Biblio

Automatic detection of TV advertisements is of paramount importance for various media monitoring agencies. Existing works in this domain have mostly focused on news channels using news specific features. Most commercial products use near copy detection algorithms instead of generic advertisement classification. A generic detector needs to handle inter-class and intra-class imbalances present in data due to variability in content aired across channels and frequent repetition of advertisements. Imbalances present in data make classifiers biased towards one of the classes and thus require special treatment. We propose to use tree of perceptrons to solve this problem. The training data available for each perceptron node is balanced using cluster based over-sampling and TOMEK link cleaning as we traverse the tree downwards. The trained perceptron node then passes the original unbalanced data to its children. This process is repeated recursively till we reach the leaf nodes. We call this new algorithm as "Progressively Balanced Perceptron Tree". We have also contributed a TV advertisements dataset consisting of 250 hours of videos recorded from five non-news TV channels of different genres. Experimentations on this dataset have shown that the proposed approach has comparatively superior and balanced performance with respect to six baseline methods. Our proposal generalizes well across channels, with varying training data sizes and achieved a top F1-score of 97% in detecting advertisements.

Smartphones nowadays are customized to help users with their daily tasks such as storing important data or making transactions through the internet. With the sensitivity of the data involved, authentication mechanism such as fixed-text password, PIN, or unlock patterns are used to safeguard these data against intruders. However, these mechanisms have the risk from security threats such as cracking or shoulder surfing. To enhance mobile and/or information security, this study aimed to develop a free-form handwriting gesture user authentication for smartphones. It also tried to discover the static and dynamic handwriting features that significantly influence the recognition of a legitimate user. The experiment was then conducted by asking thirty (30) individuals to draw or swipe using their fingertip their desired free-form security pattern ten (10) times. These patterns were then cleaned and processed, and extracted seven (7) static and eleven (11) dynamic handwriting features. By means of Neural Network classifier of the RapidMiner data mining tool, these features were used to develop, validate, and test a model for user authentication. The model showed a very promising recognition rate of 96.67%. The model is further tested through a prototype, and it still gave a very satisfactory result.

The output of 3D volume segmentation is crucial to a wide range of endeavors. Producing accurate segmentations often proves to be both inefficient and challenging, in part due to lack of imaging data quality (contrast and resolution), and because of ambiguity in the data that can only be resolved with higher-level knowledge of the structure and the context wherein it resides. Automatic and semi-automatic approaches are improving, but in many cases still fail or require substantial manual clean-up or intervention. Expert manual segmentation and review is therefore still the gold standard for many applications. Unfortunately, existing tools (both custom-made and commercial) are often designed based on the underlying algorithm, not the best method for expressing higher-level intention. Our goal is to analyze manual (or semi-automatic) segmentation to gain a better understanding of both low-level (perceptual tasks and actions) and high-level decision making. This can be used to produce segmentation tools that are more accurate, efficient, and easier to use. Questioning or observation alone is insufficient to capture this information, so we utilize a hybrid capture protocol that blends observation, surveys, and eye tracking. We then developed, and validated, data coding schemes capable of discerning low-level actions and overall task structures.

Record linkage refers to the task of finding same entity across different databases. We propose a machine learning based record linkage algorithm for financial entity databases. Record linkage on financial databases are essential for information integration on certain financial entity, since those databases do not have common unified identifier. Our algorithm works in two steps to determine if a pair of record is same entity or not. First we check with proposed rules if the record pair can be exactly matched after cleaning the entity name and address. Second, inspired by earlier work on author name disambiguation, we train a binary Random Forest classifier to decide the linkage. To reduce and scale the computation, this process is done only for candidate pairs within a proposed heuristic. Initial evaluation for precision, recall and F1 measures on two different linking tasks in the Financial Entity Identification and Information Integration (FEIII) Challenge show promising results.

Maintaining a clean and hygienic civic environment is an indispensable yet formidable task, especially in developing countries. With the aim of engaging citizens to track and report on their neighborhoods, this paper presents a novel smartphone app, called SpotGarbage, which detects and coarsely segments garbage regions in a user-clicked geo-tagged image. The app utilizes the proposed deep architecture of fully convolutional networks for detecting garbage in images. The model has been trained on a newly introduced Garbage In Images (GINI) dataset, achieving a mean accuracy of 87.69%. The paper also proposes optimizations in the network architecture resulting in a reduction of 87.9% in memory usage and 96.8% in prediction time with no loss in accuracy, facilitating its usage in resource constrained smartphones.

