Severity invariant feature selection for machine health monitoring
- Authors: Yaqub, Muhammad , Gondal, Iqbal , Kamruzzaman, Joarder
- Date: 2011
- Type: Text , Journal article
- Relation: International Review of Electrical Engineering Vol. 6, no. 1 (2011), p. 238-248
- Full Text: false
- Reviewed:
- Description: Vibration signals used for abnormality detection in machine health monitoring (MHM) suffer from significant variation in the patterns with fault severity. This variation results in overlap among the features extracted against different fault types and causes severe degradation in fault detection accuracy. This paper identifies a newfangled problem originated by severity variant features and mitigates this impact by using appropriate feature selection based on Fisher linear discriminant (FLD) and Bhattacharyya distance (BCD) to enhance fault classification accuracy. In order to validate the performance of the proposed scheme, training and testing data are obtained from different severity levels. To capture the non-stationary behavior of vibration signal, robust tools such as wavelet transform (WT) for time-frequency analysis is employed. Simulation studies show that the proposed scheme ensures good fault diagnostic accuracy even if training and testing data belong to different severity levels. [ABSTRACT FROM AUTHOR]
Severity invariant machine fault diagnosis
- Authors: Yaqub, Muhammad , Gondal, Iqbal , Kamruzzaman, Joarder
- Date: 2011
- Type: Text , Conference paper
- Relation: 6th IEEE Conference on Industrial Electronics and Applications p. 21-26
- Full Text: false
- Reviewed:
- Description: Vibration signals used for abnormality detection in machine health monitoring (MHM) suffer from significant variation with fault severity. This variation causes overlap among the features belonging to different types of faults resulting in severe degradation of fault detection accuracy. This paper identifies a new problem due to severity variant features and proposes a novel adaptive training set and feature selection (ATSFS) scheme based upon the orientation of the test data. In order to build ATSFS and validate its performance, training and testing data are obtained from different severity levels. To capture the non-stationary behavior of vibration signal, robust tools such as wavelet transform (WT) for time-frequency analysis are employed. Simulation studies show that ATSFS attains high classification accuracy even if training and testing data belong to different severity levels.
Spectrum allocation framework for multiuser cognitive radio systems
- Authors: Shahid, Mohammad , Kamruzzaman, Joarder
- Date: 2011
- Type: Text , Conference paper
- Relation: 2011 IEEE International Conference on Communications, ICC 2011; Kyoto, Japan; 5th-9th June 2011 p. 1-6
- Full Text: false
- Reviewed:
- Description: One of the most challenging issues in cognitive radio networks is to dynamically access the radio frequency spectrum in an uninterrupted manner. To achieve this, omniscient allocation of spectrum bands among cognitive radio users is crucial. Most of the existing spectrum allocation methods select a band from a pool according to the service requirements of a single user, neglecting the demand of multiple users. In this paper, we introduce a collaborative framework for allocating multiple bands among multiple secondary users. The proposed method defines a capacity of service metric based on the optimal sensing parameters and utilizes this metric to assign distinct bands to all or highest possible number of contending users. Performance evaluation suggests that the proposed method exhibits significant superiority over conventional approaches in terms of improved throughput and spectrum utilization, reduced interference loss and collision, and hence, enhances dynamic spectrum access and sharing capabilities.
A contender-aware backoff algorithm for CSMA based MAC protocol for wireless sensor network
- Authors: Miraz Al-Mamun, Miraz , Karmakar, Gour , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference proceedings
- Full Text: false
- Description: Existing contention based nonpersistent medium access control protocols in Wireless Sensor Network (WSN) do not perform well in high contention. Their performances are affected by occurrence of collision due to uniform probability distribution in choosing Time Slot (TS) during backoff period. To address this issue nonuniform probability distribution was proposed. However success rate still drops for higher number of contenders. In this paper we propose CSMA/s (Collision Sense Multiple Access /per Slot based), a new approach in nonuniform contender-aware probability distribution for choosing TS in the backoff period. Rather than taking a premeditated fixed value for contender population size, our proposed scheme embeds neighborhood population size into its bedrock to automatically converge to the actual number of contenders which enables the contender to adaptively choose TS in the backoff period for reducing collision. This method produces better success rate and lower latency for even very high number of contenders.
Agile spectrum evacuation in cognitive radio networks
- Authors: Shahid, Mohammad , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference paper
- Relation: 2010 IEEE International Conference on Communications p. 1-6
- Full Text: false
- Reviewed:
- Description: One of the most important aspects of cognitive radio technology is to avoid interference on the primary system. Typically, the interference is avoided by sensing a particular spectrum band for the existence of primary transmitter while all secondary users are kept quiet. Hence, a periodic sensing method is used which incorporates alternate phases of sensing and transmission by all secondary users. In this paper, we introduce a new method of agile spectrum evacuation that allows any secondary user to continue using the band until the return of the primary user is detected through the formation of a set of users that exclusively engages in sensing primary user in a cooperative manner. The proposed method yields better interference protection and enhanced spectrum utilization.
