Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139124
K. Shoshina, I. Vasendina, A. Shoshin
The work describes a methodology for estimating the heat loss of a building, including the calculation of the heat loss of a building. In order to develop a methodology for estimating the heat loss of a building based on neural networks, the features of a wooden housing stock were studied. The stage of collecting images for training a neural network, the stage of training an optimal neural network for solving the problem of object detection are described. The technologies necessary to solve the problem are described.
{"title":"Development of a Methodology for Estimating the Heat Loss of Buildings based on Neural Networks","authors":"K. Shoshina, I. Vasendina, A. Shoshin","doi":"10.1109/ITNT57377.2023.10139124","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139124","url":null,"abstract":"The work describes a methodology for estimating the heat loss of a building, including the calculation of the heat loss of a building. In order to develop a methodology for estimating the heat loss of a building based on neural networks, the features of a wooden housing stock were studied. The stage of collecting images for training a neural network, the stage of training an optimal neural network for solving the problem of object detection are described. The technologies necessary to solve the problem are described.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128360847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10138991
Natalya V. Pustovalova, T. Avdeenko
The paper presents the results of regression analysis of specially designed dataset. The students from the second to fourth year of the Novosibirsk State Technical University have passed testing procedure, among them 123 men and 68 women at the age from 18 to 23 years. The presented dataset contains the results of eight different tests. We designed this set of psychometric tests for implementing "Learner model". The "Learner model" is an important component of personal educational environment of a university. For implementing the "Learner model", we preprocess testing data and create regression models. The method of regression analysis allows exploring the most significant predictors affecting academic performance. As a result, the most significant predictors are "conscientiousness" and "behavior inhibition system". The same predictors are significant for exploring interaction effects with categorical predictors "modality", "style of reaction on changes", "gender". We also explored combinations of psychometric characteristics for finding their influence on academic problems. For this reason, we divided students into two categories, considering their academic performance. Then, we build a logistic regression model.
{"title":"Analysis of the Influence of Psychological Characteristics and Their Combinations on the Students' Academic Performance","authors":"Natalya V. Pustovalova, T. Avdeenko","doi":"10.1109/ITNT57377.2023.10138991","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10138991","url":null,"abstract":"The paper presents the results of regression analysis of specially designed dataset. The students from the second to fourth year of the Novosibirsk State Technical University have passed testing procedure, among them 123 men and 68 women at the age from 18 to 23 years. The presented dataset contains the results of eight different tests. We designed this set of psychometric tests for implementing \"Learner model\". The \"Learner model\" is an important component of personal educational environment of a university. For implementing the \"Learner model\", we preprocess testing data and create regression models. The method of regression analysis allows exploring the most significant predictors affecting academic performance. As a result, the most significant predictors are \"conscientiousness\" and \"behavior inhibition system\". The same predictors are significant for exploring interaction effects with categorical predictors \"modality\", \"style of reaction on changes\", \"gender\". We also explored combinations of psychometric characteristics for finding their influence on academic problems. For this reason, we divided students into two categories, considering their academic performance. Then, we build a logistic regression model.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"345 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124262894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139100
A. Kharitonov, A. I. Minibaev, S. Kharintsev
Time-varying media open up unprecedented abilities for controlling electromagnetic fields. This is due to novel forms of light-matter interactions that arise when one of the optical parameters of the medium is abruptly switched in time. The latter means that the switching time is shorter than the period of wave oscillations. This requirement makes it challenging to implement time-varying materials suitable for applications in the optical spectral range. This work is devoted to the development of an approach for implementing time-varying media with a large depth and speed of modulation of the refractive index. We exploit a system, consisting of plasmonic antennas coupled to nonlinear material with epsilon-near-zero (ENZ) properties. Hybrid plasmonic-ENZ structures modulated by pulsed laser excitation have been recently proposed as a promising platform for time-varying photonics. However, the optical response of plasmonic components is typically slow, on the order of 10-100 fs. This stems from the long lifetime of plasmonic excitations. Here, we propose a mechanism that allows one to achieve an ultrashort, less than 1 fs, plasmon lifetime. The mechanism is based on reducing of the spectral dispersion of the real part of permittivity. For this purpose, we used titanium oxynitride (TiOxNy), which represents a plasmonic material with tunable optical properties. We synthesized a series of TiOxNy thin films using various parameters of magnetron sputtering. This allowed us to achieve a unique behavior, such as broadband flat dispersion of the dielectric function in the near-infrared range. Under these conditions, the optical response becomes local in time. The results of this study provide novel opportunities for designing and practical implementation of photonic devices based on time-varying media.
