Salient Pairwise Spatio-Temporal Interest Points For Real-Time Activity Recognition,
2016
Singapore Management University
Salient Pairwise Spatio-Temporal Interest Points For Real-Time Activity Recognition, Mengyuan Liu, Hong Liu, Qianru Sun, Tianwei Zhang, Runwei Ding
Research Collection School Of Computing and Information Systems
Real-time Human action classification in complex scenes has applications in various domains such as visual surveillance, video retrieval and human robot interaction. While, the task is challenging due to computation efficiency, cluttered backgrounds and intro-variability among same type of actions. Spatio-temporal interest point (STIP) based methods have shown promising results to tackle human action classification in complex scenes efficiently. However, the state-of-the-art works typically utilize bag-of-visual words (BoVW) model which only focuses on the word distribution of STIPs and ignore the distinctive character of word structure. In this paper, the distribution of STIPs is organized into a salient directed graph, …
We Can Hear You With Wi-Fi!,
2016
Singapore Management University
We Can Hear You With Wi-Fi!, Guanhua Wang, Yongpan Zou, Zimu Zhou, Kaishun Wu, Lionel M. Ni
Research Collection School Of Computing and Information Systems
Recent literature advances Wi-Fi signals to “see” people’s motions and locations. This paper asks the following question: Can Wi-Fi “hear” our talks? We present WiHear, which enables Wi-Fi signals to “hear” our talks without deploying any devices. To achieve this, WiHear needs to detect and analyze fine-grained radio reflections from mouth movements. WiHear solves this micro-movement detection problem by introducing Mouth Motion Profile that leverages partial multipath effects and wavelet packet transformation. Since Wi-Fi signals do not require line-of-sight, WiHear can “hear” people talks within the radio range. Further, WiHear can simultaneously “hear” multiple people’s talks leveraging MIMO technology. We …
Sutm System Api At Unlv: Small Uas Traffic Management System Api,
2016
University of Nevada, Las Vegas
Sutm System Api At Unlv: Small Uas Traffic Management System Api, Monetta Angelique Shaw, Ju-Yeon Jo, Yoohwan Kim
Computer Science Faculty Research
This file contains the set of APIs for small unmanned aircraft systems (UAS) Traffic Management (sUTM). The sUTM server hosts a web service that allows any software or device that can use the Internet to utilize the server’s sUAS traffic management (sUTM) functions through these application programming interfaces (API). This library was developed as part of the MS thesis by Monetta Shaw in Spring 2016, "A web based solution for small unmanned aircraft systems (sUAS) traffic management". The summary of the library and its usage instructions are described in the thesis.
Interactively Cutting And Constraining Vertices In Meshes Using Augmented Matrices,
2016
Old Dominion University
Interactively Cutting And Constraining Vertices In Meshes Using Augmented Matrices, Yu-Hong Yeung, Jessica Crouch, Alex Pothen
Computer Science Faculty Publications
We present a finite-element solution method that is well suited for interactive simulations of cutting meshes in the regime of linear elastic models. Our approach features fast updates to the solution of the stiffness system of equations to account for real-time changes in mesh connectivity and boundary conditions. Updates are accomplished by augmenting the stiffness matrix to keep it consistent with changes to the underlying model, without refactoring the matrix at each step of cutting. The initial stiffness matrix and its Cholesky factors are used to implicitly form and solve a Schur complement system using an iterative solver. As changes …
Users Acceptance Of Health Behavioral Change Support Systems,
2016
Dakota State University
Users Acceptance Of Health Behavioral Change Support Systems, Mohammad Al-Ramahi, Insu Park, Jun Liu
Research & Publications
