Guangzhi Qu

Oakland University · Department of Computer Science and Engineering

With the growing use of multi-core processors in the market, efficient and effective task parallelization strategies are on huge demand, so as the task scheduling algorithms. The scalability and efficiency of the existing algorithms on multi-core task scheduling needs to be improved. To schedule real-time tasks on a multi-core processor, any pair o...

Matrix factorization is a powerful method to implement collaborative filtering recommender systems. This paper addresses two major challenges, privacy and efficiency, which matrix factorization is facing. We based our work on DS-ADMM, a distributed matrix factorization algorithm with decent efficiency, to achieve the following two pieces of work: (...

Atmospheric visibility is an indicator of atmospheric transparency and its range directly reflects the quality of the atmospheric environment. With the acceleration of industrialization and urbanization, the natural environment has suffered some damages. In recent decades, the level of atmospheric visibility shows an overall downward trend. A decre...

With rapid industrial development, air pollution problems, especially in urban and metropolitan centers, have become a serious societal problem and require our immediate attention and comprehensive solutions to protect human and animal health and the environment. Because bad air quality brings prominent effects on our daily life, how to forecast fu...

Signature verification is essential to prevent the forgery of documents in financial, commercial, and legal settings. There are many researchers have focused on this topic, however, utilizing the 3-D information presented by a signature using a 3D optical profilometer is a relatively new idea, and the convolutional neural network is a powerful tool...

Triple‐negative breast cancer is the worst prognosis in breast cancer, accounting for 10.0–20.8% of all breast cancers. Considering that triple‐negative breast cancer has great heterogeneity and very poor prognosis, clinical medication guidance is in urgent need of a more detailed classification of breast cancer itself. Although many researchers ha...

A count-min sketch is a probabilistic data structure, which serves as a frequency table of events to process a stream of big data. It uses hash functions to map events to frequencies. Querying a count-min sketch returns the targeted event along with an estimated frequency, which is not less than the actual frequency. The estimated error, i.e., the...

Causal relationship mining of multi-dimensional meteorological time series data can reveal the potential connection between visibility and other influencing factors, and it is meaningful in terms of environmental management, air pollution chasing, and haze control. However, because causality analysis based on statistical methods or traditional mach...

Air pollution has become a substantial environmental issue in China, which has seriously affected human health. To clarify the relationship among air pollutants, pollution sources, influencing factors, evaluation indicators and harms, it is essential to build a domain ontology for air pollution. Domain ontologies have been gradually accepted as a m...

The latest implementation of the fully homomorphic encryption algorithm FHEW, FHEW-V2, takes about 0.12 seconds for a bootstrapping on a single-node computer. It seems much faster than the previous implementations. However, the 30-bit homomorphic addition requires 270 times of bootstrapping; plus those spent on key generation, the total elapsed tim...

Increasingly, more people are suffering from the effects of air pollution. This study took Beijing as an example and proposed an attention-based air quality predictor (AAQP) that could better protect people from air pollution. The AAQP is a seq2seq model, and it exploits historical air quality data and weather data to predict future air quality ind...

As a viable technology that supports ubiquitous, versatile, and cost-efficient IT solution for various applications, the wide adoption of the cloud computing is still hindered by the lack of online anomaly detection and poor accountability. Although cloud providers facilitate trusted computing with the support of hardware and software, to construct...

Word Embeddings are low-dimensional distributed representations that encompass a set of language modeling and feature learning techniques from Natural Language Processing (NLP). Words or phrases from the vocabulary are mapped to vectors of real numbers in a low-dimensional space. In previous work, we proposed using an Extreme Learning Machine (ELM)...

The unstructured nature of clinical narratives makes them complex for automatically extracting information. Feature learning is an important precursor to document classification, a sub-discipline of natural language processing (NLP). In NLP, word and document embeddings are an effective approach for generating word and document representations (vec...

Before deploying a recommender system, its performance must be measured and understood. So evaluation is an integral part of the process to design and implement recommender systems. In collaborative filtering, there are many metrics for evaluating recommender systems. Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are among the most im...

Multi-label classification has received more attention recently in the fields of data mining and machine learning. Though many approaches have been proposed, the critical issue of how to combine single labels to form a multi-label remains challenging. In this work, we propose a novel multi-label classification approach that each label is represente...

Matrix factorization has high computation complexity. It is unrealistic to directly adopt such techniques to online recommendation where users, items, and ratings grow constantly. Therefore, implementing an online version of recommendation based on incremental matrix factorization is a significant task. Though some results have been achieved in thi...

