The Experts below are selected from a list of 24687 Experts worldwide ranked by ideXlab platform

Jaewoo Kang - One of the best experts on this subject based on the ideXlab platform.

  • IJCAI - KitcheNette: Predicting and Ranking Food Ingredient Pairings using Siamese Neural Network
    Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019
    Co-Authors: Donghyeon Park, Yonggyu Park, Jungwoon Shin, Jaewoo Kang
    Abstract:

    As a vast number of Ingredients exist in the culinary world, there are countless Food Ingredient pairings, but only a small number of pairings have been adopted by chefs and studied by Food researchers. In this work, we propose KitcheNette which is a model that predicts Food Ingredient pairing scores and recommends optimal Ingredient pairings. KitcheNette employs Siamese neural networks and is trained on our annotated dataset containing 300K scores of pairings generated from numerous Ingredients in Food recipes. As the results demonstrate, our model not only outperforms other baseline models but also can recommend complementary Food pairings and discover novel Ingredient pairings.

  • kitchenette predicting and ranking Food Ingredient pairings using siamese neural network
    International Joint Conference on Artificial Intelligence, 2019
    Co-Authors: Donghyeon Park, Yonggyu Park, Jungwoon Shin, Jaewoo Kang
    Abstract:

    As a vast number of Ingredients exist in the culinary world, there are countless Food Ingredient pairings, but only a small number of pairings have been adopted by chefs and studied by Food researchers. In this work, we propose KitcheNette which is a model that predicts Food Ingredient pairing scores and recommends optimal Ingredient pairings. KitcheNette employs Siamese neural networks and is trained on our annotated dataset containing 300K scores of pairings generated from numerous Ingredients in Food recipes. As the results demonstrate, our model not only outperforms other baseline models but also can recommend complementary Food pairings and discover novel Ingredient pairings.

  • KitcheNette: Predicting and Recommending Food Ingredient Pairings using Siamese Neural Networks
    2019
    Co-Authors: Donghyeon Park, Yonggyu Park, Jungwoon Shin, Keonwoo Kim, Jaewoo Kang
    Abstract:

    As a vast number of Ingredients exist in the culinary world, there are countless Food Ingredient pairings, but only a small number of pairings have been adopted by chefs and studied by Food researchers. In this work, we propose KitcheNette which is a model that predicts Food Ingredient pairing scores and recommends optimal Ingredient pairings. KitcheNette employs Siamese neural networks and is trained on our annotated dataset containing 300K scores of pairings generated from numerous Ingredients in Food recipes. As the results demonstrate, our model not only outperforms other baseline models but also can recommend complementary Food pairings and discover novel Ingredient pairings.

Donghyeon Park - One of the best experts on this subject based on the ideXlab platform.

  • IJCAI - KitcheNette: Predicting and Ranking Food Ingredient Pairings using Siamese Neural Network
    Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019
    Co-Authors: Donghyeon Park, Yonggyu Park, Jungwoon Shin, Jaewoo Kang
    Abstract:

    As a vast number of Ingredients exist in the culinary world, there are countless Food Ingredient pairings, but only a small number of pairings have been adopted by chefs and studied by Food researchers. In this work, we propose KitcheNette which is a model that predicts Food Ingredient pairing scores and recommends optimal Ingredient pairings. KitcheNette employs Siamese neural networks and is trained on our annotated dataset containing 300K scores of pairings generated from numerous Ingredients in Food recipes. As the results demonstrate, our model not only outperforms other baseline models but also can recommend complementary Food pairings and discover novel Ingredient pairings.

  • kitchenette predicting and ranking Food Ingredient pairings using siamese neural network
    International Joint Conference on Artificial Intelligence, 2019
    Co-Authors: Donghyeon Park, Yonggyu Park, Jungwoon Shin, Jaewoo Kang
    Abstract:

    As a vast number of Ingredients exist in the culinary world, there are countless Food Ingredient pairings, but only a small number of pairings have been adopted by chefs and studied by Food researchers. In this work, we propose KitcheNette which is a model that predicts Food Ingredient pairing scores and recommends optimal Ingredient pairings. KitcheNette employs Siamese neural networks and is trained on our annotated dataset containing 300K scores of pairings generated from numerous Ingredients in Food recipes. As the results demonstrate, our model not only outperforms other baseline models but also can recommend complementary Food pairings and discover novel Ingredient pairings.

  • KitcheNette: Predicting and Recommending Food Ingredient Pairings using Siamese Neural Networks
    2019
    Co-Authors: Donghyeon Park, Yonggyu Park, Jungwoon Shin, Keonwoo Kim, Jaewoo Kang
    Abstract:

    As a vast number of Ingredients exist in the culinary world, there are countless Food Ingredient pairings, but only a small number of pairings have been adopted by chefs and studied by Food researchers. In this work, we propose KitcheNette which is a model that predicts Food Ingredient pairing scores and recommends optimal Ingredient pairings. KitcheNette employs Siamese neural networks and is trained on our annotated dataset containing 300K scores of pairings generated from numerous Ingredients in Food recipes. As the results demonstrate, our model not only outperforms other baseline models but also can recommend complementary Food pairings and discover novel Ingredient pairings.

