Calorie Estimation Research Articles

Artificial Intelligence Applications to Measure Food and Nutrient Intakes: Scoping Review.

Accurate measurement of food and nutrient intake is crucial for nutrition research, dietary surveillance, and disease management, but traditional methods such as 24-hour dietary recalls, food diaries, and food frequency questionnaires are often prone to recall error and social desirability bias, limiting their reliability. With the advancement of artificial intelligence (AI), there is potential to overcome these limitations through automated, objective, and scalable dietary assessment techniques. However, the effectiveness and challenges of AI applications in this domain remain inadequately explored. This study aimed to conduct a scoping review to synthesize existing literature on the efficacy, accuracy, and challenges of using AI tools in assessing food and nutrient intakes, offering insights into their current advantages and areas of improvement. This review followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A comprehensive literature search was conducted in 4 databases-PubMed, Web of Science, Cochrane Library, and EBSCO-covering publications from the databases' inception to June 30, 2023. Studies were included if they used modern AI approaches to assess food and nutrient intakes in human subjects. The 25 included studies, published between 2010 and 2023, involved sample sizes ranging from 10 to 38,415 participants. These studies used a variety of input data types, including food images (n=10), sound and jaw motion data from wearable devices (n=9), and text data (n=4), with 2 studies combining multiple input types. AI models applied included deep learning (eg, convolutional neural networks), machine learning (eg, support vector machines), and hybrid approaches. Applications were categorized into dietary intake assessment, food detection, nutrient estimation, and food intake prediction. Food detection accuracies ranged from 74% to 99.85%, and nutrient estimation errors varied between 10% and 15%. For instance, the RGB-D (Red, Green, Blue-Depth) fusion network achieved a mean absolute error of 15% in calorie estimation, and a sound-based classification model reached up to 94% accuracy in detecting food intake based on jaw motion and chewing patterns. In addition, AI-based systems provided real-time monitoring capabilities, improving the precision of dietary assessments and demonstrating the potential to reduce recall bias typically associated with traditional self-report methods. While AI demonstrated significant advantages in improving accuracy, reducing labor, and enabling real-time monitoring, challenges remain in adapting to diverse food types, ensuring algorithmic fairness, and addressing data privacy concerns. The findings suggest that AI has transformative potential for dietary assessment at both individual and population levels, supporting precision nutrition and chronic disease management. Future research should focus on enhancing the robustness of AI models across diverse dietary contexts and integrating biological sensors for a holistic dietary assessment approach.

KAWANKULINER: PERSONALISED FOOD RECOMMENDATION APP USING BMR AND TDEE FOR OPTIMAL DAILY NUTRITION

People often have difficulty in determining the type of food that is suitable for the composition of their body. This is due to the many types of food available, as well as the lack of information about the nutritional content of each type of food. By fulfilling the daily calorie and macro-nutrient needs required by the body, its metabolism can be maintained, preventing various health problems such as malnutrition. Based on the results of the Basic Health Research in 2018 malnutrition is one of the most serious problems in Indonesia. Several studies related to calculating calorie estimates using the BMR approach with the utilization of technology have been conducted.However, these studies were limited to only displaying the amount of daily calorie needs that were not accompanied by what foods were needed to meet these daily needs. The purpose of this research is to build an app to help individuals understand their daily calorie needs based on their Basal Metabolic Rate (BMR) and total daily expenditure energy (TDEE), using smart scale to provide body composition information and spoonacular API to provide food recommendations that match their energy needs and give them recipes on how to make their food meanwhile waterfall model is used as a software development method. The test results show that the app meets the functional and usability requirements well, with a high accuracy rate of 99.86% for calories, protein, fat, and carbohydrates. In terms of user response, 13 respondents had a very positive response, and considered the app useful for making it easier to get information about their calorie and macro-nutrient needs, as well as provide food recommendations based on their daily needs.

