Analysis of hyperspectral scattering images using locally linear embedding algorithm for apple mealiness classification

Hyperspectral scattering images between 600 nm and 1000 nm were acquired for 580 ‘Delicious’ apples for mealiness classification. A locally linear embedding (LLE) algorithm was developed to extract features directly from the hyperspectral scattering image data. Partial least squares discriminant analysis (PLSDA) and support vector machine (SVM) were applied to develop classification models based on the LLE, mean-LLE and mean spectra algorithms. The model based on the LLE algorithm achieved an overall classification accuracy of 80.4%, compared with 76.2% by the mean-LLE algorithm and 73.0% by the mean spectra method for two-class classification (i.e., mealy and nonmealy) coupled with PLSDA. For the SVM models, the LLE algorithm had an overall classification accuracy of 82.5%, compared with 79.4% by the mean-LLE algorithm and 78.3% by the mean spectra method. Hence, the LLE algorithm provided an effective means to extract hyperspectral scattering features for mealiness classification.     

Monitoring the development of thermoregulation in poultry embryos and its influence by incubation temperature

The general purpose of this review is to show the stage of the development of peripheral and central nervous thermoregulatory mechanisms in poultry embryos at the end of incubation, and the impact of long-term changes in incubation temperature. Methods are described which (a) allow continuous measurement of peripheral thermoregulatory mechanisms simultaneously with the body temperature of the embryo, and (b) can be used for identification of changes in the sensitivity of the central controller of body temperature during the development as well as after prenatal temperature experiences. Further, a method for characterisation of ‘critical periods’ in the development of the respective body function is introduced.The results of our investigations were discussed in relation to the following general rules:(a) The development of peripheral and central nervous thermoregulatory mechanisms begins in the course of the prenatal ontogeny. At the end of incubation poultry embryos have all the prerequisites to react to changes in incubation temperature. Regarding the peripheral thermoregulatory mechanisms the most sensitive parameter for characterization of the developmental level of embryonic thermoregulation is the deep body temperature.(b) Functional systems of the organism develop from open loop system without feedback control into closed system controlled by feedback mechanism. Acute changes in the environmental conditions (e.g. incubation temperature) induce as a rule, initially uncoordinated and immediately non-adaptive reactions. Later the uncoordinated (immediately non-adaptive) reactions change into coordinated (adaptive) reactions, probably with closing of the regulatory system (‘critical period’). Environmental manipulation of immature physiological mechanisms could be used for characterization of ‘critical periods’ of the respective system. Monitoring of changes in the reactions of thermoregulatory mechanisms on the applied changes in incubation temperature during different perinatal time windows could help to limit ‘critical periods’ in the development of the thermoregulatory system.(c) During this ‘critical periods’, the actual environment modulates the development of the respective physiological control systems for the entire life period. Perinatal epigenetic temperature adaptation could be a tool to adapt poultry embryos or hatchlings to later climatic conditions. For detection of immediate and long-term effects of perinatal epigenetic temperature adaptation (‘imprinting’ of the thermoregulatory system) recordings of changes in neuronal hypothalamic thermosensitivity as well as in neuronal response on temperature stress are useful and have to be verified by identification of the respective effector genes and epigenetic changes in its expression.     

The impact of farm management on value of management information systems

The value of management information systems (MISs) arises from improved managerial decision making and, therefore, will vary from farm to farm. Insight into this variation will be of use not only to farmers who consider (new) MIS investments, but also to companies that design and market MISs. In this study, the impact of farm management on the value of sow-herd MISs is investigated. Within the same research population, farm management is assessed with two conceptually different classification approaches — the sociological ‘style of farming’ approach and the farm-economic ‘management level’ approach. Management levels of sow farmers turned out to be positively correlated with MIS value (r=0.35, P=0.02). Although farmers with high management levels tend to be better informed anyway than farmers with low management levels, they get more added value from MISs.     