Keiji Yanai - One of the best experts on this subject based on the ideXlab platform.

  • ICME Workshops - [Demo paper] mirurecipe: A mobile cooking recipe recommendation system with Food Ingredient recognition
    2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 2013
    Co-Authors: Yoshiyuki Kawano, Takuma Maruyama, Takanori Sato, Keiji Yanai
    Abstract:

    In this demo, we demonstrate a cooking recipe recommendation system which runs on a consumer smartphone. The proposed system carries out object recognition on Food Ingredients in a real-time way, and recommends cooking recipes related to the recognized Food Ingredients. By only pointing a built-in camera on a mobile device to Food Ingredients, the user can obtain a recipe list instantly. The objective of the proposed system is to assist people who cook to decide a cooking recipe at grocery stores or at a kitchen. In the current implementation, the system can recognize 30 kinds of Food Ingredient in 0.15 seconds, and it achieved the 83.93% recognition rate within the top six candidates.

  • real time mobile recipe recommendation system using Food Ingredient recognition
    ACM Multimedia, 2012
    Co-Authors: Takuma Maruyama, Yoshiyuki Kawano, Keiji Yanai
    Abstract:

    In this paper, we propose a mobile cooking recipe recom mendation system employing object recognition for Food Ingredients such as vegetables and meats. The proposed system carries out object recognition on Food Ingredients in a real-time way on an Android-based smartphone, and recommends cooking recipes related to the recognized Food Ingredients. By only pointing a built-in camera on a mobile device to Food Ingredients, the user can obtain a recipe list instantly. As an object recognition method, we adopt bag-of-features with SURF and color histogram extracted from multiple images as image features and linear SVM with the one-vs-rest strategy as a classifier. We built 30 kinds of Food Ingredient short video database for experiments. With this database, we achieved the 83.93% recognition rate within the top six candidates. In the experiment, we made user study by comparing mobile recipe recommendation systems with/without Ingredient recognition.

  • IMMPD@ACM Multimedia - Real-time mobile recipe recommendation system using Food Ingredient recognition
    Proceedings of the 2nd ACM international workshop on Interactive multimedia on mobile and portable devices - IMMPD '12, 2012
    Co-Authors: Takuma Maruyama, Yoshiyuki Kawano, Keiji Yanai
    Abstract:

    In this paper, we propose a mobile cooking recipe recom mendation system employing object recognition for Food Ingredients such as vegetables and meats. The proposed system carries out object recognition on Food Ingredients in a real-time way on an Android-based smartphone, and recommends cooking recipes related to the recognized Food Ingredients. By only pointing a built-in camera on a mobile device to Food Ingredients, the user can obtain a recipe list instantly. As an object recognition method, we adopt bag-of-features with SURF and color histogram extracted from multiple images as image features and linear SVM with the one-vs-rest strategy as a classifier. We built 30 kinds of Food Ingredient short video database for experiments. With this database, we achieved the 83.93% recognition rate within the top six candidates. In the experiment, we made user study by comparing mobile recipe recommendation systems with/without Ingredient recognition.

George A Burdock - One of the best experts on this subject based on the ideXlab platform.

  • safety assessment of coriander coriandrum sativum l essential oil as a Food Ingredient
    Food and Chemical Toxicology, 2009
    Co-Authors: George A Burdock, Ioana G Carabin
    Abstract:

    Abstract Coriander essential oil is used as a flavor Ingredient, but it also has a long history as a traditional medicine. It is obtained by steam distillation of the dried fully ripe fruits (seeds) of Coriandrum sativum L. The oil is a colorless or pale yellow liquid with a characteristic odor and mild, sweet, warm and aromatic flavor; linalool is the major constituent (∼70%). Based on the results of a 28 day oral gavage study in rats, a NOEL for coriander oil is approximately 160 mg/kg/day. In a developmental toxicity study, the maternal NOAEL of coriander oil was 250 mg/kg/day and the developmental NOAEL was 500 mg/kg/day. Coriander oil is not clastogenic, but results of mutagenicity studies for the spice and some extracts are mixed; linalool is non-mutagenic. Coriander oil has broad-spectrum, antimicrobial activity. Coriander oil is irritating to rabbits, but not humans; it is not a sensitizer, although the whole spice may be. Based on the history of consumption of coriander oil without reported adverse effects, lack of its toxicity in limited studies and lack of toxicity of its major constituent, linalool, the use of coriander oil as an added Food Ingredient is considered safe at present levels of use.

