Search

Nonlinear manifold learning is a popular dimension reduction method that determines large and high dimensional datasets’ structures. However, these nonlinear manifold learning methods, including isomap and locally linear embedding, are sensitive to noise. In this paper, we focus on the noisy nonlinear manifold learning method, such as Isomap. The main problem of the Isomap is sensitivity to noise. Our proposed new method noise removal isomap with a classification (NRIC), is based on the local tangent space alignment (LTSA) algorithm with classification techniques to remove noises and optimize neighborhood structure Isomap. The primary purpose of the NRIC is to increase efficiency, reduce noise, and improve the performance of the graph. Experiments on the real-world datasets have shown that the NRIC method outperforms efficiently and maintains an accurate low dimensional representation of the noisy nonlinear manifold learning data. The results show that LTSA with classification techniques provides high accuracy, mean-precision, mean-recall, and areas under the (ROC) curve (AUC) of the high dimensional datasets and optimizes the graphs.

The classical Isomap is the most common unsupervised nonlinear manifold method and widely being used in visualizations and dimension reductions. However, when it applied to real-world datasets, it shows shortcomings for the shortest path between all pairs of data points, which are based on the nearest neighborhood $G$ graph via the Dijkstra algorithm, which makes it a very time-consuming step. The other critical problem is the classical Isomap has a lack of topological stability on the nearest neighborhood $G$ graph. In this paper, we propose a novel technique called the FastIsomapVis for the above problems of the classical Isomap. The FastIsomapVis uses hierarchal divide, conquer, and combine approach through two algorithms, which are randomized division tree (KD-tree) and Dijkstra Buckets Double (DKD). The primary aim of the FastIsomapVis is to increase the efficiency and accuracy of the graph. This research paper focuses on transforming the high dimensional datasets into a low dimensional Isomap visualization. The FastIsomapVis makes it easy to construct an accurate $K$ nearest neighborhood $G$ graph and scale high dimensional data points into low dimensional space. Our proposed method is compared to the classical Isomap to verify its effectiveness and provide highly authentic results of the high dimensional datasets. The finding of the current study shows that our proposed method is much fastened than classical Isomap.

Greenhouse plant science assays have been impacted by microclimates which causes significant level of noise to plant growth measurement data. Researchers and scientist have been randomizing pots locations, which helps to re-distribute the noise, but does not remove the noise. The impacts from microclimates can be eliminated by shuffling plants, but there has been no study on the optimization of shuffling pattern, such as the frequency and moving distance for the pots. It is important to quantitatively study the microclimates in the greenhouse, so we can optimize the shuffling pattern accordingly. The aim of this study was to propose a computer modeling approach for simulating microclimate in the greenhouse, and then use the simulation result to optimize pot movement distance and frequency. A computational greenhouse model was developed using inputs from real design, materials and location of a Purdue Lily greenhouse in West Lafayette, Indiana. Microclimate variables, including ambient temperature and lighting radiation over 24 h and 7 days were predicted with the simulation model. Thermometers and lighting sensors were also distributed in the greenhouse for the ground-truth measurements over a seven-day period. Comparison of measured microclimate variables with predicted variables obtained from the computational model demonstrated that the simulation model could precisely predict temperatures and light radiation at any time, and at different positions in the greenhouse. Optimized pot movement frequency and distance were then determined with the simulation result. The new shuffling pattern can remove over 90% of the microclimate variance but could save more than 95% shuffling efforts compared with non-stop movement.

