Khondaker A. Mamun

Cloud based framework for Parkinson’s disease diagnosis and monitoring system for remote healthcare applications

Abstract Speech signal processing and its recognition system have gained a lot of attention from last few years due to its widespread application. In this paper, a novel approach is proposed for diagnosis and monitoring the Parkinson’s Disease (PD) which is the second most severe neurological disease in the world. PD is a neurodegenerative disease which impairs person’s balance, motor skills, speech, and other characteristics such as decision making process, emotions, and sensation. Here, we proposed a cloud based framework for detecting and monitoring Parkinson patients that will enable healthcare service in low resource setting. In the developing countries, where most of the people do not get proper healthcare services and are not well aware of Parkinson’s disease, let alone detecting and getting healthcare for PD, this system can be very practical and useful. For this system, the patients of rural areas, patients from the regions where doctors are not available, can communicate to the doctors only if they have internet connections in their smart phones to access the cloud. Doctors can check and detect patient’s PD by checking their voice disorders or Dysphonia over cloud. With this system, a PD patient can be easily detected and diagnosed by giving their voice samples through their phones, regardless of their location. Based on the evaluation, our proposed systems are avail to achieve 96.6% accuracy in the cloud environment for detecting PD. It is expected that the proposed framework will have great potential to enable healthcare service for PD patients, who live in remote areas, especially in developing countries.

Online transcranial Doppler ultrasonographic control of an onscreen keyboard

Brain-computer interface (BCI) systems exploit brain activity for generating a control command and may be used by individuals with severe motor disabilities as an alternative means of communication. An emerging brain monitoring modality for BCI development is transcranial Doppler ultrasonography (TCD), which facilitates the tracking of cerebral blood flow velocities associated with mental tasks. However, TCD-BCI studies to date have exclusively been offline. The feasibility of a TCD-based BCI system hinges on its online performance. In this paper, an online TCD-BCI system was implemented, bilaterally tracking blood flow velocities in the middle cerebral arteries for system-paced control of a scanning keyboard. Target letters or words were selected by repetitively rehearsing the spelling while imagining the writing of the intended word, a left-lateralized task. Undesired letters or words were bypassed by performing visual tracking, a non-lateralized task. The keyboard scanning period was 15 s. With 10 able-bodied right-handed young adults, the two mental tasks were differentiated online using a Naïve Bayes classification algorithm and a set of time-domain, user-dependent features. The system achieved an average specificity and sensitivity of 81.44 ± 8.35 and 82.30 ± 7.39%, respectively. The level of agreement between the intended and machine-predicted selections was moderate (κ = 0.60). The average information transfer rate was 0.87 bits/min with an average throughput of 0.31 ± 0.12 character/min. These findings suggest that an online TCD-BCI can achieve reasonable accuracies with an intuitive language task, but with modest throughput. Future interface and signal classification enhancements are required to improve communication rate.

Movement decoding using neural synchronization and inter-hemispheric connectivity from deep brain local field potentials.

OBJECTIVE Correlating electrical activity within the human brain to movement is essential for developing and refining interventions (e.g. deep brain stimulation (DBS)) to treat central nervous system disorders. It also serves as a basis for next generation brain-machine interfaces (BMIs). This study highlights a new decoding strategy for capturing movement and its corresponding laterality from deep brain local field potentials (LFPs). APPROACH LFPs were recorded with surgically implanted electrodes from the subthalamic nucleus or globus pallidus interna in twelve patients with Parkinsons disease or dystonia during a visually cued finger-clicking task. We introduce a method to extract frequency dependent neural synchronization and inter-hemispheric connectivity features based upon wavelet packet transform (WPT) and Granger causality approaches. A novel weighted sequential feature selection algorithm has been developed to select optimal feature subsets through a feature contribution measure. This is particularly useful when faced with limited trials of high dimensionality data as it enables estimation of feature importance during the decoding process. MAIN RESULTS This novel approach was able to accurately and informatively decode movement related behaviours from the recorded LFP activity. An average accuracy of 99.8% was achieved for movement identification, whilst subsequent laterality classification was 81.5%. Feature contribution analysis highlighted stronger contralateral causal driving between the basal ganglia hemispheres compared to ipsilateral driving, with causality measures considerably improving laterality discrimination. SIGNIFICANCE These findings demonstrate optimally selected neural synchronization alongside causality measures related to inter-hemispheric connectivity can provide an effective control signal for augmenting adaptive BMIs. In the case of DBS patients, acquiring such signals requires no additional surgery whilst providing a relatively stable and computationally inexpensive control signal. This has the potential to extend invasive BMI, based on recordings within the motor cortex, by providing additional information from subcortical regions.

