Search Results (13)

Heat stress has been identified as one of the main challenges for dairy production systems, particularly in the context of global warming. This one-year study aimed to evaluate the impact of heat stress on milk yield and composition in a dairy farm located in the Elvas region of Portugal. A pack of electronic sensors was installed in the lactating animal facilities, allowing continuous recording of environmental data (temperature, humidity, ammonia and carbon dioxide). Based on these data, the Temperature-Humidity Index (THI) was automatically calculated on a daily basis, with the values subsequently aggregated into 7-day moving averages and integrated with milk production records, somatic cell count, and milk fat and protein content. The results indicate a significant influence of THI on both milk yield and composition, particularly on protein and fat content. The relationships between the variables were found to be non-linear, which contrasts with some results described in the literature. These discrepancies may be related to genetic differences between animals, variations in diets, production levels, management conditions, or the statistical models used in previous studies. Dry matter intake proved to be an important predictive variable. These findings reinforce the importance of ensuring animal welfare through continuous environmental monitoring and the implementation of effective heat stress mitigation strategies in the dairy sector. Full article

Proper nutrition is a fundamental aspect to maintaining overall health and well-being, influencing both physical and social aspects of human life; an unbalanced or inadequate diet can lead to various nutritional deficiencies and chronic health conditions. In today’s fast-paced world, monitoring nutritional intake has become increasingly important, particularly for those with specific dietary needs. While smartphone-based applications using image recognition have simplified food tracking, they still rely heavily on user interaction and raise concerns about practicality and privacy. To address these limitations, this paper proposes a novel, compact spectroscopic sensing platform for automatic beverage recognition. The system utilizes the AS7265x commercial sensor to capture the spectral signature of beverages, combined with a K-Nearest Neighbors (KNN) machine learning algorithm for classification. The approach is designed for integration into everyday objects, such as smart glasses or cups, offering a noninvasive and user-friendly alternative to manual tracking. Through optimization of both the sensor configuration and KNN parameters, we identified a reduced set of four wavelengths that achieves over 96% classification accuracy across a diverse range of common beverages. This demonstrates the potential for embedding accurate, low-power, and cost-efficient sensors into Internet of Things (IoT) devices for real-time nutritional monitoring, reducing the need for user input while enhancing accessibility and usability. Full article

Deep networks can facilitate the monitoring of a balanced diet to help prevent various health problems related to eating disorders. Large, diverse, and clean data are essential for learning these types of algorithms. Although data can be collected automatically, the data cleaning process is time-consuming. This study aims to provide the model with the ability to learn even when the data are not completely clean. For this purpose, we extend the Attentive Feature MixUp method to enable its learning on noisy multi-label food data. The extension was based on the hypothesis that during the MixUp phase, when a pair of images are mixed, the resulting soft labels should be different for each ingredient, being larger for ingredients that are mixed with the background because they are better distinguished than when they are mixed with other ingredients. Furthermore, to address data perturbation, the incorporation of the Laplace approximation as a post-hoc method was analyzed. The evaluation of the proposed method was performed on two food datasets, where a notable performance improvement was obtained in terms of Jaccard index and $F_1$ score, which validated the hypothesis raised. With the proposed MixUp, our method reduces the memorization of noisy multi-labels, thereby improving its performance. Full article

In overcoming the worldwide problem of overweight and obesity, automatic dietary monitoring (ADM) is introduced as support in dieting practises. ADM aims to automatically, continuously, and objectively measure dimensions of food intake in a free-living environment. This could simplify the food registration process, thereby overcoming frequent memory, underestimation, and overestimation problems. In this study, an eating event detection sensor system was developed comprising a smartwatch worn on the wrist containing an accelerometer and gyroscope for eating gesture detection, a piezoelectric sensor worn on the jaw for chewing detection, and a respiratory inductance plethysmographic sensor consisting of two belts worn around the chest and abdomen for food swallowing detection. These sensors were combined to determine to what extent a combination of sensors focusing on different steps of the dietary cycle can improve eating event classification results. Six subjects participated in an experiment in a controlled setting consisting of both eating and non-eating events. Features were computed for each sensing measure to train a support vector machine model. This resulted in F${}_1$-scores of 0.82 for eating gestures, 0.94 for chewing food, and 0.58 for swallowing food. Full article

