- BB
Authors: Zheng, Chuanpan; Advisor: -; Participants: Fan, Xiaoliang; Wen, Chenglu; Chen, Longbiao; Wang, Cheng; Li, Jonathan (2020) - Deep learning techniques have been widely applied to traffic flow prediction, considering underlying routine patterns, and multiple context factors (e.g., time and weather). However, the complex spatio-temporal dependencies between inherent traffic patterns and multiple disturbances have not been fully addressed. In this paper, we propose a two-phase end-to-end deep learning framework, namely DeepSTD to uncover the spatio-temporal disturbances (STD) to predict the citywide traffic flow. In the STD Modeling phase, we propose an STD modeling method to model both the different regional disturbances caused by various region functions and the spatio-temporal propagating effects. In the Pre...
|
- BB
Authors: Martin, Niels; Advisor: -; Participants: Solti, Andreas; Mendling, Jan; Depaire, Benoit; Caris, An (2020) - Batch processing refers to an organization of work in which cases are synchronized such that they can be processed as a group. Prior research has studied batch processing mainly from a deductive angle, trying to identify optimal rules for composing batches. As a consequence, we lack methodological support to investigate according to which rules human resources build batches in work settings where batching rules are not strictly enforced. In this paper, we address this research gap by developing a technique to inductively mine batch activation rules from process execution data. The obtained batch activation rules can be used for various purposes, including to explicate the real-life ba...
|
- BB
Authors: Fonnet, Adrien; Advisor: -; Participants: Prié, Yannick (2020) - Immersive analytics (IA) is a new term referring to the use of immersive technologies for data analysis. Yet such applications are not new, and numerous contributions have been made in the last three decades. However, no survey reviewing all these contributions is available. Here we propose a survey of IA from the early nineties until the present day, describing how rendering technologies, data, sensory mapping, and interaction means have been used to build IA systems, as well as how these systems have been evaluated. The conclusions that emerge from our analysis are that: multi-sensory aspects of IA are under-exploited, the 3DUI and VR community knowledge regarding immersive interact...
|
- BB
Authors: Halim, Zahid; Advisor: -; Participants: Ali, Omer; Ghufran Khan, Muhammad (2020) - Frequent itemsets mining is an active research problem in the domain of data mining and knowledge discovery. With the advances in database technology and an exponential increase in data to be stored, there is a need for efficient approaches that can quickly extract useful information from such large datasets. Frequent Itemsets (FIs) mining is a data mining task to find itemsets in a transactional database which occur together above a certain frequency. Finding these FIs usually requires multiple passes over the databases; therefore, making efficient algorithms crucial for mining FIs. This work presents a graph-based approach for representing a complete transactional database. The prop...
|
- BB
Authors: Ding, Yichen; Advisor: -; Participants: Zhou, Xun; Wu, Guojun; Li, Yanhua; Bao, Jie; Zheng, Yu; Luo, Jun (2020) - Given a set of user-specified locations and a massive trajectory dataset, the task of mining spatio-temporal reachable regions aims at finding which road segments are reachable from these locations within a given temporal period based on the historical trajectories. Determining such spatio-temporal reachable regions with high accuracy is vital for many urban applications, such as location-based recommendations and advertising. Traditional approaches to answering such queries essentially perform a distance-based range query over the given road network, which does not consider dynamic travel time at different time of day. By contrast, we propose a data-driven approach to formulate the p...
|
- BB
Authors: Karn, R. R.; Advisor: -; Participants: Kudva, P.; Elfadel, I. A. M. (2019) - Cloud network monitoring data is dynamic and distributed. Signals to monitor the cloud can appear, disappear or change their importance and clarity over time. Machine learning (ML) models tuned to a given data set can therefore quickly become inadequate. A model might be highly accurate at one point in time but may lose its accuracy at a later time due to changes in input data and their features. Distributed learning with dynamic model selection is therefore often required. Under such selection, poorly performing models (although aggressively tuned for the prior data) are retired or put on standby while newor standby models are brought in. The well-known method of Ensemble ML (EML) ma...
|
- BB
Authors: Hussein, S.; Advisor: -; Participants: Kandel, P.; Bolan, C. W.; Wallace, M. B.; Bagci, U. (2019) - Risk stratification (characterization) of tumors from radiology images can be more accurate and faster with
computer-aided diagnosis (CAD) tools. Tumor characterization through such tools can also enable non-invasive cancer staging, prognosis, and foster personalized treatment planning as a part of precision medicine. In this papet, we propose both supervised and unsupervised machine learning strategies to improve tumor characterization. Our first approach is based on supervised learning for which we demonstrate significant gains with deep learning algorithms, particularly by utilizing a 3D convolutional neural network and transfer learning. Motivated by the radiologists’ interpretation...
