S M Kamruzzaman - Academia.edu (original) (raw)

Papers by S M Kamruzzaman

Research paper thumbnail of Pattern Classification using Simplified Neural Networks

... 4, pp. 1265–1278, 2001. [8] M. Monirul Islam, MAH Akhand, M. Abdur Rahman and K. Murase, “Wei... more ... 4, pp. 1265–1278, 2001. [8] M. Monirul Islam, MAH Akhand, M. Abdur Rahman and K. Murase, “Weight Freezing to Reduce Training Time in Designing Artificial neural Networks”, Proceedings of 5th ICCIT, EWU, pp. 132-136, 27-28 December 2002. ...

Research paper thumbnail of Energy efficient cognitive radio MAC protocol for battlefield communications

2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE), 2015

Research paper thumbnail of Antiplatelet Activity of Phellinus baummii Methanol Extract is Mediated by Cyclic AMP Elevation and Inhibition of Collagen-activated Integrin-α IIb β 3 and MAP Kinase

Phytotherapy Research, 2011

Phellinus baumii is a mushroom that has been used as folk medicine against various diseases and i... more Phellinus baumii is a mushroom that has been used as folk medicine against various diseases and is reported to have antidiabetic, anticancer, antioxidant, antiinflammatory and antihypertensive activities. However, information on the effects of P. baumii extract in platelet function is limited. Therefore, the aim of this study was to examine the impact of a P. baumii methanol extract (PBME) on platelet activation and to investigate the mechanism behind its antiplatelet activity. PBME effects on agonist-induced platelet aggregation, granule secretion, [Ca²⁺](i) mobilization, α(IIb) β₃ activation, cyclic AMP release and mitogen-activated protein kinase (MAPK) phosphorylations were studied using rat platelets. PBME dose-dependently inhibited collagen, thrombin and ADP-induced platelet aggregation with an IC₅₀ of 51.0 ± 2.4, 54.0 ± 2.1 and 53.0 ± 4.3 μg/mL, respectively. Likewise, thrombin-induced [Ca²⁺](i) and collagen-activated ATP secretions were suppressed in PBME treated platelets. Aggregation and ATP secretion were also markedly attenuated by PBME alone or in combination with PP2 (Src inhibitor) and U-73122 (PLC inhibitor) in collagen-stimulated platelets. Besides, PBME treatment elevated basal cyclic AMP levels and inhibited collagen-induced integrin-α(IIb) β₃ activation. Moreover, PBME attenuated extracellular-signal-regulated protein kinase 2 (ERK2) and c-Jun N-terminal kinase 1 (JNK1) phosphorylations. Further PD98059 (ERK inhibitor) and SP60025 (JNK inhibitor) reduced collagen-induced platelet aggregation and ATP secretion. In conclusion, the observed PBME antiplatelet activity may be mediated by activation of cyclic AMP and inhibition of ERK2 and JNK1 phosphorylations. Finally, these data suggest that PBME may have therapeutic potential for the treatment of cardiovascular diseases that involve aberrant platelet function.

Research paper thumbnail of Inhibitory effects of Bulnesia sarmienti aqueous extract on agonist-induced platelet activation and thrombus formation involves mitogen-activated protein kinases

Journal of Ethnopharmacology, 2010

Research paper thumbnail of A noble function of BAY 11-7082: Inhibition of platelet aggregation mediated by an elevated cAMP-induced VASP, and decreased ERK2/JNK1 phosphorylations

European Journal of Pharmacology, 2010

Research paper thumbnail of Rule Extraction using Artificial Neural Networks

Artificial neural networks have been successfully applied to a variety of business application pr... more Artificial neural networks have been successfully applied to a variety of business application problems involving classification and regression. Although backpropagation neural networks generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions are not as interpretable as those of decision trees. In many applications, it is desirable to extract knowledge from trained neural networks so that the users can gain a better understanding of the solution. This paper presents an efficient algorithm to extract rules from artificial neural networks. We use two-phase training algorithm for backpropagation learning. In the first phase, the number of hidden nodes of the network is determined automatically in a constructive fashion by adding nodes one after another based on the performance of the network on training data. In the second phase, the number of relevant input units of the network is determined us...

