Xiangfang Li - Academia.edu (original) (raw)

Papers by Xiangfang Li

Cancer Informatics, 2018

Effective cancer treatment strategy requires an understanding of cancer behavior and development ... more Effective cancer treatment strategy requires an understanding of cancer behavior and development across multiple temporal and spatial scales. This has resulted into a growing interest in developing multiscale mathematical models that can simulate cancer growth, development, and response to drug treatments. This study thus investigates multiscale tumor modeling that integrates drug pharmacokinetic and pharmacodynamic (PK/PD) information using stochastic hybrid system modeling framework. Specifically, (1) pathways modeled by differential equations are adopted for gene regulations at the molecular level; (2) cellular automata (CA) model is proposed for the cellular and multicellular scales. Markov chains are used to model the cell behaviors by taking into account the gene expression levels, cell cycle, and the microenvironment. The proposed model enables the prediction of tumor growth under given molecular properties, microenvironment conditions, and drug PK/PD profile. Simulation results demonstrate the effectiveness of the proposed approach and the results agree with observed tumor behaviors.

2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2016

Because cancer usually involves multiple genes and pathways, combination therapy is considered as... more Because cancer usually involves multiple genes and pathways, combination therapy is considered as a promising approach for cancer treatment. However, when multiple drugs are taken by a patient simultaneously, toxicity becomes a concern. A potential solution is to give the drugs sequentially rather than simultaneously. In this study, we try to explore the feasibility of such an approach. Specifically, this study investigates the response of genetic regulatory networks to sequential (switched) drug inputs. The switching mechanism is based on the combination of a state-dependent and time-driven switching function. The design of the switching strategy ensures that the genetic regulatory network will be stabilized and satisfies a decay rate performance index. Simulation results using a mTOR pathway model show the effectiveness of the proposed method.

2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, 2010

ABSTRACT In this paper, we propose to study the treatment and drug effects at the molecular level... more ABSTRACT In this paper, we propose to study the treatment and drug effects at the molecular level using a hybrid system model. Specifically, we propose a generic piecewise linear model to analyze drug effects on the state of the genes in a genetic regulatory network. We intend to answer the following question: given an initial state, would a treatment or drug (control input) drive the target gene to a new desired state that are not reachable without the treatment or drug? assuming that the concentration level of the drug remains constant. In other words, we try to identify whether there is a chance that the treatment or drug will be effective for changing gene expressions at all. We provide detailed analysis for two cases. In the first case, there is only one target gene; while in the second case, there is also another gene interacting with the target gene. The relationships between various parameters (of the genetic regulatory network and the design of the drug) and the convergence and the steady state of the controlled genes are derived analytically and discussed in detail. Simulations are performed using MATLAB/SIMULINK and the results confirmed our analytical findings.

2011 IEEE International Conference on Technologies for Homeland Security (HST), 2011

In many mission-critical applications such as military operations or disaster relief efforts, wir... more In many mission-critical applications such as military operations or disaster relief efforts, wireless networks employing dynamic spectrum access enabled by cognitive radio technology gain popularity due to their high spectrum efficiency and interoperability. However, the use of cognitive radio further complicates the security problems in wireless networks and introduces additional challenges. For instance, an attacker may mimic the behavior of a licensed primary user and disrupt the communication strategy of opportunistic spectrum usage of cognitive radio nodes, known as Primary User Emulation Attacks. Another example is a smart jammer, who can scan the spectrum and jam channels selectively. A common characteristic of the attacks in both examples is that they cause anomalous spectrum usage and disrupt the dynamic spectrum access, thus we termed them Anomalous Spectrum Usage Attacks in the context of cognitive radio wireless networks. Anomalous Spectrum Usage Attacks are extremely difficult to detect. In order to address these challenges, we propose a cross-layer framework for security enhancement and attack mitigation. In addition to physical layer sensing, we also take advantage of statistical analysis of the routing information of multiple paths collected by the routing module at the network layer. Inference of congested areas due to spectrum shortage can be made by information fusion and the results from the inference module will be compared to prior knowledge of the primary users, and the suspicious spectrum shortage will be subject to selective auditing, where a manager such as a cluster head will poll more detailed data from the cognitive nodes locating near the suspicious area for further analysis. We use a spectrum-aware split multipath routing as a baseline routing for performance evaluation. The effectiveness of the proposed scheme is demonstrated by extensive simulations.

