scholarly journals A Comprehensive Survey of Image-Based Food Recognition and Volume Estimation Methods for Dietary Assessment

Healthcare ◽  
2021 ◽  
Vol 9 (12) ◽  
pp. 1676
Author(s):  
Ghalib Ahmed Tahir ◽  
Chu Kiong Loo
Keyword(s):  
Neural Networks ◽  
Dietary Habits ◽  
Volume Estimation ◽  
Estimation Methods ◽  
Monitoring Systems ◽  
Automatic Assessment ◽  
Increased Risk ◽  
Food Recognition ◽  
Food Image ◽  
Dietary Monitoring

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.

scholarly journals Computational Geometry-Based Surface Reconstruction for Volume Estimation: A Case Study on Magnitude-Frequency Relations for a LiDAR-Derived Rockfall Inventory

2021 ◽  
Vol 10 (3) ◽  
pp. 157
Author(s):  
Paul-Mark DiFrancesco ◽  
David A. Bonneau ◽  
D. Jean Hutchinson
Keyword(s):  
Computational Geometry ◽  
Surface Reconstruction ◽  
Power Law ◽  
Point Cloud ◽  
Point Clouds ◽  
Volume Estimation ◽  
Estimation Methods ◽  
Small Scale ◽  
Reconstruction Methods ◽  
3D Volume

Key to the quantification of rockfall hazard is an understanding of its magnitude-frequency behaviour. Remote sensing has allowed for the accurate observation of rockfall activity, with methods being developed for digitally assembling the monitored occurrences into a rockfall database. A prevalent challenge is the quantification of rockfall volume, whilst fully considering the 3D information stored in each of the extracted rockfall point clouds. Surface reconstruction is utilized to construct a 3D digital surface representation, allowing for an estimation of the volume of space that a point cloud occupies. Given various point cloud imperfections, it is difficult for methods to generate digital surface representations of rockfall with detailed geometry and correct topology. In this study, we tested four different computational geometry-based surface reconstruction methods on a database comprised of 3668 rockfalls. The database was derived from a 5-year LiDAR monitoring campaign of an active rock slope in interior British Columbia, Canada. Each method resulted in a different magnitude-frequency distribution of rockfall. The implications of 3D volume estimation were demonstrated utilizing surface mesh visualization, cumulative magnitude-frequency plots, power-law fitting, and projected annual frequencies of rockfall occurrence. The 3D volume estimation methods caused a notable shift in the magnitude-frequency relations, while the power-law scaling parameters remained relatively similar. We determined that the optimal 3D volume calculation approach is a hybrid methodology comprised of the Power Crust reconstruction and the Alpha Solid reconstruction. The Alpha Solid approach is to be used on small-scale point clouds, characterized with high curvatures relative to their sampling density, which challenge the Power Crust sampling assumptions.

scholarly journals Role of Dietary Habits in the Prevention of Diverticular Disease Complications: A Systematic Review

Nutrients ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 1288
Author(s):  
Marilia Carabotti ◽  
Francesca Falangone ◽  
Rosario Cuomo ◽  
Bruno Annibale
Keyword(s):  
Systematic Review ◽  
Diverticular Disease ◽  
Dietary Habits ◽  
Acute Diverticulitis ◽  
High Quality ◽  
Eligibility Criteria ◽  
Diverticular Bleeding ◽  
Recurrent Diverticulitis ◽  
Increased Risk

Recent evidence showed that dietary habits play a role as risk factors for the development of diverticular complications. This systematic review aims to assess the effect of dietary habits in the prevention of diverticula complications (i.e., acute diverticulitis and diverticula bleeding) in patients with diverticula disease. PubMed and Scopus databases were searched up to 19 January 2021, 330 records were identified, and 8 articles met the eligibility criteria and were subjected to data extraction. The quality of the studies was evaluated by the Newcastle-Ottawa quality assessment form. No study meets the criteria for being a high-quality study. A high intake of fiber was associated to a decreased risk of diverticulitis or hospitalization due to diverticular disease, with a protective effect for fruits and cereal fiber, but not for vegetable fiber; whereas, a high red meat consumption and a generally Western dietary pattern were associated with an increased risk of diverticulitis. Alcohol use seemed to be associated to diverticular bleeding, but not to recurrent diverticulitis or diverticular complications. Further high-quality studies are needed to better define these associations. It is mandatory to ascertain the role of dietary habits for the development of recurrent acute diverticulitis and diverticular bleeding.

scholarly journals 745 Risk Factors of Incident Renal Stones in Indian Population: A Hospital-Based Case-Control Study

2021 ◽  
Vol 108 (Supplement_2) ◽  
Author(s):  
S Singh ◽  
S Gupta ◽  
T S Mishra ◽  
B D Banerjee ◽  
T Sharma ◽  
...  
Keyword(s):  
Risk Factors ◽  
Heavy Metals ◽  
Case Control Study ◽  
Dietary Habits ◽  
Renal Stones ◽  
Tertiary Hospital ◽  
Case Control ◽  
The Body ◽  
Increased Risk ◽  
Control Study

