Analytics and Decision Support for Green IS and Sustainability Applications
Permanent URI for this collection
1 - 5 of 5
ItemSustainable Energy System Planning in Developing Countries: A Decision Support System Considering Variations Over Time( 2022-01-04)Planning energy systems is subject to changes in components’ health and installation costs, fossil fuel prices, and load demand. Especially in developing countries, electrical loads are reported to increase drastically after electrification. Improper sizing of the energy system’s components can lead to reduced environmental sustainability, decreased reliability, and long-term project failures. As no tools for energy system planning exist that aim at developing countries and sufficiently account for temporal variations, we modify the software NESSI4D in a design science cycle to provide the comprehensive decision support system NESSI4D+. We conduct an applicability check with a representative rural village in mountainous Nepal that validates NESSI4D+’s relevance and shows the importance of considering temporal variations for economically, ecologically, and socially long-term sustainable energy projects.
ItemIntroducing a new Workflow for Pig Posture Classification based on a combination of YOLO and EfficientNet( 2022-01-04)This paper introduces a pipeline for image-based pig posture classification by applying YOLOv5 for pig detection and EfficientNet for subsequent pig posture classification into 'lying' and 'notLying'. A high-quality dataset consisting of 5311 heterogeneous images from different sources with 78215 bounding box annotations was created. The bounding box annotations were then used to create a separate dataset for image classification, consisting of 9209 and 7855 images for each 'lying' and 'notLying'. The YOLOv5 model achieves an AP of 0.994 for pig detection, while EfficientNet achieves a precision of 0.93 for pig posture classification. Comparing the results of the proposed method with other approaches found in literature, it shows that significant improvements in terms of accuracy can be achieved by splitting the classification of pig posture into separate models. This research provides a foundation for the continued development of real-time monitoring and assistance systems in pig Precision Livestock Farming.
ItemCombining Design Thinking and the Socio-Technical-Ecological Systems Perspective to Understand Greenhouse Growers’ Experiences with Energy Management Solutions( 2022-01-04)Multiple threats to sustainability are driving the need to grow food in controlled environments, such as greenhouses. However, greenhouses consume large quantities of energy for lighting, heating, and ventilation, which places additional strain on the natural environment. For both business and environmental benefits, greenhouses must pursue sustainable energy management solutions. Combining design thinking with the socio-technical-ecological systems (STES) perspective, we analyze the greenhouse grower’s journey from awareness of potential solutions to post-implementation use. Our approach offers a novel way to understand the problem space. We find that sustainable energy management is more than a technical or even socio-technical challenge; it also involves important ecological considerations. However, ecological and social concerns are less evident in the grower’s journey as compared to the physical and information technology dimensions. The research and development of sustainable technology solutions would benefit from giving equal attention to these three systems and the interactions between them.
ItemA Deep Learning Model Compression and Ensemble Approach for Weed Detection( 2022-01-04)Site-specific weed management is an important practice in precision agriculture. Current advances in artificial intelligence have resulted in the use of large deep convolutional neural networks for weed detection. In this paper, a transfer learning, model compression, and ensemble learning approach is introduced that is suitable for resource-limited hardware such as mobile and embedded devices. The resulting ensemble model achieves 91.2% classification accuracy which is comparable to the performance of state-of-the-art deep learning models (such as the vanilla VGG16, DenseNet, and ResNet) while being about 62.22% smaller in size than DenseNet (the smallest-sized full-sized model). The approach used in this study is beneficial for further development of deep convolutional neural networks on smaller resource-limited hardware typically used in agriculture, as well as other industries such as healthcare and telecommunication.