Pub Date : 2018-07-01DOI: 10.1109/SOLI.2018.8476788
Frederico Soares Cabral, M. Pinto, Fernao A. L. N. Mouzinho, Hidekazu Fukai, S. Tamura
For developing countries like Timor-Leste, regular road surface monitoring is a major challenge not only for maintaining road quality but also for national plan of road network construction. In Timor-Leste nearly 50% of roads are still unpaved. For this reason, an automated system is required to do a survey of paved and unpaved roads. In this study, we present a new approach for the use of smartphones sensor to classify paved and unpaved roads, and anomaly detection. Although, the most remarkable factor to differentiate paved and unpaved road is based on amplitude of the vertical acceleration, each vehicle has a different type of suspension system. Therefore, we used high-dimensional features and state-of-the-art machine learning techniques to make the system robust for differences of vehicle and also smartphone type. This study divided into two stages such as paved and unpaved road classification and road anomaly detection such as pothole and bump. For paved and unpaved road classification, we tried to use the SVM, HMM and ResNet and compared the performance of these models. Of all comparison, the ResNet was the best choice in this study, because it outperformed the SVM and HMM on the all performance evaluation criteria. Furthermore, the KNN and DTW are applied for anomaly detection on the paved road. The KNN-DTW are also compared to the other machine learning techniques like SVM and classical KNN using same criteria. As a result of the comparison, the KNN-DTW and SVM performed better than classical KNN.
{"title":"An Automatic Survey System for Paved and Unpaved Road Classification and Road Anomaly Detection using Smartphone Sensor","authors":"Frederico Soares Cabral, M. Pinto, Fernao A. L. N. Mouzinho, Hidekazu Fukai, S. Tamura","doi":"10.1109/SOLI.2018.8476788","DOIUrl":"https://doi.org/10.1109/SOLI.2018.8476788","url":null,"abstract":"For developing countries like Timor-Leste, regular road surface monitoring is a major challenge not only for maintaining road quality but also for national plan of road network construction. In Timor-Leste nearly 50% of roads are still unpaved. For this reason, an automated system is required to do a survey of paved and unpaved roads. In this study, we present a new approach for the use of smartphones sensor to classify paved and unpaved roads, and anomaly detection. Although, the most remarkable factor to differentiate paved and unpaved road is based on amplitude of the vertical acceleration, each vehicle has a different type of suspension system. Therefore, we used high-dimensional features and state-of-the-art machine learning techniques to make the system robust for differences of vehicle and also smartphone type. This study divided into two stages such as paved and unpaved road classification and road anomaly detection such as pothole and bump. For paved and unpaved road classification, we tried to use the SVM, HMM and ResNet and compared the performance of these models. Of all comparison, the ResNet was the best choice in this study, because it outperformed the SVM and HMM on the all performance evaluation criteria. Furthermore, the KNN and DTW are applied for anomaly detection on the paved road. The KNN-DTW are also compared to the other machine learning techniques like SVM and classical KNN using same criteria. As a result of the comparison, the KNN-DTW and SVM performed better than classical KNN.","PeriodicalId":424115,"journal":{"name":"2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129457358","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 : 2018-07-01DOI: 10.1109/SOLI.2018.8476775
Hsin Chen, Su-Chuan Liu, Teng-Sheng Su
Many companies are focusing on reverse logistics (RL) network currently, especially in the growth of e-commerce markets around the world. Due to the convenience and fast delivery of e-commerce service, consumer behavior changes to online shopping. However, each of delivery packed by packaging material, which cause large scale of the packaging material waste. In this paper, we propose two simulation structures and develop the routing selection strategies of them. One structure simulates the full loaded cars whether decrease the cost of distribution. The other structure simulates that recycling of return of packaging material whether is reusable and redistributable. Our results provide useful framework that can benefit e-commerce practitioners for building their RL network.
