607 research outputs found
Robust Composite Nonlinear Feedback Path-Following Control for Independently Actuated Autonomous Vehicles With Differential Steering
No full textComposite nonlinear feedback control for path following of four-wheel independently actuated autonomous ground vehicles
No full textThis paper studies the path following control problem for four-wheel independently actuated (FWIA) autonomous ground vehicles (AGVs) through integrated control of active front-wheel steering (AFS) and direct yaw-moment control (DYC). A modified composite nonlinear feedback (CNF) strategy is proposed to improve the transient performance and eliminate the steady-state errors in the path following control considering the tire force saturations, in the presence of the time-varying road curvature for the desired path. The path following is achieved through vehicle lateral and yaw control, i.e., the lateral velocity and yaw rate are simultaneously controlled to track their respective desired values, where the desired yaw rate is generated according to the path following demand. CarSim-Simulink joint simulation results indicate that the proposed CNF controller can effectively improve the transient response performance, inhibit the overshoots and eliminate the steady-state errors in path following within the tire forces saturation limits
I Know What You Type on Your Phone: Keystroke Inference on Android Device Using Deep Learning
No full textGiven a list of smartphone sensor readings, such as accelerometer, gyroscope and light sensor, is there enough information present to predict a user’s input without access to either the raw text or keyboard log? With the increasing usage of smartphones as personal devices to access sensitive information on-the-go has put user privacy at risk. As the technology advances rapidly, smart- phones now equip multiple sensors to measure user motion, temperature and brightness to provide constant feedback to applications in order to receive accurate and current weather forecast, GPS information and so on. In the ecosystem of Android, sensor reading can be accessed without user permissions and this makes Android devices vulnerable to various side-channel attacks. In this thesis, we first create a native Android app to collect approximately 20700 keypresses from 30 volunteers. The text used for the data collection is carefully selected based on the bigram analysis we run on over 1.3 million tweets. We then present two approaches (single key press and bigram) for feature extraction, those features are constructed using accelerometer, gyroscope and light sensor readings. A deep neural network with four hidden layers is proposed as the baseline for this work, which achieves an accuracy of 47% using categorical cross entropy as the accuracy metric. A multi-view model then is proposed in the later work and multiple views are extracted and performance of the combination of each view is compared for analysis
Towards the Understanding of Private Content – Content-based Privacy Assessment and Protection in Social Networks
No full textIn the wake of the Facebook data breach scandal, users begin to realize how vulnerable their per-sonal data is and how blindly they trust the online social networks (OSNs) by giving them an inordinate amount of private data that touch on unlimited areas of their lives. In particular, stud-ies show that users sometimes reveal too much information or unintentionally release regretful messages, especially when they are careless, emotional, or unaware of privacy risks. Additionally, friends on social media platforms are also found to be adversarial and may leak one’s private in-formation. Threats from within users’ friend networks – insider threats by human or bots – may be more concerning because they are much less likely to be mitigated through existing solutions, e.g., the use of privacy settings. Therefore, we argue that the key component of privacy protection in social networks is protecting sensitive/private content, i.e. privacy as having the ability to control dissemination of information. A mechanism to automatically identify potentially sensitive/private posts and alert users before they are posted is urgently needed. In this dissertation, we propose a context-aware, text-based quantitative model for private in-formation assessment, namely PrivScore, which is expected to serve as the foundation of a privacy leakage alerting mechanism. We first explicitly research and study topics that might contain private content. Based on this knowledge, we solicit diverse opinions on the sensitiveness of private infor-mation from crowdsourcing workers, and examine the responses to discover a perceptual model behind the consensuses and disagreements. We then develop a computational scheme using deep neural networks to compute a context-free PrivScore (i.e., the “consensus” privacy score among average users). Finally, we integrate tweet histories, topic preferences and social contexts to gener-ate a personalized context-aware PrivScore. This privacy scoring mechanism could be employed to identify potentially-private messages and alert users to think again before posting them to OSNs. It could also benefit non-human users such as social media chatbots