Crowd simulation in visual effects and animation is a field where creativity is often bound by the scalability of its tools. High end animation systems like Autodesk Maya [Autodesk ] are tailored for scenes with at most tens of characters, whereas more scaleable VFX packages like SideFX's Houdini [SideFX] can lack the directability required by character animation. We present a suite of technologies built around Houdini that vastly improves both its scalability and directability for agent based crowd simulation. Dubbed MURE (Japanese for "crowd"), this system employs a new VEX context with lock-free, multithreaded KD-Tree construction/look-up, a procedural finite state machine for massive animation libraries, a suite of VEX nodes for fuzzy logic, and a fast GPU drawing plugin built upon the open source USD (Universal Scene Description) library [Pixar Animation Studios ]. MURE has proven its success on two feature films, The Good Dinosaur, and Finding Dory, with crowd spectacles including flocks of birds, swarms of fireflies, automobile traffic, and schools of fish. Pixar has a history with agent based crowd simulation using a custom Massive [Massive Software] based pipeline, first developed on Ratatouille [Ryu and Kanyuk 2007], and subsequently used on Wall-E, Up, and Cars 2. A re-write of the studio's proprietary animation software, Presto, deprecated this crowd pipeline. The crowds team on Brave and Monster's University replaced it with a new system for "non-simulated" crowds that sequenced geometry caches [Kanyuk et al. 2012] via finite state machines and sketch based tools [Arumugam et al. 2013]. However, the story reels for The Good Dinosaur called for large crowds with such complex inter-agent and environment interaction that simulated crowds were necessary. This creative need afforded Pixar's crowd team the opportunity of evaluate the pros and cons of our former agent based simulation pipeline and weigh which features would be part of its successor. Fuzzy logic brains and customizable navigation were indispensable, but our practice of approximating hero quality rigs with simulatable equivalents was fraught with problems. Creating the mappings was labor intensive, lossy, and even when mostly correct, animators found the synthesized animation splines so foreign that many would start from scratch rather than build upon a crowd simulation. The avoid this pitfall, we instead opted to start building our new pipeline around pre-cached clips of animation and thus always be able to deliver crowd animators clean splines. This reliance on caches also affords tremendous opportunities for interactivity at massive scales. Thus, rather than focusing on rigging/posing, the goals of our new system, MURE, became interactivity and directability.

We present new algorithms for Personalized PageRank estimation and Personalized PageRank search. First, for the problem of estimating Personalized PageRank (PPR) from a source distribution to a target node, we present a new bidirectional estimator with simple yet strong guarantees on correctness and performance, and 3x to 8x speedup over existing estimators in experiments on a diverse set of networks. Moreover, it has a clean algebraic structure which enables it to be used as a primitive for the Personalized PageRank Search problem: Given a network like Facebook, a query like "people named John," and a searching user, return the top nodes in the network ranked by PPR from the perspective of the searching user. Previous solutions either score all nodes or score candidate nodes one at a time, which is prohibitively slow for large candidate sets. We develop a new algorithm based on our bidirectional PPR estimator which identifies the most relevant results by sampling candidates based on their PPR; this is the first solution to PPR search that can find the best results without iterating through the set of all candidate results. Finally, by combining PPR sampling with sequential PPR estimation and Monte Carlo, we develop practical algorithms for PPR search, and we show via experiments that our algorithms are efficient on networks with billions of edges.

Hand gesture is becoming an increasingly popular means of interacting with consumer electronic devices, such as mobile phones, tablets and laptops. In this paper, we present AudioGest, a device-free gesture recognition system that can accurately sense the hand in-air movement around user's devices. Compared to the state-of-the-art, AudioGest is superior in using only one pair of built-in speaker and microphone, without any extra hardware or infrastructure support and with no training, to achieve fine-grained hand detection. Our system is able to accurately recognize various hand gestures, estimate the hand in-air time, as well as average moving speed and waving range. We achieve this by transforming the device into an active sonar system that transmits inaudible audio signal and decodes the echoes of hand at its microphone. We address various challenges including cleaning the noisy reflected sound signal, interpreting the echo spectrogram into hand gestures, decoding the Doppler frequency shifts into the hand waving speed and range, as well as being robust to the environmental motion and signal drifting. We implement the proof-of-concept prototype in three different electronic devices and extensively evaluate the system in four real-world scenarios using 3,900 hand gestures that collected by five users for more than two weeks. Our results show that AudioGest can detect six hand gestures with an accuracy up to 96%, and by distinguishing the gesture attributions, it can provide up to 162 control commands for various applications.

