{"title":"Minimizing Total Weighted Completion Time on a Single Machine Scheduling Problem with Resumable Jobs and Flexible Maintenance","authors":"Ya-Chih Tsai, Yarong Chen, F. Chou","doi":"10.1145/3297097.3297112","DOIUrl":"https://doi.org/10.1145/3297097.3297112","url":null,"abstract":"This paper considers the problem of scheduling n resumable jobs to minimize total weighted completion time, in which maintenance activities periodically occur after a continuously working time. This problem has been proven to be NP-hard. Using lower bounds and several dominance rules, a branch and bound scheme is proposed to solve optimally efficiently for small problems. A mixed integer programming model is also introduced to obtain benchmark solutions.","PeriodicalId":349577,"journal":{"name":"Proceedings of the 4th International Conference on Robotics and Artificial Intelligence","volume":"32 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126171787","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}
T. Lo, Pei-Yin Wei, Chia-Heng Yen, J. Lirng, Muh-Hwa Yang, P. Chu, Shinn-Ying Ho
{"title":"Prediction of Metastasis in Head and Neck Cancer from Computed Tomography Images","authors":"T. Lo, Pei-Yin Wei, Chia-Heng Yen, J. Lirng, Muh-Hwa Yang, P. Chu, Shinn-Ying Ho","doi":"10.1145/3297097.3297108","DOIUrl":"https://doi.org/10.1145/3297097.3297108","url":null,"abstract":"The current medical method for determining whether the malignant tumor of the head and neck metastasizes to the lymph is to interpret the pathological section of the patient's lymph. This study proposes a support vector machine (SVM) based method Pred-Meta to predict metastasis of a malignant tumor from a patient's computed tomography (CT) image. Pred-Meta utilizes three feature types, including texture, morphology, and grayscale, and an optimal feature selection method cooperated with SVM. The data set consists of 75 samples from 70 patients in head and neck cancer provided by Taipei Veterans General Hospital of Taiwan with a record of lymphatic metastasis. Pred-Meta using leave-one-out cross-validation achieved 100% in predicting metastasis. The merit of the Pred-Meta method is its non-invasiveness and low cost. Auxiliary physicians screen out patients with high risk of diversion in the early stages to help plan treatment guidelines. The limitation of Pred-Meta suffers from the small number of training samples. It is expected that Pred-Meta would perform better in testing independent cohort when the number of training samples significantly increases.","PeriodicalId":349577,"journal":{"name":"Proceedings of the 4th International Conference on Robotics and Artificial Intelligence","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129887016","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}
{"title":"Artificial Intelligence for Sport Actions and Performance Analysis using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM)","authors":"W. Fok, Louis C. W. Chan, C. Chen","doi":"10.1145/3297097.3297115","DOIUrl":"https://doi.org/10.1145/3297097.3297115","url":null,"abstract":"The development of Human Action Recognition (HAR) system is getting popular. This project developed a HAR system for the application in the surveillance system to minimize the man-power for providing security to the citizens such as public safety and crime prevention. In this research, deep learning network using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) are used to analyze dynamic video motion of sport actions and classify different types of actions and their performance. It could classify different types of human motion with a small number of video frame for efficiency and memory saving. The current accuracy achieved is up to 92.9% but with high potential of further improvement.","PeriodicalId":349577,"journal":{"name":"Proceedings of the 4th International Conference on Robotics and Artificial Intelligence","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127957599","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}
{"title":"Recurrent Spatiotemporal Feature Learning for Action Recognition","authors":"Ze Chen, Hongtao Lu","doi":"10.1145/3297097.3297107","DOIUrl":"https://doi.org/10.1145/3297097.3297107","url":null,"abstract":"Recurrent neural networks (RNNs) like Long Short-term Memory (LSTM) have shown excellent performance for a variety of sequence learning problems on language and speech processing. Previous works leveraging RNNs for action recognition mainly apply LSTM on the top of Convolutional Neural Networks (CNNs), feeding high level semantic feature to RNNs and neglecting to learn spatiotemporal features in video, which makes the models unable to capture complex action patterns and lead to inferior performance. In this work, instead of adopting RNNs as classifiers, we propose to learn spatiotemporal feature in a recurrent way by replacing intermediate convolutional layers in CNNs with recurrent layers to model spatiotemporal information. In order to learn discriminative spatiotemporal features, we extend the bottleneck structure of Residual Network (ResNet) to model the spatiotemporal information in action video. To fully utilize the pretrained CNN model, we also introduce approaches to transfer the weight of original convolutional layer to our proposed model. Our proposed architecture is end-to-end trainable, and of significant flexibility to be adapted in any CNN-based structure. Our model produces the state-of-the-art performance on two standard benchmark for action recognition over RNN-based approaches.","PeriodicalId":349577,"journal":{"name":"Proceedings of the 4th International Conference on Robotics and Artificial Intelligence","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127647653","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}
