OS and Networks Commons^™

Perception Coordination Network: A Neuro Framework For Multimodal Concept Acquisition And Binding, You-Lu Xing, Xiao-Feng Shi, Fu-Rao Shen, Jin-Xi Zhao, Jing-Xin Pan, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

To simulate the concept acquisition and binding of different senses in the brain, a biologically inspired neural network model named perception coordination network (PCN) is proposed. It is a hierarchical structure, which is functionally divided into the primary sensory area (PSA), the primary sensory association area (SAA), and the higher order association area (HAA). The PSA contains feature neurons which respond to many elementary features, e.g., colors, shapes, syllables, and basic flavors. The SAA contains primary concept neurons which combine the elementary features in the PSA to represent unimodal concept of objects, e.g., the image of an apple, the Chinese …

Maximizing Multifaceted Network Influence, Yuchen Li, Ju Fan, George V. Ovchinnikov, Panagiotis Karras

Research Collection School Of Computing and Information Systems

An information dissemination campaign is often multifaceted, involving several facets or pieces of information disseminating from different sources. The question then arises, how should we assign such pieces to eligible sources so as to achieve the best viral dissemination results? Past research has studied the problem of Influence Maximization (IM), which is to select a set of k promoters that maximizes the expected reach of a message over a network. However, in this classical IM problem, each promoter spreads out the same unitary piece of information. In this paper, we propose the Optimal Influential Pieces Assignment (OIPA) problem, which is …

Manifold-Valued Image Generation With Wasserstein Generative Adversarial Nets, Zhiwu Huang, Wu J., G. L. Van

Research Collection School Of Computing and Information Systems

Generative modeling over natural images is one of the most fundamental machine learning problems. However, few modern generative models, including Wasserstein Generative Adversarial Nets (WGANs), are studied on manifold-valued images that are frequently encountered in real-world applications. To fill the gap, this paper first formulates the problem of generating manifold-valued images and exploits three typical instances: hue-saturation-value (HSV) color image generation, chromaticity-brightness (CB) color image generation, and diffusion-tensor (DT) image generation. For the proposed generative modeling problem, we then introduce a theorem of optimal transport to derive a new Wasserstein distance of data distributions on complete manifolds, enabling us to …

A Coordination Framework For Multi-Agent Persuasion And Adviser Systems, Budhitama Subagdja, Ah-Hwee Tan, Yilin Kang

Research Collection School Of Computing and Information Systems

Assistive agents have been used to give advices to the users regarding activities in daily lives. Although adviser bots are getting smarter and gaining more popularity these days they are usually developed and deployed independent from each other. When several agents operate together in the same context, their advices may no longer be effective since they may instead overwhelm or confuse the user if not properly arranged. Only little attentions have been paid to coordinating different agents to give different advices to a user within the same environment. However, aligning the advices on-the-fly with the appropriate presentation timing at the …

Task Relation Networks, Jianshu Li, Pan Zhou, Yunpeng Chen, Jian Zhao, Sujoy Roy, Shuicheng Yan, Jiashi Feng, Terence Sim

Research Collection School Of Computing and Information Systems

Multi-task learning is popular in machine learning and computer vision. In multitask learning, properly modeling task relations is important for boosting the performance of jointly learned tasks. Task covariance modeling has been successfully used to model the relations of tasks but is limited to homogeneous multi-task learning. In this paper, we propose a feature based task relation modeling approach, suitable for both homogeneous and heterogeneous multi-task learning. First, we propose a new metric to quantify the relations between tasks. Based on the quantitative metric, we then develop the task relation layer, which can be combined with any deep learning architecture …

Quantifying Activity Levels Of Community-Dwelling Seniors Through Beacon Monitoring, Jin Qiang Goh, Hwee-Pink Tan, Hwee Xian Tan

Research Collection School Of Computing and Information Systems

The ageing population is rapidly increasing, both in Singapore and worldwide. Due to the shortage of healthcare professionals and institutionalized care, there is a pertinent need for seniors to age-in-place-safely and in the familiarity of their neighborhoods. In addition, changing family structures and rising divorce rates, coupled with the desire for more personal space and independence, have resulted in a significant proportion of seniors who live alone at home. In this paper, we describe a scalable and low-cost monitoring system that can help to identify community-dwelling seniors who are at risk of social isolation and/or frailty. This is achieved by …