Estimating Indian Food Calorie with Convolution Neural Networks and Transfer Learning

The project's primary objective is to develop a robust and adaptable neural network model capable of recognizing the diverse range of Indian dishes from images. By harnessing the power of transfer learning, the model leverages pre-trained neural networks to extract relevant features, allowing for accurate identification of distinct dishes, even with limited training data. Endeavors addresses the vital need for precise and efficient estimation of calorie in Indian cuisine through the application of stateof-the-art transfer learning techniques in the realm of the food image recognition. Beyond food recognition, the project introduces a novel calorie estimation component. The neural network model, after identifying the dish in the image, utilizes its knowledge of the dish's ingredients and portion sizes to estimate calorie content. This integration of food recognizes and calorie content estimation serves a valuable tool for the individuals seeking to monitor their dietary intake and make informed nutritional choices, promoting a healthier lifestyle.

FOOD CLASSIFICATION AND CALORIE ESTIMATION USING CNN

This research paper explores the transformative impact of deep learning methodologies in the domains of food image recognition, classification, and calorie estimation. By utilizing the convergence of machine learning with convolutional neural networks (CNNs), the study tackles the growing concerns surrounding obesity and health difficulties, highlighting the need for creative methods of nutritional monitoring. Motivated by challenges in fruit classification and the limitations of traditional methods, the research progressively shifts towards efficient and accurate image-based approaches, particularly highlighting the effectiveness of CNNs. The methodology focuses on machine learning-based approaches for food calorie estimation, with a specific emphasis on parameter-optimized lightweight CNN models utilizing TensorFlow's Object Detection API and CNN. The results showcase impressive accuracy levels, often exceeding 90%, across diverse food items, albeit with persistent challenges such as limited datasets, computational costs, and real-world application constraints. In conclusion, this comprehensive review underscores the transformative potential of deep learning in fostering healthier lifestyles, combating obesity, and providing valuable insights for dietary guidance and health management. Further research is recommended to enhance dataset representativeness and optimize model generalization for broader practical applicability Keywords: Calorie estimation, Classification, Convolutional neural network, Object detection.

SURVEY ON FOOD CLASSIFICATION AND CALORIE ESTIMATION USING CNN

This research paper explores the transformative impact of deep learning methodologies in the domains of food image recognition, classification, and calorie estimation. By utilizing the convergence of machine learning with convolutional neural networks (CNNs), the study tackles the growing concerns surrounding obesity and health difficulties, highlighting the need for creative methods of nutritional monitoring. Motivated by challenges in fruit classification and the limitations of traditional methods, the research progressively shifts towards efficient and accurate image-based approaches, particularly highlighting the effectiveness of CNNs. The methodology focuses on machine learning-based approaches for food calorie estimation, with a specific emphasis on parameter-optimized lightweight CNN models utilizing TensorFlow's Object Detection API and Mask R-CNN. The results showcase impressive accuracy levels, often exceeding 90%, across diverse food items, albeit with persistent challenges such as limited datasets, computational costs, and real-world application constraints. In conclusion, this comprehensive review underscores the transformative potential of deep learning in fostering healthier lifestyles, combating obesity, and providing valuable insights for dietary guidance and health management. Further research is recommended to enhance dataset representativeness and optimize model generalization for broader practical applicability Keywords: Calorie estimation, Classification, Convolutional neural network, Object detection.

Multi-Spectral Food Classification and Caloric Estimation Using Predicted Images.

In nutrition science, methods that accomplish continuous recognition of ingested foods with minimal user intervention have great utility. Our recent study showed that using images taken at a variety of wavelengths, including ultraviolet (UV) and near-infrared (NIR) bands, improves the accuracy of food classification and caloric estimation. With this approach, however, analysis time increases as the number of wavelengths increases, and there are practical implementation issues associated with a large number of light sources. To alleviate these problems, we proposed a method that used only standard red-green-blue (RGB) images to achieve performance that approximates the use of multi-wavelength images. This method used RGB images to predict the images at each wavelength (including UV and NIR bands), instead of using the images actually acquired with a camera. Deep neural networks (DNN) were used to predict the images at each wavelength from the RGB images. To validate the effectiveness of the proposed method, feasibility tests were carried out on 101 foods. The experimental results showed maximum recognition rates of 99.45 and 98.24% using the actual and predicted images, respectively. Those rates were significantly higher than using only the RGB images, which returned a recognition rate of only 86.3%. For caloric estimation, the minimum values for mean absolute percentage error (MAPE) were 11.67 and 12.13 when using the actual and predicted images, respectively. These results confirmed that the use of RGB images alone achieves performance that is similar to multi-wavelength imaging techniques.

