scholarly journals Nutrition Monitoring and Calorie Estimation using Internet of Things (IoT)

2019 ◽  
Vol 8 (11) ◽  
pp. 2669-2672
Keyword(s):  
Internet Of Things ◽  
Volume Estimation ◽  
Calorie Intake ◽  
Sensing Element ◽  
Mobile Environment ◽  
Convolutional Network ◽  
Principal Aspect ◽  
Food Image ◽  
Estimation System ◽  
Food Journaling

Diet observation is one of the principal aspect in precautionary health care that aims to cut back varied health risks. The various recent advancements in smartphone and wearable sensing element technologies have paved way to a proliferation of food observation applications that are based on automated image processing and intake detection, with an aim to beat drawbacks of the standard manual food journaling that's time overwhelming, inaccurate, underreporting, and low adherent. The currently developed food logging methods are very much time consuming and inconvenient that limits their effectiveness. The proposed work presents an Internet of Things (IoT) based mobile-controlled calorie estimation system to make technical advancements in healthcare industry. The proposed system operates on mobile environment, which allow the user to acquire the food image and quantify the calorie intake mechanically. The Mqtt protocol based MyMqtt broker is used to connect the application and the edge device and also to store the data in the Thingspeak cloud. A deep convolutional network is employed to classify the food accurately within the system. The volume estimation is done using sensors and the calorie approximation is done using formula

Automatic Kidney Volume Estimation System Using Transfer Learning Techniques

2021 ◽  
pp. 370-381
Author(s):  
Chiu-Han Hsiao ◽  
Ming-Chi Tsai ◽  
Frank Yeong-Sung Lin ◽  
Ping-Cherng Lin ◽  
Feng-Jung Yang ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Volume Estimation ◽  
Kidney Volume ◽  
Learning Techniques ◽  
Estimation System

scholarly journals Feasibility Study of an Automated Carbohydrate Estimation System Using Thai Food Images in Comparison With Estimation by Dietitians

2021 ◽  
Vol 8 ◽  
Author(s):  
Phawinpon Chotwanvirat ◽  
Narit Hnoohom ◽  
Nipa Rojroongwasinkul ◽  
Wantanee Kriengsinyos
Keyword(s):  
Estimation Error ◽  
Weight System ◽  
Registered Dietitians ◽  
Estimation Errors ◽  
Carbohydrate Counting ◽  
Measured Weight ◽  
Food Image ◽  
Food Images ◽  
Estimation System

Carbohydrate counting is essential for well-controlled blood glucose in people with type 1 diabetes, but to perform it precisely is challenging, especially for Thai foods. Consequently, we developed a deep learning-based system for automatic carbohydrate counting using Thai food images taken from smartphones. The newly constructed Thai food image dataset contained 256,178 ingredient objects with measured weight for 175 food categories among 75,232 images. These were used to train object detector and weight estimator algorithms. After training, the system had a Top-1 accuracy of 80.9% and a root mean square error (RMSE) for carbohydrate estimation of <10 g in the test dataset. Another set of 20 images, which contained 48 food items in total, was used to compare the accuracy of carbohydrate estimations between measured weight, system estimation, and eight experienced registered dietitians (RDs). System estimation error was 4%, while estimation errors from nearest, lowest, and highest carbohydrate among RDs were 0.7, 25.5, and 7.6%, respectively. The RMSE for carbohydrate estimations of the system and the lowest RD were 9.4 and 10.2, respectively. The system could perform with an estimation error of <10 g for 13/20 images, which placed it third behind only two of the best performing RDs: RD1 (15/20 images) and RD5 (14/20 images). Hence, the system was satisfactory in terms of accurately estimating carbohydrate content, with results being comparable with those of experienced dietitians.

A Volume Estimation System for Four Northern Hardwood Species

1986 ◽  
Vol 3 (1) ◽  
pp. 25-28
Author(s):  
Carolyn H. Richards ◽  
David D. Reed
Keyword(s):  
Sugar Maple ◽  
Volume Estimation ◽  
Stem Diameter ◽  
Red Maple ◽  
Northern Hardwood ◽  
Hardwood Species ◽  
Commercially Important ◽  
Estimation System ◽  
Volume Equation ◽  
Total Tree

Abstract A volume estimation system based on Schumacher's total volume equation is developed for four commercially important northern hardwood species in Upper Michigan: sugar maple, red maple, yellow birch, and aspen. Given diameter at breast height and a measure of height, then total tree volume, volume to any height or upper stem diameter limit, and upper stem diameter at any height (for determining product class) can be estimated. Coefficients are given for estimating diameter or volumes either inside or outside bark as are examples illustrating the techniques and potential uses of the volume estimation system. North. J. Appl. For. 3:25-28, Mar. 1986.

