Rajarathnam Chandramouli

Stevens Institute of Technology · Department of Electrical & Computer Engineering

We propose a deep learning architecture and test three other machine learning models to automatically detect individuals that will attempt suicide within (1) 30 days and (2) six months, using their social media post data provided in the CLPsych 2021 shared task. Additionally, we create and extract three sets of handcrafted features for suicide risk...

We propose a deep learning architecture and test three other machine learning models to automatically detect individuals that will attempt suicide within (1) 30 days and (2) six months, using their social media post data provided in the CLPsych 2021 shared task. Additionally, we create and extract three sets of handcrafted features for suicide risk...

Alzheimer's disease (AD)-related global healthcare cost is estimated to be $1 trillion by 2050. Currently, there is no cure for this disease; however, clinical studies show that early diagnosis and intervention helps to extend the quality of life and inform technologies for personalized mental healthcare. Clinical research indicates that the onset...

By understanding different musical performative formats, communication of codified tonal expression is compared between performance on the Mridangam and in Tap Dance. Although recorded materials were included in the conference presentation, sound files could not be uploaded to Research Gate.

This paper presents a joint spectrum and energy efficiency maximization mechanism for device to device (D2D) communication enabled wireless networks. Most approaches in the literature, fail to take into account link heterogeneity in terms of their demands and the traffic they inject into the network. This paper presents a linear optimization formul...

This paper presents a statistical steganalysis framework to attack quantization index modulation (QIM) based steganography. The quantization process is generally modeled as an additive noise channel. The proposed method exploits the fact that plain-quantization (quantization without message embedding) decreases local-randomness (or increases local-...

This paper provides a detailed analysis to identify factors that improve bacterial targeting times to tumor microenvironments. We utilize the “active flagellar” motion characteristic of the bacterial movement to present a continuous time Markov model and a first passage time analysis to determine the factors that affect the mean time taken for inje...

This chapter studies the network layer effects of denial of service (DoS) in 5G wireless networks. DoS attacks by malicious nodes have mostly been researched in terms of their effect on the physical layer (i.e., loss of wireless connectivity) for the good nodes or in terms of loss of services for the good nodes. However, one vital consequence of Do...

We present Software Defined Access (SDA) an architecture for HetNets. It incorporates various elements of Software Defined Networking (SDN) and Software Defined Wireless Networking (SDWN). SDA introduces novel logical control path across radio interfaces and up to mobile devices. This control path allows SDA to regulate and configure data path via...

This paper incorporates the idea of micro-financing into bandwidth allocation in wireless networks. Resource allocation in heterogeneous wireless networks has been widely studied from the perspective of maximizing the system utilization or maximizing the carried traffic in the network. However, measurements show that the distribution of signal stre...

Visualizing large and complex biochemical processes is both computationally challenging as well as visually intangible, due to the sheer number and volume of individual interactions. Effective visualization of complex biochemical processes and the overall behavioral patterns of various biological systems pivots on sifting out influential and salien...

Internet users can be classified as two types: (a) active users—actively contribute to blogs, publish opinions, write comments in Youtube, tweet messages, etc. and (b) passive consumers who only consume Internet information without contributing to it. While the majority of current social media research deals with active user analysis, there is very...

This paper combines data and mathematical mod-eling to present evidence for several dynamic hierarchical structures in Twitterverse. A model is presented to formalize the hierarchical connections between the number of tweets, population of cities, areas of cities, etc. The parameters of the model reveal several insights, such as, a topic has a broa...

Free software tool developed by our research group for deception detection from text. Analyze emails, tweets, SMS, reviews, etc.

We address a unique security vulnerability due to spectrum fragmentation, aggregation and bonding in IEEE 802.22 based dynamic spectrum access (DSA) networks and in LTE and HSPA+ networks. Typically, channel fragmentation, aggregation/bonding have been perceived as a means to enhance the bandwidth and throughput for the users. However, this could a...

Distributed spectrum sharing via congestion advertisement is modelled and studied as a game theoretic problem. A related graphical anti-coordination game problem and a suitable logit-response learning mechanism is proposed and studied. It has been shown that introducing an arbitrary small congestion advertisement term into the users utility can imp...

In this paper, we investigate the joint spectrum sensing and resource allocation problem to maximize throughput capacity of an OFDM-based cognitive radio link with a cognitive relay. By applying a cognitive relay that uses decode and forward (D&F), we achieve more reliable communications, generating less interference (by needing less transmit power...