Research paper thumbnail of Ginsenoside-Rp1 inhibits platelet activation and thrombus formation via impaired glycoprotein VI signalling pathway, tyrosine phosphorylation and MAPK activation

British Journal of Pharmacology, 2012

Research paper thumbnail of Anonymous and Secure Communication Protocol for Cognitive Radio Ad Hoc Networks

2014 IEEE International Symposium on Multimedia, 2014

ABSTRACT

Research paper thumbnail of Design of an energy-efficient and reliable data delivery mechanism for mobile ad hoc networks: a cross-layer approach

Concurrency and Computation: Practice and Experience, 2014

ABSTRACT In a mobile ad hoc network, the data packet may fail to be delivered for various reasons... more ABSTRACT In a mobile ad hoc network, the data packet may fail to be delivered for various reasons mostly for route failure, congestion, and battery energy drain. Hence, providing reliable and timely data delivery in this network in an energy-efficient way is challenging. Although there exist several solutions to solve these problems, they can handle either route failure or congestion or energy-efficient routing. Hence, to cope up with all the problems simultaneously, we propose a route failure and congestion-aware energy-efficient cross-layer design that spans the transport and network layer. In the transport layer, we introduce the concept of local packet buffering during link failure and congestion. As a result, the packet dropping rate of the network and energy consumption decreases. In the network layer, a routing protocol is proposed for selecting the energy-efficient path for data transmission. It uses the buffering mechanism in case of route maintenance. In addition, we employ a multilevel congestion detection and control mechanism at the source and intermediate nodes that can judiciously take the most appropriate decision for congestion control in the network proactively. The simulation results showed that the proposed cross-layer design provided better performance as compared with the state-of-the-art protocols. Copyright © 2014 John Wiley & Sons, Ltd.

Research paper thumbnail of Channel-Slot Aggregation Diversity Based Slot Reservation Scheme for Cognitive Radio Ad Hoc Networks

International Journal of Distributed Sensor Networks, 2014

In cognitive radio (CR) ad hoc networks, spectrum efficiency and energy efficiency are vitally im... more In cognitive radio (CR) ad hoc networks, spectrum efficiency and energy efficiency are vitally important because spectrum availability is opportunistic in nature and mobile CR nodes usually have limited energy. Aiming to improve network throughput along with improving spectrum and energy efficiencies, this paper proposes a channel-slot aggregation diversity based slot reservation (CADSR) scheme by which each CR node can utilize multiple slots in different channels simultaneously and efficiently utilize the power control mechanism with only a single CR transceiver. The proposed scheme dynamically assigns channel-slots to CR nodes using the diversity technique according to the topology density of the network and the bandwidth requirement, allowing CR nodes to join and leave the network at any time in a distributed way. A dynamic frame length expansion and shrinking scheme has also been introduced that improves the slot utilization. Extensive simulation results show that the proposed mechanism achieves significant performance improvement in network throughput, energy efficiency, and end-to-end delay.

Research paper thumbnail of Dynamic TDMA slot reservation protocol for cognitive radio ad hoc networks

Proceedings of 2010 13th International Conference on Computer and Information Technology, ICCIT 2010, 2010

Abstract In this paper, we propose a dynamic TDMA slot reservation (DTSR) protocol for cognitive ... more Abstract In this paper, we propose a dynamic TDMA slot reservation (DTSR) protocol for cognitive radio ad hoc networks. Quality of Service (QoS) guarantee plays a critically important role in such networks. We consider the problem of providing QoS guarantee to users as well as ...

Research paper thumbnail of Spectrum and energy aware routing protocol for cognitive radio ad hoc networks

IEEE International Conference on Communications, 2011

Abstract Throughput maximization is one of the core challenges in cognitive radio ad hoc networks... more Abstract Throughput maximization is one of the core challenges in cognitive radio ad hoc networks (CRANs), where local spectrum resources are changing over time and locations. This paper proposes a spectrum and energy aware routing (SER) protocol for CRANs, ...