Behavioral Change Support Systems (BCSSs) is a socio-technical information systems with psychological and behavioral outcomes aim to change users’ behavior and lifestyle. The promising outcomes of BCSSs make them especially useful in certain areas such as healthcare, where these systems could be leveraged to motivate people toward healthy behavior and then help them to achieve their goals better. However, health BCSSs cannot help facilitate self-monitoring and self-management or even improve patients’ health outcomes when patients do not accept the technology first. In this article, we extend the existing literature of users’ acceptance of health BCSSs by introducing new variables that …
Ambiguityvis: Visualization Of Ambiguity In Graph Layouts,
2016
Singapore Management University
Ambiguityvis: Visualization Of Ambiguity In Graph Layouts, Yong Wang, Qiaomu Shen, Zhiguang Zhou, Min Zhu, Sixiao Yang, Qu Huamin
Research Collection School Of Computing and Information Systems
Node-link diagrams provide an intuitive way to explore networks and have inspired a large number of automated graph layout strategies that optimize aesthetic criteria. However, any particular drawing approach cannot fully satisfy all these criteria simultaneously, producing drawings with visual ambiguities that can impede the understanding of network structure. To bring attention to these potentially problematic areas present in the drawing. this paper presents a technique that highlights common types of visual ambiguities: ambiguous spatial relationships between nodes and edges, visual overlap between community structures, and ambiguity in edge bundling and metanodes. Metrics, including newly proposed metrics for abnormal edge …
Demo: Profiling Power Utilization Behaviours Of Smartwatch Applications,
2016
Singapore Management University
Demo: Profiling Power Utilization Behaviours Of Smartwatch Applications, Joseph Joo Keng Chan, Lingxiao Jiang, Rajesh Krishna Balan, Youngki Lee, Archan Misra
Research Collection School Of Computing and Information Systems
Smartwatches complement the main mobile phone and are able to profile user-activity as well as provide links, updates and notifications with work or personal utilities (e.g. Email, Social Media, Messaging etc.). Although very promising, smartwatches are still limited by low battery life. This is due to the small size of the battery as well as the need to continuously perform sensing. Battery drain issues by apps as well as the system are a common complaint by users. Improved tools for power analysis and profiling of smartwatch apps can help both developers (by providing a platform for pre-release analysis) and users …
Demo: Sensing Gamers' Emotions Using Physiological Sensors,
2016
Singapore Management University
Demo: Sensing Gamers' Emotions Using Physiological Sensors, Sinh Huynh, Rajesh Krishna Balan, Youngki Lee
Research Collection School Of Computing and Information Systems
Understanding emotions of gamers can benefit game designers in various ways. How gamers feel while they playing a game can be treated as valuable user feedback to improve the development process of that game. Sensing player emotions also enables game designers to create adaptive game that can adjust itself to provide best gaming experience based on player emotions. However, how to effectively evaluate emotions of gamers is still an open research challenge. Two common techniques to evaluate emotional state are using self-assessments such as questionnaires or interviews, and to recognize expressed emotions by analyzing videos or images of facial expression, …
Demo: Smartwatch Based Food Diary And Eating Analytics,
2016
Singapore Management University
Demo: Smartwatch Based Food Diary And Eating Analytics, Sougata Sen, Vigneshwaran Subbaraju, Archan Misra, Youngki Lee, Rajesh Krishna Balan
Research Collection School Of Computing and Information Systems
Monitoring an individual’s daily dietary intake can provide various insights regarding the health of the individual. Applications such as My Fitness Pal exists, which allows individuals to monitor all items that the individual consumed. However, manual monitoring can be labour intensive. To overcome this limitation, wrist worn sensor based eating habit monitoring has been studied by various researchers. These systems can detect eating gesture, but they cannot determine what is being eaten. We have built a system which can (i) detect eating gesture using the smartwatch's inertial sensors (ii) use the smartwatch's camera to capture images of food consumed at …
