Pub Date : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035573
Chanwook Min, Jinhyun Ahn, Taewhi Lee, Dong-Hyuk Im
Recently, the K-BERT model was proposed to add knowledge for language representation in specialized fields. The K-BERT model uses a knowledge graph to perform transfer learning on the pre-trained BERT model. However, the K-BERT model adds the knowledge that exists in the knowledge graph rather than the data relevant to the topic of the input data when using the knowledge graph of the corresponding field. Hence, the K-BERT model can cause confusion in the training. To solve this problem, this study proposes a topic-based knowledge graph BERT (TK-BERT) model, which uses the topic modeling technique. The TK-BERT model divides the knowledge graph by topic using the knowledge graph's topic model and infers the topic for the input sentence, adding only knowledge relevant to the topic. Therefore, the TK-BERT model does not add unnecessary knowledge to the knowledge graph. Moreover, the proposed TK-BERT model outperforms the K-BERT model.
{"title":"TK-BERT: Effective Model of Language Representation using Topic-based Knowledge Graphs","authors":"Chanwook Min, Jinhyun Ahn, Taewhi Lee, Dong-Hyuk Im","doi":"10.1109/IMCOM56909.2023.10035573","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035573","url":null,"abstract":"Recently, the K-BERT model was proposed to add knowledge for language representation in specialized fields. The K-BERT model uses a knowledge graph to perform transfer learning on the pre-trained BERT model. However, the K-BERT model adds the knowledge that exists in the knowledge graph rather than the data relevant to the topic of the input data when using the knowledge graph of the corresponding field. Hence, the K-BERT model can cause confusion in the training. To solve this problem, this study proposes a topic-based knowledge graph BERT (TK-BERT) model, which uses the topic modeling technique. The TK-BERT model divides the knowledge graph by topic using the knowledge graph's topic model and infers the topic for the input sentence, adding only knowledge relevant to the topic. Therefore, the TK-BERT model does not add unnecessary knowledge to the knowledge graph. Moreover, the proposed TK-BERT model outperforms the K-BERT model.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133884164","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035660
Yerassyl Zhalgasbayev, Nguyen Anh Tu
Human Action Recognition (HAR) is a challenging computer vision task with various applications, ranging from smart surveillance to human-computer interaction. Recently, the human skeleton, a compact and intuitive data modality, has attracted increasing attention in many studies and has achieved good results in HAR. However, some challenges such as body occlusion and action similarity still need to be addressed. In this paper, to overcome these challenges, we propose a model combining short action-snippets for storing meaningful information about human body transition and a deep network configured by two parallel branches of Transformer for thoroughly learning the temporal correlation of skeletal representations in upper and lower body parts, hence concurrently enabling to handle of partial occlusions of skeleton data and boosting the HAR performance. In experiments, we validate the proposed approach's outperformance compared with the state-of-the-art methods on the JHMDB dataset in terms of both the size (i.e., number of learned parameters) and the accuracy.
{"title":"Two-Branch Stacked Transformer for 2D Skeleton-based Action Recognition","authors":"Yerassyl Zhalgasbayev, Nguyen Anh Tu","doi":"10.1109/IMCOM56909.2023.10035660","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035660","url":null,"abstract":"Human Action Recognition (HAR) is a challenging computer vision task with various applications, ranging from smart surveillance to human-computer interaction. Recently, the human skeleton, a compact and intuitive data modality, has attracted increasing attention in many studies and has achieved good results in HAR. However, some challenges such as body occlusion and action similarity still need to be addressed. In this paper, to overcome these challenges, we propose a model combining short action-snippets for storing meaningful information about human body transition and a deep network configured by two parallel branches of Transformer for thoroughly learning the temporal correlation of skeletal representations in upper and lower body parts, hence concurrently enabling to handle of partial occlusions of skeleton data and boosting the HAR performance. In experiments, we validate the proposed approach's outperformance compared with the state-of-the-art methods on the JHMDB dataset in terms of both the size (i.e., number of learned parameters) and the accuracy.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131391560","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035610
Van-Duc Nguyen, Hoang Huu Bach, L. Trang
Using knowledge distillation for unsupervised anomaly detection problems is more efficient. Recently, a reverse distillation (RD) model has been presented a novel teacher-student (T-S) model for the problem [7]. In the model, the student network uses the one-class embedding from the teacher model as input with the goal of restoring the teacher's rep-resentations. The knowledge distillation starts with high-level abstract presentations and moves down to low-level aspects using a model called one-class bottleneck embedding (OCBE). Although its performance is expressive, it still leverages the power of transforming input images before applying this architecture. Instead of only using raw images, in this paper, we transform them using augmentation techniques. The teacher will encode raw and transformed inputs to get raw representation (encoded from raw inputs) and transformed representation (encoded from transformed inputs). The student must restore the transformed representation from the bottleneck to the raw representation. Testing results obtained on benchmarks for AD and one-class novelty detection showed that our proposed model outperforms the SOTA ones, proving the utility and applicability of the suggested strategy.