The existing edge routers can not assign the link capacities between User datagram protocol (UDP) subscribers and Transmission control protocol (TCP) subscribers to ensure the multiple priorities traffics with Differentiate-Serve (DiffServ). To solve the problem, a new DiffServ edge router with Controlled-UDP (C-UDP) is proposed. The proposed DiffS...

Multi-label classification problem has emerged rapidly from more and more domains as the popularity and complexity of data nature. In this work, we proposed a framework that can solve multi-label classification problems that either there exist constraints among labels or not. Under this framework, the multi-label classification problem can be model...

The North Atlantic right whale (Eubalaena glacialis) is an endangered species. These whales continuously suffer from deadly vessel impacts alongside the eastern coast of North America. There have been countless efforts to save the remaining 350 - 400 of them. One of the most prominent works is done by Marinexplore and Cornell University. A system o...

Although social-aware opportunistic networking paradigms are considered to have broad potential applications, so far very little is known about which nodes are more important in both sustaining the network topology and forwarding or disseminating messages. To address this issue, this paper redefines the concept of walk and extends traditional Katz...

According to the characteristics of high-speed railway, we propose a scheme of wireless communication access system based on distributed interference alignment. This system contains two sets of dual-antenna integrated access units inside the train. It can support four users accessing to the high-speed railway wireless access system simultaneously....

Electronic medical records provide us with an enormous amount of data with vast potential. If properly analyzed, medical data can be converted to knowledge that improves treatment, uncovers unexpected associations, and supports the personal experience of doctors and nurses, allowing them to make more informed decisions. Medical data is often genera...

Cognitive radio (CR) technology is considered to be an effective solution to allocate spectrum resources, whereas the primary users of a network do not fully utilize available frequency bands. Spectrum auction framework has been recognized as an effective way to achieve dynamic spectrum access. From the perspective of spectrum auction, multi-band m...

It is desirable to determine minimal effective initial local anesthetic bolus required to provide satisfactory analgesia following surgery. A way to predict potential adverse effects based on the type of anesthetic and initial bolus amount administered would be a significant contribution to presonalized medicine. In this work, we propose new method...

An Opportunistic Network (Oppnet) is an enhanced evolution of Mobile ad hoc network, where at any given time a route between source and destination does not exist, yet messages are routed opportunistically via intermediate contacts. We implemented two types of Oppnet deployments, an Open Oppnet and a Selective Oppnet, and analyzed both deployments...

kNN is a popular lazy-learning algorithm used for a wide variety of machine learning applications. One problem with this algorithm is the choice of k value. Different k values can have a large impact on the predictive accuracy of the algorithm, and picking a good value is generally unintuitive by looking at the data set. Cross-validation over multi...

The current state of the art approach to preventing falls of hospitalized elderly adults with dementia is to use a video surveillance setup in each of the hospital rooms and have hospital personnel continuously monitor the video feeds. In this research, we are developing a motion monitoring system to reduce the number of accidental falls among pati...

Flood models are primarily valuable to governments, civil engineers, aid organizations, insurance companies, research groups, and specific individuals. There are existing discrete event models and time step models for flooding that these groups use to generate static and dynamic flood inundation maps. When simulating the models to generate these ma...

Recently, research on complex network theory and applications draws a lot of attention in both academy and industry. In mobile ad hoc networks (MANETs) area of research, a critical issue is to design the most effective topology for given problems. It is natural and significant to consider complex networks topology when optimising the MANET topology...

Compared with single-label classification, multi-label classification is more general in practice, since it allows one instance to have more than one label simultaneously. Bayes' Theorem has been successfully applied to deal with single-label classification. In this paper, we proposed to tackle multi-label classification using Bayes' Theorem. We pr...

A VANET consists of vehicles equipped with on board units (OBUs) that can communicate with each other and the road side base stations. Due to the mobility and sparse distribution of vehicles, the delivery delay of messages in the VANET is mainly caused by the message transmissions between vehicles. The message delivery delay directly impacts the de...

Spectral clustering has been applied in various applications. But there still exist some important issues to be resolved, among which the two major ones are to (1) specify the scale parameter in calculating the similarity between data objects, and (2) select propoer eigenvectors to reduce data dimensionality. Though these topics have been studied e...

Neuropathic pain (NeuP) is often more difficult to treat than other types of chronic pain. The ability to predict outcomes in NeuP, such as response to specific therapies and return to work, would have tremendous value to both patients and society. In this work, we propose an adaptive clustering algorithm using the Neuropathic Pain Scale (NPS) to d...

Despite the explosive growth of internet usage, satisfying users' experience in web search while understanding the dynamic nature of search engine ranking remains a challenge. The main reason is that user queries and web documents may belong to different categories given a taxonomy of information. In this study, we attempt to detangle the ambiguity...