Efficient Stochastic Gradient Hard Thresholding, Pan Zhou, Xiao-Tong Yuan, Jiashi Feng

Research Collection School Of Computing and Information Systems

Stochastic gradient hard thresholding methods have recently been shown to work favorably in solving large-scale empirical risk minimization problems under sparsity or rank constraint. Despite the improved iteration complexity over full gradient methods, the gradient evaluation and hard thresholding complexity of the existing stochastic algorithms usually scales linearly with data size, which could still be expensive when data is huge and the hard thresholding step could be as expensive as singular value decomposition in rank-constrained problems. To address these deficiencies, we propose an efficient hybrid stochastic gradient hard thresholding (HSG-HT) method that can be provably shown to have sample-size-independent gradient …

Reinforcement Learning For Collective Multi-Agent Decision Making, Duc Thien Nguyen

Dissertations and Theses Collection (Open Access)

In this thesis, we study reinforcement learning algorithms to collectively optimize decentralized policy in a large population of autonomous agents. We notice one of the main bottlenecks in large multi-agent system is the size of the joint trajectory of agents which quickly increases with the number of participating agents. Furthermore, the noiseof actions concurrently executed by different agents in a large system makes it difficult for each agent to estimate the value of its own actions, which is well-known as the multi-agent credit assignment problem. We propose a compact representation for multi-agent systems using the aggregate counts to address …

Modeling Movement Decisions In Networks: A Discrete Choice Model Approach, Larry Lin Junjie

Dissertations and Theses Collection (Open Access)

In this dissertation, we address the subject of modeling and simulation of agents and their movement decision in a network environment. We emphasize the development of high quality agent-based simulation models as a prerequisite before utilization of the model as an evaluation tool for various recommender systems and policies. To achieve this, we propose a methodological framework for development of agent-based models, combining approaches such as discrete choice models and data-driven modeling.

The discrete choice model is widely used in the field of transportation, with a distinct utility function (e.g., demand or revenue-driven). Through discrete choice models, the movement decision …

New Insight Into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling And Convexity, Pan Zhou, Xiao-Tong Yuan, Jiashi Feng

Research Collection School Of Computing and Information Systems

As an incremental-gradient algorithm, the hybrid stochastic gradient descent (HSGD) enjoys merits of both stochastic and full gradient methods for finite-sum problem optimization. However, the existing rate-of-convergence analysis for HSGD is made under with-replacement sampling (WRS) and is restricted to convex problems. It is not clear whether HSGD still carries these advantages under the common practice of without-replacement sampling (WoRS) for non-convex problems. In this paper, we affirmatively answer this open question by showing that under WoRS and for both convex and non-convex problems, it is still possible for HSGD (with constant step-size) to match full gradient descent in rate …

Authorized Function Homomorphic Signature, Qingwen Guo, Qiong Huang, Guomin Yang

Research Collection School Of Computing and Information Systems

Homomorphic signature (HS) is a novel primitive that allows an agency to carry out arbitrary (polynomial time) computation f on the signed data (m) over right arrow and accordingly gain a signature sigma(h) for the computation result f ((m) over right arrow) with respect to f on behalf of the data owner (DO). However, since DO lacks control of the agency's behavior, receivers would believe that DO did authenticate the computation result even if the agency misbehaves and applies a function that the DO does not want. To address the problem above, in this paper we introduce a new primitive …

Simknn: A Scalable Method For In-Memory Knn Search Over Moving Objects In Road Networks, Bin Cao, Chenyu Hou, Suifei Li, Jing Fan, Jianwei Yin, Baihua Zheng, Jie Bao

Research Collection School Of Computing and Information Systems

Nowadays, many location-based applications require the ability of querying k-nearest neighbors over a very large scale of5 moving objects in road networks, e.g., taxi-calling and ride-sharing services. Traditional grid index with equal-sized cells can not adapt6 to the skewed distribution of moving objects in real scenarios. Thus, to obtain the fast querying response time, the grid needs to be split7 into more smaller cells which introduces the side-effect of higher memory cost, i.e., maintaining such a large volume of cells requires a8 much larger memory space at the server side. In this paper, we present SIMkNN, a scalable and in-memory …

