A Cross-Sectional Reproducibility Study of a Standard Camera Sensor Using Artificial Intelligence to Assess Food Items: The FoodIntech Project

Having a system to measure food consumption is important to establish whether individual nutritional needs are being met in order to act quickly and to minimize the risk of undernutrition. Here, we tested a smartphone-based food consumption assessment system named FoodIntech. FoodIntech, which is based on AI using deep neural networks (DNN), automatically recognizes food items and dishes and calculates food leftovers using an image-based approach, i.e., it does not require human intervention to assess food consumption. This method uses one-input and one-output images by means of the detection and synchronization of a QRcode located on the meal tray. The DNN are then used to process the images and implement food detection, segmentation and recognition. Overall, 22,544 situations analyzed from 149 dishes were used to test the reliability of this method. The reliability of the AI results, based on the central intra-class correlation coefficient values, appeared to be excellent for 39% of the dishes (n = 58 dishes) and good for 19% (n = 28). The implementation of this method is an effective way to improve the recognition of dishes and it is possible, with a sufficient number of photos, to extend the capabilities of the tool to new dishes and foods.

Objek Deteksi Makanan Khas Palembang Menggunakan Algoritma YOLO (You Only Look Once)

Deep learning is a part of machine learning method that uses artificial neural network (ANN). The type of learning in deep learning can be supervised, semi-supervised, and unsupervised [7] . CNN & RNN (Supervised) and RBM & Autoencoder (Unsupervised) are deep learning algorithms. All of the above algorithms have uses in their respective fields, depending on what we want to use them for. One of the most frequently used cases for deep learning is object detection and classification. The Convolutional Neural Network (CNN) algorithm is the most widely used algorithm for object detection cases, one of the reasons because it is supported by Google's Tensorflow framework, but it turns out that there is one object detection algorithm that has a higher level of accuracy and processing speed, namely You Only Look Once (YOLO) which can run on 2 frameworks (Darknet & Darkflow) and is supported by GPU. That's why here the author prefers to do object detection with the You Only Look Once (YOLO) method. The research data with the title Palembang Food Detection Object Using the YOLO (You Only Look Once) Algorithm is a sample photo of food from Google Image. There are 31 types of Palembang specialties, each type consists of approximately 50 to 70 images, so the total images used are from 31 types of Palembang foods, namely 1955 images with jpeg format for training data, and 31 images with jpeg format typical Palembang foods for test data.

Attraction to Smelly Food in Birds: Insectivorous Birds Discriminate between the Pheromones of Their Prey and Those of Non-Prey Insects

Natural selection has favored the evolution of different capabilities that allow animals to obtain food—e.g., the development of senses for improving prey/food detection. Among these senses, chemical sense is possibly the most ancient mechanism used by organisms for environmental assessment. Comparative studies suggest the prime role of foraging ecology in the evolution of the olfactory apparatus of vertebrates, including birds. Here, we review empirical studies that have shown birds’ abilities to detect prey/food via olfaction and report the results of a study aiming to analyze the specificity of eavesdropping on prey pheromones in insectivorous birds. In a field study, we placed artificial larvae and a dispenser with one of three treatments—prey (Operopthera brumata) pheromones, non-prey (Rhynchophorus ferrugineus) pheromones, or a control unscented dispenser—on the branches of Pyrenean oak trees (Quercus pyrenaica). We then measured the predation rate of birds on artificial larvae. Our results show that more trees had larvae with signs of avian predation when they contained a prey pheromone dispenser than when they contained a non-prey pheromone dispenser or an unscented dispenser. Our results indicate that insectivorous birds can discriminate between the pheromones emitted by their prey and those emitted by non-prey insects and that they only exhibit attraction to prey pheromones. These results highlight the potential use of insectivorous birds in the biological control of insect pests.

