Optimizing Strawberry Disease and Quality Detection with Vision Transformers and Attention-Based Convolutional Neural Networks.

Machine learning and computer vision have proven to be valuable tools for farmers to streamline their resource utilization to lead to more sustainable and efficient agricultural production. These techniques have been applied to strawberry cultivation in the past with limited success. To build on this past work, in this study, two separate sets of strawberry images, along with their associated diseases, were collected and subjected to resizing and augmentation. Subsequently, a combined dataset consisting of nine classes was utilized to fine-tune three distinct pretrained models: vision transformer (ViT), MobileNetV2, and ResNet18. To address the imbalanced class distribution in the dataset, each class was assigned weights to ensure nearly equal impact during the training process. To enhance the outcomes, new images were generated by removing backgrounds, reducing noise, and flipping them. The performances of ViT, MobileNetV2, and ResNet18 were compared after being selected. Customization specific to the task was applied to all three algorithms, and their performances were assessed. Throughout this experiment, none of the layers were frozen, ensuring all layers remained active during training. Attention heads were incorporated into the first five and last five layers of MobileNetV2 and ResNet18, while the architecture of ViT was modified. The results indicated accuracy factors of 98.4%, 98.1%, and 97.9% for ViT, MobileNetV2, and ResNet18, respectively. Despite the data being imbalanced, the precision, which indicates the proportion of correctly identified positive instances among all predicted positive instances, approached nearly 99% with the ViT. MobileNetV2 and ResNet18 demonstrated similar results. Overall, the analysis revealed that the vision transformer model exhibited superior performance in strawberry ripeness and disease classification. The inclusion of attention heads in the early layers of ResNet18 and MobileNet18, along with the inherent attention mechanism in ViT, improved the accuracy of image identification. These findings offer the potential for farmers to enhance strawberry cultivation through passive camera monitoring alone, promoting the health and well-being of the population.

Towards Sustainable Protein Sources: The Thermal and Rheological Properties of Alternative Proteins.

Reducing meat consumption reduces carbon emissions and other environmental harms. Unfortunately, commercial plant-based meat substitutes have not seen widespread adoption. In order to enable more flexible processing methods, this paper analyzes the characteristics of commercially available spirulina, soy, pea, and brown rice protein isolates to provide data for nonmeat protein processing that can lead to cost reductions. The thermal and rheological properties, as well as viscosity, density, and particle size distribution, were analyzed for further study into alternative protein-based food processing. The differential scanning calorimetry analysis produced dry amorphous-shaped curves and paste curves with a more distinct endothermic peak. The extracted linear temperature ranges for processing within food production were 70-90 °C for spirulina, 87-116 °C for soy protein, 67-77 °C for pea protein, and 87-97 °C for brown rice protein. The viscosity analysis determined that each protein material was shear-thinning and that viscosity increased with decreased water concentration, with rice being an exception to the latter trend. The obtained viscosity range for spirulina was 15,100-78,000 cP, 3200-80,000 cP for soy protein, 1400-32,700 cP for pea protein, and 600-3500 cP for brown rice protein. The results indicate that extrusion is a viable method for the further processing of protein isolates, as this technique has a large temperature operating range and variable screw speed. The data provided here can be used to make single or multi-component protein substitutes.

Solar photovoltaic wood racking mechanical design for trellis-based agrivoltaics.

Using a trellis to plant vegetables and fruits can double or triple the yield per acre as well as reduce diseases/pests, ease harvesting and make cleaner produce. Cultivars such as cucumbers, grapes, kiwi, melons, peas, passion fruit, pole beans, pumpkins, strawberries, squash, and tomatoes are all grown with trellises. Many of these cultivars showed increased yield with partial shading with semi-transparent solar photovoltaic (PV) systems. To further increase the efficiency of trellis-based growing systems, this study investigates novel low-cost, open-source, sustainable, wood-based PV racking designs for agrivoltaic applications. Design calculations are made to ensure these racks exceed Canadian building code standards, which with snow loads surpass those of most of the world. A complete bill of materials, fabrication instructions, and proof-of-concept prototypes are provided for three system topographies (sloped, T-shaped and inverse Y) along with economic analysis. In addition, to being cost competitive, the designs can act as trellis supports and be used for irrigation/fertigation purposes. The results indicate that these racking structures have enormous promise both agriculturally and energetically. If employed on only grape farms inside Canada, 10 GW of PV potential is made available, which is more than twice the total current installed PV in Canada.

