Pub Date : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205648
Thi Phuong Thao Nguyen, Thu Giang Do, Phuong Thao Dao, M. Le
Soil moisture content is one of the key foundations in precision agriculture applications since it has a direct impact on the growth rate as well as the plant quality of the crop. However, most of the existing soil moisture sensors come with high prices as well as complications in use, or poor quality or measurement with bad durability. In this study, we propose a monopole antenna-based sensor with a compact size, good accuracy, and affordable price. The result shows a good performance of the sensor with root mean square of error (RMSE) of 0.3584, maximum absolute error of 3.16% volumetric water error.
{"title":"Underground Soil Moisture Sensor Based on Monopole Antenna for Precision Agriculture","authors":"Thi Phuong Thao Nguyen, Thu Giang Do, Phuong Thao Dao, M. Le","doi":"10.1109/IAICT59002.2023.10205648","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205648","url":null,"abstract":"Soil moisture content is one of the key foundations in precision agriculture applications since it has a direct impact on the growth rate as well as the plant quality of the crop. However, most of the existing soil moisture sensors come with high prices as well as complications in use, or poor quality or measurement with bad durability. In this study, we propose a monopole antenna-based sensor with a compact size, good accuracy, and affordable price. The result shows a good performance of the sensor with root mean square of error (RMSE) of 0.3584, maximum absolute error of 3.16% volumetric water error.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121657125","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205692
Ikhwanul Hakim Masri, B. H. Susanti
In recent years, the development of Industry 4.0 has accelerated. In their implementation, various primitive cryptography methods such as block cipher, stream cipher, hash function, and pseudo-random number generator are used in this development. These primitive cryptography algorithms, for example, are used in Internet of Things technology to improve security, as well as in cloud computing technology to improve security. Furthermore, hash functions are heavily used as primitive cryptography in blockchain technology to provide the necessary security services. To provide good results in their implementation, the primitive cryptography algorithms used must have good properties. The confusion and diffusion properties of an encryption algorithm can help determine whether or not it is good. If the confusion and diffusion properties are good, the results of their implementation will be good as well. Chaos functions, which have deterministic but chaotic properties, are suitable for designing primitive cryptography algorithms with good confusion and diffusion properties. In this paper, a general implementation of chaos functions is proposed as a building block of primitive cryptography algorithms. The proposed general implementation of chaos will be evaluated based on its confusion and diffusion properties using various chaos functions to ensure that if this proposal is used in the construction of cryptographic algorithms, it will produce algorithms with good confusion and diffusion properties. The evaluation results indicate that the proposed algorithm exhibits good confusion and diffusion characteristics and has a linear time complexity.
{"title":"General Chaos Implementation as a Construction Element of Primitive Cryptography","authors":"Ikhwanul Hakim Masri, B. H. Susanti","doi":"10.1109/IAICT59002.2023.10205692","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205692","url":null,"abstract":"In recent years, the development of Industry 4.0 has accelerated. In their implementation, various primitive cryptography methods such as block cipher, stream cipher, hash function, and pseudo-random number generator are used in this development. These primitive cryptography algorithms, for example, are used in Internet of Things technology to improve security, as well as in cloud computing technology to improve security. Furthermore, hash functions are heavily used as primitive cryptography in blockchain technology to provide the necessary security services. To provide good results in their implementation, the primitive cryptography algorithms used must have good properties. The confusion and diffusion properties of an encryption algorithm can help determine whether or not it is good. If the confusion and diffusion properties are good, the results of their implementation will be good as well. Chaos functions, which have deterministic but chaotic properties, are suitable for designing primitive cryptography algorithms with good confusion and diffusion properties. In this paper, a general implementation of chaos functions is proposed as a building block of primitive cryptography algorithms. The proposed general implementation of chaos will be evaluated based on its confusion and diffusion properties using various chaos functions to ensure that if this proposal is used in the construction of cryptographic algorithms, it will produce algorithms with good confusion and diffusion properties. The evaluation results indicate that the proposed algorithm exhibits good confusion and diffusion characteristics and has a linear time complexity.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121988011","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205917
M. Yamashita
Abnormal sounds, termed adventitious sounds, include the lung sound of an individual with pulmonary disease. In this study, we aim to automatically detect abnormal sounds from auscultatory sounds. First, stochastic models are employed to express the acoustic features of normal lung sounds from healthy individuals and abnormal lung sounds from patients. Using this, normal and abnormal lung sounds are classified. However, a low classification rate was obtained because the amount of training data for the stochastic models was small. Although large volumes of training data are necessary for constructing stochastic models with high accuracy, collecting various types of abnormal respiration from a large number of patients is challenging. Therefore, to overcome this limitation, we propose the method to expand the training data for the models. Adding the acoustic features of adventitious sounds to normal respiration and using them as abnormal respiration for training data, significantly increased the classification rate. The results indicate the effectiveness of the proposed method.