Instantaneous quantitative and qualitative assessment of pear quality using near infrared spectroscopy

A comparative study was made of the performance of different spectrophotometers as part of a research into the potential of NIR reflectance spectroscopy as a non-destructive method for predicting soluble solid content, firmness and postharvest shelf-storage time in intact pears. Three commercially available spectrophotometers were used: a scanning monochromator (SM) of 400–2500 nm, a combination of diode array and scanning monochromator (DASM) of 350–2500 nm and a diode array (DA) of 900–1700 nm. A total of 332 pears (Pyrus communis L.) cv. ‘Blanquilla’ and ‘Conference’ were used to develop calibration models in different spectral regions, using various spectral signal pretreatments. Models to predict soluble solid content yielded coefficients of determination (r²) ranging from 0.39 to 0.76, and a standard error of cross-validation (SECV) of between 0.59 and 1.49 °Brix, depending on the instrument used. Models for predicting firmness yielded r² values of between 0.45 and 0.79 and SECVs ranging from 5.33 to 7.36 N. Subsequently, the ability of these instruments to classify fruit as a function of postharvest shelf-storage time (0, 6 and 8 days) was tested using partial least squares discriminant analysis (PLS-DA), which yielded percentages of correctly classified samples (ratio of correctly classified samples to total samples) ranging from 81.1 to 94.4%, depending on the instrument used. The results obtained highlight the potential of these NIR instruments for assessing internal quality indices and predicting postharvest storage duration in pears, particularly when the instruments SM and DASM were used.     

立式旋耕对小麦生长季土壤紧实度及产量的影响

为了探究土壤立式旋耕方式对小麦生长季关键生育时期土壤紧实状况的影响,以常规旋耕（TR,12 cm±5 cm）为对照,连续两季（2017—2018年和2018—2019年）研究了立式旋耕（VR,30 cm±5 cm）在不施肥（nF）、施肥（F）条件下小麦关键生育时期土壤紧实度、产量及养分效率的变化。结果表明,与常规旋耕相比,立式旋耕能连续两季持续增加小麦产量,提高氮肥利用率,降低耕层土壤紧实程度;而且立式旋耕能进一步激发土地生产潜力,与常规旋耕不施肥（nFTR）处理相比,2018年立式旋耕施肥（FVR）、常规旋耕施肥（FTR）处理产量分别增加50.16%、36.28%,2019年分别增加42.91%、34.79%。与FTR处理相比,FVR氮肥农学效率提高38.29%（2018年）、23.35%（2019年）;氮肥偏生产力提高10.15%（2018年）、6.02%（2019年）。与常规旋耕相比,立式旋耕能显著降低第一季小麦拔节期、灌浆期10 cm土壤耕层的紧实度;而第二季处理间差异不显著。立式旋耕能降低小麦拔节期20 cm耕层土壤紧实度,在施肥情况下显著降低。两种耕作方式下灌浆期5 cm耕层的土壤紧实度差异不显著。研究表明,立式旋耕较常规旋耕能够有效降低当季小麦拔节期、灌浆期耕层（10 cm）土壤的紧实度,构建良好的土壤结构,提高小麦产量和养分利用率。     

不同产量水平对‘威代尔’果实品质和枝条抗寒性的影响

以酿酒葡萄‘威代尔’为试验材料,探讨河西走廊酿酒葡萄不同产量水平对果实品质及其枝条抗寒性的影响。结果表明,2018年和2019年,不同产量水平下‘威代尔’果实的单粒重、纵径、横径以及果形指数等外形指数无显著性差异;随着产量水平的升高,果实的可滴定酸含量升高,且在1 200 kg/667m²下最高;500、800、1 000 kg/667m²处理组果实的可溶性糖含量之间无显著性差异,1 200 kg/667m²最低;随着产量水平的升高,2018年,果实中的Vc含量呈先升后降的趋势,2019年Vc含量逐渐降低;500、800、1 000、1 200 kg/667m²的果实可溶性固形物均在25%。不同产量水平下,800 kg/667m²和1 000 kg/667m²枝条的第4节长度显著高于500 kg/667m²和1 200 kg/667m²,第4节髓心直径显著低于500 kg/667m²和1 200 kg/667m²。随着4℃~-25℃温度的逐渐降低,2018年和2019年不同产量水平下枝条的电导率呈先升后降再升的趋势;2018年,可溶性糖含量呈先升后降再升再降的趋势,2019年,500 kg/667m²和800 kg/667m²呈先升后降再升的趋势,1 000 kg/667m²和1 200 kg/667m²呈先降后升的趋势;2018年枝条的可溶性淀粉含量、可溶性蛋白含量、SOD含量均逐渐升高,2019年,可溶性蛋白含量、SOD含量均升高,可溶性淀粉含量呈先升后降的趋势。经隶属函数综合分析评价,经2 a控产试验,800 kg/667m²平均隶属函数值均为最高。表明河西走廊酿酒葡萄产区,保证树体正常越冬,‘威代尔’酿酒葡萄的适宜产量水平为800 kg/667m²。     