The future paradigm of early cardiac diagnostics is shifting the focus towards heart attack preventive medicine based on non-invasive medical imaging with the support of artificial intelligence. It is necessary to preventively detect its increased risk early and respond with preventive drugs before moving on to more effective, but also more invasive, forms of therapy. The main motivation of our study was to improve existing and develop new AI-based solutions for cardiac preventive medicine, with particular emphasis on the prevention of heart attacks. This is due to the fact that the epidemic of lifestyle diseases (including cardiologic ones) has been stopped but not reversed; hence, automatically supervised prevention using AI seems to be a key opportunity to introduce progress in the above-mentioned areas. This can have major effects not only scientific and clinical in nature, but also economic and social. The aim of this article is to develop and test an AI-based tool designed to predict the occurrence of a heart attack for the purposes of preventive medicine. It used the combination and comparison of multiple AI methods and techniques to determine a personalized heart attack probability based on a wide range of patient characteristics and, from a computational point of view, determine the minimum set of characteristics necessary to do so. When applied to a specific patient, this represents progress in this field of research, resulting in improvements in preclinical care and diagnostics, as well as predictive accuracy in preventive medicine. After an initial selection based on the authors’ knowledge and experience, four solutions turned out to be the best: linear support vector machine (Linear SVC), logistic regression, k-nearest neighbors algorithm (KNN, k-NN), and random forest. A comparison of the models developed in the study shows that models based on logistic regression proved to be the most accurate, although their predictive value is moderate, but sufficient for the initial screening diagnosis—selecting patients who require further, more accurate testing. In addition, this can be performed based on a reduced set of parameters, particularly heart rate, age, BMI, and cholesterol. This allows the development of a prevention strategy based on modifiable factors (e.g., in the form of diet, activity modification, or a hybrid combining different factors) combined with the monitoring of heart attack risk by the proposed system. The novelty and contribution of the described system lies in the use of AI for a widely available, cheap, and quick predictive analysis of cardiovascular functions in a group of patients classified as at risk, and over time in all patients as a standard periodic examination qualifying them for further, more advanced diagnosis of heart diseases. Full article

To monitor adherence to diets and to design and evaluate nutritional interventions, it is essential to obtain objective knowledge about eating behavior. In most research, measures of eating behavior are based on self-reporting, such as 24-h recalls, food records (food diaries) and food frequency questionnaires. Self-reporting is prone to inaccuracies due to inaccurate and subjective recall and other biases. Recording behavior using nonobtrusive technology in daily life would overcome this. Here, we provide an up-to-date systematic overview encompassing all (close-to) publicly or commercially available technologies to automatically record eating behavior in real-life settings. A total of 1328 studies were screened and, after applying defined inclusion and exclusion criteria, 122 studies were included for in-depth evaluation. Technologies in these studies were categorized by what type of eating behavior they measure and which type of sensor technology they use. In general, we found that relatively simple sensors are often used. Depending on the purpose, these are mainly motion sensors, microphones, weight sensors and photo cameras. While several of these technologies are commercially available, there is still a lack of publicly available algorithms that are needed to process and interpret the resulting data. We argue that future work should focus on developing robust algorithms and validating these technologies in real-life settings. Combining technologies (e.g., prompting individuals for self-reports at sensed, opportune moments) is a promising route toward ecologically valid studies of eating behavior. Full article