Research paper thumbnail of Spectrum and energy aware multipath routing for cognitive radio ad hoc networks

2014 International Conference on Information and Communication Technology Convergence (ICTC), 2014

Research paper thumbnail of An Energy Efficient Multi-channel MAC Protocol for wireless ad hoc networks

2012 IEEE Global Communications Conference (GLOBECOM), 2012

ABSTRACT This paper presents a TDMA based energy efficient cognitive radio multichannel medium ac... more ABSTRACT This paper presents a TDMA based energy efficient cognitive radio multichannel medium access control (MAC) protocol called ECR-MAC for wireless Ad Hoc Networks. ECR-MAC requires only a single half-duplex radio transceiver on each node that integrates the spectrum sensing at physical (PHY) layer and the packet scheduling at MAC layer. In addition to explicit frequency negotiation which is adopted by conventional multichannel MAC protocols, ECR-MAC introduces lightweight explicit time negotiation. This two-dimensional negotiation enables ECR-MAC to exploit the advantage of both multiple channels and TDMA, and achieve aggressive power savings by allowing nodes that are not involved in communication to go into doze mode. The IEEE 802.11 standard allows for the use of multiple channels available at the PHY layer, but its MAC protocol is designed only for a single channel. A single channel MAC protocol does not work well in a multichannel environment, because of the multichannel hidden terminal problem. The proposed energy efficient ECR-MAC protocol allows SUs to identify and use the unused frequency spectrum in a way that constrains the level of interference to the primary users (PUs). Extensive simulation results show that our proposed ECR-MAC protocol successfully exploits multiple channels and significantly improves network performance by using the licensed spectrum band opportunistically and protects QoS provisioning over cognitive radio ad hoc networks. Comment: 8 Pages, International Journal

Research paper thumbnail of CR-Mac: A Multichannel Mac Protocol for Cognitive Radio Ad Hoc Networks

International journal of Computer Networks & Communications, 2010

This paper proposes a cross-layer based cognitive radio multichannel medium access control (MAC) ... more This paper proposes a cross-layer based cognitive radio multichannel medium access control (MAC) protocol with TDMA, which integrate the spectrum sensing at physical (PHY) layer and the packet scheduling at MAC layer, for the ad hoc wireless networks. The IEEE 802.11 ...

Research paper thumbnail of Energy-aware routing protocol for cognitive radio ad hoc networks

IET Communications, 2012

ABSTRACT Routing is one of the most important issues in multihop ad hoc networks. In the routing ... more ABSTRACT Routing is one of the most important issues in multihop ad hoc networks. In the routing for mobile cognitive radio (CR) networks, the constraints on residual energy of each user and the requirements for primary user protection should be additionally taken into account. This study proposes a spectrum and energy-aware routing (SER) protocol for CR ad hoc networks, which is based on the dynamic source routing. To establish routes on-demand with reserved bandwidth, the protocol involves route selection and channel-timeslot allocation jointly. The proposed SER protocol can balance energy consumption, reduce routing overhead, eliminate contention between nodes and decompose traffics over different channels/timeslots. Extensive simulation shows that the proposed protocol achieves good performance in system throughput, network lifetime and mean message delay.

Research paper thumbnail of A constructive algorithm for feedforward neural networks with incremental training

IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 2002

Research paper thumbnail of A new data mining scheme using artificial neural networks

Sensors (Basel, Switzerland), 2011

Classification is one of the data mining problems receiving enormous attention in the database co... more Classification is one of the data mining problems receiving enormous attention in the database community. Although artificial neural networks (ANNs) have been successfully applied in a wide range of machine learning applications, they are however often regarded as black boxes, i.e., their predictions cannot be explained. To enhance the explanation of ANNs, a novel algorithm to extract symbolic rules from ANNs has been proposed in this paper. ANN methods have not been effectively utilized for data mining tasks because how the classifications were made is not explicitly stated as symbolic rules that are suitable for verification or interpretation by human experts. With the proposed approach, concise symbolic rules with high accuracy, that are easily explainable, can be extracted from the trained ANNs. Extracted rules are comparable with other methods in terms of number of rules, average number of conditions for a rule, and the accuracy. The effectiveness of the proposed approach is cl...