{"title":"Plasmonic nanostructures with local temporal response: a platform for time-varying photonics","authors":"A. Kharitonov, A. I. Minibaev, S. Kharintsev","doi":"10.1109/ITNT57377.2023.10139100","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139100","url":null,"abstract":"Time-varying media open up unprecedented abilities for controlling electromagnetic fields. This is due to novel forms of light-matter interactions that arise when one of the optical parameters of the medium is abruptly switched in time. The latter means that the switching time is shorter than the period of wave oscillations. This requirement makes it challenging to implement time-varying materials suitable for applications in the optical spectral range. This work is devoted to the development of an approach for implementing time-varying media with a large depth and speed of modulation of the refractive index. We exploit a system, consisting of plasmonic antennas coupled to nonlinear material with epsilon-near-zero (ENZ) properties. Hybrid plasmonic-ENZ structures modulated by pulsed laser excitation have been recently proposed as a promising platform for time-varying photonics. However, the optical response of plasmonic components is typically slow, on the order of 10-100 fs. This stems from the long lifetime of plasmonic excitations. Here, we propose a mechanism that allows one to achieve an ultrashort, less than 1 fs, plasmon lifetime. The mechanism is based on reducing of the spectral dispersion of the real part of permittivity. For this purpose, we used titanium oxynitride (TiOxNy), which represents a plasmonic material with tunable optical properties. We synthesized a series of TiOxNy thin films using various parameters of magnetron sputtering. This allowed us to achieve a unique behavior, such as broadband flat dispersion of the dielectric function in the near-infrared range. Under these conditions, the optical response becomes local in time. The results of this study provide novel opportunities for designing and practical implementation of photonic devices based on time-varying media.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124777756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139009
A. Agafonov, Evgeniya Efimenko
The paper is devoted to the short-term travel time prediction of individual connected vehicles in a regulated road network with adaptive control of traffic lights. The estimation of the total travel time combines both the travel time along road network links, obtained by a neural network model, and the waiting time at regulated intersections. At the first stage, it is proposed to use the model based on a neural network to estimate the travel time along the road links of the transportation network. At the second stage, the phase of the traffic light is predicted using the adaptive control method. Finally, the waiting time at the intersection is calculated based on the predicted arrival time of the vehicle at the intersection and the duration of the traffic light phase. Experimental results in a microscopic simulation environment allow us to conclude that the proposed approach outperforms baseline methods in terms of the mean absolute error criterion.
{"title":"Connected Vehicles Travel Time Prediction in a Scenario with Adaptive Traffic Light Control","authors":"A. Agafonov, Evgeniya Efimenko","doi":"10.1109/ITNT57377.2023.10139009","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139009","url":null,"abstract":"The paper is devoted to the short-term travel time prediction of individual connected vehicles in a regulated road network with adaptive control of traffic lights. The estimation of the total travel time combines both the travel time along road network links, obtained by a neural network model, and the waiting time at regulated intersections. At the first stage, it is proposed to use the model based on a neural network to estimate the travel time along the road links of the transportation network. At the second stage, the phase of the traffic light is predicted using the adaptive control method. Finally, the waiting time at the intersection is calculated based on the predicted arrival time of the vehicle at the intersection and the duration of the traffic light phase. Experimental results in a microscopic simulation environment allow us to conclude that the proposed approach outperforms baseline methods in terms of the mean absolute error criterion.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"452 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125786780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139053
A. Bavrina
A method is proposed for passive protection of a surveillance camera video from a video fragment deletion attack. The method is based on the construction of local features for the samples of two consecutive frames, followed by a multilayer neural network classification. Post-processing and calculation of statistics based on the results of the classification make it possible to decide whether a given pair of frames is sequential or a number of frames were cut between them. Experiments show the efficiency of detecting the fact of a fragment removal even from stationary scenes, when such a deletion is visually imperceptible.