An environment-aware mobility model for wireless ad hoc network
- Authors: Ahmed, Sabbir , Karmakar, Gour , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Journal article
- Relation: Computer Networks Vol. 54, no. 9 (2010), p. 1470-1489
- Full Text: false
- Reviewed:
- Description: Simulation is a cost effective, fast and flexible alternative to test-beds or practical deployment for evaluating the characteristics and potential of mobile ad hoc networks. Since environmental context and mobility have a great impact on the accuracy and efficacy of performance measurement, it is of paramount importance how closely the mobility of a node resembles its movement pattern in a real-world scenario. The existing mobility models mostly assume either free space for deployment and random node movement or the movement pattern does not emulate real-world situation properly in the presence of obstacles because of their generation of restricted paths. This demands for the development of a node movement pattern with accurately representing any obstacle and existing path in a complex and realistic deployment scenario. In this paper, we propose a general mobility model capable of creating a more realistic node movement pattern by exploiting the concept of flexible positioning of anchors. Since the model places anchors depending upon the context of the environment through which nodes are guided to move towards the destination, it is capable of representing any terrain realistically. Furthermore, obstacles of arbitrary shapes with or without doorways and any existing pathways in full or part of the terrain can be incorporated which makes the simulation environment more realistic. A detailed computational complexity has been analyzed and the characteristics of the proposed mobility model in the presence of obstacles in a university campus map with and without signal attenuation are presented which illustrates its significant impact on performance evaluation of wireless ad hoc networks.
CAM : Congestion avoidance and mitigation in wireless sensor networks
- Authors: Bhuiyan, Mohammad , Gondal, Iqbal , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference paper
- Relation: Vehicular Technology Conference (VTC 2010-Spring), 2010 IEEE 71st
- Full Text: false
- Reviewed:
Coexistence mechanism for industrial automation network
- Authors: Yaqub, Muhammad , Gondal, Iqbal , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference paper
- Relation: 12th IEEE International Conference on High Performance Computing and Communications
- Full Text: false
- Reviewed:
- Description: Increase in the number of coexisting networks in license free Industrial, Scientific and Medical (ISM) band causes interferences for industrial automation, e.g., shop floors of manufacturing facilities. In order to ensure the reliability for automation networks, interference avoidance schemes are required. This paper proposes a novel Predefined Hopping Pattern (PHP) technique for frequency hopping in ISM band, which mitigates self-interferences and static interferers as well. This technique generates optimized frequency hopping sequences which ensure sufficient frequency diversity and frequency offset among the coexisting Bluetooth piconets and exploits transmission experiences for a particular frequency in eliminating interference. Simulation studies have shown that PHP has better collision avoidance rate than well known adaptive frequency hopping (AFH) and adaptive frequency rolling (AFR) schemes.
Diversified adaptive frequency rolling to mitigate self and static interferences
- Authors: Yaqub, Muhammad , Gondal, Iqbal , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference proceedings
- Full Text: false
- Description: Increase in the number of coexisting networks in Industrial, Scientific and Medical (ISM) band cause interferences and demands for intelligent interference avoidance schemes. This paper proposes a novel Diversified Adaptive Frequency Rolling (DAFR) technique for frequency hopping in Bluetooth piconets which has the tendency to mitigate both the self and static interferences and ensures sufficient frequency diversity. Simulation studies validate the prospects for the proposed scheme to be used for frequency hopping networks against already existing techniques, Adaptive Frequency Hopping (AFH) and Adaptive Frequency Rolling (AFR).
