Faculty of Computer Science (Fredericton)

Pages

Communication-efficient privacy-preserving query for fog-enhanced Internet of Things
Communication-efficient privacy-preserving query for fog-enhanced Internet of Things
by Nafiseh Izadi Yekta, Internet of Things (IoT) has attracted significant attention in recent years and various IoT devices including industrial and utility components and other items embedded with electronics, sensors, and network connectivity already provide rich services to the end users. IoT devices report their data directly to the cloud computing constantly, which causes big data challenges in both storage and transmission. The classic centralized cloud computing paradigm is an ideal solution to deal with the storage issues. However, the cloud computing paradigm faces the challenges of low capacity, high latency, security and privacy and network failure. To address these challenges, the concept of the fog computing has been proposed by Cisco [8]. Instead of sending all the data to the cloud for processing and storing, fog computing provides local data processing capability and storage to fog devices. The goal of fog computing is to improve efficiency and reduce the amount of data transmitted to the cloud. Nevertheless, IoT still faces some security and privacy challenges. Query service is one of the standard services in IoT applications, It is when, an end user requests a value from an IoT device and the server is responsible for sending the value from the specific IoT device as per the query. In some IoT scenarios, privacy-preservation may be required for both the client and the service provider. Therefore, privacy preserving query schemes are desirable in some IoT applications. In this work, we proposed two privacy preserving query schemes with efficient communications. PQuery is characterized by combining private information retrieval and 1-out-of-m oblivious transfer techniques to preserve privacy for both the end user and the service provider in IoT query service. From the performance analysis, PQuery is very efficient in term of communication overheads, i.e., achieving O(n1/3) between the end user and the fog device. However, we also realize that the computational costs are not efficient in PQuery, especially the computational costs at the fog device. Therefore, in the second work, we tried to achieve a better balance between the communication and computational costs. We proposed XRQuery which is inspired by the XNOR gates in logical circuits to achieve privacy preservation for both the service provider and user in an IoT query service. While XRQuery is highly efficient in terms of communication cost, i.e., achieving O(log n) between the end user and the fog device, extensive performance evaluations show that it is much faster than PQuery in all three stages (end user query, fog device response and end user result checking).
Concurrent task execution on the Intel Xeon Phi
Concurrent task execution on the Intel Xeon Phi
by Yucheng Zhu, The Intel Xeon Phi coprocessor is a new choice for the high performance computing industry and it needs to be tested. In this thesis, we compared the difference in performance between the Xeon Phi and the GPU. The Smith-Waterman algorithm is a widely used algorithm for solving the sequence alignment problem. We implemented two versions of parallel SmithWaterman algorithm for the Xeon Phi and GPU. Inspired by CUDA stream which enables concurrent kernel execution on Nvidia’s GPUs, we propose a socket based mechanism to enable concurrent task execution on the Xeon Phi. We then compared our socket implementation with Intel’s offload mode and with an Nvidia GPU. The results showed that our socket implementation performs better than the offload mode but is still not as good as the GPU., M.C.S. University of New Brunswick, Faculty of Computer Science, 2015.
Contextualized embeddings encode knowledge of English verb-noun combination idiomaticity
Contextualized embeddings encode knowledge of English verb-noun combination idiomaticity
by Samin Fakharian, English verb-noun combinations (VNCs) consist of a verb with a noun in its direct object position, and can be used as idioms or as literal combinations (e.g., hit the road). As VNCs are commonly used in language and their meaning is often not predictable, they are an essential topic of research for NLP. In this study, we propose a supervised approach to distinguish idiomatic and literal usages of VNCs in a text based on contextualized representations, specifically BERT and RoBERTa. We show that this model using contextualized embeddings outperforms previous approaches, including the case that the model is tested on instances of VNC types that were not observed during training. We further consider the incorporation of linguistic knowledge of lexico-syntactic fixedness of VNCs into our model. Our findings indicate that contextualized embeddings capture this information., Electronic Only.
Conversation-based P2P botnet detection with decision fusion
Conversation-based P2P botnet detection with decision fusion
by Shaojun Zhang, Botnets have been identified as one of the most dangerous threats through the Internet. A botnet is a collection of compromised computers called zombies or bots controlled by malicious machines called botmasters through the command and control (C&C) channel. Botnets can be used for plenty of malicious behaviours, including DDOS, Spam, stealing sensitive information to name a few, all of which could be very serious threats to parts of the Internet. In this thesis, we propose a peer-to-peer (P2P) botnet detection approach based on 30-second conversation. To the best of our knowledge, this is the first time conversation-based features are used to detect P2P botnets. The features extracted from conversations can differentiate P2P botnet conversations from normal conversations by applying machine learning techniques. Also, feature selection processes are carried out in order to reduce the dimension of the feature vectors. Decision tree (DT) and support vector machine (SVM) are applied to classify the normal conversations and the P2P botnet conversations. Finally, the results from different classifiers are combined based on the probability models in order to get a better result., Electronic Only (UNB thesis number) Thesis 9143 (OCoLC) 960860070, M.C.S., University of New Brunswick, Faculty of Computer Science, 2013.