{"title":"Collaborative Pursuing of Multiple Mobile Robots in Dynamic Environment","authors":"Guangyuan Fu, Yuan Li, Tiemin Chen","doi":"10.1145/3297097.3297113","DOIUrl":"https://doi.org/10.1145/3297097.3297113","url":null,"abstract":"In the dynamic environment, the problem of constantly changing positions of obstacles and intruders, a no formation adaptive pursuit algorithm is proposed. The algorithm can complete pursuing intruders effectively under the dynamic environment, that is, after the pursuit robot searches for intruders through searching, it defines some pursuit points around it. Then, tracking the pursuit points. When all the robots reach the pursuit point, the distance is further narrowed to complete pursuing the intruders. During the pursuing intruders, static and dynamic obstacles were considered. At the same time, the intruder's escape and obstacle avoidance problems were considered, too. Compared with traditional algorithms, this algorithm reduces the formation time and improves the efficiency of pursuit. The simulation experiment verifies the correctness and effectiveness of the algorithm in solving the pursuing problem of multiple mobile robots.","PeriodicalId":349577,"journal":{"name":"Proceedings of the 4th International Conference on Robotics and Artificial Intelligence","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132645521","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}
{"title":"Increasing Diversity of Solutions in Sampling-based Path Planning","authors":"Vojtěch Vonásek, M. Saska","doi":"10.1145/3297097.3297114","DOIUrl":"https://doi.org/10.1145/3297097.3297114","url":null,"abstract":"Sampling-based path planning algorithms like Rapidly-exploring Random Trees (RRT) are widely used to solve path planning problems for robots with many Degrees Of Freedom (DOF). Although the sampling-based planners are stochastic and provide different solutions in every trial, many resulting trajectories can be quite similar, e.g., because they are close to each other. Computation of diverse paths, i.e., paths leading through different parts of the configuration space, is important for online navigation of mobile robots or for finding solutions leading through different narrow passages of the configuration space. In this paper, we propose an extension of the RRT algorithm to find diverse paths in the configuration space iteratively. The idea of the proposed method is to prohibit the exploration of selected regions of the configuration space. The prohibited regions are defined using the waypoints of paths computed in the previous iterations. We show that the proposed method finds more diverse trajectories than can be achieved by repeated computations of a single sampling-based planner.","PeriodicalId":349577,"journal":{"name":"Proceedings of the 4th International Conference on Robotics and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129274967","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}
{"title":"IMU-Aided Motion Estimation for the RGB-D Camera in Manhattan Structures","authors":"Bei B. Zhou, Jianhui Guo","doi":"10.1145/3297097.3297104","DOIUrl":"https://doi.org/10.1145/3297097.3297104","url":null,"abstract":"In this work, we develop a novel IMU (Inertial Measurement Unit)-aided plane-based visual odometry method to estimate the pose of an RGB-D camera and reconstruct large scale corridor-like environments. The camera with an IMU chip attached to it is mounted on the mobile robot which explores freely in 3 DOF. Obviously, the low textured planes and the Manhattan structure are very apparent in the corridor, we exploit those structures to estimate the rotation of the camera and meanwhile eliminate the accumulated error. In order to construct the Manhattan coordinate, we propose a fast plane segmentation method to extract the floor and the walls based on horizontal and vertical histograms induced by the inverse-depth map. Furthermore, to deal with the limitations in the presence of more clutter, we define the major planes and minor planes, and regard the IMU as the angle measuring instrument with the Gaussian noise so that we can provide a larger weight for the rotations estimated from the right Manhattan structure. By using of our real-world data, the experimental result shows the promising performance in term of accuracy and robustness.","PeriodicalId":349577,"journal":{"name":"Proceedings of the 4th International Conference on Robotics and Artificial Intelligence","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123035549","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}