Pattern classification to optimize the performance of Transcranial Doppler Ultrasonography-based brain machine interface

Determined features and classifiers that maximize TCD-BCI performance.Identified algorithms conducive to online TCD-BCI implementation.Achieved competitive accuracies while minimizing mental task duration. Transcranial Doppler Ultrasonography (TCD) is an emerging brain-computer interface (BCI) modality. Previous offline studies have demonstrated algorithmic differentiation between two mental tasks with accuracies in excess of chance, but have used computationally sophisticated features and classifiers. A preferred approach for eventual online implementation has not yet been identified. In this study, we conducted an offline analysis of TCD recordings to investigate the potential for increasing accuracy in a TCD-based BCI while adhering to features and classifiers computationally conducive to online implementation. We re-examined blood flow velocities from Lu et al. (2014), recorded from the left and right middle cerebral arteries of 10 able-bodied participants during the performance of two different mental activities (mental spelling and visual tracking). Invoking a signal processing and pattern classification method from previous offline TCD studies, we obtained an average accuracy of 73.32???4.09%. We subsequently compared systematic feature selection approaches (Fisher criterion, sequential forward selection, weighted sequential forward selection) and three classifiers, namely, linear discriminant analysis (LDA), Naive Bayes (NB), and support vector machine (SVM). With the combination of weighted sequential forward selection (WSFS), which yielded less than a handful of time domain features, and a SVM classifier, a maximum accuracy of 87.60???3. 27% was attained. Similar results were achieved with sequential forward selection and a SVM classifier. Our findings support the development of highly accurate online TCD-BCIs with computationally simple features.

Decoding movement and laterality from local field potentials in the subthalamic nucleus

Decoding of movement related neural activity is a key process required for brain computer interfaces or bio-feedback. The subthalamic nucleus (STN) is involved in the preparation, execution and imagining of movements. This study therefore aimed to decode subthalamic local field potentials (LFPs) related to movements and its laterality, left or right sided visually cued movements. STN LFPs frequency dependent components were extracted using the wavelet packet transform. The time variant amplitudes of each component were then computed with the Hilbert transform, and then ranked as classification features using a brute-force search approach. Left or right movements compared with rest were sequentially classified using a support vector machine (SVM). With optimised parameters, average correct classification of movement reached 91.5±2.3% and of side (left or right), 74.0±6.4%.

Sequential hypothesis testing for automatic detection of task-related changes in cerebral perfusion in a brain–computer interface

Evidence suggests that the cerebral blood flow patterns accompanying cognitive activity are retained in many locked-in patients. These patterns can be monitored using transcranial Doppler ultrasound (TCD), a medical imaging technique that measures bilateral cerebral blood flow velocities. Recently, TCD has been proposed as an alternative imaging modality for brain-computer interfaces (BCIs). However, most previous TCD-BCI studies have performed offline analyses with impractically lengthy tasks. In this study, we designed a BCI that automatically differentiates between counting and verbal fluency tasks using sequential hypothesis testing to make decisions as quickly as possible. Ten able-bodied participants silently alternated between counting and verbal fluency tasks within the paradigm of a simulated on-screen keyboard. During this experiment, blood flow velocities were recorded within the left and right middle cerebral arteries using bilateral TCD. Twelve features were used to characterize TCD signals. In a simulated online analysis, sequential hypothesis testing was used to update estimates of class probability every 250 ms as TCD data were processed. Classification was terminated once a threshold level of certainty was reached. Mean classification accuracy across all participants was 72% after an average of 23s, compared to an offline analysis which obtained a classification accuracy of 80% after 45 s. This represents a substantial gain in data transmission rate, while maintaining classification accuracies exceeding 70%. Furthermore, a range of decision times between 19 and 28s was observed, suggesting that the ability of sequential hypothesis testing to adapt the task duration for each individual participant is critical to achieving consistent performance across participants. These results indicate that sequential hypothesis testing is a promising alternative for online TCD-BCIs.