Finding Ideal Parameters for Recycled Material Fused Particle Fabrication-Based 3D Printing Using an Open Source Software Implementation of Particle Swarm Optimization.

As additive manufacturing rapidly expands the number of materials including waste plastics and composites, there is an urgent need to reduce the experimental time needed to identify optimized printing parameters for novel materials. Computational intelligence (CI) in general and particle swarm optimization (PSO) algorithms in particular have been shown to accelerate finding optimal printing parameters. Unfortunately, the implementation of CI has been prohibitively complex for noncomputer scientists. To overcome these limitations, this article develops, tests, and validates PSO Experimenter, an easy-to-use open-source platform based around the PSO algorithm and applies it to optimizing recycled materials. Specifically, PSO Experimenter is used to find optimal printing parameters for a relatively unexplored potential distributed recycling and additive manufacturing (DRAM) material that is widely available: low-density polyethylene (LDPE). LDPE has been used to make filament, but in this study for the first time it was used in the open source fused particle fabrication/fused granular fabrication system. PSO Experimenter successfully identified functional printing parameters for this challenging-to-print waste plastic. The results indicate that PSO Experimenter can provide 97% reduction in research time for 3D printing parameter optimization. It is concluded that the PSO Experimenter is a user-friendly and effective free software for finding ideal parameters for the burgeoning challenge of DRAM as well as a wide range of other fields and processes.

Low-cost air, noise, and light pollution measuring station with wireless communication and tinyML.

Different types of environmental pollution cause negative consequences to ecosystems throughout the globe, which humanity is now trying to mitigate. It is necessary to know the level of pollution problems in the immediate environment, to evaluate the impact of human activities, and mitigation strategies necessary to ensure habitability. For this reason, in this work, a low-cost pollution measurement station for outdoor or indoor use is proposed and developed that measures air pollution (particulate matter and CO2), noise (level and direction), light pollution (power and multispectral), and also relative humidity and ambient temperature. The system stores the data in an SD memory or transmits data in real-time to the internet via WiFi. The purposes of the system are to be used in environmental studies, to deploy monitoring networks, or to ensure the habitability of a living or working space. The prototype integrates the measurement of the different sources of contamination in a single compact device at USD$ 628.12 without sacrificing measurement accuracy. The system is validated for each variable with reference equipment, obtaining an average error of approximately 2.67% in the measurement of all the variables measured. The system is easy to assemble and has an option for power supply using solar photovoltaic devices and an alternative for connection to 2G/3G mobile networks.

Open source scientific bottle roller.

Proprietary bottle rolling systems automate some laboratory applications, however, their high costs limit accessibility. This study provides designs of an open source bottle roller that is compatible with distributed digital manufacturing using 3-D printed parts and readily-available commercial components. The experimental results show that the open source bottle roller can be fabricated for CAD$210 (about USD$150) in materials, which is 86% less expensive than the most affordable proprietary bottle roller on the market. The design, however, is more robust with enhanced capabilities. The design can be adapted to the user's needs, but is already compatible with incubators with a low profile (dimensions 50 cm x46 cm x8.8 cm) and capable of being operated at elevated temperatures. The systems can be adjusted to revolves from 1 to 200 RPM, exceeding the rotational speed of most commercial systems. The open source bottle roller as tested has a capacity greater than 1.2 kg and can roll twelve 100 mL bottles simultaneously. Validation testing showed that it can operate for days at 80 RPM without human intervention or monitoring for days at both room temperature and elevated temperatures (50 °C). Future work includes adapting the designs for different sizes and for different fabrication techniques to further reduce costs and increase flexibility.

