Abstract

Healthcare is one of the basic human rights, but providing proper healthcare in rural remote areas of developing countries has always been a challenging task. Telemonitoring has brought some relief with limitations due to accessing patient's health information by healthcare workers and specialists, but merging it with cloud services can be an optimal solution. This proposed framework, CMED (Cloud based MEDical system), is a setup consisting of both healthcare center and a portable healthcare service with a Community Health Worker(CHW), which will sort the patients into three different categories—healthy, alarming and emergency. Upon failing to diagnose a unique problem, it will suggest and contact a specialist doctor and provide suggestions. The privacy and confidentiality of patient's health information will be secured by Identity Based Encryption. In this paper, a framework has been presented for smart and secure healthcare monitoring system for rural under privileged people in developing countries.

Abstract:

Bangladesh’s health care system, particularly in rural areas, experiences enormous obstacles in
providing complete preventive and primary healthcare services due to the lack of adequate healthcare facilities,
resource constraints, and a non-functional referral system. To alleviate these problems, in this study, we introduce
the digital general practitioner (GP) model for rural Bangladesh, digital platforms and present a statistical
analysis of the data that was gathered from the pilot project.
Methods: A total of 12,746 people were provided regular health services during the pilot project, from all genders
and age groups, and provided their socio-demographic and healthcare-related data. We analyzed healthcarerelated
data by carrying out both descriptive and inferential statistics.
Results: By utilizing this digital GP model, rural residents can receive routine health screenings at their homes,
identify health risks early, receive consultation and health education, and be referred to GP and upper-level
health facilities as needed. We found that hypertension was more prevalent (4.84% of the served population),
and cancer was the least prevalent of all the NCDs in the studied population (0.05% of the served population).
The population for stroke, hypertension, diabetes increased until the 50–59 age range as age increased, following
which the population proportion declined as age increased. Additionally, 3.96% of young females were severely
malnourished, comparably higher proportion than young males (2.34%).
Conclusion: NCDs such as hypertension, diabetes was prevalent among rural people. Necessary steps should be
taken to raise preventive and primary healthcare awareness among rural people.
Public interest summary: The absence of proper healthcare facilities, resource constraints, and a non-functional
referral system hamper Bangladesh’s health care system’s ability to provide comprehensive preventive and
primary healthcare services in rural area. As a result, patients develop advanced ailments, including noncommunicable
diseases (NCDs), and must seek treatment at an expensive specialty hospital. To resolve this
issue, we introduce a digital GP model for rural Bangladesh, then show digital platforms that use the concept, and
lastly summarize significant findings from the piloted digital GP model. By utilizing this digital GP model, rural
residents can receive routine health screenings at their homes, identify health risks early, receive consultation
and health education, and be referred to GP and upper-level health facilities as need. From our data analysis, we
discovered high burden of NCDs such as hypertension and diabetes in the piloted area. Necessary steps should be
taken to raise preventive and primary healthcare awareness among rural people.

Abstract

There are different kinds of technologies being used to improve the communication opportunity of children with verbal challenges. Portable communication devices provide the facility to the users for customizing applications according to their needs. Besides, the usability and costing range of these portable communication devices make them less condemning for the users. On the other hand, communication devices efficiently help the users with less motor skills. After considering these points, a communication device named “Bolte Chai”, has been developed and experimented in a special school’s students and teachers based on five criteria to evaluate usability and effectiveness. Those criteria are, the ability to customize the program to fit the needs of the users, motor skills for operating the applications, reasonable time and resources involved in the teaching and utilization procedure, update the system based on current research and proper costing, considering the user’s affordability. Based on the evaluation, it has been seen that this communication device is usable and effective to improve communication skills of nonverbal children.

Abstract

Call support centers operate over the telephone, connecting customers and receptionists to ensure customer satisfaction by solving their problems. Due to pandemics, customer call support centers have become a popular way of communication that has been used in different domains such as e-commerce, hospitals, banks, credit card support, government offices. Moreover, humans’ limitations to serve 24 hours a day and the fluctuation of waiting time makes it more challenging to satisfy all the customers over call centers. So, customer service needs to be automated to handle customers by providing a domain-based response in the native language, especially in a developing country like Bangladesh, where call support centers are increasing. Although most people use the Bangla language to communicate, little work has been done in customer care automation in the native language. Our developed architecture, “AIMS TALK” can respond to that customer’s need by recognizing users’ voices, specifying customers’ problems in the standardized Bangla language, collecting customers’ responses to the database to give feedback according to the queries. Besides, the system uses MFCC feature extraction for speaker recognition with an average accuracy of 94.38% on 42 people in real-time testing, an RNN-based model for Bangla Automatic Speech Recognition (ASR) with a word error rate (WER) of 42.15%, and sentence summarization we used Sentence similarity measurement technique having an average loss of 0.004. Lastly, we used gTTS that works as Text to Speech Synthesis for the Bangla language in WavNet architecture.