A Three-Year Multimodal Holistic Dataset For Horticultural Tomato Cultivation

Machine learning for the intelligent analysis of 3D printing conditions using environmental sensor data to support quality assurance

We designed and evaluated an assumption-free, deep learning-based methodology for animal health monitoring, specifically for the early detection of respiratory disease in growing pigs based on environmental sensor data. Two recurrent neural networks (RNNs), each comprising gated recurrent units (GRUs), were used to create an autoencoder (GRU-AE) into which environmental data, collected from a variety of sensors, was processed to detect anomalies. An autoencoder is a type of network trained to reconstruct the patterns it is fed as input. By training the GRU-AE using environmental data that did not lead to an occurrence of respiratory disease, data that did not fit the pattern of “healthy environmental data” had a greater reconstruction error. All reconstruction errors were labelled as either normal or anomalous using threshold-based anomaly detection optimised with particle swarm optimisation (PSO), from which alerts are raised. The results from the GRU-AE method outperformed state-of-the-art techniques, raising alerts when such predictions deviated from the actual observations. The results show that a change in the environment can result in occurrences of pigs showing symptoms of respiratory disease within 1–7 days, meaning that there is a period of time during which their keepers can act to mitigate the negative effect of respiratory diseases, such as porcine reproductive and respiratory syndrome (PRRS), a common and destructive disease endemic in pigs.

This research paper explores the world of nearly real time analytics by focusing on methods of combining information obtained from Environmental Sensor data. The study utilized a customized setup consisting of three arrays of sensors connected to Raspberry Pi devices. It. Analyzed a dataset that encompassed various environmental conditions. By utilizing the Random Forest algorithm this research investigated how sensor readings, including temperature, humidity, LPG concentrations, smoke, light intensity and motion detection can be fused together. The methodology used cross-validation to ensure model training while visually presenting the intricate relationships, between environmental parameters. The results demonstrated the performance of the Random Forest model through visualizations showing Out of Bag (OOB) error rates and a comparative analysis of machine learning classifiers. The findings shed light on the potential of combining information from sensors to enable reliable predictions using Environmental Sensor data. This provides a foundation for advancements in analytics and applications related to environmental monitoring.

A fusion framework for occupancy estimation in office buildings based on environmental sensor data

Ultrasonic and light detection and ranging (LiDAR) sensors have been some of the most deeply investigated sensing technologies within the scope of digital horticulture. They can accurately estimate geometrical and structural parameters of the tree canopies providing input information for high-throughput phenotyping and precision horticulture. A review was conducted in order to describe how these technologies evolved and identify the main investigated topics, applications, and key points for future investigations in horticulture science. Most research efforts have been focused on the development of data acquisition systems, data processing, and high-resolution 3D modeling to derive structural tree parameters such as canopy volume and leaf area. Reported applications of such sensors for precision horticulture were restricted to real-time variable-rate solutions where ultrasonic or LiDAR sensors were tested to adjust plant protection product or fertilizer dose rates according to the tree volume variability. More studies exploring other applications in site-specific management are encouraged; some that integrates canopy sensing data with other sources of information collected at the within-grove scale (e.g., digital elevation models, soil type maps, historical yield maps, etc.). Highly accurate 3D tree models derived from LiDAR scanning demonstrate their great potential for tree phenotyping. However, the technology has not been widely adopted by researchers to evaluate the performance of new plant varieties or the outcomes from different management practices. Commercial solutions for tree scanning of whole groves, orchards, and nurseries would promote such adoption and facilitate more applied research in plant phenotyping and precision horticulture.