Open source framework for a Broadly Expandable and Reconfigurable data acquisition and automation device (BREAD).

Though open source data acquisition (DAQ) systems have been published, closed source proprietary systems are the standard despite often being prohibitively expensive. High costs, however, limit access to high-quality DAQ in low-resource settings. In many cases the functions executed by the closed source and proprietary DAQ cards could be carried out by an open source alternative; however, as desired function count increases, the simplicity of integrating the designs decreases substantially. Although the global library of open source electronic designs is expanding rapidly, and there is clear evidence they can reduce costs for scientists one device at a time, they are generally made to carry a function well, but are often not capable of scaling up or easily being integrated with other designs. Just as other open source projects have found success by having modular frameworks and clearly documented specifications, a framework to unify and enable interoperation of these open source electronics systems would be greatly beneficial to the scientific community. To meet these needs and ensure greater accessibility to high-quality electronics sensing and DAQ systems, this article shares and tests a news framework where new open source electronics can be developed and have plug-and-play functionality. The Broadly Reconfigurable and Expandable Automation Device (BREAD), consists of a basic set of guidelines and requirements to which others can contribute. Here 7 slices (boards) are provided, demonstrated, and validated: 1) Amplified Analog Input, 2) Audio Analysis / Fourier Transform, 3) +/- 10A Current Sensor, 4) 4-Channel Relay Controller 5) 4 Channel Stepper Motor Controller, 6) 4 Channel Type-K Thermocouple Reader and 7) 2 Channel USB Port. Implementing systems using BREAD rather than closed source and proprietary alternatives can result in cost savings of up to 93%.

Distributed manufacturing of an open-source tourniquet testing system.

Tourniquets are effective for casualty-prevention in emergency situations. The use of centrally-manufactured commercial tourniquets, however, is not always possible due to supply chain disruptions. The open-source hardware model has been applied to overcome these disruptions in humanitarian crises and several low-cost digitally manufacturable open-source tourniquets have been developed. With the low reliability of improvised tourniquets, it is important to ensure that distributed manufacturing of tourniquets is effective and safe. Tourniquets can be tested, but existing tourniquet testers are expensive, bulky, and complex to operate, which limits their accessibility to an even greater extent than tourniquets in extreme settings. This article fulfills a need by providing a small, transportable, open-source additive-manufactured tourniquet tester that enables inexpensive and accurate testing of tourniquets against known clinical parameters. The <$100 tourniquet tester is validated and tested for operating force of tourniquets in the field or in distributed manufacturing facilities. The tourniquet tester has a significant economic and operational advantage compared to proprietary counterparts available on the market. Once calibrated with a blood pressure monitor, the built-in LCD displays the measuring range of the tester as 0 to 200 N, which is enough to test the validation of all tourniquets.

AC/off-grid photovoltaic powered open-source ball mill.

Ball milling is used for comminution by rotating a drum to grind materials using balls with specific diameters. Ball milling advantages include the potential for high capacity, predicted fineness in a specific amount of time, reliability, safety, and simplicity, but has disadvantages of high weight, energy consumption and costs, which limit accessibility. To overcome these limitations this study applies the free and open source hardware approach coupled to distributed digital manufacturing to fabricate a ball mill with a simple, customizable design that can be used in a wide range of scientific applications and circumstances including those without access to reliable grid electricity. The highly-customizable design reduces the cost to

Economic Efficiency of an Open-Source National Medical Lab Software in Canada.