Mathematical Study on Palatable Diet Administration with a Reference to Diabetes Mellitus on Varying Body Frames - ANOVA Test with PFC Ratio

Abstract: A mathematical model is presented in this paper to compute the palatable prescription of chosen diet for diabetes mellitus type-II using Joselin’s principle. Two types of portions of the food as red portion and black portionare chosen for palatable diet with 1:1:1gm equivalent to 4:9:4cal.taken as Protein(P), Fat(F) and Carbohydrate(C) respectively. For the analysis, three types of body frames as Small(S), Medium(M) and Large(L) for both men and women aged 19 years and above are considered. A reference tojuvenileis introduced for the palatable diet. Differential equationsin the coupled form are definedto explain the varying glucose level and varying insulin level. Average calorie values are computed in reference to age and height for the estimation of PFC using linear regression model. ANOVA gives the comparison of results of calorie estimation for palatable diet chosen. With the administration of palatable diet, the values of PFC can be varied to meet the required glucose level of diabetes mellitus type-II

Deep Learning-based Food Calorie Estimation Method in Dietary Assessment: An Advanced Approach using Convolutional Neural Networks

Deep Learning-based Food Calorie Estimation Method in Dietary Assessment: An Advanced Approach using Convolutional Neural Networks

JoulesEye

Smartphones and smartwatches have contributed significantly to fitness monitoring by providing real-time statistics, thanks to accurate tracking of physiological indices such as heart rate. However, the estimation of calories burned during exercise is inaccurate and cannot be used for medical diagnosis. In this work, we present JoulesEye, a smartphone thermal camera-based system that can accurately estimate calorie burn by monitoring respiration rate. We evaluated JoulesEye on 54 participants who performed high intensity cycling and running. The mean absolute percentage error (MAPE) of JoulesEye was 5.8%, which is significantly better than the MAPE of 37.6% observed with commercial smartwatch-based methods that only use heart rate. Finally, we show that an ultra-low-resolution thermal camera that is small enough to fit inside a watch or other wearables is sufficient for accurate calorie burn estimation. These results suggest that JoulesEye is a promising new method for accurate and reliable calorie burn estimation.

Menu Labeling and Calories Purchased in Restaurants in a US National Fast Food Chain

Menu labeling has been implemented in restaurants in some US jurisdictions as early as 2008, but the extent to which menu labeling is associated with calories purchased is unclear. To estimate the association of menu labeling with calories and nutrients purchased and assess geographic variation in results. A cohort study was conducted with a quasi-experimental design using actual transaction data from Taco Bell restaurants from calendar years 2007 to 2014 US restaurants with menu labeling matched to comparison restaurants using synthetic control methods. Data were analyzed from May to October 2023. Menu labeling policies in 6 US jurisdictions. The primary outcome was calories per transaction. Secondary outcomes included total and saturated fat, carbohydrates, protein, sugar, fiber, and sodium. The final sample included 2329 restaurants, with menu labeling in 474 (31 468 restaurant-month observations). Most restaurants (94.3%) were located in California. Difference-in-differences model results indicated that customers purchased 24.7 (95% CI, 23.6-25.7) fewer calories per transaction from restaurants in the menu labeling group in the 3- to 24-month follow-up period vs the comparison group, including 21.9 (95% CI, 20.9-22.9) fewer calories in the 3- to 12-month follow-up period and 25.0 (95% CI, 24.0-26.1) fewer calories in the 13- to 24-month follow-up period. Changes in the nutrient content of transactions were consistent with calorie estimates. Findings in California were similar to overall estimates in magnitude and direction; yet, among restaurants outside of California, no association was observed in the 3- to 24-month period. The outcome of menu labeling also differed by item category and time of day, with a larger decrease in the number of tacos vs other items purchased and a larger decrease in calories purchased during breakfast vs other times of the day in the 3- to 24-month period. In this quasi-experimental cohort study, fewer calories were purchased in restaurants with calorie labels compared with those with no labels, suggesting that consumers are sensitive to calorie information on menu boards, although associations differed by location.

Validation of Polar Grit X Pro for Estimating Energy Expenditure during Military Field Training: A Pilot Study.