Lecture Notes in Computer Science, 2006

ABSTRACT In this study, the joint power control and scheduling problem in a multihop TD/CDMA MANE... more ABSTRACT In this study, the joint power control and scheduling problem in a multihop TD/CDMA MANET is investigated. A cluster based architecture is adopted to provide scalability and centralized control within clusters, and the corresponding power control and scheduling schemes are derived to maximize a network utility function and guarantee the minimum rate required by each traffic session. Because the resulted optimal power control suggests that the scheduled nodes transmit with full power while other nodes remain silent, the joint power control and scheduling problem is reduced to a scheduling problem. Proportional fair scheduling is selected to achieve the balance between throughput and fairness. The multi-link version of the proportional fair scheduling algorithms for multihop MANET are proposed. In addition, a generic token counter mechanism is employed to satisfy the minimum rate requirements. Service differentiation is also achieved by ensuring different minimum rate for different traffic sessions. Approximation algorithms are suggested to reduce the computational complexity. In networks that are lack of centralized control, distributed scheduling algorithms are also derived and fully distributed implementation is provided. Simulation results demonstrate the effectiveness of the proposed schemes.

IEEE Access, 2020

Through machine learning, this paper changes the fundamental assumption of the traditional medium... more Through machine learning, this paper changes the fundamental assumption of the traditional medium access control (MAC) layer design. It obtains the capability of retrieving the information even the packets collide by training a deep neural network offline with the historical radio frequency (RF) traces and inferring the STAs involved collisions online in near-real-time. Specifically, we propose a MAC protocol based on intelligent spectrum learning for the future wireless local area networks (WLANs), called SL-MAC. In the proposed MAC, an access point (AP) is installed with a pre-trained convolutional neural network (CNN) model to identify the stations (STAs) involved in the collisions. In contrast to the conventional contention-based random medium access methods, e.g., IEEE 802.11 distributed coordination function (DCF), the proposed SL-MAC protocol seeks to schedule data transmissions from the STAs suffering from the collisions. To achieve this goal, we develop a two-step offline training algorithm enabling the AP to sense the spectrum with the aid of the CNN. In particular, on receiving the overlapped signal(s), the AP firstly predicts the number of STAs involving collisions and then further identifies the STAs' ID. Furthermore, we analyze the upper bound of throughput gain brought by the CNN predictor and investigate the impact of the inference error on the achieved throughput. Extensive simulations show the superiority of the proposed SL-MAC and allow us to gain insights on the trade-off between performance gain and the inference accuracy. INDEX TERMS Medium access control (MAC), spectrum sensing, deep learning, convolutional neural network (CNN).

IEEE Wireless Communications and Networking Conference, 2005

The application of multi-path techniques in wireless ad hoc networks is advantageous because mult... more The application of multi-path techniques in wireless ad hoc networks is advantageous because multi-path routing provides means to combat the effect of unreliable wireless links and constantly changing network topology. In this paper, the performance of multi-path routing under wormhole attack is studied in both cluster and uniform network topologies. Because multi-path routing is vulnerable to wormhole attacks, a scheme called Statistical Analysis of Multi-path (SAM) is proposed to detect such attacks and to identify malicious nodes. As the name suggests, SAM will detect wormhole attacks and identify attackers by statistically analyzing the information collected by multi-path routing. Neither additional security services or systems nor security enhancement of routing protocols is needed in the proposed scheme. Simulation results demonstrate that SAM successfully detects wormhole attacks and locates the malicious nodes in networks with cluster and uniform topologies and with different node transmission range.

19th IEEE International Parallel and Distributed Processing Symposium

Various routing attacks for single-path routing have been identified for wireless ad hoc networks... more Various routing attacks for single-path routing have been identified for wireless ad hoc networks and the corresponding counter measures have been proposed in the literature. However, the effects of routing attacks on multi-path routing have not been addressed. In this paper, the performance of multi-path routing under wormhole attack is studied in detail. The results show that multi-path routing is vulnerable to wormhole attacks. A simple scheme based on statistical analysis (called SAM) is proposed to detect such attacks and to identify malicious nodes. Comparing to the previous approaches (for example, using packet leash), no special requirements (such as time synchronization or GPS) are needed in the proposed scheme. Simulation results demonstrate that SAM successfully detects wormhole attacks and locates the malicious nodes in networks with different topologies and with different node transmission range. Moreover, SAM may act as a module in local detection agents in an intrusion detection system (IDS) for wireless ad hoc networks.

