Background: There are a myriad of language cues that indicate depression in written texts, and natural language processing (NLP) researchers have proven the ability of machine learning and deep learning approaches to detect these cues. However, to date, these approaches bridging NLP and the domain of mental health for Bengali literature are not comprehensive. The Bengali-speaking population can express emotions in their native language in greater detail. Objective: Our goal is to detect the severity of depression using Bengali texts by generating a novel Bengali corpus of depressive posts. We collaborated with mental health experts to generate a clinically sound labeling scheme and an annotated corpus to train machine learning and deep learning models. Methods: We conducted a study using Bengali text-based data from blogs and open source platforms. We constructed a procedure for annotated corpus generation and extraction of textual information from Bengali literature for predictive analysis. We developed our own structured data set and designed a clinically sound labeling scheme with the help of mental health professionals, adhering to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5) during the process. We used 5 machine learning models for detecting the severity of depression: kernel support vector machine (SVM), random forest, logistic regression K-nearest neighbor (KNN), and complement naive Bayes (NB). For the deep learning approach, we used long short-term memory (LSTM) units and gated recurrent units (GRUs) coupled with convolutional blocks or self-attention layers. Finally, we aimed for enhanced outcomes by using state-of-the-art pretrained language models. Results: The independent recurrent neural network (RNN) models yielded the highest accuracies and weighted F1 scores. GRUs, in particular, produced 81% accuracy. The hybrid architectures could not surpass the RNNs in terms of performance. Kernel SVM with term frequency–inverse document frequency (TF-IDF) embeddings generated 78% accuracy on test data. We used validation and training loss curves to observe and report the performance of our architectures. Overall, the number of available data remained the limitation of our experiment. Conclusions: The findings from our experimental setup indicate that machine learning and deep learning models are fairly capable of assessing the severity of mental health issues from texts. For the future, we suggest more research endeavors to increase the volume of Bengali text data, in particular, so that modern architectures reach improved generalization capability.

Autonomous vehicle navigation in an unknown dynamic environment is crucial for both supervised- and Reinforcement Learning-based autonomous maneuvering. The cooperative fusion of these two learning approaches has the potential to be an effective mechanism to tackle indefinite environmental dynamics. Most of the state-of-the-art autonomous vehicle navigation systems are trained on a specific mapped model with familiar environmental dynamics. However, this research focuses on the cooperative fusion of supervised and Reinforcement Learning technologies for autonomous navigation of land vehicles in a dynamic and unknown environment. The Faster R-CNN, a supervised learning approach, identifies the ambient environmental obstacles for untroubled maneuver of the autonomous vehicle. Whereas, the training policies of Double Deep Q-Learning, a Reinforcement Learning approach, enable the autonomous agent to learn effective navigation decisions form the dynamic environment. The proposed model is primarily tested in a gaming environment similar to the real-world. It exhibits the overall efficiency and effectiveness in the maneuver of autonomous land vehicles.

Most women face violence in public and at home, including rape, physical and emotional abuse, mocking, and harassment. A social violence support application might allow people to seek aid from their friends, or relatives, or even request administrative assistance. The goal here is to detect clearly and reliably the screams of the individual in danger, that is, if the scream arose out of dread and horror, based on a particular collection of audio. Screams elicited by dread and panic usually have a shorter length, a higher frequency, and shrill pitches, whereas screams elicited by other emotions or intentionally have a longer duration, a fixed frequency, and pitch. In this sense, if we can use scream recognition to recognize dangerous and consequential circumstances in our society and inform the appropriate individuals at the appropriate moment, we will be able to avert these issues to a degree that will benefit both society and its citizens. To assist the wider populace, we have implemented a system using Convolutional Neural Network to identify screams automatically. This model will assist us in recognizing screams and sending SOS signals or messages to suitable contacts. As a result, people who are in danger will be able to call the people from their selected contacts or general authorities who are within their reach at any time. This system will not only assist victims in danger, but it will also provide them with a sense of security. On the other hand, the general authority will be able to use this software to limit the quantity of social and domestic violence.

In this study, we explore the design of a modular, portable, non-invasive device for remote monitoring of temperature, heart rate, oxygen saturation, blood pressure and electrocardiogram (ECG) for quadriplegic patients with near-complete body paralysis. The developed system not only enables remote monitoring, through the interaction with the Internet of Things (loT) technology, of the patients but also reduces the caretakers' workload of continuous monitoring. The system is designed to be a low-cost and user-friendly solution that can be used at home/care homes for continuous monitoring. It also provides a cloud-based platform for monitoring and analyzing data, enabling remote access and providing real-time feedback to caretakers. The results of the system are validated using a few volunteers to demonstrate its accuracy and reliability. The cost-effective design, which includes the monitoring of five vitals, makes it desirable for Bangladesh's healthcare sector.