{"title":"An Improved Reverse Distillation Model for Unsupervised Anomaly Detection","authors":"Van-Duc Nguyen, Hoang Huu Bach, L. Trang","doi":"10.1109/IMCOM56909.2023.10035610","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035610","url":null,"abstract":"Using knowledge distillation for unsupervised anomaly detection problems is more efficient. Recently, a reverse distillation (RD) model has been presented a novel teacher-student (T-S) model for the problem [7]. In the model, the student network uses the one-class embedding from the teacher model as input with the goal of restoring the teacher's rep-resentations. The knowledge distillation starts with high-level abstract presentations and moves down to low-level aspects using a model called one-class bottleneck embedding (OCBE). Although its performance is expressive, it still leverages the power of transforming input images before applying this architecture. Instead of only using raw images, in this paper, we transform them using augmentation techniques. The teacher will encode raw and transformed inputs to get raw representation (encoded from raw inputs) and transformed representation (encoded from transformed inputs). The student must restore the transformed representation from the bottleneck to the raw representation. Testing results obtained on benchmarks for AD and one-class novelty detection showed that our proposed model outperforms the SOTA ones, proving the utility and applicability of the suggested strategy.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114564882","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035567
Minho Kim, Y. Do, Jonghun Kim, Jaewook Jeon
An Ethernet-based in-vehicle network (IVN) gateway with IEEE 802.1 time-sensitive networking (TSN) is advantageous to be used in a time-aware shaper (TAS), as defined in IEEE 802.1Qbv, to safely handle periodic critical traffic, depending on the characteristics of vehicle systems operating in real time. However, the TAS defined in a TSN hampers proper handling of asynchronous traffic in an IVN. This study proposes a method for a time-aware scheduler to handle asynchronous traffic on a time-sensitive IVN.
{"title":"Asynchronous traffic handling in time-sensitive in-vehicle network","authors":"Minho Kim, Y. Do, Jonghun Kim, Jaewook Jeon","doi":"10.1109/IMCOM56909.2023.10035567","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035567","url":null,"abstract":"An Ethernet-based in-vehicle network (IVN) gateway with IEEE 802.1 time-sensitive networking (TSN) is advantageous to be used in a time-aware shaper (TAS), as defined in IEEE 802.1Qbv, to safely handle periodic critical traffic, depending on the characteristics of vehicle systems operating in real time. However, the TAS defined in a TSN hampers proper handling of asynchronous traffic in an IVN. This study proposes a method for a time-aware scheduler to handle asynchronous traffic on a time-sensitive IVN.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127114636","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035617
Yingfeng Fu, Y. Tanimura, H. Nakada
Pre-training driven by vast data has shown great power in natural language understanding. The idea has also been applied to symbolic music. However, many existing works using pre-training for symbolic music are not general enough to tackle all the tasks in musical information retrieval, and there is still space to improve the model structure. To make up for the insufficiency and compare it with the existing works, we employed a BERT-like masked language pre-training approach to train a stacked MusicTransformer on MAESTRO dataset. Then we fine-tuned our pre-trained model on several symbolic music understanding tasks. In the work, our contribution is 1)we improved MusicBERT by modifying the model structure. 2)be-sides the existing evaluation downstream tasks, we complemented several downstream tasks, including melody extraction, emotion classification, and composer classification. We pre-trained the modified model and existing works under the same condition. We make a comparison of our pre-trained model with the previous works. The result shows that the modified model is more powerful than the previous models with the same pre-training setting.