Wearables are lightweight, portable technology devices that are traditionally used to monitor physical activity and workload as well as basic physiological parameters such as heart rate. However recent advances in monitors have enabled better algorithms for estimation of caloric expenditure from heart rate for use in weight loss as well as sport performance. can be used for estimating energy expenditure and nutritional demand. Recently, the military has adopted the use of personal wearables for utilization in field studies for ecological validity of training. With popularity of use, the need for validation of these devices for caloric estimates is needed to assist in work-rest cycles. Thus the purpose of this effort was to evaluate the Polar Grit X for energy expenditure (EE) for use in military training exercises. Polar Grit X Pro watches were worn by active-duty elite male operators (N = 16; age: 31.7 ± 5.0 years, height: 180.1 ± 6.2 cm, weight: 91.7 ± 9.4 kg). Metrics were measured against indirect calorimetry of a metabolic cart and heart rate via a Polar heart rate monitor chest strap while exercising on a treadmill. Participants each performed five 10-minute bouts of running at a self-selected speed and incline to maintain a heart rate within one of five heart rate zones, as ordered and defined by Polar. Polar Grit X Pro watch had a good to excellent interrater reliability to indirect calorimetry at estimating energy expenditure (ICC = 0.8, 95% CI = 0.61-0.89, F (74,17.3) = 11.76, p < 0.0001) and a fair to good interrater reliability in estimating macronutrient partitioning (ICC = 0.49, 95% CI = 0.3-0.65, F (74,74.54) = 2.98, p < 0.0001). There is a strong relationship between energy expenditure as estimated from the Polar Grit X Pro and measured through indirect calorimetry. The Polar Grit X Pro watch is a suitable tool for estimating energy expenditure in free-living participants in a field setting and at a range of exercise intensities.

Investigating cognitive biases: does halo effect from nutrition or health claims drive negative calorie illusion in food combinations?

SummaryPeople in developed countries have access to healthier food options. However, there is also an increasing availability of energy‐dense foods. While energy‐dense foods play a major role in food accessibility, their prevalence also escalates the obesogenic environment. This paper aims to understand the role of cognitive biases on food consumption from the view of calorie underestimation. Specifically, the study examines how consumers perceive food calorie content and how consumers interpret the claims on food packaging. 525 UK respondents were asked to evaluate five different food combinations. The average calorie estimations for each meal were compared with their actual calorie contents to identify underestimation/overestimation. T‐test was conducted, and logistic regression and linear regression were estimated. The results show that heuristic is often adopted in food selection. Foods are categorised into vice and virtue according to the different goals they support. The existence of virtue food options (e.g., fruit and vegetable) reduces the perceived calorie content of the meal. Likewise, nutrition and health claims such as low‐fat and zero‐sugar also decrease the calorie estimation, especially when the labelled food is unhealthy. Considering overeating is a consequence of calorie underestimation, consumers' knowledge of nutritional quality needs to be improved.

Fast and Accurate Calorie Count Prediction from Food Images using a Convolution Neural Network Method

In the past ten years, with advances in deep learning techniques, automated object recognition has come very near to human levels of accuracy. Fast, automatic, and consistent image-based food calorie calculation is becoming a requirement with the increasing growth of overweight and other lifestyle- related disorders throughout the globe. Accurate and insightful solutions may be provided in the form of a mobile app with the aid of a deep learning-based automatic object recognition system. However, real-time image processing necessitates a high level of processing speed, which is a major consideration for such applications. Although several researchers have looked at estimating calories based on pictures of food, there is currently no image-driven, lightweight, rapid, and accurate food calorie estimation method. In this study, we offer a technique for recognizing common meals captured with a mobile phone camera by using Convolution Neural Networks (CNN) with optimum parameters. Calories and other nutritional information may be deduced from the known food class after the food items have been identified. Our research shows that our suggested method not only guarantees precision but also has the potential to greatly streamline the complex, time-consuming, and labor-intensive processes now used for estimating calorie intake by turning them together into real-time automation techniques.