Core task assistance in video games
Core task assistance in video games
by Jawad Jandali Refai, Video games can be challenging, which is part of what makes games stimulating and entertaining. However, if they are too challenging, the player may find it frustrating. Game designers may balance their game by providing players with assistance. Previous work explores the effectiveness of potential assistance techniques within a particular genre and platform. Complex games could require several types of assistance to support a wide variety of gameplay mechanics. Designers would need to gather information from scattered sources to make informed decisions to apply optimal assistance. In this thesis, we propose a generalized framework for assistance in games, irrespective of genre or target platform. We achieve this by discussing techniques targeted at the 10 fundamental core tasks in video games that are the base of any game mechanic, such as Aiming, Reaction Time, and Visual Search. We also explore the best practices for choosing, interpreting, and implementing one of the 35 assistance techniques.
Correlation between computer recognized facial emotions and informed emotions during a casino computer game
Correlation between computer recognized facial emotions and informed emotions during a casino computer game
by Nils Reichert, Emotions play an important role for everyday communication. Different methods allow computers to recognize emotions. Most are trained with acted emotions and it is unknown if such a model would work for recognizing naturally appearing emotions. An experiment was setup to estimate the recognition accuracy of the emotion recognition software SHORE, which could detect the emotions angry, happy, sad, and surprised. Subjects played a casino game while being recorded. The software recognition was correlated with the recognition of ten human observers. The results showed a strong recognition for happy, medium recognition for surprised, and a weak recognition for sad and angry faces. In addition, questionnaires containing self-informed emotions were compared with the computer recognition, but only weak correlations were found. SHORE was able to recognize emotions almost as well as humans were, but if humans had problems to recognize an emotion, then the accuracy of the software was much lower.
Cryptanalysis of a knapsack cryptosystem
Cryptanalysis of a knapsack cryptosystem
by Ruqey Alhassawi, Knapsack cryptosystems are classified as public key cryptosystems. This kind of cryptosystem uses two different keys for the encryption and decryption process. This feature offers strong security for these cryptosystems because the decryption key cannot be derived from the encryption key. Since the Merkle-Hellman knapsack cryptosystem, the first proposed version of knapsack cryptosystems, many knapsack cryptosystems have been suggested. Unfortunately, most knapsack cryptosystems that have been introduced so far are not secure against cryptanalysis attacks. These cryptanalytic attacks find weaknesses in the designs of the knapsack cipher. There are two cryptanalysis systems mentioned in this thesis. These are the Shamir Merkle-Hellman knapsack attack and the Basis Reduction Algorithm (called the LLL algorithm). Accordingly, the main goal of this thesis is to implement Visual Basic programs with these two knapsack cryptanalytic attacks. These Visual Basic programs are for testing many versions of knapsack cryptosystems including a newly invented knapsack system. The result of the testing shows that the knapsack cryptosystems are indeed weak, especially against the Reduced Basis Algorithm. This result does not appear to hold for all cases such as the new knapsack system suggested and the Super-Pascal knapsack cryptosystem., Electronic Only. (UNB thesis number) Thesis 9191 (OCoLC) 960905126, M.C.S., University of New Brunswick, Faculty of Computer Science, 2013.
Current security trends and assessment of cyber threats
Current security trends and assessment of cyber threats
by Bijiteshwar Rudra Aayush, Continuous functioning of critical infrastructure is one of the foundations for the socio economic activities and development of a country. Owing to the continuous development in technologies, computers, other computing services, software and cyber space are used for interconnection, information processing and communication. The development in technology and the use of cyber space have created new threats and vulnerabilities which could pose at least as significant a threat as a physical attack. Lately cyber criminals and terrorists are using their skills to exploit cyber space and they are committing severe crimes. The objectives of this Masters report are to explain the role of cyber space and computing technologies on critical infrastructure and highlight several cyber threats and countermeasures. This report also highlights the need of secure software development and explains how an average programmer can contribute in securing cyber space and what effect that can have on national infrastructure., A Report Submitted in Partial Fulfillment of the Requirements for the Degree of Master of Computer Science in the Graduate Academic Unit of Computer Science. Electronic Only., M.C.S. University of New Brunswick, Faculty of Computer Science, 2015.
