Pub Date : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960287
K. Namee, Rudsada Kaewsaeng-On, J. Polpinij, G. Albadrani, Kavin Rueagraklikhit, A. Meny
This research is applying the MQTT broker protocol as a medium for various work orders in smart office management. It is an experiment and development of all functions of MQTT broker whether publishing, chatting and subscribing both globally and locally. The results are able to perform all commands correctly. In addition, in this research, the command procedure was added. This is a human speech command to operate all MQTT Brokers functions. However, there are still some weaknesses in the matter of voice commands are delayed response. It might not be a very good user experience. In this experiment, many functions were woven into the smart office. Regardless of whether the bulb acts as an IoT bulb internally connected to the MQTT broker, the camera performs the function of recognizing a person's face which is internally connected to MQTT broker. Speech also serves voice commands, lamp and feedback are connected to MQTT broker. Air conditioner acts as IoT air conditioner switch externally connected to cloud server. In addition, dashboard It also acts as an IoT visual light switch that connects externally to the cloud.
{"title":"Using the MQTT Broker as a Speech-Activated Medium to Control the Operation of Devices in the Smart Office","authors":"K. Namee, Rudsada Kaewsaeng-On, J. Polpinij, G. Albadrani, Kavin Rueagraklikhit, A. Meny","doi":"10.1109/iSAI-NLP56921.2022.9960287","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960287","url":null,"abstract":"This research is applying the MQTT broker protocol as a medium for various work orders in smart office management. It is an experiment and development of all functions of MQTT broker whether publishing, chatting and subscribing both globally and locally. The results are able to perform all commands correctly. In addition, in this research, the command procedure was added. This is a human speech command to operate all MQTT Brokers functions. However, there are still some weaknesses in the matter of voice commands are delayed response. It might not be a very good user experience. In this experiment, many functions were woven into the smart office. Regardless of whether the bulb acts as an IoT bulb internally connected to the MQTT broker, the camera performs the function of recognizing a person's face which is internally connected to MQTT broker. Speech also serves voice commands, lamp and feedback are connected to MQTT broker. Air conditioner acts as IoT air conditioner switch externally connected to cloud server. In addition, dashboard It also acts as an IoT visual light switch that connects externally to the cloud.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116752841","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}
This research aims to 1) Study the use of IoT technology to measure soil moisture and air humidity and control water spraying and brightness values in Niam Hom Houses, and 2) Develop systems and tools for users to monitor and record the house's temperature, soil moisture, air humidity, and brightness values. The development tool uses Arduino MEGA and NodeMCU ESP8266 to connect the sensors to obtain data from a specific environment. Design and control the measurement circuit system in the farmhouse with a size of 4 x 6 meters using black shading nets of 50% and 70%. The IoT system helps to control soil moisture, and the air humidity is good, making onion trees grow well. Good yield and different physiology in black shading net 50% in combination with chemical fertilizer application.
{"title":"Development of Internet of Things System for Environment Control in Niam Hom (Strobilanthesnivea Craib) House","authors":"Sancha Panpaeng, Natawut Payakkhin, Pipop Maneejamnong","doi":"10.1109/iSAI-NLP56921.2022.9960279","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960279","url":null,"abstract":"This research aims to 1) Study the use of IoT technology to measure soil moisture and air humidity and control water spraying and brightness values in Niam Hom Houses, and 2) Develop systems and tools for users to monitor and record the house's temperature, soil moisture, air humidity, and brightness values. The development tool uses Arduino MEGA and NodeMCU ESP8266 to connect the sensors to obtain data from a specific environment. Design and control the measurement circuit system in the farmhouse with a size of 4 x 6 meters using black shading nets of 50% and 70%. The IoT system helps to control soil moisture, and the air humidity is good, making onion trees grow well. Good yield and different physiology in black shading net 50% in combination with chemical fertilizer application.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121695360","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 : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960266
V. Suttichaya, Niracha Eakvorachai, Tunchanok Lurkraisit
Syntax Tree (AST) is an abstract logical structure of source code represented as a tree. This research utilizes information of fingerprinting with AST to locate the similarities between source codes. The proposed method can detect plagiarism in source codes using the number of duplicated logical structures. The structural information of program is stored in the fingerprints format. Then, the fingerprints of source codes are compared to identify number of similar nodes. The final output is calculated from number of similar nodes known as similarities scores. The result shows that the proposed method accurately captures the common modification techniques from basic to advance.