‘User friendly’ software for an integrated water-energy management system for center pivot irrigation

Computers are becoming more commonly used by farmers for improving their management. The big need is ‘user friendly’ software for use by farmers. An integrated water-energy management system was developed. It includes ‘user friendly’ software run on a microcomputer which communicates to center pivot irrigation systems via radio. The program provides monitoring, control, irrigation scheduling and electrical load control. The system has been used and accepted by our cooperator for three irrigation seasons. He has been able to improve his management and reduce the amount of overirrigation and the variation between systems of total water applied.     

基于深度卷积神经网络的柑橘黄龙病症状识别

【目的】探究深度学习在柑橘Citrus spp.黄龙病症状识别上的可行性,并评估识别器的识别准确率。【方法】以黄龙病/非黄龙病引起的发病叶片图像及健康叶片图像为训练素材,基于卷积神经网络及迁移学习技术构建二类识别器(I-2-C和M-2-C)和八类识别器(I-8-C和M-8-C)。【结果】M-8-C模型的整体识别表现最优,对所有图像的识别准确率为93.7%,表明构建的神经网络识别器能有效辨别柑橘黄龙病症状;I-8-C和M-8-C对所有类型图像的平均F1分值分别为77.9%和88.4%,高于I-2-C(56.3%)和M-2-C(52.5%),表明症状细分有利于提高模型的识别能力。同时M-8-C比I-8-C略高的平均F1分值表明基于MobileNetV1结构的八类识别器识别表现略优于基于InceptionV3的八类识别器。基于M-8-C改进的识别器M-8f-C能够转移到智能手机上,在田间测试中取得较好的识别表现。【结论】基于深度学习和迁移学习开发的识别器对黄龙病单叶症状具有较好的识别效果。     

烤烟品种NC55在黑龙江烟区的适应性研究

通过研究NC55在黑龙江烟区生长发育、烟叶产量、品质和致香成分变化,以期为其在黑龙江省推广提供理论依据。试验在田间条件下,以当地主栽品种龙江911为对照,2018 ~2020年连续3年对NC55 的生长和烟叶品质进行了研究。结果表明：NC55在伸根期和旺长期株高与龙江911之间无显著差异,2019年显著高于龙江911；2018年和2019年NC55叶长与龙江911之间无显著差异,2019年叶宽在旺长期显著高于龙江911；NC55产量与龙江911之间无显著差异,显著提高了上等烟和中等烟比例；NC55与龙江911相比能够显著降低烟叶内总糖、氯离子和还原糖含量,提高烟叶外观质量和感官质量,显著增加叶黄素降解产物和新植二烯两种致香成分含量。综合分析认为,NC55在黑龙江烟区具有较好的适应性。     

Mining the ESROM: A study of breeding value classification in Manchego sheep by means of attribute selection and construction

Manchego sheep breeding represents an important factor in the economy in the region of Castilla-La Mancha, Spain. For this reason, the selection scheme for Manchego sheep (ESROM) was created to improve milk production in ewes belonging to the Manchego breed. This scheme relies on the use of several tools that depend on ewes’ genetic merit, which is calculated by using a sophisticated linear regression model. This paper presents a study about how the use of data mining techniques can help to approximate the genetic qualities of a ewe, before the official 6 months assessment is carried out, and by using less input. This study focuses on two well-known data mining tasks: pre-processing and classification. In the pre-processing stage, state-of-the-art algorithms and new proposals are used to identify relevant subsets of features by means of selection and construction. By using these subsets of highly predictive variables, different classifiers are trained, which in turn, are used to assess the genetic quality merit of any given ewe. As a result, original and constructed relevant variables have been identified for the target problem, this being a valuable result in itself. Furthermore, from simulated tests, reliable classification rates have been obtained when using the identified classifiers to approach ESROM tasks.     