Powerforecaster: Predicting Power Impact Of Mobile Sensing Applications At Pre-Installation Time,
2016
Korea Advanced Institute of Science & Technology
Powerforecaster: Predicting Power Impact Of Mobile Sensing Applications At Pre-Installation Time, Chulhong Min, Youngki Lee, Chungkuk Yoo, Seungwoo Kang, Inseok Hwang, Junehwa Song
Research Collection School Of Computing and Information Systems
Today's smartphone application (hereinafter 'app') markets miss a key piece of information, power consumption of apps. This causes a severe problem for continuous sensing apps as they consume significant power without users' awareness. Users have no choice but to repeatedly install one app after another and experience their power use. To break such an exhaustive cycle, we propose PowerForecaster, a system that provides users with power use of sensing apps at pre-installation time. Such advanced power estimation is extremely challenging since the power cost of a sensing app largely varies with users' physical activities and phone use patterns. We observe …
Gpu Accelerated On-The-Fly Reachability Checking,
2015
Singapore Management University
Gpu Accelerated On-The-Fly Reachability Checking, Zhimin Wu, Yang Liu, Jun Sun, Jianqi Shi, Shengchao Qin
Research Collection School Of Computing and Information Systems
Model checking suffers from the infamous state space explosion problem. In this paper, we propose an approach, named GPURC, to utilize the Graphics Processing Units (GPUs) to speed up the reachability verification. The key idea is to achieve a dynamic load balancing so that the many cores in GPUs are fully utilized during the state space exploration.To this end, we firstly construct a compact data encoding of the input transition systems to reduce the memory cost and fit the calculation in GPUs. To support a large number of concurrent components, we propose a multi-integer encoding with conflict-release accessing approach. We …
All Your Sessions Are Belong To Us: Investigating Authenticator Leakage Through Backup Channels On Android,
2015
Singapore Management University
All Your Sessions Are Belong To Us: Investigating Authenticator Leakage Through Backup Channels On Android, Guangdong Bai, Jun Sun, Jianliang Wu, Quanqi Ye, Li Li, Jin Song Dong, Shanqing Guo
Research Collection School Of Computing and Information Systems
Security of authentication protocols heavily relies on the confidentiality of credentials (or authenticators) like passwords and session IDs. However, unlike browser-based web applications for which highly evolved browsers manage the authenticators, Android apps have to construct their own management. We find that most apps simply locate their authenticators into the persistent storage and entrust underlying Android OS for mediation. Consequently, these authenticators can be leaked through compromised backup channels. In this work, we conduct the first systematic investigation on this previously overlooked attack vector. We find that nearly all backup apps on Google Play inadvertently expose backup data to any …
Predicting Energy Demand Peak Using M5 Model Trees,
2015
Western University
Predicting Energy Demand Peak Using M5 Model Trees, Sara S. Abdelkader, Katarina Grolinger, Miriam Am Capretz
Electrical and Computer Engineering Publications
Predicting energy demand peak is a key factor for reducing energy demand and electricity bills for commercial customers. Features influencing energy demand are many and complex, such as occupant behaviours and temperature. Feature selection can decrease prediction model complexity without sacrificing performance. In this paper, features were selected based on their multiple linear regression correlation coefficients. This paper discusses the capabilities of M5 model trees in energy demand prediction for commercial buildings. M5 model trees are similar to regression trees; however they are more suitable for continuous prediction problems. The M5 model tree prediction was developed based on a selected …
Battle Bot Ai – Patriot Bot,
2015
California Polytechnic State University, San Luis Obispo
Battle Bot Ai – Patriot Bot, James Johnston
Computer Engineering
An entry in the the 'Battle Block AI' competition hosted by 'The AI Games'.