Deep belief networks for sentiment analysis
Deep belief networks for sentiment analysis
by Yong Jin, Sentiment analysis is a highly popular issue both in academic and engineering fields. Nowadays there is an increasingly large amount of online opinion resources, so people are inclined to develop some systems that can automatically determine the polarities of opinions, especially in the decision-making process of a company. On the other hand, deep learning is a recently developed popular topic and has received much attention in machine learning area. Deep belief network (DBN) is one important deep learning model, which has proved powerful in many domains including natural language processing. However, there still exist some big challenges for DBNs in sentiment analysis because of the complexity to express opinions. Therefore, this study tries to improve DBNs in sentiment analysis area from the following three aspects: (1) The neuron models are investigated in DBNs for sentiment prediction. We perform various experiments and apply both total accuracy and F-measure to evaluate the performance, which proves that Gaussian neuron model with specific parameter setting has better efiect. (2) In addition to the traditional bag-of-words representation for each sentence, the word positional information is considered in the input. We propose a new word positional contribution form and another novel word-to-segment matrix representation for text to incorporate the positional information into DBNs for sentiment analysis. Finally, we evaluate the performance via the total accuracy. The results show that the word positional information of sentences helps to improve the performance of DBNs for sentiment classification. (3) We propose a new method to improve the DBN learning algorithm based on the unsupervised training phase of restricted Boltzmann machines (RBMs). That is, the RBM generates the hidden layer in an unsupervised fashion, and then we use this hidden layer as the output of a single-layer neural network, which is trained via the delta rule (DR). The new weights trained from DR are then transmitted into the whole network for initialization of back propagation (BP). This way keeps more correction signal for each layer in the BP algorithm compared to the ordinary DBN training. Our experimental results demonstrate that this updated learning method performs better than the ordinary learning for sentiment classification., Ph.D. University of New Brunswick, Faculty of Computer Science, 2017.
Design and implementation of a distributed rule-based query system supporting conference organization
Design and implementation of a distributed rule-based query system supporting conference organization
by Chaudhry Usman Ali, Conference organization involves a multitude of procedures consuming much time and effort of their Organization Committees ( OCs). Conference organization systems attempt to alleviate the burden of repetitive tasks through the (partial) automation of organizational processes. This thesis is focused on the design and implementation of automated query answering about a conference, retrieving and deriving QC-related information for use by (other) OC members, (candidate) PC members, (prospective) authors, as well as (potential) partners, sponsors, and participants. The Rule Responder framework is instantiated to a distributed rule-based system relieving OC members from answering such routine requests. Each team of co-chairs from the symposium's OC is supported by a Personal Agent (PA) that uses a local knowledge base containing co-chair facts and rules to answer queries for which the co-chairs are responsible. The External Agent (EA) acts as a single point of entry for users to interact with the system employing a Web form coupled to an HTTP port to which post and get requests are sent. The system has three Organizational Agents ( OAs), where one Super-Organizational Agent (Super-OA) acts as a dispatching manager to direct requests sent by a user via the EA to one of the two Sub-Organizational Agents (Sub-OAs): The “Event” Sub-OA deals with queries about the (‘temporary’) conference edition while the “Structure” Sub-OA handles queries about the (‘permanent’) institution holding the conference series. These Sub-OAs further delegate the requests to underlying PAs representing local knowledge of, respectively, the conference's (temporary) OC co-chairs and the institution's (permanent) subgroup co-chairs. The designed query-answering architecture has been implemented, evaluated, and deployed in the SymposiumPlanner-2012 use case supporting the RuleML-2012 Symposium. General design principles and implementation techniques for future conference planners are distilled from the lessons learnt from this use case., Scanned from archival print submission., M.C.S. University of New Brunswick, Faculty of Computer Science, 2013.
Design and implementation of peer collaboration service framework on cloud
Design and implementation of peer collaboration service framework on cloud
by Dong Dong, Most of the key tasks or work in today's business are strongly related to collaboration. One of the important reasons that people collaborate is to complete a task which is hard to be done by individuals independently. With the prevalence of the Internet and mobile devices accessing the Internet with high-bandwidth network, it is easier for people in different locations to form groups anywhere and anytime. However, there are few methods to manage these dynamic web based collaborations. This thesis describes implementation of a framework named \Peer Collaboration Service Framework" providing a systematic approach to create and manage network based dynamic peer collaborations. The framework consists of three layers: (1) collaboration as a service layer, consisting of services to generate peer collaborations; (2) collaboration service layer, consisting of services running at the back end of collaborations to support them; (3) collaboration instance layer, supporting the generated collaboration application instances used by participants. This framework is implemented on Amazon EC2 cloud computing platform and employs several other web services offered by Amazon. A case study on collaborative software testing applications and experiments are also presented in the thesis., Electronic Only. (UNB thesis number) Thesis 9199. (OCoLC) 960908841, M.C.S., University of New Brunswick, Faculty of Computer Science, 2013.

Pages

Zircon - This is a contributing Drupal Theme
Design by WeebPal.