{"title":"Source Code Plagiarism Detection Based on Abstract Syntax Tree Fingerprintings","authors":"V. Suttichaya, Niracha Eakvorachai, Tunchanok Lurkraisit","doi":"10.1109/iSAI-NLP56921.2022.9960266","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960266","url":null,"abstract":"Syntax Tree (AST) is an abstract logical structure of source code represented as a tree. This research utilizes information of fingerprinting with AST to locate the similarities between source codes. The proposed method can detect plagiarism in source codes using the number of duplicated logical structures. The structural information of program is stored in the fingerprints format. Then, the fingerprints of source codes are compared to identify number of similar nodes. The final output is calculated from number of similar nodes known as similarities scores. The result shows that the proposed method accurately captures the common modification techniques from basic to advance.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126658382","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}
We utilized Deep Reinforcement Learning to incor-porate schooling, foraging, and predator avoidance behaviors into a single fish behavior model. We used Proximal Policy Optimization (PPO) with Intrinsic Curiosity Reward (ICR) to make fish agents learn in our Unity Environment. We created an interactive control system on Unity that allows users to visualize and manipulate the simulation using only a mouse and keyboard. We compared our model with three variations: one without schooling reward, one without foraging reward, and one without predator avoidance reward. Our original model (schooling, foraging, and predator avoidance) clearly illustrated the unification of all three behaviors.
{"title":"Simulation of Homogenous Fish Schools in the Presence of Food and Predators using Reinforcement Learning","authors":"Ravipas Wangananont, Norapat Buppodom, Sanpat Chanthanuraks, Vishnu Kotrajaras","doi":"10.1109/iSAI-NLP56921.2022.9960278","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960278","url":null,"abstract":"We utilized Deep Reinforcement Learning to incor-porate schooling, foraging, and predator avoidance behaviors into a single fish behavior model. We used Proximal Policy Optimization (PPO) with Intrinsic Curiosity Reward (ICR) to make fish agents learn in our Unity Environment. We created an interactive control system on Unity that allows users to visualize and manipulate the simulation using only a mouse and keyboard. We compared our model with three variations: one without schooling reward, one without foraging reward, and one without predator avoidance reward. Our original model (schooling, foraging, and predator avoidance) clearly illustrated the unification of all three behaviors.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126751136","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 : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960277
S. Gulyanon, Somrudee Deepaisam, Chayud Srisumarnk, Nattapol Chiewnawintawat, Angkoon Anzkoonsawaenasuk, Seksan Laitrakun, Pakorn Ooaorakasit, P. Rakpongsiri, Thawanpat Meechamnan, D. Sompongse
Deep neural networks have become state-of-the-art for many tasks in the past decade, especially Raman spectral classification. However, these networks heavily rely on a large collection of labeled data to avoid overfitting. Although labeled data is scarce in many application domains, there are techniques to help alleviate the problem, such as data augmentation. In this paper, we investigate one particular kind of data augmentation, noise augmentation that simply adds noise to input samples, for the Raman spectra classification task. Raman spectra yield fingerprint-like information about all chemical components but are prone to noise when the material's particles are small. We study the effectiveness of three noise models for noise augmen-tation in building a robust classification model, including noise from the background chemicals, extended multiplicative signal augmentation (EMSA), and statistical noises. In the experiments, we compared the performance of 11 popular deep learning models with the three noise augmentation techniques. The results suggest that RNN-based models perform relatively well with the increase in augmented data size compared to CNN-based models and that robust noise augmentation methods require characteristics of random variations. However, hyperparameter optimization is crucial for taking optimal advantage of noise augmentation.
{"title":"A Comparative Study of Noise Augmentation and Deep Learning Methods on Raman Spectral Classification of Contamination in Hard Disk Drive","authors":"S. Gulyanon, Somrudee Deepaisam, Chayud Srisumarnk, Nattapol Chiewnawintawat, Angkoon Anzkoonsawaenasuk, Seksan Laitrakun, Pakorn Ooaorakasit, P. Rakpongsiri, Thawanpat Meechamnan, D. Sompongse","doi":"10.1109/iSAI-NLP56921.2022.9960277","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960277","url":null,"abstract":"Deep neural networks have become state-of-the-art for many tasks in the past decade, especially Raman spectral classification. However, these networks heavily rely on a large collection of labeled data to avoid overfitting. Although labeled data is scarce in many application domains, there are techniques to help alleviate the problem, such as data augmentation. In this paper, we investigate one particular kind of data augmentation, noise augmentation that simply adds noise to input samples, for the Raman spectra classification task. Raman spectra yield fingerprint-like information about all chemical components but are prone to noise when the material's particles are small. We study the effectiveness of three noise models for noise augmen-tation in building a robust classification model, including noise from the background chemicals, extended multiplicative signal augmentation (EMSA), and statistical noises. In the experiments, we compared the performance of 11 popular deep learning models with the three noise augmentation techniques. The results suggest that RNN-based models perform relatively well with the increase in augmented data size compared to CNN-based models and that robust noise augmentation methods require characteristics of random variations. However, hyperparameter optimization is crucial for taking optimal advantage of noise augmentation.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121353976","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}
Language resources as datasets are an essential component in developing an effective automatic text summarization (ATS) system. Some public datasets are relatively uncommon when compared with popular languages, due to the complexity of language preprocessing resulting in a labor-intensive annotation by linguists. ATS techniques are to condense the size of text into a shorter output and reduce the time for finding the information from the huge textual data. This paper presents the Thai ATS construction with Economics-domain data, called ThEconSum, which manifests some linguistic challenges for Thai summarization. Existing public public datasets were employed for developing the ATS system in Thai economic news articles.
