Remote sensing and nuclear techniques for high-resolution mapping and quantification of gully erosion in the highly erodible area of the Malcanska River Basin, Eastern Serbia.

Gully erosion leads to the formation of deep and wide channels that increase the risk of soil loss, flooding, and water pollution. In addition, this process reduces the productivity and viability of agricultural land and natural ecosystems. Preventing gully erosion is critical for maintaining ecological balance and preserving natural resources in certain areas. This paper presents a methodology integrating remote sensing and nuclear techniques to study gully erosion. The morphometric characterization of gullies using 360-degree camera photogrammetry was introduced as a new method in erosion research. This approach aims to investigate the suitability of unmanned aerial vehicle and terrestrial photogrammetry for modeling gullies, to study the variability of erosion processes in gullies at a small scale, and to compare the differences in erosion intensity between nearby gullies. The study's objectives include identifying the effective and economical method for gullies monitoring and providing a starting point for controlling and safeguarding gullies. Mainly erosion process was detected in the studied gullies, while deposition was identified at only 2 out of 39 sampling locations. The results showed an average soil redistribution rate of 16.2 t ha-1 yr-1 and coefficients of variation of 32%, 59%, and 91% for three investigated gullies. It was determined that aerial photogrammetry methods were not practical under the conditions prevailing in the study area. Highly detailed 3D models of the gullies were created using 360-degree photogrammetry. It was confirmed that the micro-relief obtained by photogrammetric modeling is an essential contribution to erosion research. The 360-degree camera photogrammetry serves as a reliable tool for analyzing the morphology of gullies and, in perspective, tracking changes in gully systems over time or monitoring the effectiveness of the applied protection measures.

Surgical teaching of the retropubic midurethral sling: a virtual reality training system.

INTRODUCTION AND HYPOTHESIS: The objective is to develop a low-risk, cost-effective method to teach procedures that require learning by feel and high-volume pattern recognition, starting with the midurethral sling. METHODS: This video describes the creation of a virtual reality model utilizing de-identified patient data, artificial intelligence algorithms and haptics; and demonstrates the use of the training system for trocar passage of the retropubic midurethral sling procedure. RESULTS: This innovative system overcomes the lack of visualization and "blind" nature of sling surgery. Novel artificial intelligence provides high accuracy of anatomical landmarks and a realistic 3D environment. The trainee benefits from haptic and visual alerts for real-time feedback on the trocar insertion pathway and scoring to develop competency. CONCLUSION: This is one of the first noncadaveric, nonstatic models available in the field. It allows for multiple low-risk exercises and provides more surgeons with training outside the operating room, at their own institution, and avoids the need for patient subjects. Training can be disseminated at a significantly lower cost and greater convenience than remote cadaver laboratories or intraoperative observation and has a higher fidelity than available static models, particularly after multiple passes. This has implications not only for retropubic midurethral slings but also for urogynecological and "blind" surgery as a whole.

An Interpretable Deep Learning Model for Speech Activity Detection Using Electrocorticographic Signals.

Numerous state-of-the-art solutions for neural speech decoding and synthesis incorporate deep learning into the processing pipeline. These models are typically opaque and can require significant computational resources for training and execution. A deep learning architecture is presented that learns input bandpass filters that capture task-relevant spectral features directly from data. Incorporating such explainable feature extraction into the model furthers the goal of creating end-to-end architectures that enable automated subject-specific parameter tuning while yielding an interpretable result. The model is implemented using intracranial brain data collected during a speech task. Using raw, unprocessed timesamples, the model detects the presence of speech at every timesample in a causal manner, suitable for online application. Model performance is comparable or superior to existing approaches that require substantial signal preprocessing and the learned frequency bands were found to converge to ranges that are supported by previous studies.

Nucleus Basalis of Meynert Stimulation for Dementia: Theoretical and Technical Considerations.

Deep brain stimulation (DBS) of nucleus basalis of Meynert (NBM) is currently being evaluated as a potential therapy to improve memory and overall cognitive function in dementia. Although, the animal literature has demonstrated robust improvement in cognitive functions, phase 1 trial results in humans have not been as clear-cut. We hypothesize that this may reflect differences in electrode location within the NBM, type and timing of stimulation, and the lack of a biomarker for determining the stimulation's effectiveness in real time. In this article, we propose a methodology to address these issues in an effort to effectively interface with this powerful cognitive nucleus for the treatment of dementia. Specifically, we propose the use of diffusion tensor imaging to identify the nucleus and its tracts, quantitative electroencephalography (QEEG) to identify the physiologic response to stimulation during programming, and investigation of stimulation parameters that incorporate the phase locking and cross frequency coupling of gamma and slower oscillations characteristic of the NBM's innate physiology. We propose that modulating the baseline gamma burst stimulation frequency, specifically with a slower rhythm such as theta or delta will pose more effective coupling between NBM and different cortical regions involved in many learning processes.

FN-DFE: fuzzy-neural data fusion engine for enhanced resilient state-awareness of hybrid energy systems.

Resiliency and improved state-awareness of modern critical infrastructures, such as energy production and industrial systems, is becoming increasingly important. As control systems become increasingly complex, the number of inputs and outputs increase. Therefore, in order to maintain sufficient levels of state-awareness, a robust system state monitoring must be implemented that correctly identifies system behavior even when one or more sensors are faulty. Furthermore, as intelligent cyber adversaries become more capable, incorrect values may be fed to the operators. To address these needs, this paper proposes a fuzzy-neural data fusion engine (FN-DFE) for resilient state-awareness of control systems. The designed FN-DFE is composed of a three-layered system consisting of: 1) traditional threshold based alarms; 2) anomalous behavior detector using self-organizing fuzzy logic system; and 3) artificial neural network-based system modeling and prediction. The improved control system state-awareness is achieved via fusing input data from multiple sources and combining them into robust anomaly indicators. In addition, the neural network-based signal predictions are used to augment the resiliency of the system and provide coherent state-awareness despite temporary unavailability of sensory data. The proposed system was integrated and tested with a model of the Idaho National Laboratory's hybrid energy system facility known as HYTEST. Experiment results demonstrate that the proposed FN-DFE provides timely plant performance monitoring and anomaly detection capabilities. It was shown that the system is capable of identifying intrusive behavior significantly earlier than conventional threshold-based alarm systems.