Due to explosive increase in teledensity, penetration of mobile networks in urban as well as rural areas, m-governance in India is growing from infancy to a more mature shape. Various steps are taken by Indian government for offering citizen services through mobile platform hence offering smooth transition from web based e-gov services to more pervasive mobile based services. Municipalities and Municipal corporations in India are already providing m-gov services like property and professional tax transaction, Birth and death registration, Marriage registration, due of taxes and charges etc. through SMS alerts or via call centers. To the best of our knowledge no municipality offers mobile based services in Solid Waste management sector. This paper proposes an m-gov service implemented as Android mobile application for SWM department, AMC, Ahmadabad. The application operates on real time data collected from a fully automated Solid waste Collection process integrated using RFID, GPS, GIS and GPRS proposed in the preceding work by the authors. The mobile application facilitates citizens to interactively view the status of the cleaning process of their area file complaints in the case of failure and also can follow up the status of their complaints which could be handled by SWM officials using the same application. This application also facilitates SWM officials to observe, analyze the real time status of the collection process and generated reports.

Since the emergence of emotional theories and models, which explain individuals feelings and their emotional processes, diverse research areas have shown interest in studying these ideas in order to obtain relevant information about behavior, habits and preferences of people. However, there are some limitations on emotion recognition that have forced specialists to search ways to achieve it on particular cases. This article treats collective emotions recognition case focusing on social networking sites applying a particular strategy, as follow: Firstly, state of art investigation regard emotions representation models in individual and collectives. In addition, possible solutions are provided by computing areas regarding collective emotions problems. Secondly, a collective emotion strategy was designed where it was retrieved a collection of data from Twitter, in which some cleaning and processing steps were applied, in order to keep the expression as purest. Afterward, the collective emotion tagging step arrived, whither based on consensus theory approach, the majority tagged-feelings were grouped and recognized as collective emotions. Finally, prediction step was executed and resided on modeling collective data, wherein one part was supplied into the Machine Learning during training and the other one was served to test the machine accuracy. Thirdly, An evaluation was set to check the fit of the collective recognition strategy, where results obtained allow to place the proposed work in the right path as consequence of minor differences observed, that indicate higher precision according to the distances measures used during the study development.

Fully automated vehicles will require new functionalities for perception, navigation and decision making -- an Autonomous Driving Intelligence (ADI). We consider architectural cases for such functionalities and investigate how they integrate with legacy platforms. The cases range from a robot replacing the driver -- with entire reuse of existing vehicle platforms, to a clean-slate design. Focusing on Heavy Commercial Vehicles (HCVs), we assess these cases from the perspectives of business, safety, dependability, verification, and realization. The original contributions of this paper are the classification of the architectural cases themselves and the analysis that follows. The analysis reveals that although full reuse of vehicle platforms is appealing, it will require explicitly dealing with the accidental complexity of the legacy platforms, including adding corresponding diagnostics and error handling to the ADI. The current fail-safe design of the platform will also tend to limit availability. Allowing changes to the platforms, will enable more optimized designs and fault-operational behaviour, but will require initial higher development cost and specific emphasis on partitioning and control to limit the influences of safety requirements. For all cases, the design and verification of the ADI will pose a grand challenge and relate to the evolution of the regulatory framework including safety standards.

Internet of Things(IoT) is the next big boom in the networking field. The vision of IoT is to connect daily used objects (which have the ability of sensing and actuation) to the Internet. This may or may or may not involve human. IoT field is still maturing and has many open issues. We build up on the security issues. As the devices have low computational power and low memory the existing security mechanisms (which are a necessity) should also be optimized accordingly or a clean slate approach needs to be followed. This is a survey paper to focus on the security aspects of IoT. We further also discuss the open challenges in this fie

Named Data Networking (NDN), a clean-slate data oriented Internet architecture targeting on replacing IP, brings many potential benefits for content distribution. Real deployment of NDN is crucial to verify this new architecture and promote academic research, but work in this field is at an early stage. Due to the fundamental design paradigm difference between NDN and IP, Deploying NDN as IP overlay causes high overhead and inefficient transmission, typically in streaming applications. Aiming at achieving efficient NDN streaming distribution, this paper proposes a transitional architecture of NDN/IP hybrid network dubbed Centaur, which embodies both NDN's smartness, scalability and IP's transmission efficiency and deployment feasibility. In Centaur, the upper NDN module acts as the smart head while the lower IP module functions as the powerful feet. The head is intelligent in content retrieval and self-control, while the IP feet are able to transport large amount of media data faster than that if NDN directly overlaying on IP. To evaluate the performance of our proposal, we implement a real streaming prototype in ndnSIM and compare it with both NDN-Hippo and P2P under various experiment scenarios. The result shows that Centaur can achieve better load balance with lower overhead, which is close to the performance that ideal NDN can achieve. All of these validate that our proposal is a promising choice for the incremental and compatible deployment of NDN.