{"title":"The Study for Refurbishing Process of Packaging Material in E-commerce Logistics","authors":"Hsin Chen, Su-Chuan Liu, Teng-Sheng Su","doi":"10.1109/SOLI.2018.8476775","DOIUrl":"https://doi.org/10.1109/SOLI.2018.8476775","url":null,"abstract":"Many companies are focusing on reverse logistics (RL) network currently, especially in the growth of e-commerce markets around the world. Due to the convenience and fast delivery of e-commerce service, consumer behavior changes to online shopping. However, each of delivery packed by packaging material, which cause large scale of the packaging material waste. In this paper, we propose two simulation structures and develop the routing selection strategies of them. One structure simulates the full loaded cars whether decrease the cost of distribution. The other structure simulates that recycling of return of packaging material whether is reusable and redistributable. Our results provide useful framework that can benefit e-commerce practitioners for building their RL network.","PeriodicalId":424115,"journal":{"name":"2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","volume":"279 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132830337","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 : 2018-07-01DOI: 10.1109/SOLI.2018.8476748
Songguang Ho, R. Pandi, Sarat Chandra Nagavarapu, J. Dauwels
Dial-a-ride problem (DARP) deals with the transportation of users between pickup and drop-off locations associated with specified time windows. This paper proposes a novel algorithm called multi-atomic annealing (MATA) to solve the dial-a-ride problem. Two new local search operators (burn and reform), a new construction heuristic and two request sequencing mechanisms (Sorted_List and Random_List) are developed. Computational experiments conducted on various standard DARP benchmark instances prove that MATA is an expeditious meta-heuristic in contrast to other existing methods. In all experiments, MATA demonstrates the capability to obtain high quality solutions, faster convergence, and quicker attainment of a first feasible solution. It is observed that MATA attains a first feasible solution 29.8 to 65.1% faster, and obtains a final solution that is 3.9 to 5.2% better, when compared to other algorithms within 60 sec.
{"title":"Multi-atomic Annealing Heuristic for the Dial-a-ride Problem","authors":"Songguang Ho, R. Pandi, Sarat Chandra Nagavarapu, J. Dauwels","doi":"10.1109/SOLI.2018.8476748","DOIUrl":"https://doi.org/10.1109/SOLI.2018.8476748","url":null,"abstract":"Dial-a-ride problem (DARP) deals with the transportation of users between pickup and drop-off locations associated with specified time windows. This paper proposes a novel algorithm called multi-atomic annealing (MATA) to solve the dial-a-ride problem. Two new local search operators (burn and reform), a new construction heuristic and two request sequencing mechanisms (Sorted_List and Random_List) are developed. Computational experiments conducted on various standard DARP benchmark instances prove that MATA is an expeditious meta-heuristic in contrast to other existing methods. In all experiments, MATA demonstrates the capability to obtain high quality solutions, faster convergence, and quicker attainment of a first feasible solution. It is observed that MATA attains a first feasible solution 29.8 to 65.1% faster, and obtains a final solution that is 3.9 to 5.2% better, when compared to other algorithms within 60 sec.","PeriodicalId":424115,"journal":{"name":"2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133305003","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 : 2018-07-01DOI: 10.1109/SOLI.2018.8476726
Shihua Li, Jing Yan, Lingxi Li
Intelligent Logistics is one of the most important strategic directions for the development of modern logistics industry. Automated guided vehicle (AGV) is the key equipment the benchmark for the development of Intelligent Logistics. This paper analyzes the development history of AGV and their current application status, both at home and abroad. It also points out AGV’s new direction for the development and advancement of China’s Intelligent Logistics where we should focus on the research and promotion of AGV since they are artificial intelligence-oriented and based on the needs of Intelligent Logistics. In the future, the combination of robot and autopilot technology will greatly enhance the application and service levels of AGV to Intelligent Logistics, reduce the logistics costs of trunk transportation and "the last mile", improve the efficiency of logistics transportation and distribution, and promote user’s experience.