2006 40th Annual Conference on Information Sciences and Systems, 2006

Providing security and anonymity to users are critical in wireless ad hoc networks. In this paper... more Providing security and anonymity to users are critical in wireless ad hoc networks. In this paper, a secure anonymous routing scheme is proposed for clustered wireless ad hoc networks. In the proposed scheme, intra-cluster routing uses the common broadcast channel in wireless networks to provide anonymity, while inter-cluster routing uses a sequence of temporary public keys as the trapdoor information. Symmetric cipher is employed in most part of the proposed scheme to reduce computational complexity and maximize network efficiency. Public key is only used to distribute symmetric keys. Both privacy analysis (including sender anonymity, receiver anonymity and sender-receiver anonymity) and attack analysis show the effectiveness of the proposed scheme against a wide range of strong adversarial attacks.

2009 43rd Annual Conference on Information Sciences and Systems, 2009

In this paper, interference mitigation through downlink power control is considered for Macrocell... more In this paper, interference mitigation through downlink power control is considered for Macrocell Femtocell overlay. Specifically, the strong interference in the downlink from the home base station to a nearby macrocell user should be properly controlled such that the quality-of-service of both the macrocell user and the Femtocell users can be guaranteed. In this work, the fundamental capacity limitation of spatial spectrum sharing among a macrocell user and a Femtocell user is identified. A downlink power control problem is formulated to address the co-channel interference, as well as provide quality-of-service to both the macrocell user and the Femtocell users. The feasibility condition of the problem is derived and both centralized and distributed solutions are provided. Because the co-channel interference are from heterogeneous cells, a joint power control, channel management and admission control procedure is suggested such that the priority of the macrocell users is always ensured. Simulation results demonstrate the effectiveness of the proposed schemes.

2009 International Conference on E-Business and Information System Security, 2009

Providing security and privacy to users are critical in wireless mesh networks (WMNs). In this pa... more Providing security and privacy to users are critical in wireless mesh networks (WMNs). In this paper, a distributed security architecture is introduced to manage the mesh clients and a secure routing scheme that preserves the privacy of the end-users is proposed. In order to maximize routing efficiency, key indexing is used and symmetric cipher is employed in most part of the proposed scheme to reduce computational complexity. Both single-hop mesh client to mesh router and multi-hop mesh client to mesh client secure anonymous routing are proposed and discussed. Security and anonymity analysis are conducted followed by a complete performance analysis of the proposed protocol focusing on the route establish time and the routing overhead. The results show a reasonable overhead that linearly increases with the number of intermediate nodes. It is also demonstrated that the proposed schemes perform well against a broad range of attacks.

Journal of Network and Computer Applications, 2007

Various routing attacks for single-path routing have been identified for wireless ad hoc networks... more Various routing attacks for single-path routing have been identified for wireless ad hoc networks and the corresponding counter measures have been proposed in the literature. However, the effects of routing attacks on multi-path routing have not been addressed. In this paper, the performance of multi-path routing under wormhole attack is studied in detail. The results show that multi-path routing is vulnerable to wormhole attacks. A simple scheme based on statistical analysis of multi-path (called SAM) is proposed to detect such attacks and to identify malicious nodes. Comparing to the previous approaches (for example, using packet leash), no special requirements (such as time synchronization or GPS) are needed in the proposed scheme. Simulation results demonstrate that SAM successfully detects wormhole attacks and locates the malicious nodes in networks with different topologies and with different node transmission range. Moreover, SAM may act as a module in local detection agents in an intrusion detection system (IDS) for wireless ad hoc networks.

PLOS ONE, 2019

Specific entity terms such as disease, test, symptom, and genes in Electronic Medical Record (EMR... more Specific entity terms such as disease, test, symptom, and genes in Electronic Medical Record (EMR) can be extracted by Named Entity Recognition (NER). However, limited resources of labeled EMR pose a great challenge for mining medical entity terms. In this study, a novel multitask bi-directional RNN model combined with deep transfer learning is proposed as a potential solution of transferring knowledge and data augmentation to enhance NER performance with limited data. The proposed model has been evaluated using micro average F-score, macro average F-score and accuracy. It is observed that the proposed model outperforms the baseline model in the case of discharge datasets. For instance, for the case of discharge summary, the micro average F-score is improved by 2.55% and the overall accuracy is improved by 7.53%. For the case of progress notes, the micro average F-score and the overall accuracy are improved by 1.63% and 5.63%, respectively.