Effect of probability-distance based Markovian texture extraction on discrimination in biological imaging

The effect of probability-distance based re-weighting of image texture features on their discrimination ability was evaluated in this study. A quadratic surface smoothing function was developed from the Bhattacharyya probability distance between two classes of images. The function was used as a re-weighting function for standard grey level co-occurrence matrix (GLCM) textural features in two cases. Case 1 involved 42 images of health and smokers’ lungs. Case 2 involved 144 images of well watered; partially water stressed and dry Rhacomitrium canescens plants. Multilayer perception (MLP) neural networks (NN) classifiers based on standard weighted and probabilistic-distance based re-weighted GLCM textural features were developed for each case. The classifiers were trained and tested using the leave-one-out and the cross-validation evaluation strategies.Probability-distance based re-weighting of GLCM textural features resulted in 37% and 39.22% reduction in true classification error for cases 1 and 2, respectively. It was concluded that re-weighting image texture features based on the probability distance between the classes involved, makes the GLCM texture analysis technique more discriminative and adaptive. This modification will help to overcome the fixed nature of GLCM features which is an area of weakness open to further improvement. Although GLCM features were used in this study, the method can be extended to other co-occurrence-based methods.     

宽幅播种对枣麦间作模式下冬小麦生长发育及产量的影响

【目的】研究宽幅播种对新疆南疆枣麦间作模式下冬小麦生长发育及产量的影响。【方法】在枣麦间作模式下,设置宽幅播种和常规条播2种不同的播种方式,分析不同播种方式下冬小麦叶片叶绿素含量(SPAD值)、叶面积指数(LAI)、干物质积累及产量和产量构成因素的变化规律。【结果】与常规条播相比,宽幅播种处理有利于枣麦间作模式下冬小麦叶绿素含量(SPAD值)的提高,增大了叶面积指数(LAI),促进干物质的积累,有效提高了籽粒产量。与常规条播相比,2018年、2019年宽幅播种冬小麦的有效穗数分别降低了5.31%、4.78%;穗粒数分别增加2.73%、3.47%;千粒重分别提高了4.00%、5.13%;籽粒产量分别提高了2.36%、6.10%;2018年宽幅播种的生物量降低了5.23%,但2019年宽幅播种的生物量较常规条播却增加了2.90%。【结论】枣麦间作模式下宽幅播种增加了冬小麦叶绿素含量,提高了LAI,促进了干物质积累,提高了籽粒产量。     

Introduction of electronics into milking technology

In countries, like the former German Democratic Republic (GDR), where ‘industrialized’ milk production in large herds was the goal to be reached, research on automation of machine milking was started more than 30 years ago. Initially, the main goal was to mechanize operations at the end of the milking process. This work finally resulted in milking devices that do not apply uniform parameters to all cows, but operate according to the milk flow obtained from the cow actually to be milked. This evolution towards ‘controlled milking’ would not have been possible without application of electricity and electronic components for sensors and control units. Also depending on the technical evolution of electronic control systems are devices for recording milk yield and for taking samples for milk analysis, which were available around the year 1980. At that time initial projects for automatic milk recording were evaluated, which had an obvious influence on further development of milk meters. The most demanding step of application of electronic control systems up to now was the introduction of automatic milking systems. Here not only application of teat cups has to be executed, it also is necessary to enable automatic checks of udder condition, milk quality and other operations which may be challenging even for trained human operators. Further evolution of electronic measurement procedures may be important for the milk-producing farmer too, especially when on-line milk analysis is to be introduced within the near future.     