{"title":"Examination of Training Data Expansion for Detection of Abnormal Respiration and Patients","authors":"M. Yamashita","doi":"10.1109/IAICT59002.2023.10205917","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205917","url":null,"abstract":"Abnormal sounds, termed adventitious sounds, include the lung sound of an individual with pulmonary disease. In this study, we aim to automatically detect abnormal sounds from auscultatory sounds. First, stochastic models are employed to express the acoustic features of normal lung sounds from healthy individuals and abnormal lung sounds from patients. Using this, normal and abnormal lung sounds are classified. However, a low classification rate was obtained because the amount of training data for the stochastic models was small. Although large volumes of training data are necessary for constructing stochastic models with high accuracy, collecting various types of abnormal respiration from a large number of patients is challenging. Therefore, to overcome this limitation, we propose the method to expand the training data for the models. Adding the acoustic features of adventitious sounds to normal respiration and using them as abnormal respiration for training data, significantly increased the classification rate. The results indicate the effectiveness of the proposed method.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121231798","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205608
Dion Pratama, Saiful Akbar
Transportation has been one of the main challenges for people living in urban areas, especially in big cities. Handling transportation problems traditionally is no longer considered suitable due to the increasingly large and complex data, which calls for an intelligent transportation system. One source of data that can be used to is social media (Twitter), in which the development of user-generated content can improve the management of existing transportation systems. In this study, IndoBERT, as a state-of-the-art model in natural language processing tasks, is used to perform sentiment analysis on Indonesian tweets about public transportation to have a better understanding of tweet context. Experimental results show that IndoBERT performs better than traditional machine learning algorithm, with the best combination of hyperparameter tuning results in accuracy of 94.8% which generalizes best to the dataset.
{"title":"Analysis of Public Opinion on Public Transportation in Bandung and Jakarta in Twitter using Indonesian Bidirectional Encoder Representations from Transformer","authors":"Dion Pratama, Saiful Akbar","doi":"10.1109/IAICT59002.2023.10205608","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205608","url":null,"abstract":"Transportation has been one of the main challenges for people living in urban areas, especially in big cities. Handling transportation problems traditionally is no longer considered suitable due to the increasingly large and complex data, which calls for an intelligent transportation system. One source of data that can be used to is social media (Twitter), in which the development of user-generated content can improve the management of existing transportation systems. In this study, IndoBERT, as a state-of-the-art model in natural language processing tasks, is used to perform sentiment analysis on Indonesian tweets about public transportation to have a better understanding of tweet context. Experimental results show that IndoBERT performs better than traditional machine learning algorithm, with the best combination of hyperparameter tuning results in accuracy of 94.8% which generalizes best to the dataset.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125672297","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205603
H. H. Ryanu, Muhammad Fadhil, Levy Olivia Nur
The development of 5G technology requires antennas that can support multiple services that require high data rates and low latency. A microstrip antenna with the characteristics of easy to manufacture and lightweight is suitable to meet these requirements. However, to support high data rates, it is necessary to increase the bandwidth of microstrip antennas, which usually have narrow bandwidth properties. The method used to increase the bandwidth of the microstrip antenna using a 1×2 configuration Complementary Split Ring Resonator (CSRR) on the ground plane has been investigated in this paper. The proposed antenna uses a circular ring patch and is designed on FR-4 material. From the unit cell simulation results, negative permittivity values are obtained in the frequency range 3.35 - 4 GHz or with a bandwidth of 650 MHz. The antenna simulation results show that by adding a CSRR with a 1×2 configuration, there is an increase in fractional bandwidth of 15.14% from 120 MHz to 650 MHz, compared to an antenna without a CSRR. The fabrication result bandwidth conforms with the simulation results with a bandwidth of 640 MHz. In addition, the radiation parameters from the measurement results show that the antenna has a gain of 4.9 dBi, and the radiation pattern is unidirectional.
