predict CVDs from ECG signals, comparatively little work has been done on the use of multiple-lead ECG traces and their efficient integration to diagnose CVDs. In this paper, we propose an end-to-end trainable and joint spectral-longitudinal model to predict heart attack using data-level fusion of multiple ECG leads. The spectral stage transforms the time-series waveforms to stacked spectrograms and encodes the frequency-time characteristics, whilst the longitudinal model helps to utilise the temporal dependency that exists in these waveforms using recurrent networks. We validate the proposed approach using a public MI dataset. Our results show that the proposed spectrallongitudinal model achieves the highest performance compared to the baseline methods.
We describe the new Quartus backend of hls4ml, designed to deploy Neural Networks on Intel FPGAs.... more We describe the new Quartus backend of hls4ml, designed to deploy Neural Networks on Intel FPGAs. We list the supported network components and layer architectures (dense, binary/ternary, and convolutional neural networks) and evaluate its performance on a benchmark problem previously considered to develop the Vivado backend of hls4ml. We also introduce the support for recurrent layers and introduce a new asynchronous calling model to increase performance for larger models. In addition to that, we also demonstrate the use of this new model to optimize large-sparse networks.
Gels, 2022
Ultrasound imaging is a widely used technique in every health care center and hospital. Ultrasoun... more Ultrasound imaging is a widely used technique in every health care center and hospital. Ultrasound gel is used as a coupling medium in all ultrasound procedures to replace air between the transducer and the patient’s skin, as ultrasound waves have trouble in traveling through air. This research was performed to formulate an inexpensive alternative to commercially available ultrasound gel as it is expensive and imported from other countries. Different formulations with different concentrations of carbopol 980 (CAR 980) and methylparaben were prepared with natural ingredients such as aloe vera gel and certain available chemicals that have no harmful effects on the skin. To justify the efficiency of the formulations; necessary physicochemical characteristics such as visual clarity, homogeneity, transparency, skin irritation, antibacterial activity, pH, stability, spreadability, conductivity, acoustic impedance, viscosity, and cost were evaluated. Moreover, a comparison study was also c...
JOURNAL OF WEED SCIENCE RESEARCH, 2021
Tyrosinase is a key enzyme in melanogenesis and its high activity leads to increasedpigmentations... more Tyrosinase is a key enzyme in melanogenesis and its high activity leads to increasedpigmentations causing skin disorder like freckles, melanosoma and black spot. Therefore to search for new tyrosinase inhibitors is desirable. In present study, methanolic (MeOH) extracts from leaves, fruit peel and pulp of Citrus bergamia (CB) and, leaves and fruitof Ficus carica (FC) were prepared which were further process for fractional ethyl alcohol (EA), n-hexane (n-Hx) and chloroform (CHCl3)extractions (total 20 extracts) aiming to test their anti-tyrosinase potential, in-vitro. Our results confirmed that all MeOH FC and CB extracts showed significant anti-oxidant activity with IC50 range of 461.9 ± 16.1µg/ml to 2324.4 ± 116.1 µg/ml. Moreover, CB and FC all 20 extracts have significant anti-tyrosinase activity with IC50 range of 13.9 ± 0.5 µg/ml to 320.5 ± 3.3 µg/ml. Interestingly, CB MeOH-EA peel and leaf extracts showed tyrosinase inhibition (IC50) 13.9 ± 0.5 µg/ml and 17.2 ± 0.8 µg/ml, resp...
Knowledge Management and Acquisition for Intelligent Systems, 2021
Visual inspection of electrocardiograms (ECGs) is a common clinical practice to diagnose heart di... more Visual inspection of electrocardiograms (ECGs) is a common clinical practice to diagnose heart diseases (HDs), which are still responsible for millions of deaths globally every year. In particular, myocardial infarction (MI) is the leading cause of mortality among HDs. ECGs reflect the electrical activity of the heart and provide a quicker process of diagnosis compared to laboratory blood tests. However, still it requires trained clinicians to interpret ECG waveforms, which poses a challenge in low-resourced healthcare systems, such as poor doctorto-patient ratios. Previous works in this space have shown the use of data-driven approaches to predict HDs from ECG signals but focused on domain-specific features that are less generalizable across patient and device variations. Moreover, limited work has been conducted on the use of longitudinal information and fusion of multiple ECG leads. In contrast, we propose an end-to-end trainable solution for MI diagnosis, which (1) uses 12 ECG leads; (2) fuses the leads at data-level by stacking their spectrograms; (3) employs transfer learning to encode features rather than learning representations from scratch; and (4) uses a recurrent neural network to encode temporal dependency in long duration ECGs. Our approach is validated using multiple datasets, including tens of thousands of subjects, and encouraging performance is achieved.