2016 IEEE 14th Intl Conf on Dependable, Autonomic and Secure Computing, 14th Intl Conf on Pervasive Intelligence and Computing, 2nd Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech), 2016

Dezert-Smarandache Theory (DSmT) of plausible and paradoxical reasoning has excellent performance... more Dezert-Smarandache Theory (DSmT) of plausible and paradoxical reasoning has excellent performance when the data contain uncertainty or conflicting. However, the methods developed in DSmT are in general very computationally expensive, thus they may not be directly applied to multiple data sources with high cardinality. In this paper, we explore the feasibility of using DSmT in practical applications through a case study. Specifically, we propose a DSm hybrid model with reduced number of classes and thus low computational cost to analyze temperature and humidity data received from multiple sensors to determine comfort zones in a smart building. Data from each sensor is considered as individual evidence that can be uncertain, imprecise and even conflicting. Several types of combination rules are applied to calculate the total mass function. Then the belief, plausibility and pignistic probability are deduced. They are used as metrics for decision making to determine comfort levels of the monitored environment. Both simulation and real data experiments demonstrate that the proposed method would make DSmT feasible for practical situation awareness applications.

Traditionally in sensor networks and recently in the Internet of Things, numerous heter... more Traditionally in sensor networks and recently in the Internet of Things, numerous heterogeneous sensors are deployed in distributed manner to monitor a phenomenon that often can be model by an underlying stochastic process. The big time-series data collected by the sensors must be analyzed to detect change in the stochastic process as quickly as possible with tolerable false alarm rate. However, sensors may have different accuracy and sensitivity range, and they decay along time. As a result, the big time-series data collected by the sensors will contain uncertainties and sometimes they are conflicting. In this study, we present a framework to take advantage of Evidence Theory (a.k.a. Dempster-Shafer and Dezert-Smarandache Theories) capabilities of representing and managing uncertainty and conflict to fast change detection and effectively deal with comple...

ArXiv, 2021

Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic in over 200 countries and terri... more Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic in over 200 countries and territories, which has resulted in a great public health concern across the international community. Analysis of X-ray imaging data can play a critical role in timely and accurate screening and fighting against COVID-19. Supervised deep learning has been successfully applied to recognize COVID-19 pathology from Xray imaging datasets. However, it requires a substantial amount of annotated X-ray images to train models, which is often not applicable to data analysis for emerging events such as COVID19 outbreak, especially in the early stage of the outbreak. To address this challenge, this paper proposes a two-path semisupervised deep learning model, ssResNet, based on Residual Neural Network (ResNet) for COVID-19 image classification, where two paths refer to a supervised path and an unsupervised path, respectively. Moreover, we design a weighted supervised loss that assigns higher weight for th...

Artificial neural networks (ANNs) based machine learning models and especially deep learning mode... more Artificial neural networks (ANNs) based machine learning models and especially deep learning models have been widely applied in computer vision, signal processing, wireless communications, and many other domains, where complex numbers occur either naturally or by design. However, most of the current implementations of ANNs and machine learning frameworks are using real numbers rather than complex numbers. There are growing interests in building ANNs using complex numbers, and exploring the potential advantages of the so called complex-valued neural networks (CVNNs) over their real-valued counterparts. In this paper, we discuss the recent development of CVNNs by performing a survey of the works on CVNNs in the literature. Specifically, detailed review of various CVNNs in terms of activation function, learning and optimization, input and output representations, and their applications in tasks such as signal processing and computer vision are provided, followed by a discussion on some ...