{"title":"Improve symbolic music pre-training model using MusicTransformer structure","authors":"Yingfeng Fu, Y. Tanimura, H. Nakada","doi":"10.1109/IMCOM56909.2023.10035617","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035617","url":null,"abstract":"Pre-training driven by vast data has shown great power in natural language understanding. The idea has also been applied to symbolic music. However, many existing works using pre-training for symbolic music are not general enough to tackle all the tasks in musical information retrieval, and there is still space to improve the model structure. To make up for the insufficiency and compare it with the existing works, we employed a BERT-like masked language pre-training approach to train a stacked MusicTransformer on MAESTRO dataset. Then we fine-tuned our pre-trained model on several symbolic music understanding tasks. In the work, our contribution is 1)we improved MusicBERT by modifying the model structure. 2)be-sides the existing evaluation downstream tasks, we complemented several downstream tasks, including melody extraction, emotion classification, and composer classification. We pre-trained the modified model and existing works under the same condition. We make a comparison of our pre-trained model with the previous works. The result shows that the modified model is more powerful than the previous models with the same pre-training setting.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127454741","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035657
Jullian Dominic D. Ducut, J. A. D. Leon, Mike Louie C. Enriquez, Ronnie S. Concepcion, A. Bandala, R. R. Vicerra, Renann P. Baldovino
Utilities such as pipelines are vital for the urban community. The most used material for pipelines is metal and plastic that may have different size and shape depending on its use. Due to stress, heat, and pressure overtime, underground pipelines may encounter breakage that may lead to problems such as road cracks and pipe leakage. Subsurface monitoring such as ERT can be used to detect subsurface artifacts such as underground utilities to conduct maintenance and prevent damage caused by subsurface artifacts. ERT measurement utilizes geophysical software and instruments that relies heavily on the resistivity of the subsurface that will result to the subsurface profile. The ERT profile will result to a contoured image indicating different subsurface artifacts or anomalies in the region of interest. The development of deep learning techniques paved the way for emerging studies concerning AI being applied to ERT. In this study, CNN using pretrained models such as InceptionV3, ResNet101, NasNetLarge, and MobileNetV2 was applied to homogenous ERT profiles containing pipes to classify the profile into metallic and plastic pipe. The generated synthetic profiles are pre-classified to contain either metallic pipe or plastic pipe. The performance of pretrained models will be evaluated by their confusion matrix. The model that performed best is the ResNet101 model, producing the highest accuracy of 83% compared to other models. The reconfigured pre trained model can be integrated to geophysical software to provide more information with the profile and may lead to minimized amount of effort on inversion process.
{"title":"Classifying Electrical Resistivity Tomography Profiles of Underground Utilities using Convolutional Neural Network","authors":"Jullian Dominic D. Ducut, J. A. D. Leon, Mike Louie C. Enriquez, Ronnie S. Concepcion, A. Bandala, R. R. Vicerra, Renann P. Baldovino","doi":"10.1109/IMCOM56909.2023.10035657","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035657","url":null,"abstract":"Utilities such as pipelines are vital for the urban community. The most used material for pipelines is metal and plastic that may have different size and shape depending on its use. Due to stress, heat, and pressure overtime, underground pipelines may encounter breakage that may lead to problems such as road cracks and pipe leakage. Subsurface monitoring such as ERT can be used to detect subsurface artifacts such as underground utilities to conduct maintenance and prevent damage caused by subsurface artifacts. ERT measurement utilizes geophysical software and instruments that relies heavily on the resistivity of the subsurface that will result to the subsurface profile. The ERT profile will result to a contoured image indicating different subsurface artifacts or anomalies in the region of interest. The development of deep learning techniques paved the way for emerging studies concerning AI being applied to ERT. In this study, CNN using pretrained models such as InceptionV3, ResNet101, NasNetLarge, and MobileNetV2 was applied to homogenous ERT profiles containing pipes to classify the profile into metallic and plastic pipe. The generated synthetic profiles are pre-classified to contain either metallic pipe or plastic pipe. The performance of pretrained models will be evaluated by their confusion matrix. The model that performed best is the ResNet101 model, producing the highest accuracy of 83% compared to other models. The reconfigured pre trained model can be integrated to geophysical software to provide more information with the profile and may lead to minimized amount of effort on inversion process.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129677596","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035607