Multivariate Bayesian classification of tongue movement ear pressure signals based on the wavelet packet transform

Tongue movement ear pressure signals have been used to generate controlling commands in human-machine interfaces. The objective of this study is to classify the controlled movement relating to an intended action from interfering signals that can be experienced. These interfering signals include but are not limited to, speech, coughing and drinking. Thus data was collected for six types of controlled movement and the various interfering signals, when subjects spoke, coughed or drank. The signal processing involves detection, segmentation, feature extraction and selection, and classification of tongue motions. The segmented signals were initially transformed into the wavelet packet domain, allowing for various features to be extracted based on statistical properties of the wavelet coefficients. These are then used as input into a Bayesian classifier under multivariate Gaussian assumptions. The average classification performance for identifying controlled movements and interfering tongue signals achieved 98% and 93.5% respectively. Thus the classification of tongue movement ear pressure signals based on the wavelet packet transform is robust. The application of this Bayesian classification strategy significantly reduces the interference of controlling commands when considered within a human-machine interface system operating in a challenging environment.

Autism Barta — A smart device based automated autism screening tool for Bangladesh

Autism is a neurodevelopmental disorder which is not fully curable. However, early intervention can improve the condition of the children which requires early detection of autism. For this purpose, screening tools have been immensely used in developed countries. Whereas in developing countries, people are not getting such benefits. In this paper, a new automated approach, Autism Barta is proposed to screen autism in children using smart devices. The application integrates the questions of Bengali version of M-CHAT screening tool with pictorial representation. Therefore, parents can easily understand the interactive questions and use it effectively. The app will automatically screen autism in children, inform the user, store the responses in an online database and will suggest nearby Autism resource center for confirmation and intervention. It is expected that, this system will help to identify and streamline autism for improving the condition in developing countries like Bangladesh.

A Critical Review on World University Ranking in Terms of Top Four Ranking Systems

Now-a-days ranking of universities and institutions has become an appealing topic to study or research, and it has got wide attention to all over the world to recognize the top higher education institutes. Therefore, study on the strategies of the ranking system is vital to ensure the acceptability. There are number of strategies have been developed to rank higher education institutions worldwide. This Study has focused to critically evaluate the potential shortcomings of the top four widely accepted ranking systems. These are the Times World University Rankings, QS World University Rankings, Academic Ranking of World Universities (ARWU) and Webometrics Ranking. We critically reviewed and analyzed these four higher education ranking systems to identify potential shortcomings in their strategies. Based on our investigation, it was observed that none of these ranking systems can provide satisfactory evaluation in terms of their construct validity and other parameters related to disputation. Nevertheless, these ranking systems are the most popular for what they have been doing over the decades but unfortunately each and every one of them has to some extent lacking as far as ranking excellency is concerned. Lack of availability of data and publications through which ranking is done is one major obstacle faced to determine the authenticity of ranking systems. Overall observation of these four ranking systems reflects the fact that generic challenges include adjustment for institutional size, differences between average and extreme, defining the institutions, measurement of time frame, credit allocation, excellency factors as well as adjustment for scientific fields. Misinterpretation of measurement data is also responsible for some of the ranking disputes. We have proposed a number of recommendations that could address the identified inadequacy and considerably improve the ranking system as well as incorporate more participation of higher education institutes form developing world.

An overview of brain machine interface research in developing countries: Opportunities and challenges

Brain Machine Interface (BMI) research can not only improve the quality of life of the disable population all over the world but also augment our understanding on neural systems. However, the existing studies on BMI research solely focus on developed countries. BMI research in the perspective of developing countries is therefore, poorly explored. In this study, we outline the prospects, real-life applications, future scenarios and major challenges in the perspective of developing countries. We conclude with general recommendations on future developments and funding opportunities to support a continued and sustainable growth of the BMI field in developing countries. This study will provide directions on the initiation of BMI research in developing countries and assist scientists, educators and technologists in improving better understanding about the benefits, challenges, potentials and the current state-of-the-art of BMI research.