Search

The significance of RNA functions and their role in evolution and disease control have remarkably increased the research scope in the field of RNA science. Though the availability of RNA structure data in PBD has been growing tremendously, maintaining their quality and integrity has become the greater challenge. Since the data available in PDB are results of different independent research, they might contain redundancy. As a result, there remains a possibility of data bias for both protein and RNA chains. Quite a few studies have been conducted to remove the redundancy of protein structures by introducing high-quality representatives. However, the amount of research done to remove the redundancy of RNA structures is still very low. To remove RNA chain redundancy in PDB, we have introduced RNA-NRD, a non-redundant dataset of RNA chains based on sequence and 3D structural similarity. We compared RNA-NRD with the existing non-redundant RNA structure dataset RS-RNA and showed that it has better-formed clusters of redundant RNA chains with lower average RMSD and higher average PSI, thus improving the overall quality of the dataset.

Post-traumatic stress disorder (PTSD) negatively influences a person's ability to cope and increases psychiatric morbidity. The existing diagnostic tools of PTSD are often difficult to administer within marginalized communities due to language and cultural barriers, lack of skilled clinicians, and stigma around disclosing traumatic experiences. We present an initial proof of concept for a novel, low-cost, and creative method to screen the potential cases of PTSD based on free-hand sketches within three different communities in Bangladesh: Rohingya refugees (n = 44), slum-dwellers (n = 35), and engineering students (n = 85). Due to the low overhead and nonverbal nature of sketching, our proposed method potentially overcomes communication and resource barriers. Using corner and edge detection algorithms, we extracted three features (number of corners, number and average length of strokes) from the images of free-hand sketches. We used these features along with sketch themes, participants' gender and group to train multiple logistic regression models for potentially screening PTSD (accuracy: 82.9-87.9%). We improved the accuracy (99.29%) by integrating EEG data with sketch features in a Random Forest model for the refugee population. Our proposed initial assessment method of PTSD based on sketches could potentially be integrated with phones and EEG headsets, making it widely accessible to the underrepresented communities.

Global refugee crisis around the world has displaced millions of people from their homes. Although some of them adjust well, many suffer from significant psychological distress, such as post-traumatic stress disorder (PTSD), owing to exposure to traumatic events and hardships. Here, diagnosis and access to psychological health care present particular challenges for various human-centered design issues. Therefore, analyzing the case of Rohingya refugees in Bangladesh, we propose a two-way diagnosis of PTSD using (i) short inexpensive questionnaire to determine its prevalence, and (ii) low-cost portable EEG headset to identify potential neurobiological markers of PTSD. To the best of our knowledge, this study is the first to use consumer-grade EEG devices in the scarce-resource settings of refugees. Moreover, we explored the underlying structure of PTSD and its symptoms via developing various hybrid models based on Bayesian inference by combining aspects from both reflective and formative models of PTSD, which is also the first of its kind. Our findings revealed several key components of PTSD and its neurobiological abnormality. Moreover, challenges faced during our study would inform design processes of screening tools and treatments of PTSD to incorporate refugee experience in a more meaningful way during contemporary and future humanitarian crisis.

In this era of technological growth, the diagnosis of diseases and finding cures, personal health parameter management and predicting the possibility of susceptibility to some diseases have become accessible and easy. Although all over the world millions of people are falling victim to diabetes, in most of the cases they are not even aware of their situation due to the silent nature of diabetes. Therefore, the objective of this research is to propose an intelligent system based on a machine learning algorithm to improve the accuracy of predicting diabetes. To attain this objective, an algorithm was proposed based on Naïve Bayes with prior clustering. Second, the performance of the proposed algorithm was evaluated using 532 data related to diabetic patients. Finally, the performance of the existing Naïve Bayes algorithm was compared with the proposed algorithm. The results of the comparative study showed that the improvement in the accuracy has been made apparent for the proposed algorithm.

In present-day, autism spectrum disorder (ASD) is gaining its momentum faster than ever. According to Worth Health Organization, 1 in every 160 children has ASD. Diagnosis of autism requires a considerable amount of time and cost. Also, the complex etiology of autism presents a challenge in diagnosis, as different autistic subgroups have a divergent set of behavioral characteristics. The evolution of artificial intelligence and machine learning (ML) presents the opportunity to develop prediction models that can be used to predict autism at quite an early stage. Though several researches were conducted in this field, a predictive tool for diagnosing autism for all age groups is yet to be seen. The objective of this chapter is to explore the existing tree-based ML techniques and propose a new tree-based ML method to predict autism traits of an individual at any age. In order to attain the research objective, different tree-based ML methods were used to develop predictive models of autism and were evaluated using two different datasets. Finally, a new tree-based approach was proposed that combines Iterative Dichotomiser 3 and Classification and Regression Trees in a merged random forest classifier. The evaluation results illustrated that merged random classifier outperforms the existing tree-based ML approaches.