Christian C. Anabeza, Galvin Brice S. Limt, Mark Lawrence P. Velasco, E. Sybingco, Dino Dominic F. Ligutan
In the conduct of this project, the proponents primarily aimed to explore the threshold for the deviations of the Filipino-accented utterances of selected English words using the MFCC and DTW concepts. The initial premise utilized by the proponents would be the speaker-dependent nature of the MFCC; hence, the calculations, measurements, and data-gathering methodologies were conducted by means of acquiring the said coefficients from the same individual verbally uttering selected words in that of the American accent and in their native Filipino accent and subjecting these results to a series of MA TLAB algorithms devised by the researchers. As such, the study was able to conclude that, upon preliminary calculations, the normalized DTW threshold between the Filipino-Accented English was calculated to be 4.91 with the designed system having an accuracy of 68.73 % in correctly determining which Filipino-accented utterances correspond to their respective English word counterparts. While this was able to procure plausible results, one of the limitations observed in this implementation would be the presence of noise in the samples that may have caused deviations along with the limited number of participants that partook in the acquisition of data for this study. Thus, it is then highly suggested that a wider and more robust database be implemented in future studies involving this subject and relative methodologies.
{"title":"DTW Threshold Determination for English Word Utterances in Filipino Accent using MFCC","authors":"Christian C. Anabeza, Galvin Brice S. Limt, Mark Lawrence P. Velasco, E. Sybingco, Dino Dominic F. Ligutan","doi":"10.1109/IMCOM56909.2023.10035607","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035607","url":null,"abstract":"In the conduct of this project, the proponents primarily aimed to explore the threshold for the deviations of the Filipino-accented utterances of selected English words using the MFCC and DTW concepts. The initial premise utilized by the proponents would be the speaker-dependent nature of the MFCC; hence, the calculations, measurements, and data-gathering methodologies were conducted by means of acquiring the said coefficients from the same individual verbally uttering selected words in that of the American accent and in their native Filipino accent and subjecting these results to a series of MA TLAB algorithms devised by the researchers. As such, the study was able to conclude that, upon preliminary calculations, the normalized DTW threshold between the Filipino-Accented English was calculated to be 4.91 with the designed system having an accuracy of 68.73 % in correctly determining which Filipino-accented utterances correspond to their respective English word counterparts. While this was able to procure plausible results, one of the limitations observed in this implementation would be the presence of noise in the samples that may have caused deviations along with the limited number of participants that partook in the acquisition of data for this study. Thus, it is then highly suggested that a wider and more robust database be implemented in future studies involving this subject and relative methodologies.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127846456","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035639
Kok Yin Long, Kamalanathan Shanmugam, Muhammad Ehsan Rana
Everyone understands the necessity of health management, especially in light of the COVID-19 viral infection. How to care for and manage health has emerged as the main topic of conversation, whether it concerns the elderly, adults, patients, or children. There are numerous ways to maintain one's health, and smartwatches are good at doing this because their owners can monitor their health constantly. The idea behind a smartwatch is to utilise its green light to measure the wearer's blood pressure before gathering information about their health. Because smartwatches can constantly detect and analyse users' daily health information. Users or guardians can use this information to take care of their bodies; therefore, they are an excellent choice for many people with dementia, depression, high-stress conditions, and athletes who need to monitor their physical fitness. This article analyses in depth the value of smartwatches, their applications for managing people's health, and their benefits and drawbacks.