{"title":"Automated Guided Vehicle: the Direction of Intelligent Logistics","authors":"Shihua Li, Jing Yan, Lingxi Li","doi":"10.1109/SOLI.2018.8476726","DOIUrl":"https://doi.org/10.1109/SOLI.2018.8476726","url":null,"abstract":"Intelligent Logistics is one of the most important strategic directions for the development of modern logistics industry. Automated guided vehicle (AGV) is the key equipment the benchmark for the development of Intelligent Logistics. This paper analyzes the development history of AGV and their current application status, both at home and abroad. It also points out AGV’s new direction for the development and advancement of China’s Intelligent Logistics where we should focus on the research and promotion of AGV since they are artificial intelligence-oriented and based on the needs of Intelligent Logistics. In the future, the combination of robot and autopilot technology will greatly enhance the application and service levels of AGV to Intelligent Logistics, reduce the logistics costs of trunk transportation and \"the last mile\", improve the efficiency of logistics transportation and distribution, and promote user’s experience.","PeriodicalId":424115,"journal":{"name":"2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132960294","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 : 2018-07-01DOI: 10.1109/SOLI.2018.8476768
Qiuyi Zhang, Shunli Li, Mei Yang, Xiaoxing Yin, Hongxin Zhao
The Euclid distance derived from the spatial domain distribution function for the performance characterization of imaging systems is presented and theoretically analyzed. The two-dimensional distribution functions of the objects and images, usually quadratically integrable, are investigated. The Euclid distance between the practical image and the ideal image is utilized to comprehensively characterize the imaging system performance. Moreover, the amplitude ratio and the fidelity are defined from the distribution functions of the practical and the ideal image and are related to the Euclid distance, revealing its physical meaning and merits. The geometrical representation of the Euclid distance is also derived and presented. The Euclid distance is monotonous to the performance of imaging systems, thus it can be used readily in the design and optimization of the imaging systems along with its intuitionistic and scalar features.
{"title":"Theoretical analysis on the characterization of imaging systems using Euclid distance","authors":"Qiuyi Zhang, Shunli Li, Mei Yang, Xiaoxing Yin, Hongxin Zhao","doi":"10.1109/SOLI.2018.8476768","DOIUrl":"https://doi.org/10.1109/SOLI.2018.8476768","url":null,"abstract":"The Euclid distance derived from the spatial domain distribution function for the performance characterization of imaging systems is presented and theoretically analyzed. The two-dimensional distribution functions of the objects and images, usually quadratically integrable, are investigated. The Euclid distance between the practical image and the ideal image is utilized to comprehensively characterize the imaging system performance. Moreover, the amplitude ratio and the fidelity are defined from the distribution functions of the practical and the ideal image and are related to the Euclid distance, revealing its physical meaning and merits. The geometrical representation of the Euclid distance is also derived and presented. The Euclid distance is monotonous to the performance of imaging systems, thus it can be used readily in the design and optimization of the imaging systems along with its intuitionistic and scalar features.","PeriodicalId":424115,"journal":{"name":"2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","volume":"535 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116217717","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 : 2018-07-01DOI: 10.1109/SOLI.2018.8476740
Benjamin Molter, J. Fottner
This paper presents a novel approach for detection and localization of standardized euro pallets, which are orientated up to 90° in relation to the sensor plane. There is no a priori information about the pallets pose needed. We use a time-of-flight camera. Our algorithm is based on finding surfaces in the point cloud, which represent the three wooden blocks of a euro pallet. Different kinds of geometrical checks set up our detection pipeline, where no artificial markers on the pallets are needed. Since we perform the detection while driving a forklift, the algorithm must process the point cloud within a set time limit. The detection and localization result in the pallets position and orientation in relation to the camera coordinate system. This information can be provided to higher-level systems, like advanced driver assistance systems. The results show that the localization of pallets is possible in the scenario considered.