We study the effect of pricing on the secrecy capacity of multi-terminal networks. We propose a linear and a non-linear pricing function for user terminals and present mathematical formulations to maximize the individual secrecy capacity of each transmitter-receiver pair as well as the sum secrecy capacity of the system. We show that these pricing...

In this paper, we present SpiderRadio, a software defined cognitive radio (CR) prototype for dynamic spectrum access (DSA) networking. The medium access control (MAC) layer of SpiderRadio is implemented in software on top of commodity IEEE 802.11a/b/g hardware. However, the proposed architecture and implementation are applicable to other spectrum b...

In wireless communication systems users compete for communication opportunities through a medium access control protocol. Previous research has shown that selfish behavior in medium access games could lead to inefficient and unfair resource allocation. We introduce a new notion of reciprocity in a medium access game and derive the corresponding Fai...

Information consumers in online social networks receive information from multiple information providers, which results in confusion. The amount of confusion depends on three main factors-(a) attributes of the source, (b) characteristics of the consumer and (c) trust relation between the information provider and the consumer. While information confu...

Altruism in social networks was traditionally considered based on user relationships and requirements. The capability of a user to help has seldom been taken into account while studying altruism. Also, to the best of our knowledge, no quantitative analysis has been made to determine the benefits of altruism. Here we quantitatively study the amount...

We present a distributed opportunistic channel ac-quisition mechanism in dynamic spectrum access (DSA) net-works. A novel graph-multicoloring algorithm is proposed for secondary networks, in which, each network makes use only of the local topology information (i.e., information about it-self and its one-hop neighbors) to resolve contentions during...

This paper proposes an active steganalysis method for quantization index modulation (QIM)-based steganography. The proposed nonparametric steganalysis method uses irregularity (or randomness) in the test image to distinguish between the cover image and the stego image. We have shown that plain quantization (quantization without message embedding) i...

Increasingly, researchers are mining social media as a way of inferring public sentiment from the Internet. While ways to measure social media participation are beginning to be well established, there are little ways to measure the silent voice of a passive consumer. Passive consumers refrain from actively offering opinions, and as such cannot be c...

In this paper we systematically study several channel assignment problems in multi-hop ad-hoc wireless networks in the presence of several constraints. Both regular grids and random topology models are considered in the analysis. We identify three fairness constraints (unfair, fair, and 1-fair), Signal to Interference Ratio (SINR) constraint (to me...

IP geolocation plays a critical role in location-aware network services and network security applications. Commercially deployed IP geolocation databases may provide outdated or incorrect location of Internet hosts due to slow record updates and dynamic IP address assignment by the ISPs. Measurement-based IP geolocation is used to provide real time...

We present a game theoretic power control of overlay/overt communications to maximize the goodput (effective throughput of error-free bits) of multi-terminal covert timing channels. Most approaches in the literature on covert timing channels discuss capacities of the timing channels but do not study how the overlay communication can be controlled t...

Secondary users sharing primary users' spectrum is modeled as a graphical game. Users located in random graphs and a regular lattice are considered. Secondary users are assumed to differentiate the ``quality" of the primary spectrum while interacting within their local neighborhood to minimize interference and congestion. The learning algorithm is...

We address a unique security vulnerability in long term evolution (LTE) advanced and high speed packet access (HSPA+) wireless networks due to carrier/channel bonding. This vulnerability is shown to result in various amounts of service disruption based on the radio network parameters and the user locations. Typically, channel bonding have been perc...

Over the last couple of decades, the trends in network protocols and the layering principles have witnessed deviations from the standard 7-layer OSI model or the 5-layer TCP/IP model. These deviations were necessary to improve network performance, in terms of service quality offered to the increasing numbers in users and their demands and coping wi...

We estimate the missing round trip time (RTT) measurements in computer networks using doubly non-negative (DN) matrix completion and compressed sensing. The major contributions of this paper are the following: (i) an iterative DN matrix completion that minimizes the mean square estimation error; (ii) mathematical conditions for the convergence of t...

It is easy to hide the true identity of the author of an email. The author’s actual name, email address, etc. can be changed arbitrarily to deceive an email receiver. For example, a sender can change his/her identity in the email header to send different emails to various recipients. Therefore, in this paper, we investigate techniques for authorshi...