Recently, an offshore geotechnical investigation was conducted using in situ testing equipment at several proposed offshore platform sites. A motion compensated drilling system was used to drill and handle in situ cone electrometer, vane, and push sampling tools. Laboratory soil testing comprised classification, strength and consolidation tests. Geotechnical engineering analyses were made for pile supported structures. Soil and foundation conditions varied from soft clays to hard clays and dense sands. Soils data from in situ cone electrometer tests are correlated with soil test results. The ratio of sleeve friction to cone resistance, termed the friction ratio, is correlated with general soil types. A soil classification chart is developed and shows that friction ratio can be used to identify soil types. Several approaches are presented relating cone resistance to untrained shear strength using the cone factor, Nk. The cone factor is related to plasticity of cohesive soils and compared with published results. Pile end bearing, computed directly from cone resistance, is compared to end bearing derived from typical pile capacity procedures. Sleeve friction measurements in both clay and sand are analyzed and compared to pile friction computed from pile capacity procedures. Using cone electrometer data for predicting pile drivability is briefly discussed. Results showed that cone electrometer testing provides more accurate soils data than just samples alone. Combining sleeve friction and liquidity index may provide information on the stress history of cohesive soils. The cone factor is not a unique number for a given soil, it varies with the method used to determine the factor. Cone data can be used in pile drivability predictions. Recommendations are made about selecting suitable combinations of cone soundings and sample boreholes for offshore geotechnical investigations. Introduction A major geotechnical study was recently made to determine regional and site specific marine soil conditions for proposed offshore platforms. Soil conditions were investigated by drilling boreholes, recovering soil samples, making in situ cone electrometer (CPT) soundings, and conducting in situ vane tests. Soil samples were tested in the laboratory for classification, strength, and compressibility. In situ test data and laboratory data were used in the engineering analysis for pile supported platforms. Laboratory soils data are compared to data collected from the in situ cone electrometer and vane tests. Correlations are made between various cone parameters (friction ratio, cone factor, and cone resistance) and typical soil test results (plasticity, strength, and soil type). Unit pile capacity values derived from several pile capacity methods are compared to cone resistance and sleeve friction Results from this study show that incorporating in situ cone electrometer and vane tests with soil samples improve the knowledge of the soil conditions at a particular offshore site. Description Of Equipment. The M/V SURVEYOR used during this study is a 249 ft. long (76 m), specially designed, geotechnical drilling vessel (13). The vessel is equipped with a six anchor mooring spread capable of anchoring in water depths up to about 800 ft. (245 m). A bow thruster assists in maneuvering, positioning, and anchoring.

Editorial and News

Deep learning analysis of mobile physiological, environmental and location sensor data for emotion detection

<h3>Background and goals</h3> Lake Erie Concord growers have access to high-resolution spatial soil and production data but lack protocols and information on the optimum time to collect these data. This study intends to provide clearer information regarding the type and timing of sensor information to support in-season management. <h3>Methods and key findings</h3> A three-year study in a 2.6 ha vineyard collected yield, pruning mass, canopy vigor and soil data, including yield and pruning mass from the previous year, at 321 sites. Stepwise linear regression and random forest regression approaches were used to model site-specific yield and pruning mass using spatial historical production data, multi-temporal in-season canopy vigor and soil data. The more complex yield elaboration process was best modelled with non-linear random forest regression while the simpler development of pruning mass was best modelled by linear regression. <h3>Conclusions and significance</h3> Canopy vigor in the weeks preceding bloom was the most important predictor of the current season’s yield and should be used to generate stratified sampling designs for crop estimation at 30 days after bloom. In contrast, pruning mass was not well predicted by canopy vigor, even late-season canopy vigor, which is widely advocated for pruning mass estimation in viticulture. The previous year’s pruning mass was the dominant predictor of pruning mass in the current season. To model pruning mass going forward, the best approach is to start measuring it. Further work is still needed to develop robust, local site-specific yield and pruning mass models for operational decision-making in concord vineyards.