{"title":"ThEconSum: an Economics-domained Dataset for Thai Text Summarization and Baseline Models","authors":"Sawittree Jumpathong, Akkharawoot Takhom, P. Boonkwan, Vipas Sutantayawalee, Peerachet Porkaew, Sitthaa Phaholphinyo, Charun Phrombut, T. Supnithi, Khemarath Choke-Mangmi, Saran Yamasathien, Nattachai Tretasayuth, Kasidis Kanwatchara, Atiwat Aiemleuk","doi":"10.1109/iSAI-NLP56921.2022.9960271","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960271","url":null,"abstract":"Language resources as datasets are an essential component in developing an effective automatic text summarization (ATS) system. Some public datasets are relatively uncommon when compared with popular languages, due to the complexity of language preprocessing resulting in a labor-intensive annotation by linguists. ATS techniques are to condense the size of text into a shorter output and reduce the time for finding the information from the huge textual data. This paper presents the Thai ATS construction with Economics-domain data, called ThEconSum, which manifests some linguistic challenges for Thai summarization. Existing public public datasets were employed for developing the ATS system in Thai economic news articles.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116662106","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}
Automated classification for musical genres and composers is an artificial intelligence research challenge insofar as music lacks a rigidly defined structure and may result in varied interpretations by individuals. This research collected acoustic features from a sizable musical database to create an image dataset for formulating a classification model. Each image was constructed by combining pitch, temporal index length, and additional incorporated features of velocity, onset, duration, and a combination of the three. Incorporated features underwent Sigmoid scaling, creating a novel visual-based music representation. A deep learning framework, fast.ai, was used as the primary classification instrument for generated images. The results were that using velocity solely as an incorporated feature provides optimal performance, with an F1-score of 0.85 using the ResN$e$t34 model. These findings offer preliminary insight into composer classification for heightening understanding of music composer signature characterizations.
{"title":"Visual-based Musical Data Representation for Composer Classification","authors":"S. Deepaisarn, Suphachok Buaruk, Sirawit Chokphantavee, Sorawit Chokphantavee, Phuriphan Prathipasen, Virach Sornlertlamvanich","doi":"10.1109/iSAI-NLP56921.2022.9960254","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960254","url":null,"abstract":"Automated classification for musical genres and composers is an artificial intelligence research challenge insofar as music lacks a rigidly defined structure and may result in varied interpretations by individuals. This research collected acoustic features from a sizable musical database to create an image dataset for formulating a classification model. Each image was constructed by combining pitch, temporal index length, and additional incorporated features of velocity, onset, duration, and a combination of the three. Incorporated features underwent Sigmoid scaling, creating a novel visual-based music representation. A deep learning framework, fast.ai, was used as the primary classification instrument for generated images. The results were that using velocity solely as an incorporated feature provides optimal performance, with an F1-score of 0.85 using the ResN$e$t34 model. These findings offer preliminary insight into composer classification for heightening understanding of music composer signature characterizations.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125881321","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 : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960281
Saran Deeluea, C. Jeenanunta, Apinun Tunpun
The manufacturing process must continuously be improved. One of the most efficient strategies is maintenance scheduling by predictive maintenance for early fault detection and assisting with real-time decisions. The major concern of developing a predictive maintenance system is the lack of abnormal data and the cost of a high-specification sensor device for collecting data. This paper introduces the unsupervised learning model called Generative Adversarial Networks (GANs) for generating abnormal data in the form of acceleration signals to provide a dataset for developing an early fault prediction model and assisting a real-time decision on a low-frequency sensor device. The prediction model dataset is labeled on IS010816 to classify the label of data by Velocity Vibration (mm/s). The machine learning classifier model implements a hyperparameters optimization framework called OPTUNA to provide the best model performance. The proposed system aims to assist in real-time decision and maintenance schedules for the injection molding machine and offer the prediction model based on low-frequency sensor data from a drive motor.