Recently there has been an increasing amount of research being done on the topic of swarm intelligence and modelling crowd behaviour. The reasons for this being that a variety of disciplines find simulations of swarm intelligence to be very useful. There is however one area in particular in which more research could be done, the modelling of crowds...

In this paper we proposed a cooperative MIMO cognitive network scheme. This scheme is composed of multiple source node users and multiple relay node users. Based on distributed interference alignment technology, the proposed scheme has broken the existing research on cooperative MIMO cognitive network of single source node user. Both encoding and d...

Rogue wireless access points (RWAPs) bypass physical endpoint security of local area networks and present significant security threats by creating network attack vectors behind firewalls, exposing confidential information, and allowing unauthorized utilization of network resources. A family of more promising methods detects RWAPs indirectly by iden...

Classical network fluid model and RED algorithm are based on TCP flows in internet network, and they have not considered the UDP flows' effects in network. However, in real work of the network, the network link capacity is shared by the hybrid traffics: TCP flows and UDP flows, and UDP flows can occupy the original link capacity of TCP flow. Since...

This paper reveals that the classical R-D imaging algorithm can not remove the strong noise and extract the objects in R-D imaging image by their range and azimuth matching filters. Though 2-D DCT-DWT or 2-D DFT-DWT can be a 2-D filtering for the issue, while the algorithms need huge computation amount, they can not process SAR image real time. To...

This paper focuses on how to differentiate wireless traffic from wired peer by using the temporal TCP characteristics of SYN, FIN, and ACK local round trip times (LRTT) found in all TCP sessions. With these session-based temporal characteristics, traffic from wireless and wired nodes can be differentiated by exploiting the fundamental differences b...

Mathematical analysis of current congestion control algorithms [1, 2] reveals that, as the delay-bandwidth product (BDP) increases, TCP becomes more oscillatory and prone to instability, regardless of the queuing scheme. To address this problem, a novel approach to Internet congestion control is developed recently. This new eXplicit Control Protoco...

The existing cognitive schemes have not considered cognitive spatial multiplexing (CSM) for MIMO-CDMA network, there are three vital problems to hinder CSM's application: spatial channels' estimation for mobile stations(MSs), space-time coding and decoding for base station (BS) and MSs, the implementation complexity of BS and MSs. To solve the prob...

Developments of wireless communication technology need higher standards of reliability of network and full utilization of resources. The proposition of Cognitive Network improves the utilization of frequency spectrum effectively. Main tasks of this paper are to introduce EDCA mechanism into the Cognitive Networks and validate if it can guarantee th...

The cognitive networks need the flexible utilization of the spectrum and bandwidths, without impacting the licensed Users(also called Primary Users, PU). While the cognitive radio network Media Access Control (MAC) layer is required not only to provide traditional services but also to perform an entirely new function for effective using the availab...

The existing cooperative spatial multiplexing (CSM) schemes for MIMO-CDMA network have four vital problems to hinder CSM's application: exact synchronization among the mobile stations(MSs) and base station (BS), spatial channels' estimation for MSs, space-time coding and decoding for BS and MSs, the implementation complexity of BS and MSs. To solve...

The existing controlled UDP schemes for personal terminal to personal terminal (P2P) at application layer are invalid for the congestions in transport layer since the controlled UDP traffics still block the TCP flows. Thus, it is difficult to achieve the congestion control for the TCP/UDP hybrid traffics network. To solve these problems, C-UDP prot...

The formal security policy model and security analysis is necessary to help Database Management System (DBMS) to attain a higher assurance level. In this paper we develop a formal security model for a DBMS enforcing multiple security policies including mandatory multilevel security policy, discretionary access control policy and role based access c...

Computing systems have steadily evolved into more complex, interconnected, heterogeneous entities. Ad-hoc techniques are most often used in designing them. Furthermore, researchers and designers from both academia and industry have focused on vertical approaches to emphasizing the advantages of one specific feature such as fault tolerance, security...

Classical Differentiated Service (DiffServ) routers have not considered the security problem in their designs, generally, they have no ability to countering Denial of Service (DoS ) attacks because of their simple system structures. DoS attacks against DiffServ clients are more targeted and require less attack bandwidth than current attacks for cla...

The existing cognitive network can not provide the spatial sectors for a cell, since the base-station (BS) has one omni-directional antenna. Thus it is impossible for a base-band channel to be shared by several mobile stations(MSs) with one omni-directional antenna. To solve the problem, this paper proposes the spatial multiplexing algorithms for t...

