eDakterBari: A human-centered solution enabling online medical consultation and information dissemination for resource-constrained communities in Bangladesh.

A well-accessible healthcare system is an important measure of the progress of a country, as access to adequate healthcare is one of everyone's very basic human rights. When a community lives below the poverty line, unfortunately, it gets deprived of the basic human rights like healthcare, which is a reality to many resource-constrained communities around the world. The number of such resource-constrained communities in developing countries is large. Orphans present a prominent example in this regard in the context of Bangladesh. Orphans suffer greatly from many diseases due to their resource-constrained environment of livings and they are unable to take a minimum care of their own health. Their lack of resources, inadequate literacy skills, and limited (or no) access to technology leave them in such a position that they are ignorant of healthcare services available for them directly or through technological means. Considering all these unavoidable real aspects and the fact that such resource-constrained communities are very little focused in the literature for aiding them in getting bare minimum healthcare services, in this study, we leverage technology and relevant appropriate intermediaries to bridge the gap between the orphans in the orphanages and healthcare services offered by medical doctors. To accomplish so, we conduct a series of field studies over the intended communities. The orphanage teachers and administrators, being in proximity, are the most effective ones to operate as intermediaries for the orphan children, as revealed through our field studies. Therefore, we use these intermediaries to help the orphans to get basic healthcare services via an Android healthcare app called 'Shastho-sheba'. We also use our findings from the field study to specifically tailor and modify the application for intermediaries to use on behalf of the orphans so that health professionals can provide direct healthcare services to them over the Internet. Finally, we look into our proposed techno-social solution in the context of HCI to ensure that the service is used more effectively.

Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network.

The prevalence and mobility of smartphones make these a widely used tool for environmental health research. However, their potential for determining aggregated air quality index (AQI) based on PM2.5 concentration in specific locations remains largely unexplored in the existing literature. In this paper, we thoroughly examine the challenges associated with predicting location-specific PM2.5 concentration using images taken with smartphone cameras. The focus of our study is on Dhaka, the capital of Bangladesh, due to its significant air pollution levels and the large population exposed to it. Our research involves the development of a Deep Convolutional Neural Network (DCNN), which we train using over a thousand outdoor images taken and annotated. These photos are captured at various locations in Dhaka, and their labels are based on PM2.5 concentration data obtained from the local US consulate, calculated using the NowCast algorithm. Through supervised learning, our model establishes a correlation index during training, enhancing its ability to function as a Picture-based Predictor of PM2.5 Concentration (PPPC). This enables the algorithm to calculate an equivalent daily averaged AQI index from a smartphone image. Unlike, popular overly parameterized models, our model shows resource efficiency since it uses fewer parameters. Furthermore, test results indicate that our model outperforms popular models like ViT and INN, as well as popular CNN-based models such as VGG19, ResNet50, and MobileNetV2, in predicting location-specific PM2.5 concentration. Our dataset is the first publicly available collection that includes atmospheric images and corresponding PM2.5 measurements from Dhaka. Our codes and dataset are available at  https://github.com/lepotatoguy/aqi .

A transformer-based generative adversarial learning to detect sarcasm from Bengali text with correct classification of confusing text.

Sarcasm detection research in Bengali is still limited due to a lack of relevant resources. In this context, getting high-quality annotated data is costly and time-consuming. Therefore, in this paper, we present a transformer-based generative adversarial learning for sarcasm detection from Bengali text based on available limited labeled data. Here, we use the Bengali sarcasm dataset 'Ben-Sarc'. Besides, we construct another dataset containing Bengali sarcastic and non-sarcastic comments from YouTube and newspapers to observe the model's performance on the new dataset. On top of that, we utilize another Bengali sarcasm dataset 'BanglaSarc' to further prove our models' robustness. Among all models, the Bangla BERT-based Generative Adversarial Model has achieved the highest accuracy with 77.1% for the 'Ben-Sarc' dataset. Besides, this model has achieved the highest accuracy of 68.2% for the dataset constructed from YouTube and newspaper, and 97.2% for the 'BanglaSarc' dataset.

Towards associating negative experiences and recommendations reported by Hajj pilgrims in a mass-scale survey.

The annual Hajj presents diversified negative experiences to millions of pilgrims worldwide. The negative experiences and recommendations to overcome them as per pilgrims' feedback are yet to be analyzed from an aggregated perspective in the literature, which we do in this paper. To do so, first, we perform a large-scale survey (n=988) using our comprehensive questionnaire. Then, we perform both quantitative (e.g., clustering) and qualitative (e.g., thematic) analyses on the survey data. Our quantitative analysis reveals up to seven clusters of negative experiences. Further, going beyond the quantitative analysis, our qualitative analysis reveals 21 types of negative experiences, 20 types of recommendations, and nine themes connecting the negative experiences and recommendations. Accordingly, we reveal associations among the negative experiences and recommendations based on the themes in thematic analysis and present the associations through a tripartite graph. However, we have some limitations in this study, such as fewer female and young participants. In future, we plan to collect more responses from female and young participants and extend our work by analyzing linkages in the tripartite graph by augmenting the edges within the graph with appropriate weights. Overall, the findings of this study are expected to facilitate the prioritization of tasks for the management personnel in charge of the Hajj pilgrimage.

A ubiquitous method for predicting underground petroleum deposits based on satellite data.

The method of finding new petroleum deposits beneath the earth's surface is always challenging for having low accuracy while simultaneously being highly expensive. As a remedy, this paper presents a novel way to predict the locations of petroleum deposits. Here, we focus on a region of the Middle East, Iraq to be specific, and conduct a detailed study on predicting locations of petroleum deposits there based on our proposed method. To do so, we develop a new method of predicting the location of a new petroleum deposit based on publicly available data sensed by an open satellite named Gravity Recovery and Climate Experiment (GRACE). Using GRACE data, we calculate the gravity gradient tensor of the earth over the region of Iraq and its surroundings. We use this calculated data to predict the locations of prospective petroleum deposits over the region of Iraq. In the process of our study for making the predictions, we leverage machine learning, graph-based analysis, and our newly-proposed OR-nAND method altogether. Our incremental improvement in the proposed methodologies enables us to predict 25 out of 26 existing petroleum deposits within the area under our study. Additionally, our method shows some prospective petroleum deposits that need to be explored physically in the future. It is worth mentioning that, as our study presents a generalized approach (demonstrated through investigating multiple datasets), we can apply it anywhere in the world beyond the area focused on in this study as an experimental case.

Escalating post-disaster rescue missions through ad-hoc victim localization exploiting Wi-Fi networks.

The number of disasters, accidents, and casualties in disasters is increasing, however, technological advancement has yet to ripe benefits to emergency rescue operations. This contrast is even more prominent in the Global South. The consequences are a huge loss of wealth and resources, but more importantly, the loss of lives. Locating victims of disasters as quickly as possible while speeding up rescue operations can lessen these losses. Traditional approaches for effective victim localization and rescue often requires the establishment of additional infrastructure during the construction period. Which in the context of countries of the global south such as - Bangladesh, is not followed for most of the industrial and household constructions. In this paper, we conduct a study to better understand the challenges of victim localization in emergency rescue operations and to overcome them using "whatever" resources available at hand without needing prior infrastructure facilities and pre-calibration. We design and develop a solution for this purpose and deployed it in several emulated disaster-like scenarios. We analyze and discuss the results obtained from our experiments. Finally, we point out the design implications of an infrastructure-independent and extensive emergency rescue system.