Skip to main content

Abdullah Khan

Universiti Tun Hussein Onn Malaysia, IT, Graduate Student

Followers

145

Following

82

Co-authors

8

Public Views

My name is abdullah qualification is phd in information technology. Belong to pakistan

less

University of Tehran

Kingsborough Community College, CUNY

University of California, Santa Barbara

Harvard University

Microsoft Research

The University of Sheffield

University of Melbourne

Kansas State University

Armando Marques-Guedes

UNL - New University of Lisbon

Stefano R L Campana

University of Siena / Università di Siena

InterestsView All (12)

Uploads

Papers by Abdullah Khan

Bio-inspired Algorithm Optimization of Neural Network for the Prediction of Dubai Crude Oil Price

Previous studies proposed several bio-inspired algorithms for the optimization of Neural Network ... more Previous studies proposed several bio-inspired algorithms for the optimization of Neural Network (NN) to avoid local minima and to improve accuracy and convergence speed. To advance the performance of NN, a new bio-inspired algorithm called Flower Pollination Algorithm (FPA) is used to optimize the weights and bias of NN due to its ability to explore very large search space and frequent chosen of similar solution. The FPA optimized NN (FPNN) was applied to build a model for the prediction of Dubai crude oil price unlike previous studies that mainly focus on the West Texas Intermediate and Brent crude oil price benchmarks. Results suggested that the FPNN was found to improve the convergence speed and accuracy of the cuckoo search algorithm and artificial bee colony optimized NN in the prediction of Dubai crude oil price. The Middle East region that produces a significant amount of crude oil relies on the Dubai crude oil price to benchmark prices for exporting crude oil to Asian count...

MF-Ledger: Blockchain Hyperledger Sawtooth-Enabled Novel and Secure Multimedia Chain of Custody Forensic Investigation Architecture

IEEE Access, 2021

Due to globalization and worldwide connectivity, multimedia data exchange has increased significa... more Due to globalization and worldwide connectivity, multimedia data exchange has increased significantly over the Internet in the last decade. The life cycle of multimedia content is also getting more multifaceted as more people are accessing, sharing, modifying and re-using multimedia information. This poses serious challenges for the multimedia industry to provide integrity, reliability and trustworthiness for multimedia investigations against the growing cybersecurity threats. This paper bridges this gap by enabling a secure and transparent digital forensic investigations process using blockchain technology. MF-Ledger a Blockchain Hyperledger sawtooth-enabled novel, secure and efficient digital forensic investigation architecture is proposed where participating stakeholders create a private network to exchange and agree on different investigation activities before being stored on the blockchain ledger. We have created digital contracts (smart contracts) and implemented them using sequence diagrams to handle the stakeholders' secure interaction in the investigation process. The proposed architectural solution delivers robust information integrity, prevention, and preservation mechanism to permanently and immutably store the evidence (chain of custody) in a private permissioned encrypted blockchain ledger. INDEX TERMS Blockchain, hyperledger sawtooth, smart contracts, digital signatures, digital forensics, evidence chain of custody.

Dynamics of Watermark Position in Audio Watermarked Files using Neural Networks

Applied Mathematics & Information Sciences, 2017

Studying the Effect of Training Levenberg Marquardt Neural Network by Using Hybrid Meta-Heuristic Algorithms

Journal of Computational and Theoretical Nanoscience, 2016

Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the gr... more Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the group of meta-heuristic nature inspired algorithms which provides derivative-free solutions to solve complex problems. Meanwhile, the Levenberg Marquardt Back propagation (LMBP) still it is not able to avoid local minimum. To deal with this problem, global search optimization technique has the ability to adjust the weight for NN (Neural Network) to avoid the local minima problem. This paper proposes an accelerated particle swarm optimization (APSO) is implemented in conjunction with Levenberg Marquardt back propagation (LMBP) algorithms to achieve faster convergence rate and to avoid local minima problem. The performances of the proposed Accelerated Particle Swarm Optimization Levenberg Marquardt (APSO_LM) algorithms compared by means of simulations on 7-Bit Parity and six UCI benchmark classification datasets. The simulation results show that the APSO-LM algorithm shows better performance than baseline algorithms in terms of convergence speed and Mean Squared Error (MSE).

A New Cuckoo Search Based Levenberg-Marquardt (CSLM) Algorithm

Lecture Notes in Computer Science, 2013

ABSTRACT Back propagation neural network (BPNN) algorithm is a widely used technique in training ... more ABSTRACT Back propagation neural network (BPNN) algorithm is a widely used technique in training artificial neural networks. It is also a very popular optimization procedure applied to find optimal weights in a training process. However, traditional back propagation optimized with Levenberg marquardt training algorithm has some drawbacks such as getting stuck in local minima, and network stagnancy. This paper proposed an improved Levenberg-Marquardt back propagation (LMBP) algorithm integrated and trained with Cuckoo Search (CS) algorithm to avoided local minima problem and achieves fast convergence. The performance of the proposed Cuckoo Search Levenberg-Marquardt (CSLM) algorithm is compared with Artificial Bee Colony (ABC) and similar hybrid variants. The simulation results show that the proposed CSLM algorithm performs better than other algorithm used in this study in term of convergence rate and accuracy.