{"title":"Real-time Pallet Localization with 3D Camera Technology for Forklifts in Logistic Environments","authors":"Benjamin Molter, J. Fottner","doi":"10.1109/SOLI.2018.8476740","DOIUrl":"https://doi.org/10.1109/SOLI.2018.8476740","url":null,"abstract":"This paper presents a novel approach for detection and localization of standardized euro pallets, which are orientated up to 90° in relation to the sensor plane. There is no a priori information about the pallets pose needed. We use a time-of-flight camera. Our algorithm is based on finding surfaces in the point cloud, which represent the three wooden blocks of a euro pallet. Different kinds of geometrical checks set up our detection pipeline, where no artificial markers on the pallets are needed. Since we perform the detection while driving a forklift, the algorithm must process the point cloud within a set time limit. The detection and localization result in the pallets position and orientation in relation to the camera coordinate system. This information can be provided to higher-level systems, like advanced driver assistance systems. The results show that the localization of pallets is possible in the scenario considered.","PeriodicalId":424115,"journal":{"name":"2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130121571","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 : 2018-07-01DOI: 10.1109/SOLI.2018.8476782
Teng Li, Zhi Ning Chen
A wideband differentially-fed substrate integrated waveguide (SIW) back cavity antenna is proposed for operation at 34 GHz millimeter bands. A wide rectangular slot is etched on the top of SIW back cavity loading with three square patches. The rectangular cavity with four tuning vias is employed for two resonant cavity modes and wideband operation. The transition between standard rectangular waveguide (RWG) and SIW are inspired by the same technology. The simulation shows that the impedance matching of the antenna without and with the transition for return loss better than 10 dB is 26–46 GHz (55.6%) and 26.2–42 GHz (46.3%) with the achieved gain of 6.7–9.2 dBi and 6–7.5 dBi, respectively. The proposed antenna features the advantages of low-profile and wideband, suitable for the full Ka-band system applications.
{"title":"Wideband Differentially-Fed Substrate Integrated Waveguide (SIW) Back Cavity Antenna","authors":"Teng Li, Zhi Ning Chen","doi":"10.1109/SOLI.2018.8476782","DOIUrl":"https://doi.org/10.1109/SOLI.2018.8476782","url":null,"abstract":"A wideband differentially-fed substrate integrated waveguide (SIW) back cavity antenna is proposed for operation at 34 GHz millimeter bands. A wide rectangular slot is etched on the top of SIW back cavity loading with three square patches. The rectangular cavity with four tuning vias is employed for two resonant cavity modes and wideband operation. The transition between standard rectangular waveguide (RWG) and SIW are inspired by the same technology. The simulation shows that the impedance matching of the antenna without and with the transition for return loss better than 10 dB is 26–46 GHz (55.6%) and 26.2–42 GHz (46.3%) with the achieved gain of 6.7–9.2 dBi and 6–7.5 dBi, respectively. The proposed antenna features the advantages of low-profile and wideband, suitable for the full Ka-band system applications.","PeriodicalId":424115,"journal":{"name":"2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129709157","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 : 2018-07-01DOI: 10.1109/SOLI.2018.8476784
Pradeepa Jayaratne
While the overall objective of this research was to identify the influencing factors on sustainable supply chain management in the Sri Lankan tea supply chain, the primary aim of this paper is to explore the effect of governance and policy on the management of the Sri Lankan tea supply chain, which would effect on the overall sustainability of the tea industry in Sri Lanka. Focus group discussions and individual interviews were carried out to explore the supply chain and to identify the factors related to governance and policy on the Sri Lankan tea supply chain.The analysis shows that strict governance and policy is a main influencing factor on sustainable tea supply chain management. Government bureaucracy, high tax implications, and restrictive policies on ownership, tea import and export were identified as the main categories that negatively affect the sustainability of the tea industry, as excessive quality checking and repetitive processes are highly detrimental on performance throughout the supply network. These functions are not only a waste of time and resources, but also increase the cost and destroy trust along the supply chain. The policy restrictions on the marketing channel were identified as a root cause for many challenges along the tea supply chain, as it limits flexibility in doing business, serves as a barrier to better relationships with customers and prevents innovation along the tea supply chain. This research shows that changes in supply chain governance can provide price benefits to the primary producers, and that being close to the consumer market provides better opportunities to understand consumer needs, pass price advantages on to them and develop a base of loyal customers.