Integrating Textual Ontology and Visual Features for Content Based Search in an Invertebrate Paleontology Knowledgebase
No full textThe Treatise on Invertebrate Paleontology is a definitive work completed by more than 300 authors in the field of Paleontology, covering all categories of invertebrate animals. The digital version for the Treatise is consisted of multiple PDF files, however, these files are just a clone of paper version and are not well formatted, which makes it hard to extract structured data using only straightforward methods. In order to make fossil and extant records in the Treatise organized and searchable from a web interface, a digital library which is called Invertebrate Paleontology Knowledgebase (IPKB) was built for information sharing and querying in the Treatise. It is consisted of a database which stores records of all fossils and extant invertebrate animals, and a web interface which provides an online access. The existing IPKB system provides a general framework for the Treatise’s information showing and searching, however, it has very limited search functions, only allowing users querying by pure text. Details of structural properties in the fossil descriptions are not carefully taken into consideration. Moreover, sometimes users cannot provide correct and rich enough query terms. Although authors of the Treatise are all paleontologists, the expected users of IPKB may not be that professional. In order to overcome this limitation and bring more powerful search features into the IPKB system, in this thesis, we present a content-based search function, which allows users to search using textual ontology descriptions and images of fossils. First, this thesis describes the work done by previous research on IPKB system. Except for the original text and image processing approaches, we also present our new efforts on improving these original methods. Second, this thesis presents the algorithm and approach adopted in the construction of content-based search system for IPKB. The search functions in the old IPKB system did not consider the differences among morphological details of certain regions of fossils. Three major parts are discussed in detail: (1) Textual ontology based search. (2) Image based search. (3) Text-image based search
Adaptive Cruise Control on an Electric Robotic Vehicle
No full textAdaptive Cruise Control (ACC), mostly equipped on high end vehicles, is an
optional cruise control system which automatically adjusts the vehicle speed and maintains
a safe distance ahead. The control strategy for ACC, which has been developed for decades, is still well worth being researched. In this thesis, a hierarchical control system architecture was proposed, which divides the controllers into supervisory ones and vehicle level ones. Three control methods, named linear quadratic regulator (LQR), robust LQR (RLQR), and
robust composite nonlinear feedback (RCNF) control, were applied as supervisory controllers respectively. And the active disturbance rejection control (ADRC) was chosen as the vehicle level controller. An electric robotic vehicle was built for demonstration and validation. Simulations and experiments were carried out with detailed discussions, which provide a guidance towards future research.ThesisMaster of Applied Science (MASc
Prediction of Mandatory Lane Changing Behavior Using Artificial Neural Network Model
No full textThe prediction results demonstrated that the method using six frames of variables as the input vectors for the BPNN model could improve the model prediction accuracy. Also, the number of nodes used in the hidden layer had a significant impact on the performance of the BPNN model. The results indicated that the best prediction accuracies in advance of a driver’s actual driving behavior with a lead time of 1s, 1.5s, and 1.8s were at 89.6%, 84.9%, 78.8% for merge events, and for non-merge events were at 92.2%, 87.5%, 81.1% respectively.Recently, the applications of some driver assistance systems on vehicles have reduced vehicle accidents. However, studies have shown that the number of vehicle accidents caused by improper lane-changing behavior remains at a high level. Therefore, research has been focusing on developing a lane-changing assistance system to increase the safety level of driving in traffic. Many researchers have attempted to predict lane-changing behavior, and a general trend in the study of predicting driving behavior is the greater application of computational artificial intelligence.