A fast-growing number of non-coding RNA structures have been resolved and deposited in Protein Data Bank (PDB). In contrast to the wide range of global alignment and motif search tools, there is still a lack of local alignment tools. Among all the global alignment tools for RNA 3D structures, STAR3D has become a valuable tool for its unprecedented speed and accuracy. STAR3D compares the 3D structures of RNA molecules using consecutive base-pairs (stacks) as anchors and generates an optimal global alignment. In this article, we developed a local RNA 3D structural alignment tool, named LocalSTAR3D, which was extended from STAR3D and designed to report multiple local alignments between two RNAs. The benchmarking results show that LocalSTAR3D has better accuracy and coverage than other local alignment tools. Furthermore, the utility of this tool has been demonstrated by rediscovering kink-turn motif instances, conserved domains in group II intron RNAs, and the tRNA mimicry of IRES RNAs.

In this era of digitization, ardent efforts are being made to digitize every aspect of our life. Still, people are following that same old manual and anachronous system in cloth management which requires a considerable amount of their time and effort. Finding clothes is agonizing, arduous and can be time-consuming. An automated system for keeping track of garments using a simple mobile application can help people to a great extent in this regard. In our work, we have proposed an automated smart wardrobe model which will be able to keep track of the location of clothes inside the wardrobe using image processing. Other than that, the mobile application will also be able to keep track of clothes that are in laundry or have been recently worn or have been washed or ironed. Moreover, the app will provide suggestions regarding which clothes to wear in which weather or for different occasions using Artificial Intelligence (AI) and thus help to ease daily struggle regarding clothes.

In present day Autism Spectrum Disorder (ASD) is gaining its momentum faster than ever. Detecting autism traits through screening tests is very expensive and time consuming. With the advancement of artificial intelligence and machine learning (ML), autism can be predicted at quite early stage. Though number of studies have been carried out using different techniques, these studies didn't provide any definitive conclusion about predicting autism traits in terms of different age groups. Therefore this paper aims to propose an effective prediction model based on ML technique and to develop a mobile application for predicting ASD for people of any age. As outcomes of this research, an autism prediction model was developed by merging Random Forest-CART (Classification and Regression Trees) and Random Forest-Id3(Iterative Dichotomiser 3) and also a mobile application was developed based on the proposed prediction model. The proposed model was evaluated with AQ-10 dataset and 250 real dataset collected from people with and without autistic traits. The evaluation results showed that the proposed prediction model provide better results in terms of accuracy, specificity, sensitivity, precision and false positive rate (FPR) for both kinds of datasets.

With the motto of being fully digitized by 2020, Bangladesh has already introduced technology to many sectors like administration, business, education, health etc. However, the Land management sector of Bangladesh is lagging behind in terms of usage of technology. Though land has maintained its superiority even after the meteoric rise of science and technology, it is a matter of great regret that different aspects of the land management system of Bangladesh have not seen the light of modern technology yet. Therefore, this paper introduces a cloud based multi-channel approach to synchronize various aspects of land management to improve the current paper-based system into a faster and efficient one. Digitization of the present system is the prime focus of this method without much alteration, which will help to reduce mismanagement among the respective organizations as well. This system also intends to focus on the inheritance of the lands and reduce scam activities related to the land purchase. The user friendly interface of web and mobile applications will also reduce the complexity of this age old management system to the users.

Owing to the recent increase in the number of shelter-seeking migrants and the growth of the worldwide refugee crisis, bringing this huge influx of refugees under a single system is necessary for the proper rehabilitation of these migrants. Presently in Bangladesh, Rohingya refugees arrival is a major crisis and there is no fully-developed centralized automated system here for this purpose. This paper delineates a digital system developed for the organized registration, documentation and conduction of the tedious task of refugee management. It introduces a system which aims to harmonize this task through the use of a cloud database that incorporates all the necessary information regarding the migrants.

Blindness is the inability to see due to any neurological or physical condition. Blind people find it really hard to walk through busy roads and travel new places and so the walking stick becomes their daily companion. The main objective of this paper is to introduce a small hand-carrying system which can be used as a substitute of the walking stick. This system will work based on ultrasonic sensors and GPRS module which will be able to detect obstacles, manholes and potholes; and by pressing a button user will be able to SMS user’s location to user’s close ones. This will make moving around easier and safer for the blind people without getting noticed or without taking help of others.

With the advancement of information technologies, mobile health (mHealth) technologies can be leveraged for patient self-management, patient diagnosis and determining the probability of being affected by some disease. Diabetes mellitus is a chronic and lifestyle disease and millions of people from all over the world fall victim to it. Although there are some mobile apps keeping track of calories, sugar taken, medicine doses, lifestyle, blood glucose, blood pressure, weight of individuals and giving suggestion about food, exercises to prevent or control diabetes, no application has been found that was explicitly developed to analyze the risk of being a diabetic patient. Therefore, the objective of this paper is to develop an intelligent mHealth application based on machine learning to assess his/her possibility of being diabetic, prediabetic or nondiabetic without the assistance of any doctor or medical tests.

In this modern age of digitization, Bangladesh Election Commission (EC) still uses manual system during election for vote casting. Recently, it is considering to introduce Electronic Voting Machine (EVM) in parliamentary elections though EVM is not entirely automated and has many limitations. In this work, we have designed an automated biometric voting system with a convenient user interface and integrated database system containing all voters' information. Casted votes will be counted automatically at the end of the voting process and result will be generated centrally with less time. Therefore, the proposed system will improve the voting management of Bangladesh by ceasing fraudulent activities, corruptions, ensuring security, transparency, fairness, accuracy and keeping backup trails of voting process.