Evaluating machine learning technologies for food computing from a data set perspective

Food plays an important role in our lives that goes beyond mere sustenance. Food affects behavior, mood, and social life. It has recently become an important focus of multimedia and social media applications. The rapid increase of available image data and the fast evolution of artificial intelligence, paired with a raised awareness of people’s nutritional habits, have recently led to an emerging field attracting significant attention, called food computing, aimed at performing automatic food analysis. Food computing benefits from technologies based on modern machine learning techniques, including deep learning, deep convolutional neural networks, and transfer learning. These technologies are broadly used to address emerging problems and challenges in food-related topics, such as food recognition, classification, detection, estimation of calories and food quality, dietary assessment, food recommendation, etc. However, the specific characteristics of food image data, like visual heterogeneity, make the food classification task particularly challenging. To give an overview of the state of the art in the field, we surveyed the most recent machine learning and deep learning technologies used for food classification with a particular focus on data aspects. We collected and reviewed more than 100 papers related to the usage of machine learning and deep learning for food computing tasks. We analyze their performance on publicly available state-of-art food data sets and their potential for usage in multimedia food-related applications for various needs (communication, leisure, tourism, blogging, reverse engineering, etc.). In this paper, we perform an extensive review and categorization of available data sets: to this end, we developed and released an open web resource in which the most recent existing food data sets are collected and mapped to the corresponding geographical regions. Although artificial intelligence methods can be considered mature enough to be used in basic food classification tasks, our analysis of the state-of-the-art reveals that challenges related to the application of this technology need to be addressed. These challenges include, among others: poor representation of regional gastronomy, incorporation of adaptive learning schemes, and reverse engineering for automatic food creation and replication.

Multispectral Food Classification and Caloric Estimation Using Convolutional Neural Networks.

Continuous monitoring and recording of the type and caloric content of ingested foods with a minimum of user intervention is very useful in preventing metabolic diseases and obesity. In this paper, automatic recognition of food type and caloric content was achieved via the use of multi-spectral images. A method of fusing the RGB image and the images captured at ultra violet, visible, and near-infrared regions at center wavelengths of 385, 405, 430, 470, 490, 510, 560, 590, 625, 645, 660, 810, 850, 870, 890, 910, 950, 970, and 1020 nm was adopted to improve the accuracy. A convolutional neural network (CNN) was adopted to classify food items and estimate the caloric amounts. The CNN was trained using 10,909 images acquired from 101 types. The objective functions including classification accuracy and mean absolute percentage error (MAPE) were investigated according to wavelength numbers. The optimal combinations of wavelengths (including/excluding the RGB image) were determined by using a piecewise selection method. Validation tests were carried out on 3636 images of the food types that were used in training the CNN. As a result of the experiments, the accuracy of food classification was increased from 88.9 to 97.1% and MAPEs were decreased from 41.97 to 18.97 even when one kind of NIR image was added to the RGB image. The highest accuracy for food type classification was 99.81% when using 19 images and the lowest MAPE for caloric content was 10.56 when using 14 images. These results demonstrated that the use of the images captured at various wavelengths in the UV and NIR bands was very helpful for improving the accuracy of food classification and caloric estimation.

Watch out for the healthy trap! How food flavor influences healthiness evaluations and consumption

Flavors are extensively used in food products to attract consumers, driving purchases successfully. But how do these flavors influence consumers’ calorie estimation and healthiness evaluation? In a series of four behavioral experiments, we formally examine the effect of flavor information on consumer food healthiness evaluations and behavioral responses. We find that when a base food contains a healthy flavor (vs. unhealthy flavor), consumers perceive the food to be lower (vs. higher) in calories and healthier and are more likely to purchase such flavored food. In addition, such flavor-healthiness evaluation effect as a heuristic is attenuated when consumers are aware of this effect, and the indirect effect of calorie estimation on purchase intention is magnified among consumers with high dieting tendency. These findings shed light on how flavor information shapes consumers’ responses to flavored food, contribute to food consumption-related literature, and provide practical implications for consumers and policymakers.

Foodopedia: A Convolutional Neural Network Based Food Calorie Estimation

The number of calories consumed determines how healthy a body is in the modern world; therefore, it's important to watch your calorie intake to be healthy. People must keep track of their caloric intake in order to become in shape or maintain a healthy weight. The suggested model uses a deep learning algorithm to offer a novel method of calorie measurement. In the medical area, the estimation of dietary calories is crucial. This measurement is derived from the representation of food in various objects, such as fruits and vegetables. The neural network is used to take this measurement. This technique uses a convolutional neural network to determine the calories in food. An image of food is used as the input for this calculated model. The suggested CNN model uses food object identification to calculate the calorie content of the food. Volume error estimation serves as the primary parameter for the outcome, while calorie error estimation serves as the secondary parameter.