Although the Canada federal government has invested over $3.1 billion developing health information technology (HIT), all 10 provinces still have their own separate HIT systems, which are non-interoperable, expensive, and inconsistent. After first reviewing how these systems operate, this paper analyzes the costs and savings of integrating the common billing, lab results, and diagnostic imaging (BLD) functions of these separate systems using free and open-source software and proposes a system for this, HermesAPI. Currently, 8 provincial governments representing over 95% of Canada's population allow private companies to create their own electronic medical records (EMR) system and integrate with provincial BLD systems. This study found the cost to develop and maintain HermesAPI would be between CAD$610,000 to CAD$740,000, but would prevent CAD$120,000 per company per province in development costs for a total savings of $6.4 million. HermesAPI would lower barriers to entry for the HIT industry to increase competition, improve the quality of HIT products, and ultimately patient care. The proposed open-source approach of the HermesAPI is one option towards building a more interoperable, less expensive, and more consistent HIT system for Canada.

Hangprinter for large scale additive manufacturing using fused particle fabrication with recycled plastic and continuous feeding.

The life cycle of plastic is a key source of carbon emissions. Yet, global plastics production has quadrupled in 40 years and only 9 % has been recycled. If these trends continue, carbon emissions from plastic wastes would reach 15 % of global carbon budgets by 2050. An approach to reducing plastic waste is to use distributed recycling for additive manufacturing (DRAM) where virgin plastic products are replaced by locally manufactured recycled plastic products that have no transportation-related carbon emissions. Unfortunately, the design of most 3-D printers forces an increase in the machine cost to expand for recycling plastic at scale. Recently, a fused granular fabrication (FGF)/fused particle fabrication (FPF) large-scale printer was demonstrated with a GigabotX extruder based on the open source cable driven Hangprinter concept. To further improve that system, here a lower-cost recyclebot direct waste plastic extruder is demonstrated and the full designs, assembly and operation are detailed. The <$1,700 machine's accuracy and printing performance are quantified, and the printed parts mechanical strength is within the range of other systems. Along with support from the Hangprinter and DUET3 communities, open hardware developers have a rich ecosystem to modify in order to print directly from waste plastic for DRAM.

Killing two birds with one stone: chemical and biological upcycling of polyethylene terephthalate plastics into food.

Most polyethylene terephthalate (PET) plastic waste is landfilled or pollutes the environment. Additionally, global food production must increase to support the growing population. This article explores the feasibility of using microorganisms in an industrial system that upcycles PET into edible microbial protein powder to solve both problems simultaneously. Many microorganisms can utilize plastics as feedstock, and the resultant microbial biomass contains fats, nutrients, and proteins similar to those found in human diets. While microbial degradation of PET is promising, biological PET depolymerization is too slow to resolve the global plastic crisis and projected food shortages. Evidence reviewed here suggests that by coupling chemical depolymerization and biological degradation of PET, and using cooperative microbial communities, microbes can efficiently convert PET waste into food.

Professors want to share: preliminary survey results on establishing open-source-endowed professorships.

This study proposes a novel policy to provide incentives for open science: to offer open-source (OS)-endowed professorships. To hold an open-source-endowed chair, in addition to demonstrated excellence in their field, professors would need to agree to (1) ensuring all of their writing is distributed via open access in some way and (2) releasing all of their intellectual property in the public domain or under appropriate open-source licenses. The results of this survey study of university professors in the U.S. show that a super majority (86.7%) of faculty respondents indicated willingness to accept an OS-endowed professorship, while only 13.3% of respondents would not be willing to accept the terms of an OS-endowed professorship. The terms of accepting an OS-endowed professorship that were the most popular among respondents were increased salary, annual discretionary budget, as a term of tenure and annual RA or TA lines. More than a quarter of responding professors declared that no additional compensation would be needed for them to accept the terms of an OS-endowed professorship. The results demonstrate a clear willingness of academics to expand open access to science, which would hasten scientific progress while also making science more just and inclusive. It is clear that science funders have a large opportunity to move towards open science by offering open-source-endowed chairs.

Open-Source Hardware May Address the Shortage in Medical Devices for Patients with Low-Income and Chronic Respiratory Diseases in Low-Resource Countries.