2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom), 2017

Despite the recent advancements in glycemic control for diabetic patients, the realization of an ... more Despite the recent advancements in glycemic control for diabetic patients, the realization of an automated closedloop artificial pancreas is still a challenge. The purpose of this research is to develop an integrated control system for in silico closed loop administration of insulin for Type 1 diabetic patients based on patients' medical record and real-time control-relevant data. The proposed system consists of a virtual patient model from the online AIDA diabetes simulator, a neural network predictor trained on patients' data for feedback purposes, and a Proportional-Integral Controller and data logging nodes. The virtual patient takes into account the delayed and time-varying insulin and carbohydrate absorption rate associated with the existing subcutaneous insulin delivery and complex glucose metabolism, respectively. The neural network predictor was trained using 23 features including semi-static and dynamic data, with built-in knowledge of all available past blood glucose levels. Then the controller calculates the infusion bolus to be delivered by the insulin pump. Extensive simulations are performed and it is shown that the neural network predictor has less Root-Mean-Square error than the currently used continuous glucose monitors, which takes measurement from the interstitial fluid. Simulation results also demonstrate that our proposed datadriven closed loop system for glycemic control can effectively regulate the blood glucose level of Type 1 diabetic patients without hypoglycemic excursions, and with no preset instruction on meal ingestion.

BMC Bioinformatics, 2018

Background: Electronic Medical Record (EMR) comprises patients' medical information gathered by m... more Background: Electronic Medical Record (EMR) comprises patients' medical information gathered by medical stuff for providing better health care. Named Entity Recognition (NER) is a sub-field of information extraction aimed at identifying specific entity terms such as disease, test, symptom, genes etc. NER can be a relief for healthcare providers and medical specialists to extract useful information automatically and avoid unnecessary and unrelated information in EMR. However, limited resources of available EMR pose a great challenge for mining entity terms. Therefore, a multitask bi-directional RNN model is proposed here as a potential solution of data augmentation to enhance NER performance with limited data. Methods: A multitask bi-directional RNN model is proposed for extracting entity terms from Chinese EMR. The proposed model can be divided into a shared layer and a task specific layer. Firstly, vector representation of each word is obtained as a concatenation of word embedding and character embedding. Then Bi-directional RNN is used to extract context information from sentence. After that, all these layers are shared by two different task layers, namely the parts-of-speech tagging task layer and the named entity recognition task layer. These two tasks layers are trained alternatively so that the knowledge learned from named entity recognition task can be enhanced by the knowledge gained from parts-of-speech tagging task. Results: The performance of our proposed model has been evaluated in terms of micro average F-score, macro average F-score and accuracy. It is observed that the proposed model outperforms the baseline model in all cases. For instance, experimental results conducted on the discharge summaries show that the micro average F-score and the macro average F-score are improved by 2.41% point and 4.16% point, respectively, and the overall accuracy is improved by 5.66% point. Conclusions: In this paper, a novel multitask bi-directional RNN model is proposed for improving the performance of named entity recognition in EMR. Evaluation results using real datasets demonstrate the effectiveness of the proposed model.

Cancer Informatics, 2018

2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2016

2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, 2010

2011 IEEE International Conference on Technologies for Homeland Security (HST), 2011

Lecture Notes in Computer Science, 2006

IEEE Access, 2020

IEEE Wireless Communications and Networking Conference, 2005

19th IEEE International Parallel and Distributed Processing Symposium

2006 40th Annual Conference on Information Sciences and Systems, 2006

2009 43rd Annual Conference on Information Sciences and Systems, 2009

2009 International Conference on E-Business and Information System Security, 2009

Journal of Network and Computer Applications, 2007

Various routing attacks for single-path routing have been identified for wireless ad hoc networks... more Various routing attacks for single-path routing have been identified for wireless ad hoc networks and the corresponding counter measures have been proposed in the literature. However, the effects of routing attacks on multi-path routing have not been addressed. In this paper, the performance of multi-path routing under wormhole attack is studied in detail. The results show that multi-path routing is vulnerable to wormhole attacks. A simple scheme based on statistical analysis of multi-path (called SAM) is proposed to detect such attacks and to identify malicious nodes. Comparing to the previous approaches (for example, using packet leash), no special requirements (such as time synchronization or GPS) are needed in the proposed scheme. Simulation results demonstrate that SAM successfully detects wormhole attacks and locates the malicious nodes in networks with different topologies and with different node transmission range. Moreover, SAM may act as a module in local detection agents in an intrusion detection system (IDS) for wireless ad hoc networks.

PLOS ONE, 2019

ArXiv, 2021

2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom), 2017

BMC Bioinformatics, 2018

Cancer Informatics, 2018