During recent years, hyperspectral imaging systems have been widely applied in the greenhouses for plant phenotyping purposes. Current systems are typically designed as either top view or side view imaging mode. Top view is an ideal imaging angle for top leaves with flat leaf surfaces. However, most bottom leaves are either blocked or shaded. From side view, the entire plant structure is viewable. However, most leaf surfaces are not facing the camera, which impacts measurement quality. Besides, there could be advantages with certain tilted angle(s) between top view and side view. It’s interesting to explore the impact of different imaging angles to the phenotyping quality. For this purpose, a swing hyperspectral imaging system capable of capturing images at any angle from side view (0°) to top view (90°) by rotating the camera and the lighting source was designed. Corn plants were grown and allocated into 3 different treatments: high nitrogen (N) and well-watered (control), high N and drought-stressed, and low N and well-watered. Each plant was imaged at 7 different angles from 0° to 90° with an interval of 15°. The soil plant analysis development (SPAD) values and relative water content (RWC) ground truth measurements were used to establish treatment effects. The results showed that averaged plant-level Normalized Difference Vegetation Index (NDVI) values of plants in different treatments changed at different imaging angles. The results also indicated that for pixel-level NDVI distributions, the titled imaging angle of 75° was optimal to distinguish different water treatments, whereas, the tilted imaging angle of 15° was optimal to distinguish different N treatments. For pixel-level RWC distributions, the distribution difference between different water treatments was larger at higher imaging angles.

With being rapid increasing population in worldwide, the need for satisfactory level of crop production with decreased amount of agricultural lands. Machine vision would ensure the increase of crop production by using an automated, non-destructive and cost-effective technique. In last few years, remarkable results have been achieved in different sectors of agriculture. These achievements are integrated with machine learning techniques on machine vision approach that cope with colour, shape, texture and spectral analysis from the image of objects. Despite having many applications of different machine learning techniques, this review only described the statistical machine learning technologies with machine vision systems in agriculture due to broad area of machine learning applications. Two types of statistical machine learning techniques such as supervised and unsupervised learning have been utilized for agriculture. This paper comprehensively surveyed current application of statistical machine learning techniques in machine vision systems, analyses each technique potential for specific application and represents an overview of instructive examples in different agricultural areas. Suggestions of specific statistical machine learning technique for specific purpose and limitations of each technique are also given. Future trends of statistical machine learning technology applications are discussed.

High-throughput imaging technologies have been developing rapidly for agricultural plant phenotyping purposes. With most of the current crop plant image processing algorithms, the plant canopy pixels are segmented from the images, and the averaged spectrum across the whole canopy is calculated in order to predict the plant&rsquo, s physiological features. However, the nutrients and stress levels vary significantly across the canopy. For example, it is common to have several times of difference among Soil Plant Analysis Development (SPAD) chlorophyll meter readings of chlorophyll content at different positions on the same leaf. The current plant image processing algorithms cannot provide satisfactory plant measurement quality, as the averaged color cannot characterize the different leaf parts. Meanwhile, the nutrients and stress distribution patterns contain unique features which might provide valuable signals for phenotyping. There is great potential to develop a finer level of image processing algorithm which analyzes the nutrients and stress distributions across the leaf for improved quality of phenotyping measurements. In this paper, a new leaf image processing algorithm based on Random Forest and leaf region rescaling was developed in order to analyze the distribution patterns on the corn leaf. The normalized difference vegetation index (NDVI) was used as an example to demonstrate the improvements of the new algorithm in differentiating between different nitrogen stress levels. With the Random Forest method integrated into the algorithm, the distribution patterns along the corn leaf&rsquo, s mid-rib direction were successfully modeled and utilized for improved phenotyping quality. The algorithm was tested in a field corn plant phenotyping assay with different genotypes and nitrogen treatments. Compared with the traditional image processing algorithms which average the NDVI (for example) throughout the whole leaf, the new algorithm more clearly differentiates the leaves from different nitrogen treatments and genotypes. We expect that, besides NDVI, the new distribution analysis algorithm could improve the quality of other plant feature measurements in similar ways.

Nowadays, Isomap is one of the most popular nonlinear manifold dimension reductions which have applied to the real-world datasets. However, it has various limitations for the high-dimensional and large-scale dataset. Two main limitations of the Isomap are: it may make incorrect links in the neighborhood graph G and high computational cost. In this paper, we have introduced a novel framework, which we called the FastIsomap. The main purpose of the FastIsomap is to increase the accuracy of the graph by using two state-of-the-art algorithms: a randomized division tree and NN-Descent. The basic idea of FastIsomap is to construct an accurate approximated KNN graph from millions and hundreds of dimensional’ data points and then project the graph into low-dimensional space. We have compared the FastIsomap framework with the existing Isomap algorithm to verify its efficiency and performance, which provided accurate results of the high and large-dimensional datasets.