Probabilistic Guided Exploration For Reinforcement Learning In Self-Organizing Neural Networks, Peng Wang, Weigui Jair Zhou, Di Wang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Exploration is essential in reinforcement learning, which expands the search space of potential solutions to a given problem for performance evaluations. Specifically, carefully designed exploration strategy may help the agent learn faster by taking the advantage of what it has learned previously. However, many reinforcement learning mechanisms still adopt simple exploration strategies, which select actions in a pure random manner among all the feasible actions. In this paper, we propose novel mechanisms to improve the existing knowledgebased exploration strategy based on a probabilistic guided approach to select actions. We conduct extensive experiments in a Minefield navigation simulator and the results …

Experiences & Challenges With Server-Side Wifi Indoor Localization Using Existing Infrastructure, Dheryta Jaisinghani, Rajesh Krishna Balan, Vinayak Naik, Archan Misra, Youngki Lee

Research Collection School Of Computing and Information Systems

Real-world deployments of WiFi-based indoor localization in large public venues are few and far between as most state-of-the-art solutions require either client or infrastructure-side changes. Hence, even though high location accuracy is possible with these solutions, they are not practical due to cost and/or client adoption reasons. Majority of the public venues use commercial controller-managed WLAN solutions, that neither allow client changes nor infrastructure changes. In fact, for such venues we have observed highly heterogeneous devices with very low adoption rates for client-side apps. In this paper, we present our experiences in deploying a scalable location system for such venues. …

Knowledge-Aware Attentive Neural Network For Ranking Question Answer Pairs, Ying Shen, Yang Deng, Min Yang, Yaliang Li, Nan Du, Wei Fan, Kai Lei

Research Collection School Of Computing and Information Systems

Ranking question answer pairs has attracted increasing attention recently due to its broad applications such as information retrieval and question answering (QA). Significant progresses have been made by deep neural networks. However, background information and hidden relations beyond the context, which play crucial roles in human text comprehension, have received little attention in recent deep neural networks that achieve the state of the art in ranking QA pairs. In the paper, we propose KABLSTM, a Knowledge-aware Attentive Bidirectional Long Short-Term Memory, which leverages external knowledge from knowledge graphs (KG) to enrich the representational learning of QA sentences. Specifically, we develop …

Situation-Aware Authenticated Video Broadcasting Over Train-Trackside Wifi Networks, Yongdong Wu, Dengpan Ye, Zhuo Wei, Qian Wang, William Tan, Robert H. Deng

Research Collection School Of Computing and Information Systems

Live video programmes can bring in better travel experience for subway passengers and earn abundant advertisement revenue for subway operators. However, because the train-trackside channels for video dissemination are easily accessible to anyone, the video traffic are vulnerable to attacks which may cause deadly tragedies. This paper presents a situation-aware authenticated video broadcasting scheme in the railway network which consists of train, on-board sensor, trackside GSM-R (Global System for Mobile Communications-Railway) device, WiFi AP (Access Point), and train control center. Specifically, the scheme has four modules: (1) a train uses its on-board sensors to obtain its speed, location, and RSSI …

Music Popularity, Diffusion And Recommendation In Social Networks: A Fusion Analytics Approach, Jing Ren

Dissertations and Theses Collection (Open Access)

Streaming music and social networks offer an easy way for people to gain access to a massive amount of music, but there are also challenges for the music industry to design for promotion strategies via the new channels. My dissertation employs a fusion of machine-based methods and explanatory empiricism to explore music popularity, diffusion, and promotion in the social network context.

Region-Aware Reflection Removal With Unified Content And Gradient Priors, Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, Wen Gao, Alex C. Kot

Research Collection School Of Computing and Information Systems

Removing the undesired reflections in images taken through the glass is of broad application to various image processing and computer vision tasks. Existing single image-based solutions heavily rely on scene priors such as separable sparse gradients caused by different levels of blur, and they are fragile when such priors are not observed. In this paper, we notice that strong reflections usually dominant a limited region in the whole image, and propose a region-aware reflection removal approach by automatically detecting and heterogeneously processing regions with and without reflections. We integrate content and gradient priors to jointly achieve missing contents restoration, as …

Crrn: Multi-Scale Guided Concurrent Reflection Removal Network, Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, Alex C. Kot