{"title":"A Bandwidth Enhanced Circular Ring Microstrip Antenna Based on CSRR-loaded Ground for 5G Application","authors":"H. H. Ryanu, Muhammad Fadhil, Levy Olivia Nur","doi":"10.1109/IAICT59002.2023.10205603","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205603","url":null,"abstract":"The development of 5G technology requires antennas that can support multiple services that require high data rates and low latency. A microstrip antenna with the characteristics of easy to manufacture and lightweight is suitable to meet these requirements. However, to support high data rates, it is necessary to increase the bandwidth of microstrip antennas, which usually have narrow bandwidth properties. The method used to increase the bandwidth of the microstrip antenna using a 1×2 configuration Complementary Split Ring Resonator (CSRR) on the ground plane has been investigated in this paper. The proposed antenna uses a circular ring patch and is designed on FR-4 material. From the unit cell simulation results, negative permittivity values are obtained in the frequency range 3.35 - 4 GHz or with a bandwidth of 650 MHz. The antenna simulation results show that by adding a CSRR with a 1×2 configuration, there is an increase in fractional bandwidth of 15.14% from 120 MHz to 650 MHz, compared to an antenna without a CSRR. The fabrication result bandwidth conforms with the simulation results with a bandwidth of 640 MHz. In addition, the radiation parameters from the measurement results show that the antenna has a gain of 4.9 dBi, and the radiation pattern is unidirectional.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121560158","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205949
Konstantinos Skianis, A. Giannopoulos, Alexandros Kalafatelis, P. Trakadas
Digital Twin (DT) is an emerging paradigm that enables a virtual model to effectively represent a physical process. In this paper, we present the adoption of the DT scheme by an offset printing company towards industrial optimization. The considered DT model is a virtual representation that serves as the digital copy of the physical printing process within an industrial unit. A virtual model for selecting the optimal machine line was developed to ensure cost-efficient printing. The machine line selection process was modeled as a decision process and then analyzed through simulations in a safe and cost-efficient digital environment, provided by the DT. Moreover, Machine Learning (ML) models were exploited to extract knowledge for the machine selection task, taking full advantage of the DT experiment. Based on real data and selection policies of a printing enterprise, the results revealed an improvement during the selection process, followed by a 5% cost reduction on the examined dataset.
{"title":"Digital Twin for Automated Industrial Optimization: Intelligent Machine Selection via Process Modelling","authors":"Konstantinos Skianis, A. Giannopoulos, Alexandros Kalafatelis, P. Trakadas","doi":"10.1109/IAICT59002.2023.10205949","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205949","url":null,"abstract":"Digital Twin (DT) is an emerging paradigm that enables a virtual model to effectively represent a physical process. In this paper, we present the adoption of the DT scheme by an offset printing company towards industrial optimization. The considered DT model is a virtual representation that serves as the digital copy of the physical printing process within an industrial unit. A virtual model for selecting the optimal machine line was developed to ensure cost-efficient printing. The machine line selection process was modeled as a decision process and then analyzed through simulations in a safe and cost-efficient digital environment, provided by the DT. Moreover, Machine Learning (ML) models were exploited to extract knowledge for the machine selection task, taking full advantage of the DT experiment. Based on real data and selection policies of a printing enterprise, the results revealed an improvement during the selection process, followed by a 5% cost reduction on the examined dataset.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134000350","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205947
Matthew R. Yaswinski, Jeyaprakash Chelladurai, Shivani Barot
The virtual reality gaming market is a rapidly growing industry, as advancements in technology continue to improve the way in which we consume this type of media. As a result, there is an increasing demand for unique and engaging virtual reality games that can take advantage of these advancements. The goal of this paper is to create a virtual reality escape room game that can be run using GoogleVR on an Android smartphone. The game will be designed to be an immersive and engaging experience, with a focus on using L-Systems to generate the rooms. L-Systems are a type of formal grammar used to model the growth of plants and other forms of organic structures. By incorporating L-Systems into the design of the rooms, the game will be able to create unique and realistic environments that are different each time the game is played. Overall, this project will demonstrate the potential of using L-Systems in virtual reality game design and provide players with a unique and engaging escape room experience on their Android smartphones.