Artificial Neural Network (ANN) is one of the artificial intelligence methods, and it is well-known for its high reliability in a variety of applications. An ANN model can mimic human thinking and behavior due to its ability to capture the complex relationship among different variables in an environment of uncertainty. In this thesis, a BP (back-propagation) Neural Network model established by two methods was developed to predict a driver’s mandatory lane-changing decisions (merge or non-merge) at an early stage by considering driving environment features as the input vectors. Vehicle trajectory data from the Next Generation Simulation (NGSIM) dataset was used for training and testing the model. The results of the proposed model indicated that the prediction accuracies in advance of a driver’s actual driving behavior with a lead time of 1s, 1.5s, and 1.8s were at 89.6%, 84.9%, 78.8% for merge events, and for non-merge events were at 92.2%, 87.5%, 81.1% respectively.ThesisMaster of Applied Science (MASc)Lane-changing behavior at freeway on-ramps has a significant effect on driving safety and the stability of traffic flow. During the lane-changing process, the information processed by drivers is more complicated than that processed while remaining in a lane. If drivers fail to accurately judge the appropriate lane-changing time or the relative movement characteristics of related vehicles, vehicles accidents may occur. Thus, accurate prediction of lane-changing behavior is essential for a driving assistance system to ensure driver safety
Effective Uni-Modal to Multi-Modal Crowd Estimation based on Deep Neural Networks
No full textCrowd estimation is a vital component of crowd analysis. It finds many applications in real-worldscenarios, e.g. huge gatherings management like Hajj, sporting and musical events, or political rallies. Automated crowd counting facilitates better and effective management of such events and consequently prevents any undesired situation. This is a very challenging problem in practice since there exists a significant difference in the crowd number in and across different images, varying image resolution, large perspective, severe occlusions, and dense crowd-like cluttered background regions. Current approaches do not handle huge crowd diversity well and thus perform poorly in cases ranging from extreme low to high crowd-density, thus, yielding huge crowd underestimation or overestimation. Also, manual crowd counting proves to be infeasible due to very slow and inaccurate results. To address these major crowd counting issues and challenges, we investigate two different types of input data: uni-modal (image) and multi-modal (image and audio). In the uni-modal setting, we propose and analyze four novel end-to-end crowd counting networks, ranging from multi-scale fusion-based models to uni-scale one-pass and two-pass multitask networks. The multi-scale networks employ the attention mechanism to enhance the model efficacy. On the other hand, the uni-scale models are well-equipped with novel and simple-yet effective patch re-scaling module (PRM) that functions identical but is more lightweight than multi-scale approaches. Experimental evaluation demonstrates that the proposed networks outperform the state-of-the-art in majority cases on four different benchmark datasets with up to 12.6% improvement for the RMSE evaluation metric. The better cross-dataset performance also validates the better generalization ability of our schemes. For the multi-modal input, effective feature-extraction (FE) and strong information fusion between two modalities remain a big challenge. Thus, the multi-modal novel network design focuses on investigating different features fusion techniques amid improving the FE. Based on the comprehensive experimental evaluation, the proposed multi-modal network increases the performance under all standard evaluation criteria with up to 33.8% improvement in comparison to the state-of-the-art. The application of multi-scale uni-modal attention networks also proves more effective in other deep learning domains, as demonstrated successfully on seven different scene-text recognition task datasets with better performance
Fatigue Test and Unified Fatigue Life Calculation of Q460C Steel Notched Plates
No full textIn the present study, a total of 20 fatigue tests on notched plates of Q460C steel were carried out, where the effects of relative stress amplitude, Δσ/fy, and relative nominal maximum stress, σmax/fy, on the fatigue life of these notched plates were carefully examined. Theoretical analyses and numerical simulations were subsequently conducted, based on an ellipsoidal fracture model originally proposed by the second author, which has been validated for use as a fracture criterion of fatigue crack, to investigate the fatigue cracking in the Q460C steel notched plates. The theoretical model was further developed to estimate the fatigue life of the Q460C steel notched plates using a unified crack growth approach originally proposed by the second author. Based on the theoretical and simulated results, the accuracy of the unified crack growth approach, and the allowable stress fatigue life formula recommended in China’s code GB50017-2017, were assessed. The comparisons indicate that the unified crack growth approach is able to provide a reliable fatigue life assessment for the Q460C steel notched plates
- …