Our objective was to evaluate the effect of a mobile health (mHealth) intervention on lifestyle adherence and anthropometric characteristics among individuals with uncontrolled hypertension. We performed a randomized controlled trial (ClinicalTrials.gov NCT03005470) where all participants received lifestyle counseling at baseline and were randomly allocated to receive (1) an automatic oscillometric device to measure and register blood pressure (BP) via a mobile application, (2) personalized text messages to stimulate lifestyle changes, (3) both mHealth interventions, or (4) usual clinical treatment (UCT) without technology (control). The outcomes were achieved for at least four of five lifestyle goals (weight loss, not smoking, physical activity, moderate or stopping alcohol consumption, and improving diet quality) and improved anthropometric characteristics at six months. mHealth groups were pooled for the analysis. Among 231 randomized participants (187 in the mHealth group and 45 in the control group), the mean age was 55.4 ± 9.5 years, and 51.9% were men. At six months, achieving at least four of five lifestyle goals was 2.51 times more likely (95% CI: 1.26; 5.00, p = 0.009) to be achieved among participants receiving mHealth interventions. The between-group difference reached clinically relevant, but marginally significant, reduction in body fat (−4.05 kg 95% CI: −8.14; 0.03, p = 0.052), segmental trunk fat (−1.69 kg 95% CI: −3.50; 0.12, p = 0.067), and WC (−4.36 cm 95% CI: −8.81; 0.082, p = 0.054), favoring the intervention group. In conclusion, a six-month lifestyle intervention supported by application-based BP monitoring and text messages significantly improves adherence to lifestyle goals and is likely to reduce some anthropometric characteristics in comparison with the control without technology support. Full article

A gluten-free diet (GFD) is currently the only treatment available for patients with celiac disease (CD). However, adherence to a GFD can be challenging because gluten is present in many foods. A lifelong follow-up of patients with CD must be performed to promote adherence to a GFD and to identify the appearance of symptoms and the associated diseases. Therefore, the development of tools to analyze gluten exposure in these patients is important. This study proposes the development of the first automatable ELISA to monitor adherence to a GFD through the quantification of urine gluten immunogenic peptides (u-GIP). Seven healthy volunteers without suspicion of CD and 23 patients with CD were monitored as part of this study to optimize, validate, and apply this assay. Non-interference was found in the urine matrix, and the recovery percentage for spiked samples was 81–101%. The u-GIP was stable for up to 16 days when the samples were stored at different temperatures. Overall, 100% of the patients had detectable u-GIP at diagnosis (range of 0.39–2.14 ng GIP/mL), which reduced to 27% after 12 months on a GFD. Therefore, this highly sensitive immunoassay would allow the analysis of u-GIP from a large battery of samples in clinical laboratories of specialized healthcare centers. Full article

In light of the globally increasing prevalence of diet-related chronic diseases, new scalable and non-invasive dietary monitoring techniques are urgently needed. Automatically collected digital receipts from loyalty cards hereby promise to serve as an objective and automatically traceable digital marker for individual food choice behavior and do not require users to manually log individual meal items. With the introduction of the General Data Privacy Regulation in the European Union, millions of consumers gained the right to access their shopping data in a machine-readable form, representing a historic chance to leverage shopping data for scalable monitoring of food choices. Multiple quantitative indicators for evaluating the nutritional quality of food shopping have been suggested, but so far, no comparison has validated the potential of these alternative indicators within a comparative setting. This manuscript thus represents the first study to compare the calibration capacity and to validate the discrimination potential of previously suggested food shopping quality indicators for the nutritional quality of shopped groceries, including the Food Standards Agency Nutrient Profiling System Dietary Index (FSA-NPS DI), Grocery Purchase Quality Index-2016 (GPQI), Healthy Eating Index-2015 (HEI-2015), Healthy Trolley Index (HETI) and Healthy Purchase Index (HPI), checking if any of them performs differently from the others. The hypothesis is that some food shopping quality indicators outperform the others in calibrating and discriminating individual actual dietary intake. To assess the indicators’ potentials, 89 eligible participants completed a validated food frequency questionnaire (FFQ) and donated their digital receipts from the loyalty card programs of the two leading Swiss grocery retailers, which represent 70% of the national grocery market. Compared to absolute food and nutrient intake, correlations between density-based relative food and nutrient intake and food shopping data are stronger. The FSA-NPS DI has the best calibration and discrimination performance in classifying participants’ consumption of nutrients and food groups, and seems to be a superior indicator to estimate nutritional quality of a user’s diet based on digital receipts from grocery shopping in Switzerland. Full article

