Six preprocessing algorithms for the detection of firearm gunshots are statistically evaluated, using the receiver operating characteristic method as a previous feasibility metric for their implementation on a low-power VLSI circuit. Circuits are intended to serve as the input detection sensors of a low-power environmental surveillance network. Some possible VLSI implementations for the evaluated algorithms are also evaluated. Results indicate that the use of wavelet bank filters, either discrete or continuous, might be the best choice in terms of the compromise between detection efficiency and the power requirements of the intended application.
Climate change has already shown its negative impact that has on agriculture and food production, particularly because of rainfall deficit or excess, temperature changes and other associated environmental variations not amenable to sustainable agriculture. Greenhouse horticulture has proven to be an effective way of reducing the negative effects of climate change on vegetable production, but still represents a challenge for farmers, because the behavior of most plant species grown in protected environments is markedly different from open field cultivation. To increase the understanding of plant growth in protected crops, Internet of Things (IoT) capabilities were integrated into a greenhouse, thus providing a platform for researchers that allows them to take decisions at the right time about irrigation, moisture requirements and nutrients. The designed system consists of electronic circuitry, sensors, mobile communication, actuators and software running in the cloud. The functionality of the system was tested in a cucumber vegetable production in a greenhouse, where the data acquired from environmental variables, substrate conditions, and overdrain measurements are sent over the Internet for their remote analysis by researchers. In the particular case of overdrain measurements, the traditional way of data gathering using manual procedures with pH and conductivity probes was enhanced by the introduction of drain gages, valves and probes with automatic data acquisition, and the application of an online Kalman filter to improve the accuracy of a low precision liquid flow meter. Preliminary results are encouraging and seem to point for continuing the development of efficient tools for decision taking about vegetable production in greenhouse horticulture.
A fuzzy logic controller is proposed for the evaluation of water drainage in order to determine if water content is easily available to crops; the lexical uncertainty given by “easily available” was quantified into a numerical value in this first approach. The result is a preliminary controller that embeds structural human knowledge about irrigation scheduling into an analytic fuzzy logic model (FLM), in order to provide agricultural scientists with quick access to a particular crop's main production and growth related variables, and allowing for future data driven decisions on the spot. The controller was validated with real data collected from a particular crop, using remote sensors connected to Internet.
Changes in the world's weather due to human activities have already shown its negative impact on agriculture, food production, carbon neutrality initiatives and the environment. In order to support Costa Rica's commitment to becoming the first carbon neutral country by 2021, a local group of multidisciplinary researchers have proposed, developed and tested a general system with Internet of Things capabilities, aimed at giving technical support to their projects on renewable natural energy resources and alternative eco-friendly agricultural techniques. The system consists of electronic circuitry built with commercial-off-the-shelf components (COTS), affordable sensors, mobile communication, actuators and software running on the Internet. The functionality of the device was tested on two specific applications - a microalgae culture cultivated in a photobioreactor and a greenhouse cucumber plantation -, interchanging and configuring the appropriate sensors for the different multiple variables needed (temperature, light intensity, pH and dissolved oxygen, among others), that were captured and sent to a remote database connected to the Internet cloud for post-analysis. Preliminary results seem support the continuing development of affordable yet efficient applications based on IoT, that provide effective production tools for food and biofuel producers in developing countries.
Industrial wastewater contains sources of nitrogen and phosphorus that tend to produce eutrophication in receiving water bodies when it has not been properly treated. Eutrophication is a type of chemical contamination of water that occurs when there is an excessive supply of nutrients to an aquatic ecosystem, It can occur naturally (red tides) but the anthropogenic emissions, as industrial and agricultural discharges, sewage from farms (dairies), urban waste and treatment plants that are the more common and hazardous. Microalgae are able to take advantage of the nutrients of these wastewaters and produce biomass. The objective of this study was to determine the potential energy of the algal biomass of Chlorella vulgaris using wastewater from a sugar industry and a dairy farm. Microalgae biomass was cultivated into a photobioreactor (PBR), processed, dried out in a solar drier for wood, compressed for the production of pellets and subsequent evaluation of the heating value and the physical-mechanical properties of the final product. The preliminary results showed that a higher heating value was observed in pellets using wastewater from dairy farm industry (1.23 ± 3.7) × 10 3 kJ/100 g, compared to the caloric value of pellets made using algal biomass cultivated using wastewater from sugaring industry (0.73 ± 0.7) x 10 3 kJ/100 g. The microalgae Chlorella vulgaris was cultivated in a chemical medium under laboratory conditions where an electronic device with Internet of Things (IoT) capabilities was used to measure ambient variables related to microalgae growing process.
Introducing artificial intelligence techniques in agriculture offers new opportunities for improving crop management, such as in coffee plantations, which constitute a complex agroforestry environment. This paper presents a comparative study of three deep learning frameworks: Deep Forest, RT-DETR, and Yolov9, customized for coffee plant detection and trained from images with a high spatial resolution (cm/pix). Each frame had dimensions of 640 × 640 pixels acquired from passive RGB sensors onboard a UAS (Unmanned Aerial Systems) system. The image set was structured and consolidated from UAS-RGB imagery acquisition in six locations along the Central Valley, Costa Rica, through automated photogrammetric missions. It was evidenced that the RT-DETR and Yolov9 frameworks allowed adequate generalization and detection with mAP50 values higher than 90% and mAP5095 higher than 54%, in scenarios of application with data augmentation techniques. Deep Forest also achieved good metrics, but noticeably lower when compared to the other frameworks. RT-DETR and Yolov9 were able to generalize and detect coffee plants in unseen scenarios that include complex forest structures within tropical agroforestry Systems (AFS).