An Improved Method for Broiler Weight Estimation Integrating Multi-Feature with Gradient Boosting Decision Tree.

Broiler weighing is essential in the broiler farming industry. Camera-based systems can economically weigh various broiler types without expensive platforms. However, existing computer vision methods for weight estimation are less mature, as they focus on young broilers. In effect, the estimation error increases with the age of the broiler. To tackle this, this paper presents a novel framework. First, it employs Mask R-CNN for instance segmentation of depth images captured by 3D cameras. Next, once the images of either a single broiler or multiple broilers are segmented, the extended artificial features and the learned features extracted by Customized Resnet50 (C-Resnet50) are fused by a feature fusion module. Finally, the fused features are adopted to estimate the body weight of each broiler employing gradient boosting decision tree (GBDT). By integrating diverse features with GBTD, the proposed framework can effectively obtain the broiler instance among many depth images of multiple broilers in the visual field despite the complex background. Experimental results show that this framework significantly boosts accuracy and robustness. With an MAE of 0.093 kg and an R2 of 0.707 in a test set of 240 63-day-old bantam chicken images, it outperforms other methods.

Study of Surface Integrity of Titanium Alloy (TC4) by Belt Grinding to Achieve the Same Surface Roughness Range.

Titanium alloy materials are used in a variety of engineering applications in the aerospace, aircraft, electronics, and shipbuilding industries, and due to the continuous improvement of the contemporary age, surface integrity needs to be improved for engineering applications. Belt grinding parameters and levels directly affect the surface integrity of titanium alloys (TC4), which further affects the fatigue life of the titanium alloys during service. In order to investigate the surface integrity of titanium alloys at different roughness levels, the surfaces were repeatedly ground with the same type and different models of abrasive belts. The results showed that at roughness Ra levels of 0.4 µm to 0.2 µm, the compressive residual stresses decreased with increasing linear velocity and there were problems with large surface morphological defects. At the roughness Ra of 0.2 µm or less, grinding improves the surface morphology, the compressive residual stress increases with increasing feed rate, and the surface hardness decreases with increasing linear velocity. In addition, the research facilitates the engineering of grinding parameters and levels that affect surface integrity under different roughness conditions, providing a theoretical basis and practical reference.

Intelligently Thermoresponsive Ionic Liquid toward Molecular Firefighting and Thermal Energy Management.

Hydrocarbon-based phase change materials (PCMs) are accompanied by an inherent fire risk, which is hindering their further application especially in construction. Molecular-firefighting PCMs can be ideal and promising candidates to simultaneously ensure the highly efficient energy management and fire safety of PCMs. In this work, two novel phosphorus/nitrogen-containing ionic liquids ([DP][MI] and [DP][TEA]), composed of imidazole (MI) or triethylamine (TEA) cations and dicetyl phosphate (DP) anion, were synthesized for fire-proofing thermal energy management. The fire risk assessment confirmed that the extinguishing time of prepared [DP][MI] and [DP][TEA] was greatly shortened to 20 s and 3.5 min from 45 min for controlled sample, respectively. Moreover, the thermal enthalpy of [DP][MI] reached about 99.0 J g-1. In addition, [DP][MI] and [DP][TEA] achieved low supercooling extents of 2.2 and 4.4 °C, separately. Both molecular firefighting and efficient energy management were achieved for [DP][MI] and [DP][TEA]. As applied in wood-plastic composite which is ubiquitous in construction, [DP][TEA] endowed the composite with temperature-regulating capability of about 10 °C in hut test and remarkably suppressed fire hazard of the composite, displaying a potential application value.

Nanoflake-Constructed Supramolecular Hierarchical Porous Microspheres for Fire-Safety and Highly Efficient Thermal Energy Storage.