Earth and Space Science Open Archive PosterOpen AccessYou are viewing the latest version by default [v2]Hypnos Board: A Low-Cost All-In-One Solution for Environment Sensor Power Management, Data Storage, and Task SchedulingAuthorsBrysonGotoiDBaoNguyeniDJohnSelkeriDChetUdelliDSee all authors Bryson GotoiDCorresponding Author• Submitting AuthorOregon State UniversityiDhttps://orcid.org/0000-0002-9224-3290view email addressThe email was not providedcopy email addressBao NguyeniDOregon State UniversityiDhttps://orcid.org/0000-0002-5692-3176view email addressThe email was not providedcopy email addressJohn SelkeriDOregon State UniversityiDhttps://orcid.org/0000-0001-9751-6094view email addressThe email was not providedcopy email addressChet UdelliDOregon State UniversityiDhttps://orcid.org/0000-0001-5815-8319view email addressThe email was not providedcopy email address

This paper describes the design and implementation of a rail-guided mobile robot-based monitoring system that can be used for autonomous monitoring of the facilities and rapid response to the on-site event. It is necessary to improve the safety and efficiency of the monitoring system when applying a robot system, and the implementation of intelligent functions can increase the level of automation to facilitate operation. In order to increase driving safety and lower the level of control, a two-track rail structure of circular pipes, U-shaped wheels, and a differential gear are used to develop a driving system that enables rotational path driving even with forward and backward movement. For the proper monitoring of facility conditions, high-temperature occurrence, and environmental quality, cameras (RGB and thermal imaging) and air quality sensors are chosen by considering the range of the monitoring site and target subjects. Data communication between the robot and the remote control room(a remote server) is built up to patrol in a planned schedule and deliver acquired video streams and environmental sensor data. Emergency alarms about high temperatures and the abnormality of air conditions can be generated by processing the transferred data. Additionally, deep network-based detection services on video data are implemented on the server for the detection of emergency situations; fall downs. Integrating the developed driving system, image/sensor data communication, and alarm function through data analysis in an operating framework reduces management work through automatic patrol and enables efficient on-site response when an alarm occurs. The validity of the proposed system is demonstrated by building and operating the system in the existing multi-use facility. The automatic patrol function and the manual operation function are performed through a test operation similar to the facility monitoring task of a human operator. The operator can control the robot to move to a desired position along the path, and by manipulating the camera module, the operator can check the on-site situation via a video stream The environmental sensor data is also transferred to the server and stored during operation, and the robot normally completes the automatic patrol task and returns to the charging station. In a simulation experiment to verify the detection alarm service, the test shows that a human falling down is detected even in the field.

Idaho ranks in the top 10 in the U.S. for dairy, potato, barley, hay, sugar beet, corn silage, and dry bean production. The highest producing areas in the state for these commodities are in southern Idaho where irrigation is necessary. Water quality is impaired in the region but has been improving due to some best management practice implementation. To measure progress in producer efforts for reducing erosion and runoff, appropriate methods need to be identified. The soils in this region are prone to crusting, have low organic matter, and are high in calcium carbonates making these soils unique to much of the U.S. Thus, the overall goal of this project was to identify the best method for the assessment of aggregate stability properties. Two study sites were located on the USDA-ARS Northwest Irrigation and Soils Research Laboratory in Kimberly, Idaho, and were established in 2013 (Long-Term Manure) and 2016 (Cover Crop). A randomized complete block design with four replicates was used for the Long-Term Manure study; plots were under different manure and fertilizer treatments. Briefly, the study design consisted of eight treatments: three rates solid dairy manure applied annually or biannually, a control (no fertility additions, and inorganic fertilizer only. The cover crop study was set up as a split-plot design with four replications with tillage as the main experimental factor (direct seeding vs disk/chisel plow) and treatment as the subfactor (cover crop with manure, cover crop without manure, no cover crop with manure, no cover crop without manure). Both studies were assessed for soil physical properties in late summer 2020. Three methods were used to measure soil aggragate stability: wet sieving, a hybrid method utilizing a Cornell Sprinkle Infiltrometer (CSI; van Es and Schindelbeck, 2001), and the Slakes mobile application (Fajardo & McBratney, 2019). For the wet sieving method, samples were submerged in water and oscillated at 30 oscillations min^-1 for 10 min. A CSI was used to measure soil aggregate stability at the heights of 30, 90, and 150 cm. The CSI operated at a constant rainfall rate of 2 cm of rainfall per 10 min of operation. Soils data were analyzed using a linear mixed-effects model (lme function) using the nlme package in R. No differences in aggregate stability were found when the wet sieving method was used among treatments for both studies. However, the CSI hybrid method was found to be statistically different at an operational height of 30 cm among treatments at mean values of 3.73 ± 0.36 mm (cover crop with manure), 3.67 ± 0.38 mm (cover crop only), and 3.70 ± 0.30 mm (manure only) as compared to the control (3.13 ± 0.46 mm) for the Cover Crop study. There were also statistical differences found at an operational height of 90 cm between cover crop + manure (3.14 ± 0.86 mm) and cover crop only (2.54 ± 0.54 mm). However, none of the treatments were different from the control. Further, mean weight diameters (MWD) were different between the CSI and wet aggregate seiving method. Average MWD for the wet seiving method in the Cover Crop study ranged from 1.1 ± 0.40 mm (control) to 1.5 ± 0.32 mm (cover crop + manure). For the hybrid CSI method, MWD measured under the heighest operational height (150 cm) were the closest to the wet seiving method; MWD ranged from 2.0 ± 0.62 mm (control) to 2.4 ± 0.54 mm (cover crop + manure). These initial results<b> </b>not only have implications on which methods are best for assessing progress, but also what management practices can be utilized to decrease water erosion from irrigated cropland. Under these soil conditions, the CSI hybrid method was more sensitive to management change than the traditional wet seiving method. The CSI hybrid method better captures and assesses typical erosion processes occuring in irrigated crop land.