ArXiv, 2021
Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devic... more Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devices and systems are extremely valuable across a broad range of application domains. In scientific domains, real-time near-sensor processing can drastically improve experimental design and accelerate scientific discoveries. We have developed hls4ml, an open-source software-hardware co-design workflow to interpret and translate machine learning algorithms for implementation in FPGAs and ASICs specifically to support domain scientists. In this paper, we describe the essential features of the hls4ml workflow including network optimization techniques— such as pruning and quantization-aware training—which can be incorporated naturally into the device implementations. We expand on previous hls4ml work by extending capabilities and techniques towards low-power implementations and increased usability: new PythonAPIs, quantization-aware pruning, end-to-end FPGAworkflows, long pipeline kernels for l...
PLOS ONE, 2021
Background Delays in patient flow and a shortage of hospital beds are commonplace in hospitals du... more Background Delays in patient flow and a shortage of hospital beds are commonplace in hospitals during periods of increased infection incidence, such as seasonal influenza and the COVID-19 pandemic. The objective of this study was to develop and evaluate the efficacy of machine learning methods at identifying and ranking the real-time readiness of individual patients for discharge, with the goal of improving patient flow within hospitals during periods of crisis. Methods and performance Electronic Health Record data from Oxford University Hospitals was used to train independent models to classify and rank patients’ real-time readiness for discharge within 24 hours, for patient subsets according to the nature of their admission (planned or emergency) and the number of days elapsed since their admission. A strategy for the use of the models’ inference is proposed, by which the model makes predictions for all patients in hospital and ranks them in order of likelihood of discharge within...
Journal of Ayub Medical College, Abbottabad : JAMC, 2020
Background Anaplastic thyroid carcinoma is a high-grade tumour with poor prognosis. Most of the c... more Background Anaplastic thyroid carcinoma is a high-grade tumour with poor prognosis. Most of the cases are easily diagnosed on cytology and some of these are associated with increased neutrophils in cytology specimen as well as in the blood. The objective of the study is to determine the frequency of neutrophilia with fever in anaplastic thyroid carcinoma. Methods This descriptive cross-sectional study was performed in the Department of Pathology Ayub Teaching Hospital Abbottabad as well as in association with Advance lab Abbottabad. All the cases diagnosed as anaplastic thyroid carcinoma on cytology were included, histopathological examination was done only in 5 cases. The duration of study was from October 2016 to October 2019 were included in the study. Results Out of 150 cases of thyroid cytology 09 were diagnosed as anaplastic thyroid carcinoma. The mean age of patients was 65.7±6.96. Gender distribution was 5/9 (55.6%) males and 4/9 (44.4%) were females. Out of which 05 were co...
Journal of Ayub Medical College, Abbottabad : JAMC, 2021
BACKGROUND Evaluation of the educational environment is key to the delivery of high-quality medic... more BACKGROUND Evaluation of the educational environment is key to the delivery of high-quality medical education. Especially, when an institute is in the transition phase of curriculum. In curriculum transformation phase of Ayub Medical College Abbottabad, no such evaluation has been done. This study aimed to find the direction of Educational environment in the transition phase curriculum of Ayub Medical College Abbottabad and compare different domains of educational environment with gender, residency, pre-medical education's medium of instruction, and doctors among sibling or parents. Methods This descriptive cross-sectional survey was conducted among students of integrated and traditional curriculum of Ayub Medical College, Abbottabad from 1st December 2019 to 29th February 2020. By Non-probability convenience sampling technique, pre-validated Dundee Ready Educational Environment Measure questionnaire was used. Descriptive and inferential statistics were calculated in SPSS v22. R...
Artificial Intelligence in Medicine, 2021
Myocardial Infarction (MI) has the highest mortality of all cardiovascular diseases (CVDs). Detec... more Myocardial Infarction (MI) has the highest mortality of all cardiovascular diseases (CVDs). Detection of MI and information regarding its occurrence-time in particular, would enable timely interventions that may improve patient outcomes, thereby reducing the global rise in CVD deaths. Electrocardiogram (ECG) recordings are currently used to screen MI patients. However, manual inspection of ECGs is time-consuming and prone to subjective bias. Machine learning methods have been adopted for automated ECG diagnosis, but most approaches require extraction of ECG beats or consider leads independently of one another. We propose an end-to-end deep learning approach, DeepMI, to classify MI from normal cases as well as identifying the time-occurrence of MI (defined as acute, recent and old), using a collection of fusion strategies on 12 ECG leads at data-, feature-, and decision-level. In order to minimise computational overhead, we employ transfer learning using existing computer vision networks. Moreover, we use recurrent neural networks to encode the longitudinal information inherent in ECGs. We validated DeepMI on a dataset collected from 17,381 patients, in which over 323,000 samples were extracted per ECG lead. We were able to classify normal cases as well as acute, recent and old onset cases of MI, with AUROCs of 96.7%, 82.9%, 68.6% and 73.8%, respectively. We have demonstrated a multi-lead fusion approach to detect the presence and occurrence-time of MI. Our end-to-end framework provides flexibility for different levels of multi-lead ECG fusion and performs feature extraction via transfer learning.