Respiratory diseases pose an increasing socio-economic burden worldwide given their high prevalence and their elevated morbidity and mortality. Medical devices play an important role in managing acute and chronic respiratory failure, including diagnosis, monitoring, and providing artificial ventilation. Current commercially available respiratory devices are very effective but, given their cost, are unaffordable for most patients in low- and middle-income countries (LMICs). Herein, we focus on a relatively new design option-the open-source hardware approach-that, if implemented, will contribute to providing low-cost respiratory medical devices for many patients in LMICs, particularly those without full medical insurance coverage. Open source reflects a set of approaches to conceive and distribute the comprehensive technical information required for building devices. The open-source approach enables free and unrestricted use of the know-how to replicate and manufacture the device or modify its design for improvements or adaptation to different clinical settings or personalized treatments. We describe recent examples of open-source devices for diagnosis/monitoring (measuring inspiratory/expiratory pressures or flow and volume in mechanical ventilators) and for therapy (non-invasive ventilators for adults and continuous positive airway pressure support for infants) that enable building simple, low-cost (hence, affordable), and high-performance solutions for patients in LMICs. Finally, we argue that the common practice of approving clinical trials by the local hospital ethics board can be expanded to ensure patient safety by reviewing, inspecting, and approving open hardware for medical application to maximize the innovation and deployment rate of medical technologies.

Methane Single Cell Protein: Potential to Secure a Global Protein Supply Against Catastrophic Food Shocks.

Global catastrophes such as a supervolcanic eruption, asteroid impact, or nuclear winter could cause global agricultural collapse due to reduced sunlight reaching the Earth's surface. The human civilization's food production system is unprepared to respond to such events, but methane single cell protein (SCP) could be a key part of the solution. Current preparedness centers around food stockpiling, an excessively expensive solution given that an abrupt sunlight reduction scenario (ASRS) could hamper conventional agriculture for 5-10 years. Instead, it is more cost-effective to consider resilient food production techniques requiring little to no sunlight. This study analyses the potential of SCP produced from methane (natural gas and biogas) as a resilient food source for global catastrophic food shocks from ASRS. The following are quantified: global production potential of methane SCP, capital costs, material and energy requirements, ramp-up rates, and retail prices. In addition, potential bottlenecks for fast deployment are considered. While providing a more valuable, protein-rich product than its alternatives, the production capacity could be slower to ramp up. Based on 24/7 construction of facilities, 7%-11% of the global protein requirements could be fulfilled at the end of the first year. Despite significant remaining uncertainties, methane SCP shows significant potential to prevent global protein starvation during an ASRS at an affordable price-US$3-5/kg dry.

Design of a low-cost mobile multispectral albedometer with geopositioning and absolute orientation.

Albedo is the percentage of radiation that a given surface reflects. Its study is important to evaluate thermal effects in buildings, generation capacity with bifacial panels, among others. In this work, the design and validation of a low-cost mobile albedometer is presented, which measures the reflection in 8 spectral bands in the visible, additionally the system is equipped with a Global Navigation Satellite System (GNSS) receiver, to reference its position and an Inertial Measurement Unit (IMU) to know its absolute orientation, make corrections in real time or detect errors. The purpose of designing the mobile device is to measure a larger area and, since it is georeferenced, it is to feed GIS tools that allow designers to use the information.

Low cost climate station for smart agriculture applications with photovoltaic energy and wireless communication.

Measuring climatic conditions is a fundamental task for a wide array of scientific and practical fields. Weather variables change depending on position and time, especially in tropical zones without seasons. Additionally, the increasing development of precision or smart agriculture makes it necessary to improve the measurement systems while widely distributing them at the location of crops. For these reasons, in this work, the design, construction and fabrication of an adaptable autonomous solar-powered climatic station with wireless 3G or WiFi communication is presented. The station measures relative humidity, temperature, atmospheric pressure, precipitation, wind speed, and light radiation. In addition, the system monitors the charge state of the main battery and the energy generated by the photovoltaic module to act as a reference cell for solar energy generation capability and agrivoltaic potential in the installation area. The station can be remotely controlled and reconfigured. The collected data from all sensors can be uploaded to the cloud in real-time. This initiative aims at enhancing the development of free and open source hardware that can be used by the agricultural sector and that allows professionals in the area to improve harvest yield and production conditions.

