Search

Precision agriculture-based orchard management relies heavily on the accurate delineation of tree canopies, especially for high-value crops like mangoes. Traditional GIS and remote sensing methods, such as Object-Based Imagery Analysis (OBIA), often face challenges due to overlapping canopies, complex tree structures, and varied light conditions. This study aims to enhance the accuracy of mango orchard mapping by developing a novel deep-learning approach that combines fine-tuned object detection and segmentation techniques. UAV imagery was collected over a 65-acre mango orchard in Multan, Pakistan, and processed into an RGB orthomosaic with a 3 cm ground sampling distance. The You Only Look Once (YOLOv7) framework was trained on an annotated dataset to detect individual mango trees. The resultant bounding boxes were used as prompts for the segment anything model (SAM) for precise delineation of canopy boundaries. Validation against ground truth data of 175 manually digitized trees showed a strong correlation (R2 = 0.97), indicating high accuracy and minimal bias. The proposed method achieved a mean absolute percentage error (MAPE) of 4.94% and root mean square error (RMSE) of 80.23 sq ft against manually digitized tree canopies with an average size of 1290.14 sq ft. The proposed approach effectively addresses common issues such as inaccurate bounding boxes and over- or under-segmentation of tree canopies. The enhanced accuracy can substantially assist in various downstream tasks such as tree location mapping, canopy volume estimation, health monitoring, and crop yield estimation.

Precision agriculture-based orchard management relies heavily on the accurate delineation of tree canopies, especially for high-value crops like mangoes. Traditional GIS and remote sensing methods, such as Object-Based Imagery Analysis (OBIA), often face challenges due to overlapping canopies, complex tree structures, and varied light conditions. This study aims to enhance the accuracy of mango orchard mapping by developing a novel deep-learning approach that combines fine-tuned object detection and segmentation techniques. UAV imagery was collected over a 65-acre mango orchard in Multan, Pakistan, and processed into an RGB orthomosaic with a 3 cm ground sampling distance. The You Only Look Once (YOLOv7) framework was trained on an annotated dataset to detect individual mango trees. The resultant bounding boxes were used as prompts for the segment anything model (SAM) for precise delineation of canopy boundaries. Validation against ground truth data of 175 manually digitized trees showed a strong correlation ( R 2 = 0.97), indicating high accuracy and minimal bias. The proposed method achieved a mean absolute percentage error (MAPE) of 4.94% and root mean square error (RMSE) of 80.23 sq ft against manually digitized tree canopies with an average size of 1290.14 sq ft. The proposed approach effectively addresses common issues such as inaccurate bounding boxes and over- or under-segmentation of tree canopies. The enhanced accuracy can substantially assist in various downstream tasks such as tree location mapping, canopy volume estimation, health monitoring, and crop yield estimation. [ABSTRACT FROM AUTHOR]

Detection and estimation of t-wave alternans (TWA) in presence of indispensable physiological artifacts is still a challenging task, as in most of the cases, the signal of interest resides well below the noise levels. In this paper, a generalized detection theoretic framework (GDFT) is proposed for the detection and estimation of TWA from the stress test ECG signal. The analytical foundations, TWA signal modeling, and finally simulations of nine TWA detectors and estimators belonging to median match filtering, empirical mode decomposition (EMD) based match filtering, and generalized likelihood ratio test (GLRT) for GDTF are presented. GLRT schemes require noise statistics for parameter estimation and are computationally efficient. GLRT detectors outperform all the detectors including the benchmark spectral method by ≥ 2 dB for a broad spectrum of SNR ranging from -15 dB to 30 dB under Gaussian noise. EMD based strategies also outperform spectral method under Gaussian and Laplacian noise by ≥ 1 dB.

Coronary artery disease (CAD) is one of the most common causes of sudden cardiac arrest, accounting for a large percentage of global mortality. A timely diagnosis and detection may save a person's life. The research suggests a methodological framework for non-invasive risk stratification based on information only possible after invasive coronary angiography. Novel clinical, chemical, and molecular cardiac biomarkers were used as input features from an especially collected dataset. Following a thorough evaluative search in the biomarker feature space, the optimum feature and classifier or regression technique (regressor) set were selected using K-fold cross-validation. Ten machine learning (ML) classifiers were employed in classification tasks to determine the number of affected cardiac vessels, the Gensini group, and the severity of CAD with 82.58%, 86.26%, and 90.91% accuracy, respectively. Eleven approaches were used in regression tasks to calculate stenosis percentage and Gensini score, with R-squared values of 0.58 and 0.56, respectively. Following a thorough evaluative search in the biomarkers feature space, the optimum feature and classifier or regressor set were selected using K-fold cross-validation. The biomarkers and classifier or regressor combinations serve as the foundation for the proposed risk stratification framework, incorporating clinical protocol. Finally, our proposed framework is compared to state-of-the-art studies, offering a robust, well-rounded, early detection capable, and novel 'biomarkers-ML combination' approach to risk stratification.