油稻免耕种植模式的土壤理化特性和酶活性

2016年，在湖南省益阳市南县免耕试验基地开始设计不同种植模式处理；2018—2020年，采集冬闲–稻(IR)、冬闲–稻–稻(IRR)、油–稻(OR)、油–稻–稻(ORR)等4种油稻种植模式的土壤样品，测定土壤的容重、微团聚体、养分和酶活性，探究免耕条件下不同油稻种植模式对土壤理化特性和酶活性的影响。结果表明：2018、2019年，同一年内不同油稻种植模式土壤容重间的差异无统计学意义；2020年，IR和IRR的土壤容重显著高于OR和ORR的；2020年，OR和ORR的0.250~1.000 mm粒级微团聚体质量分数较2018年的分别降低了52.04%和49.41%，不同种植模式对大粒级(>0.010 mm)微团聚体质量分数的影响较大，对小粒级(<0.010 mm)的影响较小；2018、2019年，同一年内4种种植模式土壤有机质质量分数间的差异无统计学意义，2020年，ORR的土壤有机质质量分数显著高于其他模式的；同一年内，OR、ORR的土壤速效钾质量分数显著低于IR、IRR的，ORR的土壤纤维素酶、磷酸酶活性均较IRR的高。可见，免耕条件下，油–稻和油–稻–稻种植模式可减缓土壤的紧实度，改变土壤微团聚体组分，延缓有机质含量降低速率，提高土壤纤维素酶和磷酸酶活性。     

遮光处理对谷子农艺性状、小米品质及蒸煮特性的影响

为探讨弱光胁迫对谷子农艺性状、小米品质及蒸煮特性的影响，并为黄土高原低洼地带谷子种植提供理论数据，以长生13号为材料，2018—2019年重复调查其在4种遮光程度(正常自然光照为A1、遮光面积30%为A2、遮光面积50%为A3、遮光面积70%为A4)下的农艺性状、产量、干物质量、小米品质及蒸煮特性变化情况。结果表明：遮光程度的增加显著降低了谷子穗粗、穗重、穗粒重、单株干物质量和产量，其中A1处理与A4处理间的产量减幅2018年为1 695.11 kg·hm^-2、2019年为1 774.95 kg·hm^-2；相对叶绿素含量（SPAD）也是随着遮光程度的增加而降低，其中A4处理SPAD均值比A1处理2018年减小2.18、2019年减小2.68；而峰值粘度、直链淀粉、胶稠度、脂肪含量均是随着遮光程度的增加而先增后减。相关性分析表明，产量与遮光程度呈显著负相关，2018、2019年相关系数分别为-0.899、-0.917。     

Possible adoption of precision agriculture for developing countries at the threshold of the new millennium

The concept of precision agriculture, based on information technology, is becoming an attractive idea for managing natural resources and realizing modern sustainable agricultural development. It is bringing agriculture into the digital and information age. The practice has smoothly extended into some developing countries. The basic principle of managing soil and crop variability within a field is certainly not new. It was named ‘intensive and meticulous cultivation’ by the Chinese people and has been long regarded as the cream of Chinese conventional agriculture. Toward the new millennium, China is preparing to follow the experience of the developed world and is starting to investigate the new technology. This paper considers the possible adoption of precision agriculture for developing countries and ideas in conducting the practice in China.     

Ultrasonic Acoustic Emissions from Leaf Xylem of Potted Wheat Subject to a Soil Drought and Rewatering Cycle

Ultrasonic acoustic emissions （AEs） from leaf xylem of both water stressed and well watered potted winter wheat （Triticum aestivum L.） plants during drought and rewatering cycle were investigated with a ‘PCI-2 Based AE System＇ （Physical Acoustics Corp. New Jersey, USA） for estimation of leaf xylem cavitation and embolism. Very few AEs occurred in xylem of wheat leaves in well-watered plant, and also in plant subject to mild and moderate soil water stress conditions over the first 4 d of the drought cycle. Great amounts of AEs have occurred since d 5 of the drought cycle as plant showed obvious leaf curling, indicating significant cavitation in leaf xylem on plant exposed to severe soil water deficit. At this point, relative soil water content （RSWC） and leaf xylem pressure （ψ1） dropped to 24.0-26.5% and -1.92 MPa, respectively, with reductions in leaf stomatal conductance （gs）, leaf transpiration （Tr） and leaf CO2 assimilation rate （A） of as much as 69.8, 60.7 and 46.5%, respectively. The effect of soil water deficit was in the order gs 〉 Tr 〉 A 〉 AE. Waveform physical property parameters such as amplitude, counts, rise time, duration, absolute energy and signal strength were analyzed. These parameters varied within very broad ranges, with frequency distribution of most parameters being well fitted by the exponential function y = yo- A exp （-x/t）. The proportion of stronger AE signals rose as soil dehydrated. While AEs occurrence in water stressed plant remained higher than in well-watered control at the following day after rewatering, waveform signal strength and related physical property parameters dropped immediately to that of control. Difference in AEs occurrence characterization between field-grown and potted wheat leaves was discussed.     