This article describes our recent progress on the development of rigorous analytical metrics for assessing the threat-performance trade-off in control systems. Computing systems that monitor and control physical processes are now pervasive, yet their security is frequently an afterthought rather than a first-order design consideration. We investigate a rational basis for deciding—at the design level—how much investment should be made to secure the system.

The amount of personal information contributed by individuals to digital repositories such as social network sites has grown substantially. The existence of this data offers unprecedented opportunities for data analytics research in various domains of societal importance including medicine and public policy. The results of these analyses can be considered a public good which benefits data contributors as well as individuals who are not making their data available. At the same time, the release of personal information carries perceived and actual privacy risks to the contributors. Our research addresses this problem area. In our work, we study a game-theoretic model in which individuals take control over participation in data analytics projects in two ways: 1) individuals can contribute data at a self-chosen level of precision, and 2) individuals can decide whether they want to contribute at all (or not). From the analyst's perspective, we investigate to which degree the research analyst has flexibility to set requirements for data precision, so that individuals are still willing to contribute to the project, and the quality of the estimation improves. We study this tradeoffs scenario for populations of homogeneous and heterogeneous individuals, and determine Nash equilibrium that reflect the optimal level of participation and precision of contributions. We further prove that the analyst can substantially increase the accuracy of the analysis by imposing a lower bound on the precision of the data that users can reveal.

Vulnerabilities usually represents the risk level of software, and it is of high value to forecast vulnerabilities so as to evaluate the security level of software. Current researches mainly focus on predicting the number of vulnerabilities or the occurrence time of vulnerabilities, however, to our best knowledge, there are no other researches focusing on the prediction of vulnerabilities' severity, which we think is an important aspect reflecting vulnerabilities and software security. To compensate for this deficiency, we borrows the grey model GM(1,1) from grey system theory to forecast the severity of vulnerabilities. The experiment is carried on the real data collected from CVE and proves the feasibility of our predicting method.

The modern day approach in boulevard network centers on efficient factor in safe routing. The safe routing must follow up the low risk cities. The troubles in routing are a perennial one confronting people day in and day out. The common goal of everyone using a boulevard seems to be reaching the desired point through the fastest manner which involves the balancing conundrum of multiple expected and unexpected influencing factors such as time, distance, security and cost. It is universal knowledge that travelling is an almost inherent aspect in everyone's daily routine. With the gigantic and complex road network of a modern city or country, finding a low risk community for traversing the distance is not easy to achieve. This paper follows the code based community for detecting the boulevard network and fuzzy technique for identifying low risk community.

The use of multi-terminal HVDC to integrate wind power coming from the North Sea opens de door for a new transmission system model, the DC-Independent System Operator (DC-ISO). DC-ISO will face highly stressed and varying conditions that requires new risk assessment tools to ensure security of supply. This paper proposes a novel risk-based static security assessment methodology named risk-based DC security assessment (RB-DCSA). It combines a probabilistic approach to include uncertainties and a fuzzy inference system to quantify the systemic and individual component risk associated with operational scenarios considering uncertainties. The proposed methodology is illustrated using a multi-terminal HVDC system where the variability of wind speed at the offshore wind is included.

The integration of physical systems with distributed embedded computing and communication devices offers advantages on reliability, efficiency, and maintenance. At the same time, these embedded computers are susceptible to cyber-attacks that can harm the performance of the physical system, or even drive the system to an unsafe state; therefore, it is necessary to deploy security mechanisms that are able to automatically detect, isolate, and respond to potential attacks. Detection and isolation mechanisms have been widely studied for different types of attacks; however, automatic response to attacks has attracted considerably less attention. Our goal in this paper is to identify trends and recent results on how to respond and reconfigure a system under attack, and to identify limitations and open problems. We have found two main types of attack protection: i) preventive, which identifies the vulnerabilities in a control system and then increases its resiliency by modifying either control parameters or the redundancy of devices; ii) reactive, which responds as soon as the attack is detected (e.g., modifying the non-compromised controller actions).