Energy Forecasting For Event Venues: Big Data And Prediction Accuracy,
2015
Western University
Energy Forecasting For Event Venues: Big Data And Prediction Accuracy, Katarina Grolinger, Alexandra L'Heureux, Miriam Am Capretz, Luke Seewald
Electrical and Computer Engineering Publications
Advances in sensor technologies and the proliferation of smart meters have resulted in an explosion of energy-related data sets. These Big Data have created opportunities for development of new energy services and a promise of better energy management and conservation. Sensor-based energy forecasting has been researched in the context of office buildings, schools, and residential buildings. This paper investigates sensor-based forecasting in the context of event-organizing venues, which present an especially difficult scenario due to large variations in consumption caused by the hosted events. Moreover, the significance of the data set size, specifically the impact of temporal granularity, on energy …
Students' Perspectives Of Mobile Learning Platforms: An Empirical Study,
2015
Western University
Students' Perspectives Of Mobile Learning Platforms: An Empirical Study, Muasaad Alrasheedi, Luiz Fernando Capretz, Arif Raza
Electrical and Computer Engineering Publications
Educational institutions are becoming involved in adopting technological innovations like th e mobile learning (m-Learning) platform for education. Mobile technologies are the next frontier as infrast ructure for m-Learning because they can provide high-quality learning capab ilities to satisfy the rising student demand for mobility and flexibility due to the ubiquitous nature of mobile tec hnology (smartphones) and the va st opportunities it offers, there ar e indications that smartphones could lead the next generation for learning platforms. Researchers have examin ed the idea from several angles and produced a copious amount of literature devoted to explaining the interrelationships of …
Management's Perspective On Critical Success Factors Affecting Mobile Learning In Higher Education Institutions - An Empirical Study,
2015
Western University
Management's Perspective On Critical Success Factors Affecting Mobile Learning In Higher Education Institutions - An Empirical Study, Muasaad Alrasheedi, Luiz Fernando Capretz, Arif Raza
Electrical and Computer Engineering Publications
Mobile learning (m-Learning) is considered to be one of the fastest growing learning platforms. The immense interest in m-Learning is attributed to the incredible rate of growth of mobile technology and its proliferation into every aspect of modern life. Despite this, m-Learning has not experienced a similar adoption rate in the education sector, chiefly higher education. Researchers have attempted to explain this anomaly by conducting several studies in the area. However, mostly the research in m-Learning is examined from the perspective of the students and educators. In this research, it is contended that there is a third important stakeholder group …
Toward Unification Of Explicit And Implicit Invocation-Style Programming,
2015
The University of Texas at El Paso
Toward Unification Of Explicit And Implicit Invocation-Style Programming, Yoonsik Cheon
Departmental Technical Reports (CS)
Subprograms like procedures and methods can be invoked explicitly or implicitly; in implicit invocation, an event implicitly causes the invocation of subprograms that are registered an interest in the event. Mixing these two styles is common in programming and often unavoidable in developing such software as GUI applications and event-based control systems. However, it isn't also uncommon for the mixed use to complicate programming logic and thus produce unclean code, code that is hard to read and understand. We show, through a small but realistic example, that the problem is not much on mixing two different styles itself but more …
A Systematic Derivation Of Loop Specifications Using Patterns,
2015
The University of Texas at El Paso
A Systematic Derivation Of Loop Specifications Using Patterns, Aditi Barua, Yoonsik Cheon
Departmental Technical Reports (CS)
Any non-trivial program contains loop control structures such as while, for and do statements. A formal correctness proof of code containing loop control structures is typically performed using an induction-based technique, and oftentimes the most challenging step of an inductive proof is formulating a correct induction hypothesis. An incorrectly-formulated induction hypothesis will surely lead to a failure of the proof. In this paper we propose a systematic approach for formulating and driving specifications of loop control structures for formal analysis and verification of programs. We explain our approach using while loops and a functional program verification technique in which a …
Real Time Analytics On Digital Distraction,
2015
California Polytechnic Institute of San Luis Obispo
Real Time Analytics On Digital Distraction, Kristian Welch
Computer Science and Software Engineering
Hypothesis: empirically measuring the users productivity has the potential to significantly increase their productivity. This paper is the documentation of the process of building software capable of verifying this hypothesis. Starting with the research which gives enough evidence to warrant the hypothesis, also included is commentary on the prototyping, design decisions, and iteration based on user feedback of the software.