Design and implementation of 3-D printed radiation shields for environmental sensors.

The measurement of outdoor environmental and climatic variables is needed for many applications such as precision agriculture, environmental pollution monitoring, and the study of ecosystems. Some sensors deployed for these purposes such as temperature, relative humidity, atmospheric pressure, and carbon dioxide sensors require protection from climate factors to avoid bias. Radiation shields hold and protect sensors to avoid this bias, but commercial systems are limited, often expensive, and difficult to implement in low-cost contexts or large deployments for collaborative sensing. To overcome these challenges, this work presents an open source, easily adapted and customized design of a radiation shield. The device can be fabricated with inexpensive off-the-shelf parts and 3-D printed components and can be adapted to protect and isolate different types of sensors. Two material approaches are tested here: polylactic acid (PLA), the most common 3-D printing filament, and acrylonitrile styrene acrylate (ASA), which is known to offer better resistance against UV radiation, greater hardness, and generally higher resistance to degradation. To validate the designs, the two prototypes were installed on a custom outdoor meteorological system and temperature and humidity measurements were made in several locations for one month and compared against a proprietary system and a system with no shield. The 3-D printed materials were also both tested multiple times for one month for UV stability of their mechanical properties, their optical transmission and deformation under outdoor high-heat conditions. The results showed that ASA is the preferred material for this design and that the open source radiation shield could match the performance of proprietary systems. The open source system can be constructed for about nine US dollars, which enables mass development of flexible weather stations for monitoring needed in smart agriculture.

Nutrition in Abrupt Sunlight Reduction Scenarios: Envisioning Feasible Balanced Diets on Resilient Foods.

Abrupt sunlight reduction scenarios (ASRS) following catastrophic events, such as a nuclear war, a large volcanic eruption or an asteroid strike, could prompt global agricultural collapse. There are low-cost foods that could be made available in an ASRS: resilient foods. Nutritionally adequate combinations of these resilient foods are investigated for different stages of a scenario with an effective response, based on existing technology. While macro- and micronutrient requirements were overall met, some-potentially chronic-deficiencies were identified (e.g., vitamins D, E and K). Resilient sources of micronutrients for mitigating these and other potential deficiencies are presented. The results of this analysis suggest that no life-threatening micronutrient deficiencies or excesses would necessarily be present given preparation to deploy resilient foods and an effective response. Careful preparedness and planning-such as stock management and resilient food production ramp-up-is indispensable for an effective response that not only allows for fulfilling people's energy requirements, but also prevents severe malnutrition.

3D Printed SiOC(N) Ceramic Scaffolds for Bone Tissue Regeneration: Improved Osteogenic Differentiation of Human Bone Marrow-Derived Mesenchymal Stem Cells.

Bone tissue engineering has developed significantly in recent years as there has been increasing demand for bone substitutes due to trauma, cancer, arthritis, and infections. The scaffolds for bone regeneration need to be mechanically stable and have a 3D architecture with interconnected pores. With the advances in additive manufacturing technology, these requirements can be fulfilled by 3D printing scaffolds with controlled geometry and porosity using a low-cost multistep process. The scaffolds, however, must also be bioactive to promote the environment for the cells to regenerate into bone tissue. To determine if a low-cost 3D printing method for bespoke SiOC(N) porous structures can regenerate bone, these structures were tested for osteointegration potential by using human mesenchymal stem cells (hMSCs). This includes checking the general biocompatibilities under the osteogenic differentiation environment (cell proliferation and metabolism). Moreover, cell morphology was observed by confocal microscopy, and gene expressions on typical osteogenic markers at different stages for bone formation were determined by real-time PCR. The results of the study showed the pore size of the scaffolds had a significant impact on differentiation. A certain range of pore size could stimulate osteogenic differentiation, thus promoting bone regrowth and regeneration.