Research Collection School Of Computing and Information Systems

Removing the undesired reflections from images taken through the glass is of broad application to various computer vision tasks. Non-learning based methods utilize different handcrafted priors such as the separable sparse gradients caused by different levels of blurs, which often fail due to their limited description capability to the properties of real-world reflections. In this paper, we propose the Concurrent Reflection Removal Network (CRRN) to tackle this problem in a unified framework. Our proposed network integrates image appearance information and multi-scale gradient information with human perception inspired loss function, and is trained on a new dataset with 3250 reflection images …

Survey Of Randomization Defenses On Cloud Computing, Jianming Fu, Yan Lin, Xiuwen Liu, Xu Zhang

Research Collection School Of Computing and Information Systems

Cloud computing has changed the processing mode on resources of individuals and industries by providing computing and storage services to users. However, existing defenses on cloud, such as virtual machine monitoring and integrity detection, cannot counter against attacks result from the homogeneity and vulnerability of services effectively. In this paper, we have investigated the threats on cloud computing platform from the perspective of cloud service, service interface and network interface, such as code reuse attack, side channel attack and SQL injection. Code reuse attack chains code snippets (gadgets) located in binaries to bypass Data Execution Prevention (DEP). Side channel attack …

Empirical Risk Landscape Analysis For Understanding Deep Neural Networks, Pan Zhou, Jiashi Feng

Research Collection School Of Computing and Information Systems

This work aims to provide comprehensive landscape analysis of empirical risk in deep neural networks (DNNs), including the convergence behavior of its gradient, its stationary points and the empirical risk itself to their corresponding population counterparts, which reveals how various network parameters determine the convergence performance. In particular, for an l-layer linear neural network consisting of di neurons in the i-th layer, we prove the gradient of its empirical risk uniformly converges to the one of its population risk, at the rate of O(r 2l p l √ maxi dis log(d/l)/n). Here d is the total weight dimension, s is …

Learning Latent Characteristics Of Locations Using Location-Based Social Networking Data, Thanh Nam Doan

Dissertations and Theses Collection (Open Access)

This dissertation addresses the modeling of latent characteristics of locations to describe the mobility of users of location-based social networking platforms. With many users signing up location-based social networking platforms to share their daily activities, these platforms become a gold mine for researchers to study human visitation behavior and location characteristics. Modeling such visitation behavior and location characteristics can benefit many use- ful applications such as urban planning and location-aware recommender sys- tems. In this dissertation, we focus on modeling two latent characteristics of locations, namely area attraction and neighborhood competition effects using location-based social network data. Our literature survey …

Breathing-Based Authentication On Resource-Constrained Iot Devices Using Recurrent Neural Networks, Jagmohan Chauhan, Suranga Seneviratne, Yining Hu, Archan Misra, Aruna Seneviratne, Youngki Lee

Research Collection School Of Computing and Information Systems

Recurrent neural networks (RNNs) have shown promising resultsin audio and speech-processing applications. The increasingpopularity of Internet of Things (IoT) devices makes a strongcase for implementing RNN-based inferences for applicationssuch as acoustics-based authentication and voice commandsfor smart homes. However, the feasibility and performance ofthese inferences on resource-constrained devices remain largelyunexplored. The authors compare traditional machine-learningmodels with deep-learning RNN models for an end-to-endauthentication system based on breathing acoustics.

Virtualization In Wireless Sensor Networks: Fault Tolerant Embedding For Internet Of Things, Omprakash Kaiwartya, Abdul Hanan Abdullah, Yue Cao, Jaime Lloret, Sushil Kumar, Rajiv Ratn Shah, Mukesh Prasad, Shiv Prakash

Research Collection School Of Computing and Information Systems

Recently, virtualization in wireless sensor networks (WSNs) has witnessed significant attention due to the growing service domain for IoT. Related literature on virtualization in WSNs explored resource optimization without considering communication failure in WSNs environments. The failure of a communication link in WSNs impacts many virtual networks running IoT services. In this context, this paper proposes a framework for optimizing fault tolerance in virtualization in WSNs, focusing on heterogeneous networks for service-oriented IoT applications. An optimization problem is formulated considering fault tolerance and communication delay as two conflicting objectives. An adapted non-dominated sorting based genetic algorithm (A-NSGA) is developed to …

Scaling Human Activity Recognition Via Deep Learning-Based Domain Adaptation, Md Abdullah Hafiz Khan, Nirmalya Roy, Archan Misra