{"title":"An Evaluation of Smartwatch Contribution in Improving Human Health","authors":"Kok Yin Long, Kamalanathan Shanmugam, Muhammad Ehsan Rana","doi":"10.1109/IMCOM56909.2023.10035639","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035639","url":null,"abstract":"Everyone understands the necessity of health management, especially in light of the COVID-19 viral infection. How to care for and manage health has emerged as the main topic of conversation, whether it concerns the elderly, adults, patients, or children. There are numerous ways to maintain one's health, and smartwatches are good at doing this because their owners can monitor their health constantly. The idea behind a smartwatch is to utilise its green light to measure the wearer's blood pressure before gathering information about their health. Because smartwatches can constantly detect and analyse users' daily health information. Users or guardians can use this information to take care of their bodies; therefore, they are an excellent choice for many people with dementia, depression, high-stress conditions, and athletes who need to monitor their physical fitness. This article analyses in depth the value of smartwatches, their applications for managing people's health, and their benefits and drawbacks.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129192262","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035542
Min Wei, Shujie Yang
In industrial application, it is necessary to select different kind of networks according to different kind of communication requirement. The converged network of wired and wireless networks is able to meet this need. It is a challenge to meet the end-to-end transmission requirements of converged networks. Therefore, the converged network scheduling mechanism is important. In this paper, a network scheduling method for convergence of industrial wireless network and TSN is proposed. Then, a test and verification for the method proposed is implemented. The results show that the end-to-end average transmission delay is reduced and the jitter is acceptable.
{"title":"A Network Scheduling Method for Convergence of Industrial Wireless Network and TSN","authors":"Min Wei, Shujie Yang","doi":"10.1109/IMCOM56909.2023.10035542","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035542","url":null,"abstract":"In industrial application, it is necessary to select different kind of networks according to different kind of communication requirement. The converged network of wired and wireless networks is able to meet this need. It is a challenge to meet the end-to-end transmission requirements of converged networks. Therefore, the converged network scheduling mechanism is important. In this paper, a network scheduling method for convergence of industrial wireless network and TSN is proposed. Then, a test and verification for the method proposed is implemented. The results show that the end-to-end average transmission delay is reduced and the jitter is acceptable.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121535593","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 : 2023-01-03DOI: 10.1109/IMCOM56909.2023.10035579
N. Sangkhiew, Arnat Watanasungsuit, C. Inthawongse, Peerapop Jomthong, Kawinthorn Saichareon, C. Pornsing
The fundamental decision-making of a firm is forecasting. It is an important activity that affects the performance of a company. Among forecasting tools, exponential smoothing techniques are the most relevant in industries. They yield exceptional results with low forecasting errors. The triple exponential smoothing technique, viz. the Holt-Winter (HW) method, is the most popular when the seasonality is embedded in the data. However, the three smoothing parameters predetermined by the analyst are still problematic in practice. We proposed two improved HW methods in this study by combining two artificial intelligence techniques to adapt the three smoothing parameters iteratively. The proposed methods are tested by forecasting a local stainless steel price data set. We found that the PSO-HW method outperforms the traditional HW and GSA-HW method in the mean absolute percentage error measurement. However, the GSA-HW method surpasses the other two methods in the direction accuracy percentage.
{"title":"Adaptive Holt-Winters Forecasting Method based on Artificial Intelligence Techniques","authors":"N. Sangkhiew, Arnat Watanasungsuit, C. Inthawongse, Peerapop Jomthong, Kawinthorn Saichareon, C. Pornsing","doi":"10.1109/IMCOM56909.2023.10035579","DOIUrl":"https://doi.org/10.1109/IMCOM56909.2023.10035579","url":null,"abstract":"The fundamental decision-making of a firm is forecasting. It is an important activity that affects the performance of a company. Among forecasting tools, exponential smoothing techniques are the most relevant in industries. They yield exceptional results with low forecasting errors. The triple exponential smoothing technique, viz. the Holt-Winter (HW) method, is the most popular when the seasonality is embedded in the data. However, the three smoothing parameters predetermined by the analyst are still problematic in practice. We proposed two improved HW methods in this study by combining two artificial intelligence techniques to adapt the three smoothing parameters iteratively. The proposed methods are tested by forecasting a local stainless steel price data set. We found that the PSO-HW method outperforms the traditional HW and GSA-HW method in the mean absolute percentage error measurement. However, the GSA-HW method surpasses the other two methods in the direction accuracy percentage.","PeriodicalId":230213,"journal":{"name":"2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129866683","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：