European inter-comparison studies as a tool for perfecting irradiated food detection methods

In this paper, we present the results of inter-comparison studies on identification of irradiated food carried out by the leading European laboratories from 1991 to 2018. In 1990s, the Federal Institute for Health Protection of Consumers and Veterinary Medicine in Germany played the leading role in the organization of the inter-laboratory tests on this subject. At the beginning of the present century, the Spanish Agency for Food Safety and Nutrition and Food National Spanish Centre took over this role. In total, 47 international tests were carried out in which nearly 500 samples of alimentary products were analysed in 37 laboratories from 14 European countries. The tests were aimed at proving the reliability of analytical methods – thermoluminescence (TL), photostimulated luminescence (PSL), and electron paramagnetic resonance (EPR) spectroscopy – for identification of specific irradiated food products and to control the analytical skills and experience of participating laboratories. The results made possible a discussion on why some irradiated food samples are more difficult for identification. In general, the tests showed that TL measurements of products such as herbs, nuts, peppers, and raisins, and EPR studies of fish and chicken bones, fresh strawberries, and dried fruits could be used as reliable control methods. The challenge that control laboratories are facing now, is related to the identification of complex food products such as diet supplements or biopharmaceuticals, in which only some additives are irradiated.

Mining Public Metagenomes for Environmental Surveillance of Parasites: A Proof of Principle

Parasites often have complex developmental cycles that account for their presence in a variety of difficult-to-analyze matrices, including feces, water, soil, and food. Detection of parasites in these matrices still involves laborious methods. Untargeted sequencing of nucleic acids extracted from those matrices in metagenomic projects may represent an attractive alternative method for unbiased detection of these pathogens. Here, we show how publicly available metagenomic datasets can be mined to detect parasite specific sequences, and generate data useful for environmental surveillance. We use the protozoan parasite Cryptosporidium parvum as a test organism, and show that detection is influenced by the reference sequence chosen. Indeed, the use of the whole genome yields high sensitivity but low specificity, whereas specificity is improved through the use of signature sequences. In conclusion, querying metagenomic datasets for parasites is feasible and relevant, but requires optimization and validation. Nevertheless, this approach provides access to the large, and rapidly increasing, number of datasets from metagenomic and meta-transcriptomic studies, allowing unlocking hitherto idle signals of parasites in our environments.

Application of Raman Spectroscopic Methods in Food Safety: A Review

Food detection technologies play a vital role in ensuring food safety in the supply chains. Conventional food detection methods for biological, chemical, and physical contaminants are labor-intensive, expensive, time-consuming, and often alter the food samples. These limitations drive the need of the food industry for developing more practical food detection tools that can detect contaminants of all three classes. Raman spectroscopy can offer widespread food safety assessment in a non-destructive, ease-to-operate, sensitive, and rapid manner. Recent advances of Raman spectroscopic methods further improve the detection capabilities of food contaminants, which largely boosts its applications in food safety. In this review, we introduce the basic principles of Raman spectroscopy, surface-enhanced Raman spectroscopy (SERS), and micro-Raman spectroscopy and imaging; summarize the recent progress to detect biological, chemical, and physical hazards in foods; and discuss the limitations and future perspectives of Raman spectroscopic methods for food safety surveillance. This review is aimed to emphasize potential opportunities for applying Raman spectroscopic methods as a promising technique for food safety detection.

Fabrication of Nano/Micro-Structured Electrospun Detection Card for the Detection of Pesticide Residues

A novel nano/micro-structured pesticide detection card was developed by combining electrospinning and hydrophilic modification, and its feasibility for detecting different pesticides was investigated. Here, the plain and hydrophilic-modified poly(ε-caprolactone) (PCL) fiber mats were used for the absorption of indolyl acetate and acetylcholinesterase (AChE), respectively. By pre-treating the fiber mat with ethanol, its surface wettability was improved, thus, promoting the hydrolysis of the PCL fiber mat. Furthermore, the absorption efficiency of AChE was improved by almost two times due to the increased hydrophilicity of the modified fiber mat. Noteworthily, this self-made detection card showed a 5-fold, 2-fold, and 1.5-fold reduction of the minimum detectable concentration for carbofuran, malathion, and trichlorfon, respectively, compared to the national standard values. Additionally, it also exhibited good stability when stored at 4 °C and room temperature. The food detection test showed that this nano/micro-based detection card had better detectability than the commercial detection card. Therefore, this study offers new insights into the design of pesticide detection cards, which also broadens the application of electrospinning technique.