{"title":"Escape the Castle: A Virtual Reality Game Utilizing L-Systems for Dynamic Level Generation","authors":"Matthew R. Yaswinski, Jeyaprakash Chelladurai, Shivani Barot","doi":"10.1109/IAICT59002.2023.10205947","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205947","url":null,"abstract":"The virtual reality gaming market is a rapidly growing industry, as advancements in technology continue to improve the way in which we consume this type of media. As a result, there is an increasing demand for unique and engaging virtual reality games that can take advantage of these advancements. The goal of this paper is to create a virtual reality escape room game that can be run using GoogleVR on an Android smartphone. The game will be designed to be an immersive and engaging experience, with a focus on using L-Systems to generate the rooms. L-Systems are a type of formal grammar used to model the growth of plants and other forms of organic structures. By incorporating L-Systems into the design of the rooms, the game will be able to create unique and realistic environments that are different each time the game is played. Overall, this project will demonstrate the potential of using L-Systems in virtual reality game design and provide players with a unique and engaging escape room experience on their Android smartphones.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133541220","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205885
Tirta Inovan, A. Cahyadi, O. Wahyunggoro
The increasing demand for higher-quality specialty coffee is making the industry pay special attention to temperature management during roasting. Instead of keeping the temperature at an exact point, managing the temperature over time is more important, directly impacting flavor development on the final roasted beans. Generally, the temperature within the coffee roaster is managed by a human operator, making it hard to recreate a similar temperature profile between different roasting batches. This paper proposes a novel embedded system that implements trajectory tracking control based on Adaptive PID-M with the goal of eliminating over-reliance on an operator’s skill to manage the repetitive roasting process. Experimental results show that the implemented system is able to recreate temperature profile with a mean square error (MSE) of $4.56^{circ}mathrm{C}$ which is a huge improvement from human operators with an MSE of $21.7^{circ}mathrm{C}$. Implementing this system will allow coffee roasting shops to improve quality control and reduce waste from inconsistent roasting batches.
{"title":"Implementation of Adaptive-PID Based Temperature Trajectory Tracking Control to Improve Repeatability in Coffee Roasting","authors":"Tirta Inovan, A. Cahyadi, O. Wahyunggoro","doi":"10.1109/IAICT59002.2023.10205885","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205885","url":null,"abstract":"The increasing demand for higher-quality specialty coffee is making the industry pay special attention to temperature management during roasting. Instead of keeping the temperature at an exact point, managing the temperature over time is more important, directly impacting flavor development on the final roasted beans. Generally, the temperature within the coffee roaster is managed by a human operator, making it hard to recreate a similar temperature profile between different roasting batches. This paper proposes a novel embedded system that implements trajectory tracking control based on Adaptive PID-M with the goal of eliminating over-reliance on an operator’s skill to manage the repetitive roasting process. Experimental results show that the implemented system is able to recreate temperature profile with a mean square error (MSE) of $4.56^{circ}mathrm{C}$ which is a huge improvement from human operators with an MSE of $21.7^{circ}mathrm{C}$. Implementing this system will allow coffee roasting shops to improve quality control and reduce waste from inconsistent roasting batches.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130600776","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205590
N. Septa, S. Wagh
The surge in motorization and urbanization has resulted in a notable increase in road traffic, leading to heightened congestion and a rise in the frequency of road accidents. To ensure reliable transportation, the timely and stable transmission of safety messages through Vehicle Ad-hoc Networks (VANETs) is crucial. The movement of vehicles and changes in network topology can lead to link breakage and packet loss. To address this issue, a solution is proposed that utilizes a fuzzy logic system in both the Medium Access Control (MAC) layer and the network layer (NetMac-Fuzzy) to efficiently disseminate safety messages to a fixed destination such as a hospital. To accommodate changing traffic conditions, the proposed model optimizes both the Contention Window (CW) and the process of selecting the next forwarder. By considering network parameters such as traffic flow and link strength, the model selects the appropriate size of CW. For multi-hop communication, the model considers various factors such as traffic direction, vehicle density, divergence in speed, and storage between the transmitter vehicle and surrounding vehicles within its transmission range to determine the next forwarding relay. The simulation results demonstrate that the NetMac-Fuzzy model exhibits consistent throughput performance with an increase in vehicle density, and it also shows a 5% improvement in average packet delay compared to other models.