  • safety assessment of coriander coriandrum sativum l essential oil as a Food Ingredient
    Food and Chemical Toxicology, 2009
    Co-Authors: George A Burdock, Ioana G Carabin
    Abstract:

    Coriander essential oil is used as a flavor Ingredient, but it also has a long history as a traditional medicine. It is obtained by steam distillation of the dried fully ripe fruits (seeds) of Coriandrum sativum L. The oil is a colorless or pale yellow liquid with a characteristic odor and mild, sweet, warm and aromatic flavor; linalool is the major constituent (approximately 70%). Based on the results of a 28 day oral gavage study in rats, a NOEL for coriander oil is approximately 160 mg/kg/day. In a developmental toxicity study, the maternal NOAEL of coriander oil was 250 mg/kg/day and the developmental NOAEL was 500 mg/kg/day. Coriander oil is not clastogenic, but results of mutagenicity studies for the spice and some extracts are mixed; linalool is non-mutagenic. Coriander oil has broad-spectrum, antimicrobial activity. Coriander oil is irritating to rabbits, but not humans; it is not a sensitizer, although the whole spice may be. Based on the history of consumption of coriander oil without reported adverse effects, lack of its toxicity in limited studies and lack of toxicity of its major constituent, linalool, the use of coriander oil as an added Food Ingredient is considered safe at present levels of use.

  • safety assessment of hydroxypropyl methylcellulose as a Food Ingredient
    Food and Chemical Toxicology, 2007
    Co-Authors: George A Burdock
    Abstract:

    Hydroxypropyl methyl cellulose (HPMC; CAS No. 9004-65-3) is an odorless and tasteless, white to slightly off-white, fibrous or granular, free-flowing powder that is a synthetic modification of the natural polymer, cellulose. It is used in the Food industry as a multipurpose Food Ingredient. HPMC is approved by FDA as both a direct and an indirect Food additive, and is approved for use as a Food additive by the EU. The JECFA has evaluated the Food uses of HPMC and established an acceptable daily intake (ADI) of 'not specified' for such uses. Based on the no-observed-adverse-effect level (NOAEL) of 5000 mg/kg body weight/day from a 90-day feeding study in rats, a tolerable intake for ingestion of HPMC by humans of 5 mg/kg body weight/day is posited and, as such, is more than 100-fold greater than the estimated current consumption of 0.047 mg/kg body weight/day.

D. Val-laillet - One of the best experts on this subject based on the ideXlab platform.

  • Neuromodulatory and possible anxiolytic-like effects of a spice functional Food Ingredient in a pig model of psychosocial chronic stress
    Journal of Functional Foods, 2020
    Co-Authors: S. Menneson, S. Ménicot, C.-h. Malbert, P. Meurice, Y. Serrand, V. Noirot, P. Etienne, N. Coquery, D. Val-laillet
    Abstract:

    Psychological chronic stress is associated with the development of mood disorders, and spices have shown protective properties in this context. This research investigated the effects of a supplementation with a functional Food Ingredient containing spice extracts in a pig model of psychosocial chronic stress. Its impact on behavior, neurophysiology, immune system and gastrointestinal tract were evaluated. Almost no significant results were found at the gut and immune levels. An increased expression of 5-HT1AR and BDNF in the hippocampus and prefrontal cortex, respectively, and blood perfusion changes in several brain regions including the olfactory bulb, hippocampus, dorsolateral prefrontal cortex and dorsal anterior cingulate cortex were observed. Also, slight anxiolytic-like effects were observed in the Open-field and Novelty-Suppressed Feeding tests. These modulations of brain regions associated with the regulation of emotions and cognition as well as the potential effects on anxiety might come from the repeated stimulation of the olfactory system.

  • Regular exposure to a citrus-based sensory functional Food Ingredient alleviates the BOLD brain responses to acute pharmacological stress in a pig model of psychosocial chronic stress
    PLoS ONE, 2020
    Co-Authors: S. Menneson, Y. Serrand, V. Noirot, P. Etienne, N. Coquery, Regis Janvier, D. Val-laillet
    Abstract:

    Psychosocial chronic stress is a critical risk factor for the development of mood disorders. However, little is known about the consequences of acute stress in the context of chronic stress, and about the related brain responses. In the present study we examined the physio-behavioural effects of a supplementation with a sensory functional Food Ingredient (FI) containing Citrus sinensis extract (D11399, Phodé, France) in a pig psychosocial chronic stress model. Female pigs underwent a 5- to 6-week stress protocol while receiving daily the FI (FI, n = 10) or a placebo (Sham, n = 10). We performed pharmacological magnetic resonance imaging (phMRI) to study the brain responses to an acute stress (injection of Synacthen®, a synthetic ACTH-related agonist) and to the FI odour with or without previous chronic supplementation. The olfactory stimulation with the Ingredient elicited higher brain responses in FI animals, demonstrating memory retrieval and habituation to the odour. Pharmacological stress with Synacthen injection resulted in an increased activity in several brain regions associated with arousal, associative learning (hippocampus) and cognition (cingulate cortex) in chronically stressed animals. This highlighted the specific impact of acute stress on the brain. These responses were alleviated in animals previously supplemented by the FI during the entire chronic stress exposure. As chronic stress establishes upon the accumulation of acute stress events, any attenuation of the brain responses to acute stress can be interpreted as a beneficial effect, suggesting that FI could be a viable treatment to help individuals coping with repeated stressful events and eventually to reduce chronic stress. This study provides additional evidence on the potential benefits of this FI, of which the long-term consequences in terms of behaviour and physiology need to be further investigated.