{"title":"Effect of Governance and Policy on the Management of a Sustainable Agri-Supply Supply Network: An Example from the Sri Lankan Tea Industry","authors":"Pradeepa Jayaratne","doi":"10.1109/SOLI.2018.8476784","DOIUrl":"https://doi.org/10.1109/SOLI.2018.8476784","url":null,"abstract":"While the overall objective of this research was to identify the influencing factors on sustainable supply chain management in the Sri Lankan tea supply chain, the primary aim of this paper is to explore the effect of governance and policy on the management of the Sri Lankan tea supply chain, which would effect on the overall sustainability of the tea industry in Sri Lanka. Focus group discussions and individual interviews were carried out to explore the supply chain and to identify the factors related to governance and policy on the Sri Lankan tea supply chain.The analysis shows that strict governance and policy is a main influencing factor on sustainable tea supply chain management. Government bureaucracy, high tax implications, and restrictive policies on ownership, tea import and export were identified as the main categories that negatively affect the sustainability of the tea industry, as excessive quality checking and repetitive processes are highly detrimental on performance throughout the supply network. These functions are not only a waste of time and resources, but also increase the cost and destroy trust along the supply chain. The policy restrictions on the marketing channel were identified as a root cause for many challenges along the tea supply chain, as it limits flexibility in doing business, serves as a barrier to better relationships with customers and prevents innovation along the tea supply chain. This research shows that changes in supply chain governance can provide price benefits to the primary producers, and that being close to the consumer market provides better opportunities to understand consumer needs, pass price advantages on to them and develop a base of loyal customers.","PeriodicalId":424115,"journal":{"name":"2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129383945","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 : 2018-07-01DOI: 10.1109/SOLI.2018.8476774
Ryan Tan, I. Atmosukarto, Wee Han Lim
This paper demonstrates the usage of security camera footages with deep convolutional neural networks to provide cabin-level crowd density estimates in the video frames. Some applications for this include cabin-level crowd density estimates of incoming trains. With this information, train passengers may choose to board the trains at less crowded cabins, potentially decreasing the dwell time of trains at stations and experiencing a more pleasant commute overall. In a way, the crowd level estimation information will also help to maximize the train and platform capacity. Leveraging on the security camera footages would also serve as a cost-effective solution to the train operator as compared to installing new sensing equipment in the trains. Due to privacy and security concerns of publishing train cabin video frames, this paper will present the experiment results on an indoor pedestrian dataset.
{"title":"Video Analytics for Indoor Crowd Estimation","authors":"Ryan Tan, I. Atmosukarto, Wee Han Lim","doi":"10.1109/SOLI.2018.8476774","DOIUrl":"https://doi.org/10.1109/SOLI.2018.8476774","url":null,"abstract":"This paper demonstrates the usage of security camera footages with deep convolutional neural networks to provide cabin-level crowd density estimates in the video frames. Some applications for this include cabin-level crowd density estimates of incoming trains. With this information, train passengers may choose to board the trains at less crowded cabins, potentially decreasing the dwell time of trains at stations and experiencing a more pleasant commute overall. In a way, the crowd level estimation information will also help to maximize the train and platform capacity. Leveraging on the security camera footages would also serve as a cost-effective solution to the train operator as compared to installing new sensing equipment in the trains. Due to privacy and security concerns of publishing train cabin video frames, this paper will present the experiment results on an indoor pedestrian dataset.","PeriodicalId":424115,"journal":{"name":"2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129175786","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 : 2018-07-01DOI: 10.1109/SOLI.2018.8476795
Vosco Pereira, S. Tamura, S. Hayamizu, Hidekazu Fukai
This research proposes a low-cost solution for detecting road potholes image by using convolutional neural network (CNN). Our model is trained entirely on the image which collected from several different places and has variation such as in wet, dry and shady conditions. The experiment using the 500 testing images showed that our model can achieve (99.80 %) of Accuracy, Precision (100%), Recall (99.60%), and F-Measure (99.60%) simultaneously.
{"title":"A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste","authors":"Vosco Pereira, S. Tamura, S. Hayamizu, Hidekazu Fukai","doi":"10.1109/SOLI.2018.8476795","DOIUrl":"https://doi.org/10.1109/SOLI.2018.8476795","url":null,"abstract":"This research proposes a low-cost solution for detecting road potholes image by using convolutional neural network (CNN). Our model is trained entirely on the image which collected from several different places and has variation such as in wet, dry and shady conditions. The experiment using the 500 testing images showed that our model can achieve (99.80 %) of Accuracy, Precision (100%), Recall (99.60%), and F-Measure (99.60%) simultaneously.","PeriodicalId":424115,"journal":{"name":"2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117086544","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：