Research paper thumbnail of REx: An Efficient Rule Generator

Research paper thumbnail of Text Classification using Artificial Intelligence

Research paper thumbnail of Pattern Classification using Simplified Neural Networks

... 4, pp. 1265–1278, 2001. [8] M. Monirul Islam, MAH Akhand, M. Abdur Rahman and K. Murase, “Wei... more ... 4, pp. 1265–1278, 2001. [8] M. Monirul Islam, MAH Akhand, M. Abdur Rahman and K. Murase, “Weight Freezing to Reduce Training Time in Designing Artificial neural Networks”, Proceedings of 5th ICCIT, EWU, pp. 132-136, 27-28 December 2002. ...

Research paper thumbnail of Energy efficient cognitive radio MAC protocol for battlefield communications

2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE), 2015

Research paper thumbnail of Antiplatelet Activity of Phellinus baummii Methanol Extract is Mediated by Cyclic AMP Elevation and Inhibition of Collagen-activated Integrin-α IIb β 3 and MAP Kinase

Phytotherapy Research, 2011

Phellinus baumii is a mushroom that has been used as folk medicine against various diseases and i... more Phellinus baumii is a mushroom that has been used as folk medicine against various diseases and is reported to have antidiabetic, anticancer, antioxidant, antiinflammatory and antihypertensive activities. However, information on the effects of P. baumii extract in platelet function is limited. Therefore, the aim of this study was to examine the impact of a P. baumii methanol extract (PBME) on platelet activation and to investigate the mechanism behind its antiplatelet activity. PBME effects on agonist-induced platelet aggregation, granule secretion, [Ca²⁺](i) mobilization, α(IIb) β₃ activation, cyclic AMP release and mitogen-activated protein kinase (MAPK) phosphorylations were studied using rat platelets. PBME dose-dependently inhibited collagen, thrombin and ADP-induced platelet aggregation with an IC₅₀ of 51.0 ± 2.4, 54.0 ± 2.1 and 53.0 ± 4.3 μg/mL, respectively. Likewise, thrombin-induced [Ca²⁺](i) and collagen-activated ATP secretions were suppressed in PBME treated platelets. Aggregation and ATP secretion were also markedly attenuated by PBME alone or in combination with PP2 (Src inhibitor) and U-73122 (PLC inhibitor) in collagen-stimulated platelets. Besides, PBME treatment elevated basal cyclic AMP levels and inhibited collagen-induced integrin-α(IIb) β₃ activation. Moreover, PBME attenuated extracellular-signal-regulated protein kinase 2 (ERK2) and c-Jun N-terminal kinase 1 (JNK1) phosphorylations. Further PD98059 (ERK inhibitor) and SP60025 (JNK inhibitor) reduced collagen-induced platelet aggregation and ATP secretion. In conclusion, the observed PBME antiplatelet activity may be mediated by activation of cyclic AMP and inhibition of ERK2 and JNK1 phosphorylations. Finally, these data suggest that PBME may have therapeutic potential for the treatment of cardiovascular diseases that involve aberrant platelet function.

Research paper thumbnail of Inhibitory effects of Bulnesia sarmienti aqueous extract on agonist-induced platelet activation and thrombus formation involves mitogen-activated protein kinases

Journal of Ethnopharmacology, 2010

Research paper thumbnail of A noble function of BAY 11-7082: Inhibition of platelet aggregation mediated by an elevated cAMP-induced VASP, and decreased ERK2/JNK1 phosphorylations

European Journal of Pharmacology, 2010

Research paper thumbnail of Rule Extraction using Artificial Neural Networks

Artificial neural networks have been successfully applied to a variety of business application pr... more Artificial neural networks have been successfully applied to a variety of business application problems involving classification and regression. Although backpropagation neural networks generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions are not as interpretable as those of decision trees. In many applications, it is desirable to extract knowledge from trained neural networks so that the users can gain a better understanding of the solution. This paper presents an efficient algorithm to extract rules from artificial neural networks. We use two-phase training algorithm for backpropagation learning. In the first phase, the number of hidden nodes of the network is determined automatically in a constructive fashion by adding nodes one after another based on the performance of the network on training data. In the second phase, the number of relevant input units of the network is determined us...