Deception detection in e-mails is addressed in this paper. An adaptive probabilistic context modeling method that spans information theory and suffix trees is proposed. Some properties of the proposed adaptive context model are also discussed. Experimental results on truthful (ham) and deceptive (scam) e-mail data sets are presented to evaluate the...

We address a unique security threat that arises due to channel fragmentation (or aggregation or bonding) in dynamic spectrum access (DSA) based IEEE 802.22 networks. Typically, channel fragmentation, aggregation and bonding have been studied in the literature as a means to enhance the spectrum utilization. However, the loss of orthogonality between...

Text is still the most prevalent Internet media type. Examples of this include popular social networking applications such as Twitter, Craigslist, Facebook, etc. Other web applications such as e-mail, blog, chat rooms, etc. are also mostly text based. A question we address in this paper that deals with text based Internet forensics is the following...

We study the dynamics of social networks in terms of population growth and control of user behavior. Most of the current research in social networks focus on static analysis through graph theoretic models to represent the networks or focus on modeling the traffic. Here, we study the cost of collaborative vs individualistic behavior of users in orde...

In this article we present SpiderRadio, a cognitive radio prototype for dynamic spectrum access networking. SpiderRadio is built using commodity IEEE 802.11a/b/g hardware and the open source MadWiFi driver. This helps us in developing and testing our prototype without having to buy and manage several licensed spectrum bands. We begin with a discuss...

Traditional cyber threats or attacks have targeted information and communication infrastructure that usually result in economic loss. Typically, launching these attacks requires an advanced skill level. Governments around the world have a good understanding of these threats and therefore have put in place many policies to deal with them. The rapid...

We study the temporal behavior of messages arriving in a social network. We specifically study the tweets and re-tweets sent to president Barack Obama on Twitter. We characterize the inter-arrival times between the tweets, the number of re-tweets and the spatial coordinates (latitude, longitude) of the users who sent the tweets. The modeling of the...

This chapter discusses a specific class of denial - of - service (DoS) attacks in cognitive radio networks known as the primary user emulation (PUE) attack. It also focus on the issue of self-coexistence among multiple good overlapping and competing cognitive radio (CR) networks in a geographical region. The chapter discusses the approaches to inve...

Spectrum sensing is one of the critical features in cognitive radio based dynamic spectrum access networking. In this paper, we discuss a new spectrum sensing technique for primary incumbent detection. The proposed method is based on observing the PHY errors, received signal strength and n-moving window averaging of the observed measurement. The se...

Efficient routing is a fundamental issue in multi-hop wireless ad hoc networks. In this paper, we study the limitation of traditional routing structure in multi-hop wireless ad hoc networks due to (a) the layered structure of a wireless protocol stack and (b) the lack of coordination between medium access control (MAC) and routing protocols. These...

We discuss malicious interference based denial of service (DoS) attacks in multi-band covert timing networks using an adversarial game theoretic approach. A covert timing network operating on a set of multiple spectrum bands is considered. Each band has an associated utility which represents the critical nature of the covert data transmitted in the...

We study the optimum location of an eavesdropper from a secrecy capacity perspective in multi-terminal networks with power control. We determine the logical location of an eavesdropper which a) results in zero secrecy capacity for maximum number of users in the network and b) results in zero secrecy capacity for the bottle-neck links. We then analy...

In this paper, we present a network flow based approach for dynamic network and channel selection for secondary users in dynamic spectrum access networks. Most approaches in the current literature on dynamic spectrum access networks do not consider dynamic network and channel selection. We present a network flow framework for network selection. We...

Spectrum crowding, spectrum management, quality of service, and user support are the topics of vigorous research in the cognitive and dynamic spectrum access network communities. As research matures, standardization provides a bridge between research results, implementation, and widespread deployment of such networks. This article reports recent de...

In this paper, we study tactical covert timing networks with dynamic spectrum access ca-pability amidst adversaries. We present a two-tier game framework to model the attack-defense scenario. There are very few studies available in the literature on covert timing channels with multiple parallel transmissions. This paper presents a new paradigm com-...

In this paper, we present the research of a foreign currency investment framework involving the prediction of the foreign currency exchange rates and the portfolio optimization under certain constrains. We adopt two machine learning methods, support vector machines (SVMs) and neural networks (NNs), as well as the traditional moving average method,...