Food Detection and Calorie Estimation using Deep Learning

Abstract: For the fight against obesity, precise food and energy intake measurement techniques are essential. One of the most important lessons for long-term prevention and effective treatment programmes is the provision of users and patients with practical and intelligent solutions that assist them in measuring their food intake and gathering dietary information. In this article, we suggest a calorie measurement technique to assist patients and medical professionals in their battle against dietrelated illnesses. In this document, we suggest a food identification system that, when given the appropriate quantity of data, can assist a user in keeping track of daily caloric consumption. Calorie estimation for the current method must be done by hand. The proposed model will use a deep learning algorithm to offer a special method of calculating calories. In the world of medicine, calorie calculations for food are crucial. because the calories in this food are beneficial to your health. This measurement is derived from photographs of various foods, including fruits and vegetables. Our suggested solution relies on cell phones, which enable the user to take a picture of the food and instantly calculate the number of calories consumed. We classify food photos for system training using deep convolutional neural networks to reliably identify the food in the system. In this study, we use a convolutional neural network (CNN) to detect and identify images of food. Given the huge range of food types, picture recognition of food products is frequently very difficult. Whatever the case, deep learning has recently been shown to be an incredibly innovative image identification approach, and CNN is the greatest way to use deep learning.

High Protein Whole Food Snack and Albumin Outcomes in Patients With Dialysis-Dependent Chronic Kidney Disease

Protein-energy wasting is common among patients on hemodialysis (HD). This study sought to define effects that a novel, post-HD, high-calorie, high-protein whole food snack had on patients' serum albumin (serum alb), serum phosphorus and equilibrated normalized protein catabolic rate (enPCR). A 12-month (6months intervention, 6months pre/post data collection), single-center, unblinded study was conducted. Participants (n=67) consumed, ad libitum, a whole food snack post-HD for 6 treatments each month. Upon analysis, regression models identified relationships between serum alb and whole food snack consumption across follow up. Predefined effect size anticipated was + 0.2g/dL. Patients were stratified by high (≥4g/dL) or low (<4g/dL) mean serum alb during a 3-month baseline period. Paired t-tests compared mean per patient difference in serum alb, enPCR and serum phosphorus from baseline to each month of follow up, stratified by high (≥640 g) or low (<640 g) consumption of the whole food snack (a priori caloric estimation). Linear regression models showed positive associations between higher serum alb and enPCR with higher whole food snack consumption across follow up (all P<.05). Assessments from baseline to each follow-up month show some increases in serum alb, yet t test comparisons were not significant. No significant changes were seen in serum phosphorus levels during follow-up. Albeit the catabolic effects of HD are well-known, effective nutritional interventions are scarce. Results showed that providing a whole food snack post-HD to individuals with serum alb <4.0g/dL may be beneficial but further studies are recommended.

Food Image Detection System and Calorie Content Estimation Using Yolo to Control Calorie Intake in the Body

Excess calories in the body can cause obesity and several degenerative diseases, such as diabetes mellitus, heart disease, stroke, hypertension, and others. This system helps people maintain a balanced calorie content that enters the body. The research designs this system using the YOLO algorithm model to detect the type of food which is then developed using the Python programming language to estimate the calories of the detected food. YOLO uses the principle of feature extraction in images that are processed through filters as arrays to perform detection. This system calculates the food calories estimation by multiplying the calories for each food by the amount according to the type of food detected. The calorie value of the food provided is based on the number of calories for each portion of food taken from FatSecret Indonesia. The result is that food detection performance is quite good with average precision, recall, and F1-score values of 0.94, 0.90, and 0.91 respectively, when testing the model. However, when tested on Hugging Face, the performance decreased with the average values of precision, recall, and F1-score respectively, namely 0.84, 0.32, and 0.41. This decrease in performance is because of poor CPU usage and a decrease in image quality when uploaded to the Hugging Face.