{"title":"Method for Frame Removal Detection in Static Camera Surveillance Video","authors":"A. Bavrina","doi":"10.1109/ITNT57377.2023.10139053","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139053","url":null,"abstract":"A method is proposed for passive protection of a surveillance camera video from a video fragment deletion attack. The method is based on the construction of local features for the samples of two consecutive frames, followed by a multilayer neural network classification. Post-processing and calculation of statistics based on the results of the classification make it possible to decide whether a given pair of frames is sequential or a number of frames were cut between them. Experiments show the efficiency of detecting the fact of a fragment removal even from stationary scenes, when such a deletion is visually imperceptible.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126025197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139061
Anna Glazkova, Dmitry Morozov
Automatic selection of keyphrases (keywords) is a major challenge to finding and systematizing scholarly documents. This paper investigates the efficiency of using titles of scientific papers as additional information for keyphrase generation. We propose an approach to multi-task fine-tuning the BART model using control codes1. It is shown that the suggested approach can improve the performance of BART for the task of keyphrase generation. In some cases, the presented model outperforms state-of-the-art models for keyphrase extraction. Moreover, the results have demonstrated that multitask fine-tuning also increases the performance of title generation.
{"title":"Multi-task fine-tuning for generating keyphrases in a scientific domain","authors":"Anna Glazkova, Dmitry Morozov","doi":"10.1109/ITNT57377.2023.10139061","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139061","url":null,"abstract":"Automatic selection of keyphrases (keywords) is a major challenge to finding and systematizing scholarly documents. This paper investigates the efficiency of using titles of scientific papers as additional information for keyphrase generation. We propose an approach to multi-task fine-tuning the BART model using control codes1. It is shown that the suggested approach can improve the performance of BART for the task of keyphrase generation. In some cases, the presented model outperforms state-of-the-art models for keyphrase extraction. Moreover, the results have demonstrated that multitask fine-tuning also increases the performance of title generation.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"33 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123339714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139262
M. Nikitina
Classification of plant component on image histological sections is critical for determining non-compliance type of undeclared additiveand further action for technologist, or other responsible person. However, this task is often challenging due to the absence of professional histologists or non-compliance with the conditions of microstructural analysis and also the subjective criteria for evaluation. In this study, we propose a machine learning model that automatically classifies the plant component on images histological sections. Our model uses a convolutional neural network to identify regions of plant components, then aggregates those classifications to infer predominant and minor plant components on histological sections image. We evaluated our model on an independent set of 95 images histological sections. It achieved a kappa score of 0.525 and an agreement of 66.6% with three histologists for classifying the predominant plant component, slightly higher than the inter-histologists kappa score of 0.485 and agreement of 62.7% on this test set. All evaluation metrics for our model and the three histologists were within 95% confidence intervals of agreement.
{"title":"Evaluation of Neural Network for Automated Classification of Plant Component on Histological Section","authors":"M. Nikitina","doi":"10.1109/ITNT57377.2023.10139262","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139262","url":null,"abstract":"Classification of plant component on image histological sections is critical for determining non-compliance type of undeclared additiveand further action for technologist, or other responsible person. However, this task is often challenging due to the absence of professional histologists or non-compliance with the conditions of microstructural analysis and also the subjective criteria for evaluation. In this study, we propose a machine learning model that automatically classifies the plant component on images histological sections. Our model uses a convolutional neural network to identify regions of plant components, then aggregates those classifications to infer predominant and minor plant components on histological sections image. We evaluated our model on an independent set of 95 images histological sections. It achieved a kappa score of 0.525 and an agreement of 66.6% with three histologists for classifying the predominant plant component, slightly higher than the inter-histologists kappa score of 0.485 and agreement of 62.7% on this test set. All evaluation metrics for our model and the three histologists were within 95% confidence intervals of agreement.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116809161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/itnt57377.2023.10139106
{"title":"ITNT 2023 Cover Page","authors":"","doi":"10.1109/itnt57377.2023.10139106","DOIUrl":"https://doi.org/10.1109/itnt57377.2023.10139106","url":null,"abstract":"","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131569725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139242
N. Dorodnykh, A. Stolbov, Olga O. Nikolaychuk, A. Yurin
One of the trends in the development of information technologies and artificial intelligence is intelligent assistants in the form of chatbots or voice assistants, which are actively beginning to be implemented in various domains. In this paper, the modeling and software implementation of a chatbot to support technical personnel in diagnosing aircraft malfunctions are considered. The models of the dialog, elements of the knowledge base implementation, as well as an example of its operation, are described. The constructed models are considered as content ontological patterns and describe the object of the study, the malfunction, and the relationships between the signs of the malfunction and its causes. These templates are used in the design of a knowledge base, containing logical rules presented in the form of decision tables of a special type. The novelty of the proposed solution is the use as a methodological basis of the principles of model-driven development in the context of creating problem-specific virtual assistants.