Wild blueberry crop yields are dependent on heavy agrochemical applications to control weeds competing with the crop. Goldenrod is a creeping herbaceous perennial weed that occurred in 90% of wild blueberry fields surveyed in Nova Scotia. A colour co-occurrence matrices (CCMs) based algorithm can be used for spot-application of herbicide on goldenrod within wild blueberry fields. The objective of this study was to analyse the effect of different parameters on computational complexity and goldenrod identification accuracy of CCMs in wild blueberry cropping system. An image acquisition graphical user interface (GUI) and CCMs based textural analysis algorithm were developed in Microsoft Visual® C# programming language. The GUI was used to acquire 2244 area of interest images along with a set of 2244 full frame images from two different wild blueberry fields in central Nova Scotia, Canada. Six image intensity levels, seven image sizes, and three CCMs were used to for the study. The results indicated that intensity levels and image size significantly influenced the computational requirements of CCMs. Images with 256 or 128 intensity levels could be used as these levels correctly classified 94% and 89% of test observations respectively. The processing times were increased from 535 μs to 10,650 μs and 9864 μs to 63,750 μs as the intensity increased from 8 to 256 levels and image size increased from 16 × 16 to 1024 × 1024 pixels, respectively. The time required for textural feature extraction was not statistically significant for different image sizes used in this study. Overall, the results indicated that intensity levels of 128 or 256, a unit image size of 128 × 128 pixels, and saturation colour plane alone or in combination with hue can help to minimise the processing burden without compromising the classification accuracy for real-time applications.

The farinograph and mixograph are the most commonly used empirical instruments to determine three parameters: 1) characterize dough rheology; 2) evaluate dough performance during processing; 3) and quality control. Maize, chickpea, and soybean flours ranging from 10% to 50% (in 10% increments) were blended with wheat flour to prepare composite flours for rheological studies. Mixographic results indicated that as flour percentages increased among treatments, peak times and mixing tolerance indices increased. Farinographic results indicated that as flour percentages increased, an increase in water absorption with a concurrent decrease in development and dough stability times due to less gluten content occurred.

Aerial imaging technologies have been widely applied in agricultural plant remote sensing. However, an as yet unexplored challenge with field imaging is that the environmental conditions, such as sun angle, cloud coverage, temperature, and so on, can significantly alter plant appearance and thus affect the imaging sensor’s accuracy toward extracting plant feature measurements. These image alterations result from the complicated interaction between the real-time environments and plants. Analysis of these impacts requires continuous monitoring of the changes through various environmental conditions, which has been difficult with current aerial remote sensing systems. This paper aimed to propose a modeling method to comprehensively understand and model the environmental influences on hyperspectral imaging data. In 2019, a fixed hyperspectral imaging gantry was constructed in Purdue University’s research farm, and over 8000 repetitive images of the same corn field were taken with a 2.5 min interval for 31 days. Time-tagged local environment data, including solar zenith angle, solar irradiation, temperature, wind speed, and so on, were also recorded during the imaging time. The images were processed for phenotyping data, and the time series decomposition method was applied to extract the phenotyping data variation caused by the changing environments. An artificial neural network (ANN) was then built to model the relationship between the phenotyping data variation and environmental changes. The ANN model was able to accurately predict the environmental effects in remote sensing results, and thus could be used to effectively eliminate the environment-induced variation in the phenotyping features. The test of the normalized difference vegetation index (NDVI) calculated from the hyperspectral images showed that variance in NDVI was reduced by 79%. A similar performance was confirmed with the relative water content (RWC) predictions. Therefore, this modeling method shows great potential for application in aerial remote sensing applications in agriculture, to significantly improve the imaging quality by effectively eliminating the effects from the changing environmental conditions.