Efficient utilization of WLAN networks in the next-generation heterogeneous environments
- Authors: Haider, Ammar , Gondal, Iqbal , Kamruzzaman, Joarder , Qiu, Bin
- Date: 2010
- Type: Text , Conference paper
- Relation: Vol. , no. (2010), p.398-403
- Full Text: false
- Reviewed:
Increasing voice capacity over IEEE 802.11 WLAN using virtual access points
- Authors: Siddique, Md , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference paper
- Relation: Global Telecommunications Conference (GLOBECOM 2010), 2010 IEEE p. 1-6
- Full Text: false
- Reviewed:
- Description: Voice capacity over IEEE 802.11 networks can be increased with time synchronized medium access, but it is restricted to single hop networks only. We propose a collaborative mechanism that enables client nodes to carry out the time synchronization on ad hoc basis, thereby extends the time synchronized access mechanism over multiple hops, and increases voice capacity considerably. To model real scenario closely, we consider the impact of channel error and employ a Markov chain to determine delay and loss in both medium access and in queue which is then used to derive user perceived voice quality using ITU-T E-model. Our model is then used to determine voice capacity of multichannel, multihop networks. The impact of data rate, interference range, and multiple channels are also analyzed
Interference protection in cognitive radio networks
- Authors: Shahid, Mohammad , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference paper
- Relation: 2010 IEEE 71st Vehicular Technology Conference p. 1-5
- Full Text: false
- Reviewed:
- Description: Protection of interference on the primary system is the key requirement for deployment of a cognitive radio system. Typically, spectrum sensing is interleaved in the transmission process of a secondary user to detect the return of primary user for quick evacuation, resulting in frequent stopping of transmission. In this paper, we introduce a novel method of agile spectrum evacuation that ensures continuous transmission by the secondary user until the primary user actually returns. The sensing process goes on simultaneously by a dedicated set of users working in a cooperative manner. The proposed method is evaluated under fading and shadowing conditions and better interference protection and improved utilization of RF spectrum is obtained.
LACAR : Location aided congestion aware routing in wireless sensor networks
- Authors: Bhuiyan, Mohammad , Gondal, Iqbal , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference paper
- Relation: Wireless Communications and Networking Conference (WCNC), p. 1-6
- Full Text: false
- Reviewed:
- Description: Trade-off between energy-efficiency and reliability in wireless sensor networks is application dependent. Without the reliability, the extended lifetime of a network is of limited use. Due to the inherent correlation between reliability and congestion, it is necessary to reduce congestion to improve reliability. Existing congestion control algorithms in wireless sensor networks are reactive. They attempt to reduce the congestion only after its detection. In this paper, we present Location Aided Congestion Aware Routing (LACAR) protocol that proactively avoids congestion formation and improves data delivery success rate in data gathering wireless sensor networks. Location, energy and congestion information of neighbours together with the location information of the base station determine appropriate routes. Simulation results show that LACAR achieves high packet success rate in an energy-efficient way.
Performance analysis of m-retry BEB based DCF under unsaturated traffic condition
- Authors: Siddique, Md , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference paper
- Relation: 2010 IEEE Wireless Communications and Networking Conference (WCNC) p. 1-6
- Full Text: false
- Reviewed:
- Description: The IEEE 802.11 standard offers a cheap and promising solution for small scale wireless networks. Due to the self configuring nature, WLANs do not require large scale infrastructure deployment, and are scalable and easily maintainable which incited its popularity in both literature and industry. In real environment, these networks operate mostly under unsaturated condition. We investigate performance of such a network with m-retry limit BEB based DCF. We consider imperfect channel with provision for power capture. Our method employs a Markov model and represents the most common performance measures in terms of network parameters making the model and mathematical analysis useful in network design and planning. We also explore the effects of packet error, network size, initial contention window, and retry limit on overall performance of WLANs.
Performance analysis of PCF based WLANs with imperfect channel and failure retries
- Authors: Siddique, Md , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference paper
- Relation: 2010 IEEE Global Telecommunications Conference p. 1-6
- Full Text: false
- Reviewed:
- Description: Wi-Fi enabled hand-held devices quickly occupied the consumer market as a result of the remarkable customer acceptance of IEEE 802.11 standard. But the widely used contention based medium access mechanism is unable to meet the increasing traffic demand of today's home users. Especially, delay sensitive multimedia contents suffer heavily from quality degradation under high traffic load. However, the time synchronized medium access mechanism of 802.11 called PCF offers lower delay and loss, and holds true potential in supporting high traffic load. For design and planning of such networks, a thorough performance analysis of PCF based 802.11 WLANs is of profound importance. But existing studies on this lack proper and accurate mathematical modeling considering realistic assumptions, which is investigated in this paper. We develop a Markov chain to analyze the time synchronized PCF based medium access mechanism considering error prone channels, and determine throughput, delay, and packet loss in a WLAN. The impact of traffic load and retry limit is also analyzed. We use our model to analyze performance of PCF mechanism in supporting both data and multimedia traffic.