Dietary studies showed that dietary problems such as obesity are associated with other chronic diseases, including hypertension, irregular blood sugar levels, and increased risk of heart attacks. The primary cause of these problems is poor lifestyle choices and unhealthy dietary habits, which are manageable using interactive mHealth apps. However, traditional dietary monitoring systems using manual food logging suffer from imprecision, underreporting, time consumption, and low adherence. Recent dietary monitoring systems tackle these challenges by automatic assessment of dietary intake through machine learning methods. This survey discusses the best-performing methodologies that have been developed so far for automatic food recognition and volume estimation. Firstly, the paper presented the rationale of visual-based methods for food recognition. Then, the core of the study is the presentation, discussion, and evaluation of these methods based on popular food image databases. In this context, this study discusses the mobile applications that are implementing these methods for automatic food logging. Our findings indicate that around 66.7% of surveyed studies use visual features from deep neural networks for food recognition. Similarly, all surveyed studies employed a variant of convolutional neural networks (CNN) for ingredient recognition due to recent research interest. Finally, this survey ends with a discussion of potential applications of food image analysis, existing research gaps, and open issues of this research area. Learning from unlabeled image datasets in an unsupervised manner, catastrophic forgetting during continual learning, and improving model transparency using explainable AI are potential areas of interest for future studies. Full article

In recent years, telehealthcare systems (TSs) have become more and more widespread, as they can contribute to promoting the continuity of care and managing chronic conditions efficiently. Most TSs and nutrition recommendation systems require much information to return appropriate suggestions. This work proposes an ontology-based TS, namely HeNuALs, aimed at fostering a healthy diet and an active lifestyle in older adults with chronic pathologies. The system is built on the formalization of users’ health conditions, which can be obtained by leveraging existing standards. This allows for modeling different pathologies via reusable knowledge, thus limiting the amount of information needed to retrieve nutritional indications from the system. HeNuALs is composed of (1) an ontological layer that stores patients and their data, food and its characteristics, and physical activity-related data, enabling the inference a series of suggestions based on the effects of foods and exercises on specific health conditions; (2) two applications that allow both the patient and the clinicians to access the data (with different permissions) stored in the ontological layer; and (3) a series of wearable sensors that can be used to monitor physical exercise (provided by the patient application) and to ensure patients’ safety. HeNuALs inferences have been validated considering two different use cases. The system revealed the ability to determine suggestions for healthy, adequate, or unhealthy dishes for a patient with respiratory disease and for a patient with diabetes mellitus. Future work foresees the extension of the HeNuALs knowledge base by exploiting automatic knowledge retrieval approaches and validation of the whole system with target users. Full article

The Mediterranean diet (MD) is regarded as a healthy eating pattern with beneficial effects both for the decrease of the risk for non-communicable diseases and also for body weight reduction. In the current manuscript, we propose an automated smartphone application which monitors and evaluates the user’s adherence to MD using images of the food and drinks that they consume. We define a set of rules for automatic adherence estimation, which focuses on the main MD food groups. We use a combination of a convolutional neural network (CNN) and a graph convolutional network to detect the types of foods and quantities from the users’ food images and the defined set of rules to evaluate the adherence to MD. Our experiments show that our system outperforms a basic CNN in terms of recognizing food items and estimating quantity and yields comparable results as experienced dietitians when it comes to overall MD adherence estimation. As the system is novel, these results are promising; however, there is room for improvement of the accuracy by gathering and training with more data and certain refinements can be performed such as re-defining the set of rules to also be able to be used for sub-groups of MD (e.g., vegetarian type of MD). Full article

A balanced diet is the key to a healthy lifestyle and is crucial for preventing or dealing with many chronic diseases such as diabetes and obesity. Therefore, monitoring diet can be an effective way of improving people’s health. However, manual reporting of food intake has been shown to be inaccurate and often impractical. This paper presents a new approach to food intake quantity estimation using image-based modeling. The modeling method consists of three steps: firstly, a short video of the food is taken by the user’s smartphone. From such a video, six frames are selected based on the pictures’ viewpoints as determined by the smartphone’s orientation sensors. Secondly, the user marks one of the frames to seed an interactive segmentation algorithm. Segmentation is based on a Gaussian Mixture Model alongside the graph-cut algorithm. Finally, a customized image-based modeling algorithm generates a point-cloud to model the food. At the same time, a stochastic object-detection method locates a checkerboard used as size/ground reference. The modeling algorithm is optimized such that the use of six input images still results in an acceptable computation cost. In our evaluation procedure, we achieved an average accuracy of $92\%$ on a test set that includes images of different kinds of pasta and bread, with an average processing time of about 23 s. Full article