长期施肥方式对双季稻根系生理特性与产量的影响

为探明双季稻区不同施肥模式对双季水稻根系生理指标和产量的影响,以1986—2018年的长期大田定位试验为平台,2018—2019年设置不施肥(CK)、单施化肥(MF)、秸秆还田配施化肥(RF)和有机、无机肥配施(OM)4种施肥模式,对双季稻根系超氧化物歧化酶(SOD)、过氧化物酶(POD)、过氧化氢酶(CAT)、硝酸还原酶、谷氨酰胺合成酶活性、植株干物质积累和产量变化等指标进行测定。结果表明,与MF和CK相比,RF和OM增加早、晚稻各个生育时期水稻根系的SOD、POD和CAT酶活性,降低其丙二醛(MDA)和游离脯氨酸(Pro)含量。各个生育时期,植株根系的硝酸还原酶、谷氨酰胺合成酶和根系活力由高到低早稻均为OMRFMFCK,晚稻均为RFOMMFCK。OM的水稻根系和茎叶干重均显著高于MF和CK。2个年份的早稻产量均以OM和RF为最高,分别比MF增加944.8～1143.2和435.9～516.1kg/hm2;晚稻产量均以RF和OM为最高,分别比MF增加386.2～387.4和119.8～123.7kg/hm2。因此,在湖南省双季稻生产中,长期采取有机肥、秸秆还田配合施用化肥措施有利于提高水稻根系保护性酶活性和产量。     

Effects of changing simulated sky cover on hyperspectral reflectance measurements for dry matter yield and forage quality prediction

Sensor based analysis methods to assess dry matter yield and nutritive values of legume-grass swards are time and labour saving and can facilitate a site-specific forage management. Nevertheless, in-field measurements, based on canopy reflectance are highly dependent on weather conditions, like, e.g. wind or clouds. This study was conducted to explore the potential of field spectral measurements for a non destructive prediction of dry matter yield (DM), metabolisable energy (ME), ash content (XA), and crude protein (XP), of a binary legume-grass mixture (Trifolium pratense L. and Lolium multiflorum L.) under changing weather conditions. Five different degrees of sky cover were simulated by shadowing measurement plots with layers of cotton to reduce incoming radiation at different growth stages (leaf developing to flowering). Additionally, a halogen lamp was established over the plots to examine the influence of an artificial light source on the spectral response under changing cloud stages. Modified partial least squares (MPLS) regression was used for analysis of the hyperspectral data set (350-2500 nm). Artificial illumination led to spectral interferences of solar radiation and additional light, and hence, partly reduced prediction accuracies. In contrast, prediction accuracy increased, when solar radiation was completely excluded. Coefficients of determination (RSQ_cal) range from 0.87 to 0.94 without artificial illumination and from 0.86 to 0.94 with artificial illumination for DM yield and nutritive values, respectively.     

干旱胁迫条件下两个葡萄品种光合荧光特性的研究

以葡萄品种红地球和新郁的扦插苗作为试材,采用盆栽模拟干旱处理法,测定和对比在不同干旱胁迫条件下两个葡萄品种叶片相对含水量、光合色素含量、光合特性和叶绿素荧光特征参数等指标.结果表明,随土壤相对含水量的减少,两个葡萄品种的叶片相对含水量均呈下降趋势,其中新郁的下降幅度显著小于红地球（P ＜0．05）.与红地球相比,新郁叶片中叶绿素 a、叶绿素 b含量的下降幅度及类胡萝卜素含量的上升幅度均较小.土壤相对含水量15％处理下红地球的净光合速率及土壤相对含水量50％处理的水分利用效率均极显著高于新郁（P＜0．01）.两个葡萄品种的叶绿素荧光特征参数随土壤相对含水量的减少呈现出不同变化趋势,但相同处理下两个葡萄品种各叶绿素荧光指标之间均无显著差异（P ＞0．01）.在干旱胁迫条件下,两个葡萄品种光合荧光特征参数有不同的响应,其中新郁对干旱的适应性强于红地球.