{"title":"Fault Prediction Model for Motor and Generative Adversarial Networks for Acceleration Signal Generation","authors":"Saran Deeluea, C. Jeenanunta, Apinun Tunpun","doi":"10.1109/iSAI-NLP56921.2022.9960281","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960281","url":null,"abstract":"The manufacturing process must continuously be improved. One of the most efficient strategies is maintenance scheduling by predictive maintenance for early fault detection and assisting with real-time decisions. The major concern of developing a predictive maintenance system is the lack of abnormal data and the cost of a high-specification sensor device for collecting data. This paper introduces the unsupervised learning model called Generative Adversarial Networks (GANs) for generating abnormal data in the form of acceleration signals to provide a dataset for developing an early fault prediction model and assisting a real-time decision on a low-frequency sensor device. The prediction model dataset is labeled on IS010816 to classify the label of data by Velocity Vibration (mm/s). The machine learning classifier model implements a hyperparameters optimization framework called OPTUNA to provide the best model performance. The proposed system aims to assist in real-time decision and maintenance schedules for the injection molding machine and offer the prediction model based on low-frequency sensor data from a drive motor.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126488006","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 : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960261
Mya Ei San, Ye Kyaw Thu, T. Supnithi, Sasiporn Usanavasin
To improve the data resource of low-resource English- Myanmar- Thai language pairs, we build the first parallel medical corpus, named as En-My- Th medical corpus which is composed of total 14,592 parallel sentences. In our paper, we make experiments on the English-Myanmar language pair of new En-My-Th medical corpus and in addition, English-Thai and Thai-Myanmar language pairs from the existing ASEAN- MT corpus. The experiments of SwitchOut data augmentation algorithm and the baseline attention-based sequence to sequence model are trained on the aforementioned language pairs in both directions. Experimental results show that combination of Switch Out algorithm with the baseline model outperforms the baseline only model in the translation of most language pairs for both corpora. Furthermore, we investigate the performance of the baseline model and baseline+SwitchOut model by adding or removing word dropout at the recurrent layers, at which baseline+SwitchOut model with the dropout increases around (+1.0) BLEU4 and GLEU scores in some of language nairs.
{"title":"Improving Neural Machine Translation for Low-resource English-Myanmar-Thai Language Pairs with SwitchOut Data Augmentation Algorithm","authors":"Mya Ei San, Ye Kyaw Thu, T. Supnithi, Sasiporn Usanavasin","doi":"10.1109/iSAI-NLP56921.2022.9960261","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960261","url":null,"abstract":"To improve the data resource of low-resource English- Myanmar- Thai language pairs, we build the first parallel medical corpus, named as En-My- Th medical corpus which is composed of total 14,592 parallel sentences. In our paper, we make experiments on the English-Myanmar language pair of new En-My-Th medical corpus and in addition, English-Thai and Thai-Myanmar language pairs from the existing ASEAN- MT corpus. The experiments of SwitchOut data augmentation algorithm and the baseline attention-based sequence to sequence model are trained on the aforementioned language pairs in both directions. Experimental results show that combination of Switch Out algorithm with the baseline model outperforms the baseline only model in the translation of most language pairs for both corpora. Furthermore, we investigate the performance of the baseline model and baseline+SwitchOut model by adding or removing word dropout at the recurrent layers, at which baseline+SwitchOut model with the dropout increases around (+1.0) BLEU4 and GLEU scores in some of language nairs.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121042020","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 : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960251
S. Watcharabutsarakham, S. Marukatat, K. Kiratiratanapruk, Pitchayagan Temniranrat
Before each trip, tourists generally gather information or photos from different places. This work aims at providing additional information about touristic sites in Thailand via automatic image captioning. Image captioning is the process of generating a textual description for given images. In recent years, the development of Artificial Intelligence in combining image processing and natural language processing has gained attention worldwide. Image captioning can be regarded as a sequence-to-sequence modeling problem, as it converts images, which are considered a sequence of pixels, to a sequence of words. This work proposed a finetuned model that combined CNNs and LSTM to generate the image description. In the experiment part, we use BLEU to evaluate the model.
{"title":"Image Captioning for Thai Cultures","authors":"S. Watcharabutsarakham, S. Marukatat, K. Kiratiratanapruk, Pitchayagan Temniranrat","doi":"10.1109/iSAI-NLP56921.2022.9960251","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960251","url":null,"abstract":"Before each trip, tourists generally gather information or photos from different places. This work aims at providing additional information about touristic sites in Thailand via automatic image captioning. Image captioning is the process of generating a textual description for given images. In recent years, the development of Artificial Intelligence in combining image processing and natural language processing has gained attention worldwide. Image captioning can be regarded as a sequence-to-sequence modeling problem, as it converts images, which are considered a sequence of pixels, to a sequence of words. This work proposed a finetuned model that combined CNNs and LSTM to generate the image description. In the experiment part, we use BLEU to evaluate the model.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131084074","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：