Search

In order to achieve accurate, fast, and robust recognition of blueberry fruit maturity stages for edge devices such as orchard inspection robots, this research proposes a lightweight detection method based on an improved YOLOv5 algorithm. In the improved YOLOv5 algorithm, the ShuffleNet module is used to achieve lightweight deep-convolutional neural networks. The Convolutional Block Attention Module (CBAM) is also used to enhance the feature fusion capability of lightweight deep-convolutional neural networks. The effectiveness of this method is evaluated using the blueberry fruit dataset. The experimental results demonstrate that this method can effectively detect blueberry fruits and recognize their maturity stages in orchard environments. The average recall (R) of the detection is 92.0%. The mean average precision (mAP) of the detection at a threshold of 0.5 is 91.5%. The average speed of the detection is 67.1 frames per second (fps). Compared to other detection algorithms, such as YOLOv5, SSD, and Faster R-CNN, this method has a smaller model size, smaller network parameters, lower memory usage, lower computation usage, and faster detection speed while maintaining high detection performance. It is more suitable for migration and deployment on edge devices. This research can serve as a reference for the development of fruit detection systems for intelligent orchard devices. [ABSTRACT FROM AUTHOR]

Continuing progress in machine learning (ML) has led to significant advancements in agricultural tasks. Due to its strong ability to extract high-dimensional features from fruit images, deep learning (DL) is widely used in fruit detection and automatic harvesting. Convolutional neural networks (CNN) in particular have demonstrated the ability to attain accuracy and speed levels comparable to those of humans in some fruit detection and automatic harvesting fields. This paper presents a comprehensive overview and review of fruit detection and recognition based on DL for automatic harvesting from 2018 up to now. We focus on the current challenges affecting fruit detection performance for automatic harvesting: the scarcity of high-quality fruit datasets, fruit detection of small targets, fruit detection in occluded and dense scenarios, fruit detection of multiple scales and multiple species, and lightweight fruit detection models. In response to these challenges, we propose feasible solutions and prospective future development trends. Future research should prioritize addressing these current challenges and improving the accuracy, speed, robustness, and generalization of fruit vision detection systems, while reducing the overall complexity and cost. This paper hopes to provide a reference for follow-up research in the field of fruit detection and recognition based on DL for automatic harvesting. [ABSTRACT FROM AUTHOR]

As one of the most common features of obesity, insulin resistance is central to the pathogenesis of the metabolic syndrome. Low insulin-like growth factor 1 (IGF-1) levels have been proven to be associated with many traditional cardiovascular risk factors, but it still remains controversial with the relationship between IGF-1 and insulin resistance. Accordingly, the main purpose of this study is to investigate the relationship between IGF-1 and insulin resistance in obese prepubertal boys. We used the whole-body insulin sensitivity index (WBISI) to represent insulin resistance. 70 obese prepubertal boys were included in the study, and the obese subjects were divided into two groups by using 1.285 as a threshold value for WBISI. Clinical examination and laboratory examinations were assessed for all participants. Among obese boys, the group of children with WBISI ≤ 1.285 had lower IGF-1 standard deviation scores (SDS) (p = 0.021) than the WBISI > 1.285 group. The results of multiple linear analyses show that lg WBISI was positively correlated with IGF-1 SDS (p = 0.031) after adjusting for traditional cardiovascular risk factors. IGF-1 SDS was negatively associated with insulin resistance in obese prepubertal boys, independent of other traditional cardiovascular disease risk markers. [ABSTRACT FROM AUTHOR]

Abstract: Very good electronic properties of hot-wire CVD a-Si,Ge:H alloys have been established by junction capacitance methods. The samples were deposited using a tantalum filament maintained at about 1800°C instead of the usual 2000°C tungsten filament process. Urbach energies below 45meV were found, as well as annealed defect densities below 1016 cm−3, for Ge fractions up to 30at.%. However, samples with 1019 cm−3 levels of oxygen exhibited much broader Urbach energies and higher defect densities. Light induced degradation was examined in detail for one a-Si,Ge:H alloy sample and compared to the behavior of PECVD grown a-Si:H alloys of similar optical gap. [Copyright &y& Elsevier]

The authors report a study by small-angle x-ray scattering (SAXS) and tilting SAXS of nanovoids in amorphous silicon films undergoing solid phase crystallization (SPC) by annealing. SPC causes nanovoids in hot-wire chemical vapor deposited (HWCVD) amorphous Si films to decrease in total void fraction but increase in individual void volume. During annealing, the voids also change shape from prolate spheroids to more spherical geometries. Preexisting, large H clusters in as-deposited HWCVD films may provide favorable sites for void expansion driven by H2 pressure, while energy minimization and strain relaxation drive geometric changes. [ABSTRACT FROM AUTHOR]

Postdeposition ultraviolet (UV) illumination, followed by etching, improves the stability of hydrogenated amorphous-silicon thin films against subsequent light-induced degradation of photosensitivity. The etch removes a heavily damaged layer extending about 100 nm below the surface, but beneath the damage, the UV has improved the stability of 200 to 300 nm of bulk film. The open-circuit voltage of Schottky solar cells is also stabilized by UV-etch treatment. Possible mechanisms are discussed. [ABSTRACT FROM AUTHOR]

A large redshift of the photoluminescence (PL) peak energy is found in hydrogenated amorphous silicon films prepared by hot-wire chemical-vapor deposition with a high-growth rate ≥ 50 Å/s. The PL intensity is as high as that in the standard film and its temperature dependence shows thermalization behavior. The origin of the redshift is clarified by employing ¹H nuclear magnetic resonance and mass density measurements. A ∼2% volume fraction of tube-like nanoscale voids is identified. The long spin-lattice relaxation time of H² in the nanovoids implies a negligible density of silicon dangling bonds on the nanovoid surfaces. We suggest that highly strained bonds on these surfaces form broad conduction-band tail states that are responsible for the PL redshift. [ABSTRACT FROM AUTHOR]

Abstract: We report the observation of light induced electron capture in oxygen contaminated (∼5×1020 cm−3) hydrogenated amorphous silicon–germanium alloys grown by hot-wire chemical vapor deposition (HWCVD). By examining the time evolution of dark capacitance after 1.2eV photoexcitation, we are able to estimate the free energy barrier (⩾0.8eV) for the release of electrons into the conduction band. Such a large thermal barrier, for a defect whose optical threshold is centered (∼1.35eV) so close to the band-gap (1.5eV), indicates significant configurational relaxation once the oxygen impurity state is occupied with photoexcited electrons. [Copyright &y& Elsevier]