JOURNAL OF WEED SCIENCE RESEARCH, 2021
-Tyrosinase is a key enzyme of melanogenesis which determines the mammalian skin, hair and eye co... more -Tyrosinase is a key enzyme of melanogenesis which determines the mammalian skin, hair and eye colour. Hyper-pigmentation leads to various skin disorders like melasma, sunspots, age spots and freckles. Moreover, abnormal skin pigmentation is a serious aesthetic concern which leads to psychosocial problems. Thus to achieve melanin inhibition, inhibition of tyrosinase might be an effective approach. To this end we prepared methanolic (MeOH) extracts from leaves and roots of Allium sativum (AS) and Mentha piperita (MP), which were further processed for 1:1 fractional distillation to prepare methanolic n-hexane (MeOH_n-Hx), methanolic ethyl acetate (MeOH_EA) and methanolic chloroform (MeOH_CHCl3) extracts, aiming to evaluate tyrosinase and anti-oxidant activities in-vitro. Our results confirmed that all MeOH-crude AS and MP extracts showed significant anti-oxidant activity with IC50 values ranging from 0.05 ± 0.2 mg/ml to 4.3 ± 2.3mg/ml. Moreover, AS and MP all 16 extracts have significant anti-tyrosinase activity with IC50 range from 0.014 ± 0mg/ml to 1.205 ± 0.07mg/ml. Interestingly, AS leaf MetOH_EA, AS leaf MetOH_CHCl3, AS root MetOH_EA and MP leaf MetOH_CHCl3 showed significant anti-tyrosinase activity even higher than positive control kojic acid. AS leaf MetOH_CHCl3 extract being the most potent among all tested extracts is proposed as potential candidate to treat tyrosinase rooted hyper-pigmentation in future.
Pure and Applied Biology, 2020
Bacterial infections and their increasing resistance to common antibiotics is posing serious thre... more Bacterial infections and their increasing resistance to common antibiotics is posing serious threat to global public health. To this end, finding new alternatives and evaluating their antibacterial efficacy is always desirable. Therefore, in the present study we used methanol (MeOH), n-hexane (n-Hex), ethyl acetate (ETAC) and chloroform (CHCl3) to prepared four different types of extracts from Moringa oleifera (M. oliefera) leaves aiming to inhibit five selected bacteria. Initially, agar well diffusion methods was used, and zones of inhibition were measured as an indicator of bacterial susceptibility. MeOH, n-Hex, ETAC and CHCl3 leaf extracts showed highest zone of inhibition against E. coli, B. cereus, S. pyogenes, S. aureus and S. enterica, respectively. Moreover, highest zones of inhibition were observed at lowest incubation (24hr) and lowest zones were observed at highest incubation period (72hr) for all tested concentrations. Later, macrodilution method was used to access the antibacterial susceptibility in liquid medium. Results confirmed the susceptibility of all test bacteria with different level of IC50 values ranging from 7.07 ± 0.44 to10.91 ± 0.10 mg/ml for MeOH extract, 1.66 ± 0.08 to 2.11 ± 0.11 mg/ml for n-Hex extract, 2.58 ± 0.13 to 3.84 ± 0.21 mg/ml for ETAC extract and 3.73 ± 0.75 to 8.36 ± 0.20 mg/ml for CHCl3 extract. Interestingly, none of the tested bacteria showed resistance against any of the tested extract in well diffusion or macrodilution method expressing the M. oliefera leaves extracts as potent candidates to kill bacteria in semisolid or in liquid medium to fulfill medical needs in future.
Healthcare Technology Letters, 2020
IEEE Journal of Biomedical and Health Informatics, 2020
In low and middle income countries, infectious diseases continue to have a significant impact, pa... more In low and middle income countries, infectious diseases continue to have a significant impact, particularly amongst the poorest in society. Tetanus and hand foot and mouth disease (HFMD) are two such diseases and, in both, death is associated with autonomic nervous system dysfunction (ANSD). Currently, photoplethysmogram or electrocardiogram monitoring is used to detect deterioration in these patients, however expensive clinical monitors are often required. In this study, we employ low-cost and mobile wearable devices to collect patient vital signs unobtrusively; and we develop machine learning algorithms for automatic and rapid triage of patients that provide efficient use of clinical resources. Existing methods are mainly dependent on the prior detection of clinical features with limited exploitation of multi-modal physiological data. Moreover, the latest developments in deep learning (e.g. cross-domain transfer learning) have not been sufficiently applied for infectious disease diagnosis. In this paper, we present a fusion of multi-modal physiological data to predict the severity of ANSD with a hierarchy of resourceaware decision making. First, an on-site triage process is performed using a simple classifier. Second, personalised longitudinal modelling is employed that takes the previous states of the patient into consideration. We have also employed a spectrogram representation of the physiological waveforms to exploit existing networks for cross-domain transfer learning, which avoids the laborious and data intensive process of training a network from scratch. Results show that the proposed framework has promising potential in supporting severity grading of infectious diseases in low-resources settings, such as in the developing world.