Abstract Introduction Nephrolithiasis is pathological calcification in the excretory passages of the body and is prevalent among 7.6% of Indians. We aimed to study the various risk factors associated with renal stones from India. Method It was a hospital-based case-control study conducted over 18 months in a tertiary hospital in Delhi. Cases were defined as patients with renal stones diagnosed on the basis of history and radiological examination. Controls were similar to cases in all respects except for the diagnosis and selected from the hospital. A total of 18 risk factors, including age, gender, heavy metals, stress, metabolic factors, alcohol intake, dietary habits, co-morbidities, etc. were assessed. Logistic regression analysis was performed to calculate the strength of the risk associations. Results In the analysis of 60 cases and controls, we found 6 times, 5.5 times, and 2.4 times increased odds of renal stones in patients with increased arsenic, cadmium, and lead concentrations in blood, respectively. Similarly, there are 3 times increased odds of renal stones in patients suffering from stress. Conclusions Exposure to smoke, occupation dust, and contaminated water may lead to an increased ingestion/inhalation of heavy metals like cadmium, arsenic, and predisposing people to an increased risk of renal stones.

scholarly journals Food Recognition for Dietary Monitoring during Smoke Quitting

2021 ◽  
Author(s):  
Sebastiano Battiato ◽  
Pasquale Caponnetto ◽  
Oliver Giudice ◽  
Mazhar Hussain ◽  
Roberto Leotta ◽  
...  
Keyword(s):  
Food Recognition ◽  
Dietary Monitoring

scholarly journals Vehicle Trajectory Estimation Based on Fusion of Visual Motion Features and Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7969
Author(s):  
Lianen Qu ◽  
Matthew N. Dailey
Keyword(s):  
Neural Networks ◽  
Optical Flow ◽  
Convolutional Neural Networks ◽  
Situation Awareness ◽  
Visual Motion ◽  
Accurate Method ◽  
Estimation Methods ◽  
Single Type ◽  
Global Localization ◽  
Trajectory Estimation

Driver situation awareness is critical for safety. In this paper, we propose a fast, accurate method for obtaining real-time situation awareness using a single type of sensor: monocular cameras. The system tracks the host vehicle’s trajectory using sparse optical flow and tracks vehicles in the surrounding environment using convolutional neural networks. Optical flow is used to measure the linear and angular velocity of the host vehicle. The convolutional neural networks are used to measure target vehicles’ positions relative to the host vehicle using image-based detections. Finally, the system fuses host and target vehicle trajectories in the world coordinate system using the velocity of the host vehicle and the target vehicles’ relative positions with the aid of an Extended Kalman Filter (EKF). We implement and test our model quantitatively in simulation and qualitatively on real-world test video. The results show that the algorithm is superior to state-of-the-art sequential state estimation methods such as visual SLAM in performing accurate global localization and trajectory estimation for host and target vehicles.

scholarly journals Long-Term Overconsumption of Sugar Starting at Adolescence Produces Persistent Hyperactivity and Neurocognitive Deficits in Adulthood

2021 ◽  
Vol 15 ◽  
Author(s):  
Kate Beecher ◽  
Ignatius Alvarez Cooper ◽  
Joshua Wang ◽  
Shaun B. Walters ◽  
Fatemeh Chehrehasa ◽  
...  
Keyword(s):  
Dietary Habits ◽  
Hippocampal Neurogenesis ◽  
Neurocognitive Deficits ◽  
Long Term Effects ◽  
Sugar Consumption ◽  
Food And Beverages ◽  
Increased Risk ◽  
Newborn Neurons ◽  
Dependent Learning

Sugar has become embedded in modern food and beverages. This has led to overconsumption of sugar in children, adolescents, and adults, with more than 60 countries consuming more than four times (>100 g/person/day) the WHO recommendations (25 g/person/day). Recent evidence suggests that obesity and impulsivity from poor dietary habits leads to further overconsumption of processed food and beverages. The long-term effects on cognitive processes and hyperactivity from sugar overconsumption, beginning at adolescence are not known. Using a well-validated mouse model of sugar consumption, we found that long-term sugar consumption, at a level that significantly augments weight gain, elicits an abnormal hyperlocomotor response to novelty and alters both episodic and spatial memory. Our results are similar to those reported in attention deficit and hyperactivity disorders. The deficits in hippocampal-dependent learning and memory were accompanied by altered hippocampal neurogenesis, with an overall decrease in the proliferation and differentiation of newborn neurons within the dentate gyrus. This suggests that long-term overconsumption of sugar, as that which occurs in the Western Diet might contribute to an increased risk of developing persistent hyperactivity and neurocognitive deficits in adulthood.

An ensemble feature method for food classification

2017 ◽  
Vol 26 (1) ◽  
pp. 13-39
Author(s):  
Niki Martinel ◽  
Christian Micheloni ◽  
Claudio Piciarelli
Keyword(s):  
Random Forest ◽  
State Of The Art ◽  
Texture Feature ◽  
Random Forest Classifier ◽  
Texture Feature Extraction ◽  
Feature Encoding ◽  
Food Recognition ◽  
Feature Based ◽  
Food Image ◽  
Comparative Results

In the last years, several works on automatic image-based food recognition have been proposed, often based on texture feature extraction and classification. However, there is still a lack of proper comparisons to evaluate which approaches are better suited for this specific task. In this work, we adopt a Random Forest classifier to measure the performances of different texture filter banks and feature encoding techniques on three different food image datasets. Comparative results are given to show the performance of each considered approach, as well as to compare the proposed Random Forest classifiers with other feature-based state-of-the-art solutions.

Sign in / Sign up

Export Citation Format

Share Document