Electricity production from photovoltaic (PV) systems has accelerated in the last few decades. Numerous environmental factors, particularly the buildup of dust on PV panels have resulted in a significant loss in PV energy output. To detect the dust and thus reduce power loss, several techniques are being researched, including thermal imaging, image processing, sensors, cameras with IoT, machine learning, and deep learning. In this study, a new dataset of images of dusty and clean panels is introduced and applied to the current state-of-the-art (SOTA) classification algorithms. Afterward, a new convolutional neural network (CNN) architecture, SolNet, is proposed that deals specifically with the detection of solar panel dust accumulation. The performance and results of the proposed SolNet and other SOTA algorithms are compared to validate its efficiency and outcomes where SolNet shows a higher accuracy level of 98.2%. Hence, both the dataset and SolNet can be used as benchmarks for future research endeavors. Furthermore, the classes of the dataset can also be expanded for multiclass classification. At the same time, the SolNet model can be fine-tuned by tweaking the hyperparameters for further improvements.

Computer vision coupled with Deep Learning (DL) techniques bring out a substantial prospect in the field of traffic control, monitoring and law enforcing activities. This paper presents a YOLOv4 object detection model in which the Convolutional Neural Network (CNN) is trained and tuned for detecting the license plate of the vehicles of Bangladesh and recognizing characters using tesseract from the detected license plates. Here we also present a Graphical User Interface (GUI) based on Tkinter, a python package. The license plate detection model is trained with mean average precision (mAP) of 90.50% and performed in a single TESLA T4 GPU with an average of 14 frames per second (fps) on real time video footage.

Identifying stress in older adults is a crucial field of research in health and well-being. This allows us to take timely preventive measures that can help save lives. That is why a nonobtrusive way of accurate and precise stress detection is necessary. Researchers have proposed many statistical measurements to associate stress with sensor readings from digital biomarkers. With the recent progress of Artificial Intelligence in the healthcare domain, the application of machine learning is showing promising results in stress detection. Still, the viability of machine learning for digital biomarkers of stress is under-explored. In this work, we first investigate the performance of a supervised machine learning algorithm (Random Forest) with manual feature engineering for stress detection with contextual information. The concentration of salivary cortisol was used as the golden standard here. Our framework categorizes stress into No Stress, Low Stress, and High Stress by analyzing digital biomarkers gathered from wearable sensors. We also provide a thorough knowledge of stress in older adults by combining physiological data obtained from wearable sensors with contextual clues from a stress protocol. Our context-aware machine learning model, using sensor fusion, achieved a macroaverage F-1 score of 0.937 and an accuracy of 92.48% in identifying three stress levels. We further extend our work to get rid of the burden of manual feature engineering. We explore Convolutional Neural Network (CNN)-based feature encoder and cortisol biomarkers to detect stress using contextual information. We provide an in-depth look at the CNN-based feature encoder, which effectively separates useful features from physiological inputs. Both of our proposed frameworks, i.e., Random Forest with engineered features and a Fully Connected Network with CNN-based features validate that the integration of digital biomarkers of stress can provide more insight into the stress response even without any self-reporting or caregiver labels. Our method with sensor fusion shows an accuracy and F-1 score of 83.7797% and 0.7552, respectively, without context and 96.7525% accuracy and 0.9745 F-1 score with context, which also constitutes a 4% increase in accuracy and a 0.04 increase in F-1 score from RF.

This paper analyses how well a Fast Fully Convolutional Network (FastFCN) semantically segments satellite images and thus classifies Land Use/Land Cover(LULC) classes. FastFCN was used on Gaofen-2 Image Dataset (GID-2) to segment them in five different classes: Builtup, Meadow, Farmland, Water and Forest. The results showed better accuracy (0.93), precision (0.99), recall (0.98) and mean Intersection over Union (mIoU) (0.97) than other approaches like using FCN-8 or eCognition, a readily available software. We presented a comparison between the results. We propose FastFCN to be both faster and more accurate automated method than other existing methods for LULC classification.