Research paper thumbnail of Ginsenoside-Rp1 inhibits platelet activation and thrombus formation via impaired glycoprotein VI signalling pathway, tyrosine phosphorylation and MAPK activation

British Journal of Pharmacology, 2012

Research paper thumbnail of Anonymous and Secure Communication Protocol for Cognitive Radio Ad Hoc Networks

2014 IEEE International Symposium on Multimedia, 2014

ABSTRACT

Research paper thumbnail of Design of an energy-efficient and reliable data delivery mechanism for mobile ad hoc networks: a cross-layer approach

Concurrency and Computation: Practice and Experience, 2014

ABSTRACT In a mobile ad hoc network, the data packet may fail to be delivered for various reasons... more ABSTRACT In a mobile ad hoc network, the data packet may fail to be delivered for various reasons mostly for route failure, congestion, and battery energy drain. Hence, providing reliable and timely data delivery in this network in an energy-efficient way is challenging. Although there exist several solutions to solve these problems, they can handle either route failure or congestion or energy-efficient routing. Hence, to cope up with all the problems simultaneously, we propose a route failure and congestion-aware energy-efficient cross-layer design that spans the transport and network layer. In the transport layer, we introduce the concept of local packet buffering during link failure and congestion. As a result, the packet dropping rate of the network and energy consumption decreases. In the network layer, a routing protocol is proposed for selecting the energy-efficient path for data transmission. It uses the buffering mechanism in case of route maintenance. In addition, we employ a multilevel congestion detection and control mechanism at the source and intermediate nodes that can judiciously take the most appropriate decision for congestion control in the network proactively. The simulation results showed that the proposed cross-layer design provided better performance as compared with the state-of-the-art protocols. Copyright © 2014 John Wiley & Sons, Ltd.

Research paper thumbnail of Channel-Slot Aggregation Diversity Based Slot Reservation Scheme for Cognitive Radio Ad Hoc Networks

International Journal of Distributed Sensor Networks, 2014

In cognitive radio (CR) ad hoc networks, spectrum efficiency and energy efficiency are vitally im... more In cognitive radio (CR) ad hoc networks, spectrum efficiency and energy efficiency are vitally important because spectrum availability is opportunistic in nature and mobile CR nodes usually have limited energy. Aiming to improve network throughput along with improving spectrum and energy efficiencies, this paper proposes a channel-slot aggregation diversity based slot reservation (CADSR) scheme by which each CR node can utilize multiple slots in different channels simultaneously and efficiently utilize the power control mechanism with only a single CR transceiver. The proposed scheme dynamically assigns channel-slots to CR nodes using the diversity technique according to the topology density of the network and the bandwidth requirement, allowing CR nodes to join and leave the network at any time in a distributed way. A dynamic frame length expansion and shrinking scheme has also been introduced that improves the slot utilization. Extensive simulation results show that the proposed mechanism achieves significant performance improvement in network throughput, energy efficiency, and end-to-end delay.

Research paper thumbnail of Dynamic TDMA slot reservation protocol for cognitive radio ad hoc networks

Proceedings of 2010 13th International Conference on Computer and Information Technology, ICCIT 2010, 2010

Abstract In this paper, we propose a dynamic TDMA slot reservation (DTSR) protocol for cognitive ... more Abstract In this paper, we propose a dynamic TDMA slot reservation (DTSR) protocol for cognitive radio ad hoc networks. Quality of Service (QoS) guarantee plays a critically important role in such networks. We consider the problem of providing QoS guarantee to users as well as ...

Research paper thumbnail of Spectrum and energy aware routing protocol for cognitive radio ad hoc networks

IEEE International Conference on Communications, 2011

Abstract Throughput maximization is one of the core challenges in cognitive radio ad hoc networks... more Abstract Throughput maximization is one of the core challenges in cognitive radio ad hoc networks (CRANs), where local spectrum resources are changing over time and locations. This paper proposes a spectrum and energy aware routing (SER) protocol for CRANs, ...