The leakage and fire hazard of organic solid-liquid phase change material (PCM) tremendously limit its long-term and safe application in thermal energy storage and regulation. In this work, novel nanoflake-fabricated organic-inorganic supramolecular hierarchical microspheres denoted as BPL were synthesized through the electrostatically driven assembly of poly(ethylene ammonium phenylphosphamide) (BP) decorated layered double hydroxides using sodium dodecyl sulfate as a template. Then the BPL was simultaneously utilized as a porous supporting material and flame retardant for polyethylene glycol to fabricate shape-stabilized PCM (BS-PCM). Benefiting from the structural uniqueness of the BPL microsphere, the BS-PCM possessed a high latent heat capacity of 116.7 J g-1 and excellent thermoregulatory capability. Moreover, the BS-PCM had no apparent leakage after a 200-cycle heating/cooling process and showed excellent thermal reversibility, superior to similar solid-liquid PCMs reported in recent literature. More interestingly, unlike flammable PEG, BS-PCM showed excellent fire resistance when exposed to a fire source. The unique BPL porous microsphere provided not only a microcontainer with high storage capacity for solid-liquid PCM, but also a fire resistant barrier to PEG, supplying a promising solution for highly efficient and fire-safe thermal energy storage.

Gray-matter structure in long-term abstinent methamphetamine users.

BACKGROUND: Previous studies of brain structure in methamphetamine users have yielded inconsistent findings, possibly reflecting small sample size and inconsistencies in duration of methamphetamine abstinence as well as sampling and analyses methods. Here we report on a relatively large sample of abstinent methamphetamine users at various stages of long-term abstinence. METHODS: Chronic methamphetamine users (n = 99), abstinent from the drug ranging from 12 to 621 days, and healthy controls (n = 86) received T1-weighted structural magnetic resonance imaging brain scans. Subcortical and cortical gray-matter volumes and cortical thickness were measured and the effects of group, duration of abstinence, duration of methamphetamine use and onset age of methamphetamine use were investigated using the Freesurfer software package. RESULTS: Methamphetamine users did not differ from controls in gray-matter volumes, except for a cluster in the right lateral occipital cortex where gray-matter volume was smaller, and for regions mainly in the bilateral superior frontal gyrui where thickness was greater. Duration of abstinence correlated positively with gray-matter volumes in whole brain, bilateral accumbens nuclei and insulae clusters, and right hippocampus; and with thickness in a right insula cluster. Duration of methamphetamine use correlated negatively with gray-matter volume and cortical thickness of a cluster in the right lingual and pericalcarine cortex. CONCLUSIONS: Chronic methamphetamine use induces hard-to-recover cortical thickening in bilateral superior frontal gyri and recoverable volumetric reduction in right hippocampus, bilateral accumbens nuclei and bilateral cortical regions around insulae. These alternations might contribute to methamphetamine-induced neurocognitive disfunctions and reflect a regional specific response of the brain to methamphetamine.

Flame Retardation of Natural Rubber: Strategy and Recent Progress.

Natural rubber (NR) as a kind of commercial polymer or engineering elastomer is widely used in tires, dampers, suspension elements, etc., because of its unique overall performance. For some NR products, their work environment is extremely harsh, facing a serious fire safety challenge. Accordingly, it is important and necessary to endow NR with flame retardancy via different strategies. Until now, different methods have been used to improve the flame retardancy of NR, mainly including intrinsic flame retardation through the incorporation of some flame-retarding units into polymer chains and additive-type flame retardation via adding some halogen or halogen-free flame retardants into NR matrix. For them, the synergistic flame-retarding action is usually applied to simultaneously enhance flame retardancy and mechanical properties, in which some synergistic flame retardants such as organo-montmorillonite (OMMT), carbon materials, halloysite nanotube (HNT), etc., are utilized to achieve the above-mentioned aim. The used flame-retarding units in polymer chains for intrinsic flame retardation mainly include phosphorus-containing small molecules, an unsaturated chemical bonds-containing structure, a cross-linking structure, etc.; flame retardants in additive-type flame retardation contain organic and inorganic flame retardants, such as magnesium hydroxide, aluminum hydroxide, ammonium polyphosphate, and so on. Concerning the flame retardation of NR, great progress has been made in the past work. To achieve the comprehensive understanding for the strategy and recent progress in the flame retardation of NR, we thoroughly analyze and discuss the past and current flame-retardant strategies and the obtained progress in the flame-retarding NR field in this review, and a brief prospect for the flame retardation of NR is also presented.