|
- BB
Authors: Sartzetakis, I.; Advisor: -; Participants: Christodoulopoulos, K. K.; Varvarigos, E. M. (2019) - In optical transport networks the quality of transmission (QoT) is estimated before provisioning new
connections or upgrading existing ones. Traditionally, a physical layer model (PLM) is used for QoT estimation
coupled with high margins to account for the model inaccuracy and the uncertainty in the evolving physical layer
conditions. Reducing the margins increases network efficiency but requires accurate QoT estimation. We present
two machine learning (ML) approaches to formulate such an accurate QoT estimator. We gather physical layer feedback, by monitoring the QoT of existing connections, to understand the actual physical conditions of the network. These data are used to train...
|
- BB
Authors: Di, C.; Advisor: -; Participants: Zhang, B.; Liang, Q.; Li, S.; Guo, Y. (2019) - The machine-to-machine (M2M) communications, which achieve the implementation of Internet of Things (IoT), can be carried over wireless cellular networks. The massive random access (RA) in M2M communications will cause radio access network congestion in the base station (BS), leading to sharp deterioration in access delay and access probability. Access class barring (ACB) that can directly control the flow of machine-type communication (MTC) devices by an ACB factor is an efficient scheme to prevent the BS from traffic overload. In wireless cellular networks, the RA resources (i.e., preambles) are shared by M2M and human-to-human (H2H) devices, and research on ACB scheme ordinarily assum...
|
- BB
Authors: Bauer, A.; Advisor: -; Participants: Nakajima, S.; Görnitz, N.; Müller, K. (2019) - Many learning tasks in the field of natural language processing including sequence tagging, sequence segmentation, and syntactic parsing have been successfully approached by means of structured prediction methods. An appealing property of the corresponding training algorithms is their ability to integrate the loss function of interest into the optimization process improving the final results according to the chosen
measure of performance. Here, we focus on the task of constituency parsing and show how to optimize the model for the F -score in the max-margin framework of a structural support vector machine (SVM).
For reasons of computational efficiency, it is a common approach to binari...
|
- BB
Authors: Liu, H.; Advisor: -; Participants: Liu, Z.; Liu, S.; Liu, Y.; Bin, J.; Shi, F.; Dong, H. (2019) - The integrity of geomagnetic data is a critical factor in understanding the evolutionary process of Earth’s
magnetic field, as it provides useful information for near-surface exploration, unexploded explosive ordnance detection, and so on. Aimed to reconstruct undersampled geomagnetic data, this paper presents a geomagnetic data reconstruction approach based on machine learning techniques. The traditional linear interpolation approaches are prone to time inefficiency and high labor cost, while the proposed approach has a significant
improvement. In this paper, three classic machine learning models, support vector machine, random forests, and gradient boosting were built. Besides, a dee...
|
- BB
Authors: Jeong, S.; Advisor: -; Participants: Hester, J. G. D.; Su, W.; Tentzeris, M. M. (2019) - This letter describes the implementation of a machine learning (ML) classification strategy for read/interrogation
enhancement in chipless radio frequency identification (RFID) applications. A novel ML-based approach for classification and of detection tag identifications (IDs) has been presented, which can perform effective transponder readings for a wide variety of ranges and contexts, while providing tag-ID detection accuracy of up to
99.3%. Four tags encoding the four 2 bit IDs were inkjet-printed onto flexible low-cost polyethylene terephtalate substrates and interrogated without crosstalk or clutter interference de-embedding at ranges up to 50 cm, with different orientations and wi...
|
- BB
Authors: Dang, Xiangying; Advisor: -; Participants: Yao, Xiangjuan; Gong, Dunwei; Tian, Tian (2020) - Mutation testing is a fault-oriented software testing technique, and a test suite generated based on the criterion of mutation testing generally has a high capability in detecting faults. A mutant that is hard killed is called a stubborn one. The traditional methods of test data generation often fail to generate test data that kill stubborn mutants. To improve the efficiency of killing stubborn mutants, in this article, we propose a method of generating test data by dynamically reducing the search domain under the criterion of strong mutation testing. To fulfill this task, we first present a method of measuring the stubbornness of a mutant based on the reachability condition of a muta...