{"title":"Swarm Intelligence for Object Retrieval Applying Cooperative Transportation in Unknown Environments","authors":"Ysmaldo Landaez, H. Dohi, H. Iba","doi":"10.1145/3297097.3297106","DOIUrl":"https://doi.org/10.1145/3297097.3297106","url":null,"abstract":"Mini-robots have been developed as a way of getting in narrow and critical spaces in order to explore collapsed structures, hazardous places for rescuers to preserve lives. The objective is to distribute the agents on these environments and complete tasks autonomously. The previous methods can accomplish this task only in open spaces or by manually guiding the robots to push the object. In this paper, we propose a novel plug-and-play robot team, where the agents cooperatively push an object towards the destination inside of an unknown environment. Our method consists on adding a guiding process to work together with the Occlusion-Base Pushing (OBP) method. The guiding algorithm establishes sub-goals between the object and the final destination, which helps the robots to push the object through the unknown environment. Based on the results of the simulations performed in V-REP. We demonstrate the effectiveness of our method over existing methods in terms of speed and reliability.","PeriodicalId":349577,"journal":{"name":"Proceedings of the 4th International Conference on Robotics and Artificial Intelligence","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128256257","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}
{"title":"Quantitative Analysis of Phosphorus in Compound Fertilizer by Support Vector Machine","authors":"Jiangtao Li, Wen Sha, Chunhou Zhen","doi":"10.1145/3297097.3297111","DOIUrl":"https://doi.org/10.1145/3297097.3297111","url":null,"abstract":"In the production of compound fertilizer, real-time detection of components was required to achieve the purpose of guiding production. In this paper, laser-induced breakdown spectroscopy technique combined with support vector machine (SVM)was used to quantitatively analyze phosphorus (P)in compound fertilizer. 58 compound fertilizer samples were provided by Anhui Huilong Group. Three spectral lines of P I: 213.5 nm, 214.9 nm, and 215.4 nm were selected as analytical lines. 58 samples were divided into a training set (43 samples)and a test set (15 samples)using the K-S method. By constructing the SVM of P element in compound fertilizer analysis model, the grid search method was used to optimize the parameters of quantitative analysis model. The results showed that the correlation coefficient R2 of the established training set calibration model was 0.981. It indicated the correlation between the reference value and the predicted value of the training set was relatively high. In the test set, the correlation coefficient R2 between the reference value and the predicted value of the sample phosphorus(P)element was 0.992, and the mean squared error CVmse was 4.951*10-3. It indicated that the constructed SVM model had strong applicability. The average absolute error of the training set was 0.059% and the relative error was 0.399%. The average absolute error and relative error of the test set were 0.056% and 0.328%, respectively. It meant that the accuracy of the LIBS measurement was greatly improved. This shows that combining the SVM algorithm with LIBS technology can achieve rapid detection of phosphorus in compound fertilizers.","PeriodicalId":349577,"journal":{"name":"Proceedings of the 4th International Conference on Robotics and Artificial Intelligence","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123652682","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}
{"title":"The Influence Simulation Analysis of the Sensitive Area of the Instrument Landing System's Localizer On The Position Of The Aircraft Take-off Waiting Line","authors":"Huan Lin, Bo Wang, Bin Yuan, Qingdong Li","doi":"10.1145/3297097.3297100","DOIUrl":"https://doi.org/10.1145/3297097.3297100","url":null,"abstract":"With the increasing capacity of airports, the phenomenon of aircrafts queuing for takeoff is becoming more and more common. For category II/III instrument landing operations, there are strict regulations for the protection areas (including critical and sensitive areas) around the runway. If the aircrafts waiting to take off at the runway entrance which is in the localizer's sensitive area, it may affect the signal of the localizer, thus affecting flight safety. According to MH/T 4003.1-2014 \"the regulation of civil aviation communication, navigation and surveillance equipment (stations) siting Part 1: Navigation\", the sensitive area is maximum at the entrance of the runway, if the take-off waiting line is established on the basis of the range, it may reduce the operation efficiency of the airport. Therefore, collect the buildings data around the runway by using the satellite remote sensing image acquisition technology, and establish the take-off waiting line for the aircrafts by analyzing, modelling, simulating according to the terrain, buildings, runways and the basic parameters of the localizers of the different airports, then analyze the queuing capacity behind the take-off waiting line, which may improve the efficiency of the airports, and have a high engineering application value.","PeriodicalId":349577,"journal":{"name":"Proceedings of the 4th International Conference on Robotics and Artificial Intelligence","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124273533","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}