{"title":"An Intelligent Assistant for Decision Support in the Case of Aircraft Troubleshooting","authors":"N. Dorodnykh, A. Stolbov, Olga O. Nikolaychuk, A. Yurin","doi":"10.1109/ITNT57377.2023.10139242","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139242","url":null,"abstract":"One of the trends in the development of information technologies and artificial intelligence is intelligent assistants in the form of chatbots or voice assistants, which are actively beginning to be implemented in various domains. In this paper, the modeling and software implementation of a chatbot to support technical personnel in diagnosing aircraft malfunctions are considered. The models of the dialog, elements of the knowledge base implementation, as well as an example of its operation, are described. The constructed models are considered as content ontological patterns and describe the object of the study, the malfunction, and the relationships between the signs of the malfunction and its causes. These templates are used in the design of a knowledge base, containing logical rules presented in the form of decision tables of a special type. The novelty of the proposed solution is the use as a methodological basis of the principles of model-driven development in the context of creating problem-specific virtual assistants.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131337377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139184
Vitaly Konovalov
Colorization task consists of acquiring a full-color RGB image from grayscale image or a sketch. Article is concerned with the task of colorizing grayscale cartoon images and image sequences using neural networks. Efficiency of an existing prototype algorithm is reviewed with different modifications, as well as different combinations of loss functions. A new neural network loss function is proposed. It is based on a hypothesis that specifics of cartoons, such as clear object boundaries and color consistency within those boundaries can be used to improve colorization quality. Proposed loss function uses segmentation of cartoon images in the bilateral space, and minimizes difference between closest found segments and inside each segment, thus bringing closer predicted colors within the segment and between neighboring segments. Quantitative and qualitative experiments are conducted on efficiency as well as generalization ability of modified prototype algorithm with proposed loss function. Quantitative experiments consisted of measuring PSNR, LPIPS, MSE in Lab color space and CC, while qualitative focused on comparing temporal consistency, quality of colorization and quality of generalization.
{"title":"Method for automatic cartoon colorization","authors":"Vitaly Konovalov","doi":"10.1109/ITNT57377.2023.10139184","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139184","url":null,"abstract":"Colorization task consists of acquiring a full-color RGB image from grayscale image or a sketch. Article is concerned with the task of colorizing grayscale cartoon images and image sequences using neural networks. Efficiency of an existing prototype algorithm is reviewed with different modifications, as well as different combinations of loss functions. A new neural network loss function is proposed. It is based on a hypothesis that specifics of cartoons, such as clear object boundaries and color consistency within those boundaries can be used to improve colorization quality. Proposed loss function uses segmentation of cartoon images in the bilateral space, and minimizes difference between closest found segments and inside each segment, thus bringing closer predicted colors within the segment and between neighboring segments. Quantitative and qualitative experiments are conducted on efficiency as well as generalization ability of modified prototype algorithm with proposed loss function. Quantitative experiments consisted of measuring PSNR, LPIPS, MSE in Lab color space and CC, while qualitative focused on comparing temporal consistency, quality of colorization and quality of generalization.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125760127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：