Interface-confinement is a common mechanism that secures untrusted code by executing it inside a sandbox. The sandbox limits (confines) the code's interaction with key system resources to a restricted set of interfaces. This practice is seen in web browsers, hypervisors, and other security-critical systems. Motivated by these systems, we present a program logic, called System M, for modeling and proving safety properties of systems that execute adversary-supplied code via interface-confinement. In addition to using computation types to specify effects of computations, System M includes a novel invariant type to specify the properties of interface-confined code. The interpretation of invariant type includes terms whose effects satisfy an invariant. We construct a step-indexed model built over traces and prove the soundness of System M relative to the model. System M is the first program logic that allows proofs of safety for programs that execute adversary-supplied code without forcing the adversarial code to be available for deep static analysis. System M can be used to model and verify protocols as well as system designs. We demonstrate the reasoning principles of System M by verifying the state integrity property of the design of Memoir, a previously proposed trusted computing system.

Nowadays, a typical household owns multiple digital devices that can be connected to the Internet. Advertising companies always want to seamlessly reach consumers behind devices instead of the device itself. However, the identity of consumers becomes fragmented as they switch from one device to another. A naive attempt is to use deterministic features such as user name, telephone number and email address. However consumers might refrain from giving away their personal information because of privacy and security reasons. The challenge in ICDM2015 contest is to develop an accurate probabilistic model for predicting cross-device consumer identity without using the deterministic user information. In this paper we present an accurate and scalable cross-device solution using an ensemble of Gradient Boosting Decision Trees (GBDT) and Random Forest. Our final solution ranks 9th both on the public and private LB with F0.5 score of 0.855.

Pervasive Computing is one of the latest and more advanced paradigms currently available in the computers arena. Its ability to provide the distribution of computational services within environments where people live, work or socialize leads to make issues such as privacy, trust and identity more challenging compared to traditional computing environments. In this work we review these general issues and propose a Pervasive Computing architecture based on a simple but effective trust model that is better able to cope with them. The proposed architecture combines some Artificial Intelligence techniques to achieve close resemblance with human-like decision making. Accordingly, Apriori algorithm is first used in order to extract the behavioral patterns adopted from the users during their network interactions. Naïve Bayes classifier is then used for final decision making expressed in term of probability of user trustworthiness. To validate our approach we applied it to some typical ubiquitous computing scenarios. The obtained results demonstrated the usefulness of such approach and the competitiveness against other existing ones.

Language vector space models (VSMs) have recently proven to be effective across a variety of tasks. In VSMs, each word in a corpus is represented as a real-valued vector. These vectors can be used as features in many applications in machine learning and natural language processing. In this paper, we study the effect of vector space representations in cyber security. In particular, we consider a passive traffic analysis attack (Website Fingerprinting) that threatens users' navigation privacy on the web. By using anonymous communication, Internet users (such as online activists) may wish to hide the destination of web pages they access for different reasons such as avoiding tyrant governments. Traditional website fingerprinting studies collect packets from the users' network and extract features that are used by machine learning techniques to reveal the destination of certain web pages. In this work, we propose the packet to vector (P2V) approach where we model website fingerprinting attack using word vector representations. We show how the suggested model outperforms previous website fingerprinting works.

Privacy analysis is essential in the society. Data privacy preservation for access control, guaranteed service in wireless sensor networks are important parts. In programs' verification, we not only consider about these kinds of safety and liveness properties but some security policies like noninterference, and observational determinism which have been proposed as hyper properties. Fairness is widely applied in verification for concurrent systems, wireless sensor networks and embedded systems. This paper studies verification and analysis for proving security-relevant properties and hyper properties by proposing deductive proof rules under fairness requirements (constraints).

This paper proposes a fast and robust procedure for sensing and reconstruction of sparse or compressible magnetic resonance images based on the compressive sampling theory. The algorithm starts with incoherent undersampling of the k-space data of the image using a random matrix. The undersampled data is sparsified using Haar transformation. The Haar transform coefficients of the k-space data are then reconstructed using the orthogonal matching Pursuit algorithm. The reconstructed coefficients are inverse transformed into k-space data and then into the image in spatial domain. Finally, a median filter is used to suppress the recovery noise artifacts. Experimental results show that the proposed procedure greatly reduces the image data acquisition time without significantly reducing the image quality. The results also show that the error in the reconstructed image is reduced by median filtering.