Different from the MAC of IEEE 802.11, the application of IEEE 802.22 suffers the uncertain spectrum and frequency width, which can not ensure the access of mobile users to be valid. To solve the problem, in this paper, we modify the CSMA/CA mechanism in order to make it suit the Cognitive Radio environments, in which the spectrum can be effectivel...

The formal security policy model and security analysis is necessary to help Database Management System (DBMS) to attain a higher assurance level. In this paper we develop a formal security model for a DBMS enforcing multiple security policies including mandatory multilevel security policy, discretionary access control policy and role based access c...

It is always desirable to improve the quality of a global classification model in the light of the existing models. In this work, the Bucket Learning methodology is first proposed to improve the model quality by enhancing its local patterns. We formally define the concept of a board as a tri-tuple 〈D,M,R〉, which unifies the data view, model view an...

The continuing employment of distributed embedded systems in various safety critical applications requires the demonstration of a high degrees of dependability. Fault-tolerance is the primary means to achieve dependability at runtime and has been an active research area for decades. In addition to traditional hardware and software redundancy, hybri...

Computing systems have steadily evolved into more complex, interconnected, heterogeneous entities. Ad-hoc techniques are most often used in designing them. Furthermore, researchers and designers from both academia and industry have focused on vertical approaches to emphasizing the advantages of one specific feature such as fault tolerance, security...

One of the major problems in network behavior analysis is to discover the underlying patterns from huge amount of network traffic data in order to identify anomalies from the norm. A great deal of work has been conducted through modeling the attribute-value network traffic data into different models. However, the abstract models generated by machin...

As the deployment of network-centric systems increases, network attacks are proportionally increasing in intensity as well as complexity. Attack detection techniques can be broadly classified as being signature-based, classification-based, or anomaly-based. In this paper we present a multi level intrusion detection system (ML-IDS) that uses autonom...

The proliferation of networked systems and services along with their exponential growth in complexity and size has increased the control and management complexity of such systems and services by several orders of magnitude. As a result, management tools have failed to cope with and handle the complexity, dynamism, and coordination among network att...

The Internet has grown exponentially over the last few years and has expanded commensurately in both scope and variety. In addition to the increasing number and dependence upon Internet resources and services, there are also increasing interconnectedness and interdependence among large and complex systems; a failure in one sector can easily affect...

With increasing faults and attacks on the Internet infrastructure, there is an impending need to provide automatic techniques to detect and mitigate the impact of attacks on network services. Denial-of-service attacks have been successful in denying legitimate traffic access to its required resources because existing routing protocols treat the att...

The quality of the data being analyzed is a critical factor that affects the accuracy of data mining algorithms. There are two important aspects of the data quality, one is relevance and the other is data redundancy. The inclusion of irrelevant and redundant features in the data mining model results in poor predictions and high computational overhe...

The Internet has been growing at an amazing rate and concurrent with the growth, the vulnerability of the Internet is also increasing. Though the Internet has been designed to withstand various forms of failure, the intrusion tools and attacks are becoming increasingly sophisticated, exposing the Internet to new threats. To make networked systems r...

Summary form only given. Detection and self-protection against viruses, worms, and network attacks is urgently needed to protect network systems and their applications from catastrophic failures. Once a network component is infected by viruses, worms, or became a target of network attacks, its operational state shifts from normal to abnormal state....

The objective of this research is to develop a theoretical framework and a general methodology for anomaly analysis and protection against network attacks to achieve (a) online monitoring, and analysis of network attacks; (b) automatically identifying critical vulnerable resources; and (c) proactive self-protection of network systems and their appl...

Internet has been growing at an amazing rate and it becomes pervasive in all aspects of our life. On the other hand, the ubiquity of networked computers and their services has significantly increased their vulnerability to virus and worm attacks. To make pervasive systems and their services reliable and secure it becomes highly essential to develop...

Internet has been growing at an amazing rate and it becomes pervasive in all aspects of our life. On the other hand, the ubiquity of networked computers and their services has significantly increased their vulnerability to virus and worm attacks. To make pervasive systems and their services reliable and secure it becomes highly essential to develop...

In this paper, we present an online monitoring and analysis framework to achieve self-protection against a wide range of network attacks. Our approach uses the software agents to online monitor several attributes to characterize the state of any network or computing resource as normal, uncertain, or abnormal. The software agents execute the appropr...

In this paper, we present an online monitoring and analysis framework to achieve self-protection against a wide range of network attacks. Our approach uses the software agents to online monitor several attributes to characterize the state of any network or computing resource as normal, uncertain, or abnormal. The software agents execute the appropr...