In this paper, we investigate the topic of gender identification for short length, multi-genre, content-free e-mails. We introduce for the first time (to our knowledge), psycholinguistic and gender-linked cues for this problem, along with traditional stylometric features. Decision tree and support vector machines learning algorithms are used to ide...

We study a buffer that implements the Random Early Detect/Discard (RED) mechanism to cope with congestion, and offers service differentiation by proposing a finite number of slopes at different prices for the RED probability. As a characteristic, the smaller the slope, the better the resulting QoS. Users are sensitive to their average throughput an...

In this paper, we model a market-based cognitive radio network where multiple wireless service providers (WSPs) offer competitive prices to users. We assume that WSPs use a mix of access technologies to provide a wide variety of wireless services (e.g., voice, data etc.) with a certain level of QoS while maximizing their revenues. Using a non-coope...

In this paper we study the complexity of spectrum assignment problems in cognitive radio networks (CRNs) in the presence of several constraints. Although optimal spectrum assignment for secondary transmissions in CRNs is generally believed to be NP complete, the impact of fairness and link quality constraints on the hardness of the problem is not w...

Cognitive radio networks are supposed to be capable of sensing their operating environment (with little or no prior information) and learning to adapt their behavior accordingly. We note that such a cognitive process is inherent in human behavior as well. One application of these networks is in dynamic spectrum access. Human beings evolve by learni...

This chapter provides an overview of techniques and tools to detect deception on the Internet. A classification of state-of-the-art hypothesis testing and data mining based deception detection methods are presented. A psycho-linguistics based statistical model for deception detection is also described in detail. Passive and active methods for detec...

The development of software-defined-radio-(SDR) enabled1 cognitive radio networks has facilitated dynamic sharing by users of the available spectrum on an opportunistic basis. Users belonging to one network can sense spectrum opportunities in another network and contend for the unused spectrum in the new network. These users thereby become secondar...

A special issue on cognitive radio oriented wireless networks and communications is discussed in Mobile Network Application journal. The paper on 'Distributed Scheduling and Resource Allocation for Cognitive OFDMA Radios' by Bazerque and Giannakis considers scheduling spectrum access and allocating power and rate resources in CR networks. Xin, Ma,...

Traditional automatic repeat request (ARQ) protocols are channel unaware. That is, they react to channel errors by simply retransmitting erroneous packets and do not proactively decide whether or not to transmit a packet in a given slot based on past channel conditions. Clearly, ARQ protocols operating in this mode are not energy efficient. For exa...

Distributed power control is an important issue in wireless networks. Recently, noncooperative game theory has been applied to investigate interesting solutions to this problem. The majority of these studies assumes that the transmitter power level can take values in a continuous domain. However, recent trends such as the GSM standard and Qualcomm'...

The IEEE 802.22 standard based on cognitive radio is envisioned as one of the solutions that can harness the unused or under-utilized spectrum that was primarily been allocated for licensed TV services. This allows the cognitive radio enabled devices to opportunistically use the spectrum without spatial and temporal interference with the licensed d...

In this paper, we compute the primary exclusive region (PER) and the secrecy capacity at a primary receiver in a fading cognitive radio network. We consider Rayleigh fading and log-normal shadowing. We also study the effect of secrecy capacity on the PER. We show that log-normal shadowing and Rayleigh fading can degrade the PER by about 40% and the...

In this paper we discuss a random walk model to characterize the pulse discharge battery process. Several theoretical results are derived including the mean and variance of an unattended battery-driven sensor lifetime. Some numerical results are presented.

This paper proposes a nonparametric steganalysis method for quantization index modulation (QIM) based steganography. The proposed steganalysis method uses irregularity (or randomness) in the test-image to distinguish between the cover- and the stego-image. We have shown that plain-quantization (quantization without message embedding) induces regula...

With the explosive growth of wireless multimedia applications over the wireless Internet in recent years, the demand for radio spectral resources has increased significantly. In order to meet the quality of service, delay, and large bandwidth requirements, various techniques such as source and channel coding, distributed streaming, multicast etc. h...

The cognitive radio based IEEE 802.22 wireless regional area network (WRAN) is designed to operate in the under-utilized TV bands by detecting and avoiding primary TV transmission bands in a timely manner. Such networks, deployed by competing wireless service providers, would have to self-coexist by accessing different parts of the available spectr...