In order to model growth, stress reactions, and ecosystem dynamics, plant digital twins’ virtual representations of real-time plant systems integrate biological, environmental, and agronomic data. These models have revolutionary potential in climate adaption, sustainability planning, and precision agriculture. However, its implementation presents difficult governance and ethical issues. Data ownership, privacy, and justice are important issues, particularly when data frequently comes from local communities and farms but is owned by organizations or companies. Decision-making procedures may be obscured and smallholder practices marginalized by algorithmic bias and opaque AI models. Another concern is ecological oversimplification, in which digital systems put efficiency ahead of local resilience and biodiversity. The chapter promotes value-sensitive design and multi-stakeholder governance in order to solve these problems. It also highlights responsible innovation that is governed by the AREA framework Anticipation, Reflection, Engagement, and Action.

At present, the environmental monitoring of the substation suffers from complex wiring, low intelligence, high staff work intensity, and a lack of information-based overall management. Moreover, the distribution of substations is relatively scattered, making it complex and costly to set up a dedicated communication network. In response to these problems, this paper combines modern communication technology, sensor technology, and mobile intelligent terminal development technology to study an overall information-based substation environmental monitoring system. The monitoring system proposed in this paper includes a main controller, a data collection terminal, and a mobile communication terminal. The environmental data collected by the main controller is sent to the server through the communication method of subscription and substation using wireless communication technology, and the interface of the mobile communication terminal can display indoor environmental monitoring data. When the environmental data of the Substation exceeds the set threshold value to issue an early warning alert, the user can control it remotely through the mobile communication terminal to improve the indoor environment of the Substation. The system has a simple operation interface, low power consumption, and strong expansion compatibility, which effectively realizes remote monitoring and control of the substation environment and has good engineering application value.

Regarding the data collection process for a comprehensive automated environmental monitoring and precaution platform, this paper first analyses the key issues and challenges, including setting of monitoring targets, heterogeneity of monitoring equipments, diversity of communication methods, and online monitoring. Based on this, an embedded real-time environmental data collecting system is proposed. The contributions of the paper are as follows: we have designed an embedded environmental data collector which supports three collecting modes; we have proposed a novel integration technique for heterogeneous monitoring devices and an adaptive internetworking approach. The proposed system is a component of a distributed environmental monitoring platform which will be deployed in Guangzhou city.