{"title":"Emergency Message Distribution in Vehicular Networks with Fuzzy Logic Model at MAC and Network Layer","authors":"N. Septa, S. Wagh","doi":"10.1109/IAICT59002.2023.10205590","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205590","url":null,"abstract":"The surge in motorization and urbanization has resulted in a notable increase in road traffic, leading to heightened congestion and a rise in the frequency of road accidents. To ensure reliable transportation, the timely and stable transmission of safety messages through Vehicle Ad-hoc Networks (VANETs) is crucial. The movement of vehicles and changes in network topology can lead to link breakage and packet loss. To address this issue, a solution is proposed that utilizes a fuzzy logic system in both the Medium Access Control (MAC) layer and the network layer (NetMac-Fuzzy) to efficiently disseminate safety messages to a fixed destination such as a hospital. To accommodate changing traffic conditions, the proposed model optimizes both the Contention Window (CW) and the process of selecting the next forwarder. By considering network parameters such as traffic flow and link strength, the model selects the appropriate size of CW. For multi-hop communication, the model considers various factors such as traffic direction, vehicle density, divergence in speed, and storage between the transmitter vehicle and surrounding vehicles within its transmission range to determine the next forwarding relay. The simulation results demonstrate that the NetMac-Fuzzy model exhibits consistent throughput performance with an increase in vehicle density, and it also shows a 5% improvement in average packet delay compared to other models.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"277 1-2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116851512","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 : 2023-07-13DOI: 10.1109/IAICT59002.2023.10205667
Vladislav Li, B. Villarini, Jean-Christophe Nebel, Argyriou Vasileios
Taking as input natural images and videos, augmented reality (AR) applications aim to enhance the real world with superimposed digital contents, enabling interaction between the user and the environment. One important step in this process is automatic scene analysis and understanding, which should be performed both in real time and with a good level of object recognition accuracy. In this work, an end-to-end framework based on the combination of a Super Resolution network with a detection and recognition deep network has been proposed to increase performance and lower processing time. This novel approach has been evaluated on two different datasets: the popular COCO dataset, whose real images are used for benchmarking many different computer vision tasks, and a generated dataset with synthetic images recreating a variety of environmental, lighting, and acquisition conditions. The evaluation analysis is focused on small objects, which are more challenging to correctly detect and recognise. The results show that the Average Precision is higher for small and low-resolution objects for the proposed end-to-end approach in most of the selected conditions.
{"title":"A Modular Deep Learning Framework for Scene Understanding in Augmented Reality Applications","authors":"Vladislav Li, B. Villarini, Jean-Christophe Nebel, Argyriou Vasileios","doi":"10.1109/IAICT59002.2023.10205667","DOIUrl":"https://doi.org/10.1109/IAICT59002.2023.10205667","url":null,"abstract":"Taking as input natural images and videos, augmented reality (AR) applications aim to enhance the real world with superimposed digital contents, enabling interaction between the user and the environment. One important step in this process is automatic scene analysis and understanding, which should be performed both in real time and with a good level of object recognition accuracy. In this work, an end-to-end framework based on the combination of a Super Resolution network with a detection and recognition deep network has been proposed to increase performance and lower processing time. This novel approach has been evaluated on two different datasets: the popular COCO dataset, whose real images are used for benchmarking many different computer vision tasks, and a generated dataset with synthetic images recreating a variety of environmental, lighting, and acquisition conditions. The evaluation analysis is focused on small objects, which are more challenging to correctly detect and recognise. The results show that the Average Precision is higher for small and low-resolution objects for the proposed end-to-end approach in most of the selected conditions.","PeriodicalId":339796,"journal":{"name":"2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132168467","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：