Sondersammlungen

Permanent URI for this communityhttps://hohpublica.uni-hohenheim.de/handle/123456789/7011

Browse

Browsing Sondersammlungen by Journal "Applied food research"

Type the first few letters and click on the Browse button
Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Effect of packaging and storage conditions on the pasting and functional properties of pretreated yellow-fleshed cassava flour
    (2024) Ekeledo, Esther; Abass, Adebayo; Müller, Joachim
    Cassava is highly susceptible to post harvest physiological deterioration which makes it necessary to initiate processing so as to extend the shelf life. In order to improve and enhance the nutritional characteristics of the processed cassava flour, this research was carried out so as to evaluate the adequate packaging materials and storage conditions necessary for safe storage and good flour quality. Pasting properties of food/flour is an indication of the different applicability of starch-based food ingredients in product development. The effect of packaging materials (cylindric polyvinyl containers and aluminum ziplock pouch bags) on quality attributes of pretreated yellow-fleshed cassava flour (YFCF) samples stored in two storage conditions a (cooling chamber at 5 ◦ C and 30 % relative humidity and; in a climate chamber at 30 ◦C and 50 % relative humidity) was investigated for 8 weeks. Flour samples from each package type were evaluated for water absorption capacity, pasting and oil absorption capacity fortnightly. The treated initial flour sample before storage-sulfured (BSS) had the highest peak viscosity (891 RVU). The low peak time at the end of storage in non-sulfured flours packed in aluminum pouch bags and stored at 5 ◦C is an evidence of time and energy saving capacity. The water absorption capacity of non-sulfured flour samples packed in cylindric polyvinyl containers and the sulfured flour sample packed in an aluminum pouch bag at 30 ◦C increased with storage duration. The aluminum ziplock pouch bags showed excellent storage quality and retained better pasting property. The climatic storage condition revealed better keeping quality. The use of sodium metabisulphite revealed its suitability as a pretreatment tool.
  • Thumbnail Image
    Publication
    Poultry perfection : comparison of computer vision models to detect and classify poultry products in a production setting
    (2025) Einsiedel, Daniel; Vita, Marco; Jox, Dana; Dunnewind, Bertus; Meulendijks, Johan; Krupitzer, Christian
    This study explores the use of computer vision, specifically object detection, for quality control in ready-to-eat meat products. We focused on a single process step, labeling products as “good” or “imperfect”. An “imperfect product” constitutes a product that deviates from the norm regarding shape, size, or color (having a hole, missing edges, dark particles, etc.). Imperfect does not mean the product is inedible or a risk to food safety, but it affects the overall product quality. Various object detectors, such as YOLO, including YOLO12, were compared using the mAP50-95 metric. Most models achieved mAP scores over 0.9, with YOLO12 reaching a peak score of 0.9359. The precision and recall curves indicated that the model learned the “imperfect product” class better, most likely due to its higher representation. This underscores the importance of a balanced dataset, which is challenging to achieve in real-world settings. The confusion matrix revealed false positives, suggesting that increasing dataset volume or hyperparameter tuning could help. However, increasing the dataset volume is usually the more difficult path since data acquisition and especially labeling are by far the most time-consuming steps of the whole process. Overall, current models can be applied to quality control tasks with some margin of error. Our experiments show that high-quality, consistently labeled datasets are potentially more important than the choice of the model for achieving good results. The applied hyperparameter tuning on the YOLO12 model did not outperform the default model in this case. Future work could involve training models on a multi-class dataset with hyperparameter optimization. A multi-class dataset could contain more specific classes than just “good” and “imperfect,” making trained models capable of actually predicting specific quality deviations.