Spatial variations in wild blueberry plant height pose a serious challenge for the operator to maintain the optimum harvester picking head height. Harvester head adjustment based on plant height increases harvestable fruit yield and quality while preventing plant pulling. An advanced Ultrasonic Plant Height Measurement System II (UPHMS II) was developed and incorporated into a commercial mechanical harvester. The developed system consisted of three ultrasonic sensors covering the width of the harvester head, a real-time kinematics global positioning system (RTK-GPS), custom built software, and a rugged computer. The custom software acquired and processed the ultrasonic sensing data in real-time during mechanical harvesting. Four wild blueberry fields were selected in central Nova Scotia to evaluate the performance of the developed system. Forty eight experimental plots were randomly constructed within four fields and wild blueberry plant heights were recorded manually prior to harvest. The UPHMS II was tested and evaluated to estimate plant height. The manual plant height measurements were compared with ultrasonically sensed data to ensure the accuracy of the developed system. A previous system (UPHMS I) comprising of one ultrasonic sensor was also tested and evaluated. Results of regression and scatter plots revealed that the UPHMS II was able to sense plant height in real-time more accurately with root mean square error (RMSE) of 1.7 cm when compared with the UPHMS I (RMSE = 5.7 cm). The UPHMS II equipped with three sensors covered the complete width of the harvester (0.91 m), which showed higher accuracy compared to the UPHMS I.

Unfortunately, Pakistan is facing severe energy crises from the last decade due to increasing population and heavily dependence on the import of the fossil fuels. The electricity breakdown/blackouts was 14–18 h in rural areas and 8–10 h in urban areas. This situation has drastically affected the residential, industrial and commercial sector of the country. Currently, it is a big challenge for the government to sustain the future energy supply of the country. Under these circumstances, the research have been increased for the exploration of renewable energy sources in the country to fulfill the deficit scenario of the country. Fortunately, Pakistan is lying in such a geographical location where potential for all the renewable energy sources exists abundantly viz. solar, wind, biogas production, bio-energy from biomass and feedstock, mini and micro hydel. About 81 million ton/annum biomass production has a huge potential to produce enough bio-energy by employing different technologies viz. combustion, gasification, pyrolysis, trans-esterification process etc. Similarly, available dung from 72 million animals (cows and buffalos) and available poultry droppings from 785 million poultry birds can produce considerable biogas to produce heat and electricity. Pakistan is also blessed with 5.5 Wh m −2 d −1 solar insolation with annual mean sunshine duration of 8–10 h d −1 throughout the country. Wind speed 5–7 m s −1 persists in the coastal regions of Sindh and Baluchistan provinces with more than 20,000 MW of economically feasible wind power potential. The worldwide utilization of renewable energy is already on a fast track, however, Pakistan is still lacking in adaptation of these blessed technologies. Therefore, it is a high time that the government should launch a comprehensive program for R&D, commercialization and awareness of the community by incentivizing for the wide scale adaption of renewable energy technologies for the sustainable energy supply of the country in future.

The spectral reflectance signature of the plants contains rich information about their biophysical, physiological and chemical characteristics. Learning the patterns directly from the plant spectra is critical for predictive plant phenotyping applications. In this study, we developed an end-to-end deep learning model based on 1-D convolutional neural networks, called DeepRWC, to predict the relative water content (RWC) of plants directly from mean spectral reflectance. The proposed model incorporated a modified Inception module to learn multi-scale spectral features at different abstraction levels. To train the proposed network, maize plants grown under well-watered and drought-stressed treatments were imaged using push-broom style, top-view, visible near-infrared (VNIR) hyperspectral camera in the greenhouse environment. Results showed that our proposed model achieved good performance with an R2 of 0.872 for RWC. The performance of the developed model was compared with two standard approaches, partial least squares regression (PLSR) and support vector machine regression (SVR) on two external test datasets. The quantitative analysis showed that the DeepRWC outperformed both linear (PLSR) and non-linear (SVR) approaches by achieving the lowest RMSE and better R2 value on all test datasets included in the study. Our proposed DeepRWC eliminated the need for any preprocessing or dimensionality reduction, as in the case of other standard techniques (PLSR/SVR). These results confirmed the ability of DeepRWC to better predict the RWC of plants using spectral reflectance signature.

