IndianFoodNet-30

About IndianFoodNet-30

IndianFoodNet-30 is created by Ritu Agarwal, Nikunj Bansal, Tanupriya Choudhury, Tanmay Sarkar & Neelu Jyothi Ahuja with a goal of building an Indian Food detection model. It contains more than 5500 images of 30 popular Indian food items.

Data collection

We used search engines (Google and Bing) to crawl and look for suitable images using JavaScript queries for each food item from the list created. The images with incomplete RGB channels were removed, and the images collected from different search engines were compiled. When downloading images from search engines, many images were irrelevant to the purpose, especially the ones with a lot of text in them. We deployed the EAST text detector to segregate such images. Finally, a comprehensive manual inspection was conducted to ensure the relevancy of images in the dataset.

Fair use

This dataset contains some copyrighted material whose use has not been specifically authorized by the copyright owners. In an effort to advance scientific research, we make this material available for academic research. If you wish to use copyrighted material in our dataset for purposes of your own that go beyond non-commercial research and academic purposes, you must obtain permission directly from the copyright owner. We believe this constitutes a 'fair use' of any such copyrighted material as provided for in section 107 of the US Copyright Law. In accordance with Title 17 U.S.C. Section 107, the material on this site is distributed without profit to those who have expressed a prior interest in receiving the included information for non-commercial research and educational purposes.(adapted from Christopher Thomas).

Citation

If you find our dataset useful, please cite us as: @dataset{dataset, author = {Agarwal, Ritu and Bansal, Nikunj and Choudhury, Tanupriya and Sarkar, Tanmay and J.Ahuja, Neelu}, year = {2023}, title = {IndianFoodNet-30 Dataset}, publisher = {Roboflow Universe}, url = {https://universe.roboflow.com/indianfoodnet/indianfoodnet}, }

IndianFood-7

About IndianFood-7

IndianFood-7 is created by Ritu Agarwal, Nikunj Bansal, Tanmay Sarkar, Tanupriya Choudhury and Neelu Jyothi Ahuja with a goal of building a Indian Food detection model. It contains more than 800 images of 7 popular Indian food items.

Data collection

We used search engines (Google and Bing) to crawl and look for suitable images using JavaScript queries for each food item from the list created. The images with incomplete RGB channels were removed, and the images collected from different search engines were compiled. When downloading images from search engines, many images were irrelevant to the purpose, especially the ones with a lot of text in them. We deployed the EAST text detector to segregate such images. Finally, a comprehensive manual inspection was conducted to ensure the relevancy of images in the dataset.

Fair use

This dataset contains some copyrighted material whose use has not been specifically authorized by the copyright owners. In an effort to advance scientific research, we make this material available for academic research. If you wish to use copyrighted material in our dataset for purposes of your own that go beyond non-commercial research and academic purposes, you must obtain permission directly from the copyright owner. We believe this constitutes a 'fair use' of any such copyrighted material as provided for in section 107 of the US Copyright Law. In accordance with Title 17 U.S.C. Section 107, the material on this site is distributed without profit to those who have expressed a prior interest in receiving the included information for non-commercial research and educational purposes.(adapted from Christopher Thomas).

This dataset is a provincial sub-dataset generated from the all-sky 1 km daily surface air temperature product over mainland China (http://doi.org/10.5281/zenodo.4399453) after resampling and clipping. The raw dataset was developed mainly from the Moderate Resolution Imaging Spectroradiometer (MODIS) products and the Global Land Data Assimilation System (GLDAS) dataset. The sub-dataset has a total data volume of only 264MB after compressed, making data download and understanding easier, and it also presents the characteristics of the raw dataset well. People who are interested in that big dataset can download the provincial sub-dataset first.

This sub-dataset was validated using ground measurements from 20 meteorological stations, with R2 and root mean square error (RMSE) values of 0.987 and 1.295 K, respectively, which proved reliability of this high-resolution dataset. In order to make this big dataset easier to understand and use, we made a provincial sub-dataset with a smaller geographic coverage.

Data set - responses of participants in a survey on well-being of students during self-isolation due to pandemic. Background: Covid-19 pandemic resulted with a lock-down measure imposed by the government of North Macedonia. Conditions of self-isolation during pandemic affect the mental health. We research the possible protective factors of psychological well-being. Method: A total of 510 college students from the biggest university in the country (70% females, M age = 21.12 years, SD = 1.58) responded to a structured online questionnaire, one month after the country's complete lock down. Results: The correlational analysis suggests that at this age, psychological well-being in conditions of isolation is higher when the perceived social support and adequacy of being informed about the virus, as well the self-engagement with physical activities are higher. Further, respondents who assessed and accept the official medical and restrictive measures higher, reported better overall well-being. Finally, those students who hold conspiratorial beliefs about the virus spread tend to feel more contented than those who do not. Conclusions: In the face of the possible second wave of pandemic, policy creators and scientific community should develop well-thought strategy, tailored to different groups, to support people to cope with pandemic, and to prevent fake news and conspiracy theories which undermine confidence in the health system.

Background Diabetic foot is one of the important causes of disability and death in diabetic patients, and effective measures can reduce or prevent the occurrence of diabetic foot, among which, the screening of diabetic high-risk foot helps to identify the risk groups that may progress to diabetic foot, and targeted intervention for this group of people can effectively reduce the prevalence of diabetic foot and the incidence of adverse consequences. Objective To investigate the occurrence of high-risk foot with type 2 diabetes in elderly people in a community in Beijing and analyze its influencing factors, so as to provide evidence for preventing the occurrence of diabetic foot. Methods 269 elderly patients with type 2 diabetes in Xinjiekou community of Beijing were selected for foot examination by convenient sampling, and the high-risk foot was classified according to the international Diabetic Foot Working Group grading system. Results The detection rate of high risk foot of type 2 diabetes was 51.7%. Binary Logistic regression analysis showed that age, glycosylated hemoglobin, hyperlipidemia, insulin therapy, and diabetic retinopathy were independent influencing factors for the occurrence of diabetic High-risk foot. Conclusion The incidence of high-risk foot in elderly type 2 diabetes patients is high in this community. Community health care workers should pay attention to elderly diabetic patients with hyperlipidemia, insulin therapy, high glycated hemoglobin, and diabetic retinopathy to reduce the occurrence of foot ulcers.