Research paper thumbnail of Spectrum and energy aware multipath routing for cognitive radio ad hoc networks

2014 International Conference on Information and Communication Technology Convergence (ICTC), 2014

Research paper thumbnail of An Energy Efficient Multi-channel MAC Protocol for wireless ad hoc networks

2012 IEEE Global Communications Conference (GLOBECOM), 2012

ABSTRACT This paper presents a TDMA based energy efficient cognitive radio multichannel medium ac... more ABSTRACT This paper presents a TDMA based energy efficient cognitive radio multichannel medium access control (MAC) protocol called ECR-MAC for wireless Ad Hoc Networks. ECR-MAC requires only a single half-duplex radio transceiver on each node that integrates the spectrum sensing at physical (PHY) layer and the packet scheduling at MAC layer. In addition to explicit frequency negotiation which is adopted by conventional multichannel MAC protocols, ECR-MAC introduces lightweight explicit time negotiation. This two-dimensional negotiation enables ECR-MAC to exploit the advantage of both multiple channels and TDMA, and achieve aggressive power savings by allowing nodes that are not involved in communication to go into doze mode. The IEEE 802.11 standard allows for the use of multiple channels available at the PHY layer, but its MAC protocol is designed only for a single channel. A single channel MAC protocol does not work well in a multichannel environment, because of the multichannel hidden terminal problem. The proposed energy efficient ECR-MAC protocol allows SUs to identify and use the unused frequency spectrum in a way that constrains the level of interference to the primary users (PUs). Extensive simulation results show that our proposed ECR-MAC protocol successfully exploits multiple channels and significantly improves network performance by using the licensed spectrum band opportunistically and protects QoS provisioning over cognitive radio ad hoc networks. Comment: 8 Pages, International Journal

Research paper thumbnail of CR-Mac: A Multichannel Mac Protocol for Cognitive Radio Ad Hoc Networks

International journal of Computer Networks & Communications, 2010

This paper proposes a cross-layer based cognitive radio multichannel medium access control (MAC) ... more This paper proposes a cross-layer based cognitive radio multichannel medium access control (MAC) protocol with TDMA, which integrate the spectrum sensing at physical (PHY) layer and the packet scheduling at MAC layer, for the ad hoc wireless networks. The IEEE 802.11 ...

Research paper thumbnail of Energy-aware routing protocol for cognitive radio ad hoc networks

IET Communications, 2012

ABSTRACT Routing is one of the most important issues in multihop ad hoc networks. In the routing ... more ABSTRACT Routing is one of the most important issues in multihop ad hoc networks. In the routing for mobile cognitive radio (CR) networks, the constraints on residual energy of each user and the requirements for primary user protection should be additionally taken into account. This study proposes a spectrum and energy-aware routing (SER) protocol for CR ad hoc networks, which is based on the dynamic source routing. To establish routes on-demand with reserved bandwidth, the protocol involves route selection and channel-timeslot allocation jointly. The proposed SER protocol can balance energy consumption, reduce routing overhead, eliminate contention between nodes and decompose traffics over different channels/timeslots. Extensive simulation shows that the proposed protocol achieves good performance in system throughput, network lifetime and mean message delay.

Research paper thumbnail of A constructive algorithm for feedforward neural networks with incremental training

IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 2002

Research paper thumbnail of A new data mining scheme using artificial neural networks

Sensors (Basel, Switzerland), 2011

Classification is one of the data mining problems receiving enormous attention in the database co... more Classification is one of the data mining problems receiving enormous attention in the database community. Although artificial neural networks (ANNs) have been successfully applied in a wide range of machine learning applications, they are however often regarded as black boxes, i.e., their predictions cannot be explained. To enhance the explanation of ANNs, a novel algorithm to extract symbolic rules from ANNs has been proposed in this paper. ANN methods have not been effectively utilized for data mining tasks because how the classifications were made is not explicitly stated as symbolic rules that are suitable for verification or interpretation by human experts. With the proposed approach, concise symbolic rules with high accuracy, that are easily explainable, can be extracted from the trained ANNs. Extracted rules are comparable with other methods in terms of number of rules, average number of conditions for a rule, and the accuracy. The effectiveness of the proposed approach is cl...

Research paper thumbnail of REx: An Efficient Rule Generator

Research paper thumbnail of Text Classification using Artificial Intelligence