Research Collection School Of Computing and Information Systems

We investigate the problem of making human activityrecognition (AR) scalable–i.e., allowing AR classifiers trainedin one context to be readily adapted to a different contextualdomain. This is important because AR technologies can achievehigh accuracy if the classifiers are trained for a specific individualor device, but show significant degradation when the sameclassifier is applied context–e.g., to a different device located ata different on-body position. To allow such adaptation withoutrequiring the onerous step of collecting large volumes of labeledtraining data in the target domain, we proposed a transductivetransfer learning model that is specifically tuned to the propertiesof convolutional neural networks (CNNs). Our model, …

Sequential Recommendation With User Memory Networks, Xu Chen, Hongteng Xu, Yongfeng Zhang, Jiaxi Tang, Yixin Cao, Zheng Qin, Hongyuan Zha

Research Collection School Of Computing and Information Systems

User preferences are usually dynamic in real-world recommender systems, and a user»s historical behavior records may not be equally important when predicting his/her future interests. Existing recommendation algorithms -- including both shallow and deep approaches -- usually embed a user»s historical records into a single latent vector/representation, which may have lost the per item- or feature-level correlations between a user»s historical records and future interests. In this paper, we aim to express, store, and manipulate users» historical records in a more explicit, dynamic, and effective manner. To do so, we introduce the memory mechanism to recommender systems. Specifically, we design …

Building Deep Networks On Grassmann Manifolds, Zhiwu Huang, J. Wu, Gool L. Van

Research Collection School Of Computing and Information Systems

Learning representations on Grassmann manifolds is popular in quite a few visual recognition tasks. In order to enable deep learning on Grassmann manifolds, this paper proposes a deep network architecture by generalizing the Euclidean network paradigm to Grassmann manifolds. In particular, we design full rank mapping layers to transform input Grassmannian data to more desirable ones, exploit re-orthonormalization layers to normalize the resulting matrices, study projection pooling layers to reduce the model complexity in the Grassmannian context, and devise projection mapping layers to respect Grassmannian geometry and meanwhile achieve Euclidean forms for regular output layers. To train the Grassmann networks, …

Collaborative Fall Detection Using Smartphone And Kinect, Xue Li, Lanshun Nie, Hanchuan Xu, Xianzhi Wang

Research Collection School Of Computing and Information Systems

Humanfall detection has attracted broad attentions as sensors and mobile devices are increasingly adopted in real-life scenarios such as smart homes. The complexity of activities in home environments pose severe challenges to the fall detection research with respect to the detection accuracy. We propose a collaborative detection platform that combines two subsystems: a threshold-based fall detection subsystem using mobile phones and a support vector machine (SVM)-based fall detection subsystem using Kinects. Both subsystems have their respective confidence models and the platform detects falls by fusing the data of both subsystems using two methods: the logical rules-based and D-S evidence fusion …

Multi-Target Deep Neural Networks: Theoretical Analysis And Implementation, Zeng Zeng, Nanying Liang, Xulei Yang, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

In this work, we propose a novel deep neural network referred to as Multi-Target Deep Neural Network (MT-DNN). We theoretically prove that different stable target models with shared learning paths are stable and can achieve optimal solutions respectively. Based on GoogleNet, we design a single model with three different targets, one for classification, one for regression, and one for masks that is composed of 256  ×  256 sub-models. Unlike bounding boxes used in ImageNet, our single model can draw the shapes of target objects, and in the meanwhile, classify the objects and calculate their sizes. We validate our single MT-DNN …

Bikemate: Bike Riding Behavior Monitoring With Smartphones, Weixi Gu, Zimu Zhou, Yuxun Zhou, Han Zou, Yunxin Liu, Costas J. Spanos, Lin Zhang

Research Collection School Of Computing and Information Systems

Detecting dangerous riding behaviors is of great importance to improve bicycling safety. Existing bike safety precautionary measures rely on dedicated infrastructures that incur high installation costs. In this work, we propose BikeMate, a ubiquitous bicycling behavior monitoring system with smartphones. BikeMate invokes smartphone sensors to infer dangerous riding behaviors including lane weaving, standing pedalling and wrong-way riding. For easy adoption, BikeMate leverages transfer learning to reduce the overhead of training models for different users, and applies crowdsourcing to infer legal riding directions without prior knowledge. Experiments with 12 participants show that BikeMate achieves an overall accuracy of 86.8% for lane …