The analysis of the rhythm of leaf movement is a simple yet effective method to quantify the impacts of external (e.g. abiotic stress) and/or internal (e.g. gene mutations) perturbations on plant growth. We developed an automated monitoring system to quantify leaf movement using time-lapse imaging and a subsequent leaf-tracking algorithm. The leaf-tracking algorithm was based on dense optical flow algorithm to directly record temporal motion events. The algorithm measures motion directly, rather than detecting leaf or cotyledon tip in every image, so multiple leaves, including occluded leaves, can be measured simultaneously. To test the monitoring system, wild-type and drought-tolerant mutant genotypes of Arabidopsis (Arabidopsis thaliana) were subjected to a combinatorial two water and two nitrogen levels. High-frequency time-lapse images were acquired from top view for little over 6 consecutive days at a frequency of 4 min. Results showed that nitrogen and water treatments elicited differences in mean plant displacement in both genotypes. It also showed significant differences among the two different genotypes in the mean displacement when plants were under water or nitrogen stress. These results confirmed the new monitoring system’s ability to discern environmental and genotypic differences in plant response.

During recent years, portable plant phenotyping instruments have become increasingly important to monitor conditions of plant health non-destructively in the greenhouse and field environments. These devices, such as the Soil Plant Analysis Development (SPAD) meter, leverage indices that represent leaf chlorophyll content due to its strong correlation with leaf nitrogen (N) content. However, instruments such as SPAD meters are expensive and measure only individual, restricted leaf regions per data capture. In this publication, we developed a Leaf Scanner device to analyze the chlorophyll content distributions of whole leaves with greater efficiency and precision. The validating samples for this device were top-collared corn leaves grown under high and low N treatments in a greenhouse. For each region of a corn leaf, this device rapidly flashed visible and near infrared (NIR) LEDs to obtain the visible and NIR transmittance images of leaves. These images were summarized pixel-wisely into the Green NDVI index. A sufficient high framerate permitted continuous collection of regional index images. Using image registration techniques, these regional images were stitched together into a ‘leaf panorama’. The total pixel amount of each leaf panorama, thus, served as a substitute for leaf area. A Minolta SPAD-502Plus meter collected ground-truth measurements along the length of each leaf sample. The results showed that there was a strong correlation between the average Leaf Scanner’s measurements and averaged SPAD values (R2 = 0.92), and the Leaf Scanner was able to clearly detect differences between high and low fertilized samples in terms of chlorophyll content and leaf area. Furthermore, this Leaf Scanner device enabled us to study the chlorophyll content distributions on the plants under different treatments.

Wild blueberry ( Vaccinium angustifolium Ait.) is a perennial rhizomatous low shrub and mostly mechanically harvested. The operator of the harvester needs to maintain the optimum height of harvester‘s head according to the plant height for better yield and quality while decreasing plant pulling. An ultrasonic on-the-go plant height measurement system (UPHMS II) was developed and compared with previous height measurement system (UPHMS I). A real-time kinematics differential global positioning system (RTK-GPS), a custom program and a ruggedized computer and both plant height sensing system were mounted on a commercial mechanical harvester for real-time plant height measurement during harvesting. A custom program was developed to acquire and process ultrasonic sensing data in real-time from both UPHMS I and UPHMS II simultaneously. Two wild blueberry fields were selected in central Nova Scotia to evaluate the performance of both UPHMS I and UPHMS II. Manually measured plant height values from 24 plots were compared with real-time measured values of two systems. UPHMS II performed better to predict wild blueberry plant height with higher accuracy than UPHMS I. The RMSE of the sensed height of UPHMS I and UPHMS II were 6.4 cm and 1.6 cm, respectively. UPHMS II can be an economic option to control wild blueberry harvester head automatically to increase harvester and operator‘s efficiency. Real-time and accurate sensing of plant height is the first step toward the automation of the wild blueberry harvester. Refinements for the optimum head height according to the plant height is required for future studies.