QoS-centric collision window shaping for CSMA-CA MAC protocol
- Authors: Miraz Al-Mamun, Miraz , Karmakar, Gour , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference proceedings
- Full Text: false
- Description: Collision Sense Multiple Access (CSMA) has been preferred to Time Division Multiple Access (TDMA) as medium access scheme for Wireless Multimedia Sensor Network (WMSN) in the scenarios where the traffic is bursty in nature and multiple consecutive and contiguous packets generated from the same collision neighborhood need to be sent. Protocols based on nonuniform probability distribution do not perform well in high contention and heterogeneous traffic scenarios due to nonadaptive nature to contention neighborhood. In this paper we have proposed a scheme to adapt the Contention Window (CW) size according to the collision neighborhood population complying with the application specific latency and success probability constraints. This scheme shows improved performance compared with SIFT, a stereotype of non-uniform probability based CSMA protocol and can be deployed with any CSMA-CA (CSMA with Collision Avoidance) based backoff algorithm
Query processing over distributed heterogeneous sensor networks in Future Internet : Scalable architecture and challenges
- Authors: Azad, Arman , Kamruzzaman, Joarder , Srinivasan, Bala , Alam, K. , Pervin, Shaila
- Date: 2010
- Type: Text , Conference paper
- Relation: Second International Conference on Advances in Future Internet p. 75-81
- Full Text: false
- Reviewed:
- Description: The wireless networked sensors embedded with everyday objects will become an integral part of Future Internet, where the interaction among people, computer and those objects will shift the current Internet to a new paradigm, namely the Internet of Things. The terabyte torrent of data generated by billions of sensors belonging to a large number of distributed heterogeneous sensor networks in Future Internet will only be valuable if they can be effectively used on purpose, which leads to the necessity of an Internet scale query processing framework. In this paper, firstly, we focus on the distinct challenges present in Internet scale query processing over distributed sensor networks. Then, we propose a flexible and scalable system architecture capable of handling the complex scenario that might arise from the integration of a large number of such networks in Future Internet. Finally, we discuss the overall query processing methodology over such system and present some directions on the possible solutions to a number of identified research challenges. The outcome of this paper would foster the sensor network research in Future Internet domain
Voice over multi-channel multi-radio WLANs with power capture and imperfect channel
- Authors: Siddique, Md , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference paper
- Relation: 2010 IEEE Wireless Communications and Networking Conference p. 1-6
- Full Text: false
- Reviewed:
- Description: VoIP offers cheap voice communication which instigated its quick market growth. IEEE 802.11 WLANs offer cheap wireless coverage which can be used to provide VoIP service in mobile devices. But call capacity of such networks is very low compared to wired networks. To increase voice capacity in WLANs incorporation of power capture, increased data rate, and use of multiple channels are of great importance. Moreover, these networks should be carefully designed considering voice quality requirements to avoid call jitter and call drops. We propose an analytical model to estimate VoIP call capacity for multichannel WLANs with consideration for power capture, imperfect channel, and multiple network interfaces. We employed ITU-T E-model to assess voice quality which is used as the limiting factor to ensure that voice quality does not degrade in such networks. The model will be extremely helpful to network designers in planning single channel or multi-channel WLANs.
VoIP service over multihop 802.11 networks with power capture and channel noise
- Authors: Siddique, Md , Kamruzzaman, Joarder
- Date: 2010
- Type: Text , Conference paper
- Relation: 2010 IEEE International Conference on Communications p. 1-6
- Full Text: false
- Reviewed:
- Description: The quick market growth and ubiquitous acceptance of VoIP are primarily due to cheap service. VoIP services can be availed in mobile devices at a very low cost by employing IEEE 802.11 to provide last mile coverage. But call capacity is very low in these networks and call jitter occurs if voice quality requirements are not precisely met. We present a VoIP call capacity model for 802.11 networks which considers the most important real world factors like power capture and imperfect channel. Incorporating multiple channels can increase call capacity while multihop network can provide considerably large coverage. Our capacity model incorporates the effects of both multiple channels and multihop networks. We also consider the availability of multiple radio interfaces and conference call scenarios for ubiquitous applications of our model. To ensure voice quality, in addition to contention analysis, we also model the queue considering collision domain at each hop and formulate call capacity by estimating precise impairment budget over multihop.
Combining segmental semi-Markov models with neural networks for protein secondary structure prediction
- Authors: Bidargaddi, Niranjan , Chetty, Madhu , Kamruzzaman, Joarder
- Date: 2009
- Type: Text , Journal article
- Relation: Neurocomputing Vol. 72, no. 3943-3950 (2009), p.3943-3950
- Full Text: false
- Reviewed:
- Description: Predicting the secondary structure of proteins from a primary sequence alone has been variously approached from either a classification or a generative model perspective. The most prominent classification methods have used neural networks, which involves mappings from a local window of residues in the sequence to the structural state of the central residue in the window, thus capturing the local interactions effectively. However, they fail to capture distant interactions among residues. The generative models based on Bayesian segmentation capture sequence structure relationships using generalized hidden Markov models with explicit state duration. They capture non-local interactions through a joint sequence-structure probability distribution based on structural segments. In this paper, we investigate a combined architecture of Bayesian segmentation at the first stage and neural network at the second stage which captures both local and non-local correlation, to increase the single sequence prediction accuracy. The combined architecture is further enhanced by using neural network optimization and ensemble techniques.