|
- BB
Authors: Hung, Shao-Yen; Advisor: -; Participants: Lee, Chia-Yen; Lin, Yung-Lun (2020) - The transformation of wafers into chips is a complex manufacturing process involving literally thousands of equipment parameters. Delamination, a leading cause of defective products, can occur between die and epoxy molding compound (EMC), epoxy and substrate, lead frame and EMC, etc. Troubleshooting is generally on a case-by-case basis and is both time-consuming and labor intensive. We propose a three-phase data science framework for process prognosis and prediction. The first phase is for data preprocessing. The second phase uses LASSO regression and stepwise regression to identify the key variables affecting delamination. The third phase develops backpropagation neural network (BPNN...
|
- BB
Authors: Li, Tengyue; Advisor: -; Participants: Fong, Simon; Li, Xuqi; Lu, ZhiHui; Gandomi, Amir H. (2020) - Building energy demand prediction (BEDP) concerns sensing the environment using the Internet of Things (IoT), making seamless decisions and responding and controlling certain devices automatically, intelligently and quickly. Typically, BEDP application can be empowered by Fog computing where the sensed data are processed at the edge nodes rather than in a central Cloud. The challenge is that in this decentralized IoT environment, the machine learning algorithm implemented at the Fog node must learn a model from the incoming data accurately and fast. Which type of incremental learning algorithms, combined with traditional or swarm types of stochastic feature selection methods, are more...
|
- BB
Authors: Lei Wang; Advisor: -; Participants: Jianwei Niu; Shui Yu (2020) - Twitter sentiment analysis has become a hot research topic in recent years. Most of existing solutions to Twitter sentiment analysis basically only consider textual information of Twitter messages, and struggle to perform well when facing short and ambiguous Twitter messages. Recent studies show that sentiment diffusion patterns on Twitter have close relationships with sentiment polarities of Twitter messages. Therefore, in this paper we focus on how to fuse textual information of Twitter messages and sentiment diffusion patterns to obtain better performance of sentiment analysis on Twitter data. To this end, we first analyze sentiment diffusion by investigating a phenomenon called se...
|
- BB
Authors: Chunyou Zhang; Advisor: -; Participants: Xiaoqiang Wu; Wei Yan; Lukun Wang; Lei Zhang (2020) - The academic society is stepping into the age of scholarly big data, where finding suitable scholars for collaboration has become ever difficult. Scholarly recommendation approaches are designed to overcome the information overload problems. However, previous methods mainly consider network topology without considering scholars’ academic information and the manually designed similarity measurements may not have a good performance when applying to large-scale sparse networks. To this end, this paper proposes to design a scholarly friend recommendation system by taking advantages of network embedding and scholar attributes. It is worth mentioning that different from traditional scientif...
|
- BB
Authors: Tao, R.; Advisor: -; Participants: Zhang, S.; Huang, X.; Tao, M.; Ma, J.; Ma, S.; Zhang, C.; Zhang, T.; Tang, F.; Lu, J.; Shen, C.; Xie, X. (2019) - Objective: This study focused on developing a fast and accurate automatic ischemic heart disease
detection/localization methodology. Methods: Twavewas segmented from averaged Magnetocardiography (MCG)
recordings and 164 features were subsequently extracted. These features were categorized into three groups: time domain features, frequency domain features, and informa-tion theory features. Next, we compared different machine learning classifiers including: k-nearest neighbor, decision tree, support vector machine (SVM), and XGBoost. To identify ischemia heart disease (IHD) case, we selected three classifiers with best performance and applied model ensemble to average results. All 164 f...
|
- BB
Authors: Yu, H.; Advisor: -; Participants: Yang, X.; Zheng, S.; Sun, C. (2019) - It is well known that active learning can simultaneously improve the quality of the classification model and decrease the complexity of training instances. However, several previous studies have indicated that the performance of active learning is easily disrupted by an imbalanced data distribution. Some existing imbalanced active learning approaches also suffer from either low performance or high time consumption. To address
these problems, this paper describes an efficient solution based on the extreme learning machine (ELM) classification model, called active online-weighted ELM (AOW-ELM). The main contributions of this paper include: 1) the reasons why active learning can be disrupt...
|
- BB
Authors: Mcgraw, G.; Advisor: -; Participants: Bonett, R.; Figueroa, H.; Shepardson, V. (2019) - Artificial intelligence is in the midst of a popular resurgence in the guise of machine learning
(ML). Neural networks and deep learning architectures have been shown empirically to solve many real-world problems. We ask what kinds of risks ML systems pose in terms of security engineering and software security.
|