A simple volume estimation system and its application to three coniferous species

1994 ◽  
Vol 24 (6) ◽  
pp. 1289-1294 ◽  
Author(s):  
Kazukiyo Yamamoto
Keyword(s):  
Prediction Error ◽  
Volume Estimation ◽  
Stem Volume ◽  
Coniferous Species ◽  
Breast Height ◽  
Sample Data ◽  
Estimation System ◽  
Volume Equation ◽  
Using Data ◽  
Volume Equations

A simple system for the estimation of stem volume is presented based on the compatible stem profile and volume equations. This system can directly predict the stem volume above breast height from measurements of stem diameter at breast height and at an another point along the upper stem, and does not require any sample data for determining a parameter of volume equation. In comparison with the prediction accuracy of existing volume equations from the literature, using data from Cryptomeriajaponica D. Don, Chamaecyparisobtsusa Endl., and Pseudotsugamenziesii (Mirb.) Franco, this system has the advantage of reducing prediction error.

scholarly journals An Intelligent Mobile Application to Automate the Analysis of Food Calorie using Artificial Intelligence and Deep Learning

2021 ◽  
Author(s):  
Yongqing Yu ◽  
Yishan Zou ◽  
Yu Sun
Keyword(s):  
Eating Habits ◽  
Learning Rate ◽  
Classification Model ◽  
Batch Size ◽  
Calorie Intake ◽  
Dynamic Learning ◽  
Standard Size ◽  
Control And Prevention ◽  
Food Image

As obesity becomes increasingly common worldwide [9], more and more people want to lose weight – for both their health and their image. According to the Centers for Disease Control and Prevention (CDC), long-term changes in daily eating habits (such as regarding food/nutrition type, calorie intake) are successful at keeping weights off [10]. Therefore, it would be helpful to have an AI mobile program that identifies the types of food the user consumes and automatically calculates the total calories. This paper examines the development and optimization of an 11-categorical food classification model based on the MobileNet neural network using Python. Specifically, it classifies any food image as one of bread, dairy, dessert, egg product, fried food, meat, noodles, rice, seafood, soup, or fruit/vegetables. Methods of optimization include data preprocessing and learning rate and batch size adjustments. Experimental results show that scaling image inputs to standard size (Python Numpy resize() function), 300 training epochs, dynamic learning rate (start with 0.001 and *0.1 for every 30 epochs), and a batch size of 16 yields our best model of 83.44% accuracy.

Trash Monitoring and Alerting System Using Internet of Things

2020 ◽  
Vol 17 (5) ◽  
pp. 2363-2368
Author(s):  
T. Thilagam ◽  
S. N. Ananthi ◽  
T. Padmavathy ◽  
A. Lallithashri
Keyword(s):  
Internet Of Things ◽  
Radio Frequency Identification ◽  
Sensing Element ◽  
The World ◽  
Photoelectric Sensor ◽  
Alerting System ◽  
The Status ◽  
Frequency Identification ◽  
Weight Sensor ◽  
Geographical Point

Waste management is primitive problem faced by around the world this case is Developed or developing country. Since flooding of garbage bins the reproducing of germs and it makes awful wellbeing condition for the general population by spreading a few savage sicknesses, to keep away from such circumstance, wanting to plan a smart bins means it contains some sensors like IR sensor, weight sensor, photoelectric sensor and Radio frequency identification (RFID) CARD reader with help of these improve squander accumulation and keep up the neatness of the area. Internet of Things (IoT) is changing into associate more and more growing conception each in geographical point and out of doors of it. In this paper, we intends to structure an IoT based trash bin will consequently and constantly intimate the status of the trash in to the Municipality with help of IR sensing element it’ll send the information to the specialists United Nations office responsible for that correct space. Thus, the specific specialists can get the messages until the point that the bin is squashed and the each bin is given a specific ID it will in showcase in the screen of the revered officer and that they will take immediate action. The district laborers get the notice and they can find the region evacuate the trash receptacle supplant the enhanced one.

scholarly journals A Simple, Variable Form Volume Estimation System

1985 ◽  
Vol 61 (2) ◽  
pp. 87-90 ◽  
Author(s):  
David D. Reed ◽  
John C. Byrne
Keyword(s):  
Pinus Banksiana ◽  
Large Diameter ◽  
Small Diameter ◽  
Volume Ratio ◽  
Volume Estimation ◽  
Tree Form ◽  
Variable Form ◽  
Stem Taper ◽  
Estimation System ◽  
Total Tree

A volume estimation system giving the stem profile (upper stem diameter outside bark), total tree volume, and merchantable volume to a height or diameter limit is developed based on a simple, variable form stem taper curve. The stem taper curve is defined by coefficient values indicating conic and parabolic tree forms. For a given height, small diameter trees are assigned parabolic forms and large diameter trees are assigned conic forms. A tree's position in the tree form continuum is defined by its total height to diameter at breast height ratio. Performance of the volume estimation system is evaluated using stem analysis information on red pine, jack pine, and white spruce from the upper Great Lakes Region. Key words: Pinus resinosa Ait., Pinus banksiana Lamb., Picea glauca (Moench) Voss, taper curve, merchantable volume, volume ratio, total tree volume.

Sign in / Sign up

Export Citation Format

Share Document