A New Back-Propagation Neural Network Optimized with Cuckoo Search Algorithm

Lecture Notes in Computer Science, 2013

Back-propagation Neural Network (BPNN) algorithm is one of the most widely used and a popular tec... more Back-propagation Neural Network (BPNN) algorithm is one of the most widely used and a popular technique to optimize the feed forward neural network training. Traditional BP algorithm has some drawbacks, such as getting stuck easily in local minima and slow speed of convergence. Nature inspired meta-heuristic algorithms provide derivative-free solution to optimize complex problems. This paper proposed a new meta-heuristic search algorithm, called cuckoo search (CS), based on cuckoo bird's behavior to train BP in achieving fast convergence rate and to avoid local minima problem. The performance of the proposed Cuckoo Search Back-Propagation (CSBP) is compared with artificial bee colony using BP algorithm, and other hybrid variants. Specifically OR and XOR datasets are used. The simulation results show that the computational efficiency of BP training process is highly enhanced when coupled with the proposed hybrid method.

The Effect of Bat Population in Bat-BP Algorithm

Lecture Notes in Electrical Engineering, 2014

ABSTRACT A new metaheuristic based back-propagation algorithm known as Bat-BP is presented in thi... more ABSTRACT A new metaheuristic based back-propagation algorithm known as Bat-BP is presented in this paper. The proposed Bat-BP algorithm successfully solves the problems like slow convergence to global minima and network stagnancy in back-propagation neural network (BPNN) algorithm. In this paper, the bat population is increased from 10 to 500 bats to detect the performance decline or incline in the Bat-BP algorithm by performing simulations on XOR and OR datasets. The simulation results show that the convergence rate to global minimum in Bat-BP is directly proportional with an increase in bats on 2-bit XOR dataset. In case of 3-bit XOR and 4-bit OR datasets, the results deteriorated with an increase in the bat population.

A New Optimized Cuckoo Search Recurrent Neural Network (CSRNN) Algorithm

Lecture Notes in Electrical Engineering, 2014

ABSTRACT Selecting the optimal topology of neural network for a particular application is a diffi... more ABSTRACT Selecting the optimal topology of neural network for a particular application is a difficult task. In case of recurrent neural networks (RNN), most methods only introduce topologies in which their neurons are fully connected. However, recurrent neural network training algorithm has some drawbacks such as getting stuck in local minima, slow speed of convergence and network stagnancy. This paper propose an improved recurrent neural network trained with Cuckoo Search (CS) algorithm to achieve fast convergence and high accuracy. The performance of the proposed Cuckoo Search Recurrent Neural Network (CSRNN) algorithm is compared with Artificial Bee Colony (ABC) and similar hybrid variants. The simulation results show that the proposed CSRNN algorithm performs better than other algorithms used in this study in terms of convergence rate and accuracy.

A New Levenberg Marquardt based Back Propagation Algorithm Trained with Cuckoo Search

Procedia Technology, 2013

Back propagation training algorithm is widely used techniques in artificial neural network and is... more Back propagation training algorithm is widely used techniques in artificial neural network and is also very popular optimization task in finding an optimal weight sets during the training process. However, traditional back propagation algorithms have some drawbacks such as getting stuck in local minimum and slow speed of convergence. This research proposed an improved Levenberg Marquardt (LM) based back propagation (BP) trained with Cuckoo search algorithm for fast and improved convergence speed of the hybrid neural networks learning method. The performance of the proposed algorithm is compared with Artificial Bee Colony (ABC) and the other hybridized procedure of its kind. The simulation outcomes show that the proposed algorithm performed better than other algorithm used in this study in term of convergence speed and rate.

CSLM: Levenberg Marquardt based Back Propagation Algorithm Optimized with Cuckoo Search

Journal of ICT Research and Applications, 2013

Training an artificial neural network is an optimization task, since it is desired to find optima... more Training an artificial neural network is an optimization task, since it is desired to find optimal weight sets for a neural network during training process. Traditional training algorithms such as back propagation have some drawbacks such as getting stuck in local minima and slow speed of convergence. This study combines the best features of two algorithms; i.e. Levenberg Marquardt back propagation (LMBP) and Cuckoo Search (CS) for improving the convergence speed of artificial neural networks (ANN) training. The proposed CSLM algorithm is trained on XOR and OR datasets. The experimental results show that the proposed CSLM algorithm has better performance than other similar hybrid variants used in this study.

Countering the Problem of Oscillations in Bat-BP Gradient Trajectory by Using Momentum

Lecture Notes in Electrical Engineering, 2013

Metaheuristic techniques have been recently used to counter the problems like slow convergence to... more Metaheuristic techniques have been recently used to counter the problems like slow convergence to global minima and network stagnancy in backpropagation neural network (BPNN) algorithm. Previously, a meta-heuristic search algorithm called Bat was proposed to train BPNN to achieve fast convergence in the neural network. Although, Bat-BP algorithm achieved fast convergence but it had a problem of oscillations in the gradient path, which can lead to sub-optimal solutions. In-order to remove oscillations in the BAT-BP algorithm, this paper proposed the addition of momentum coefficient to the weights update in the Bat-BP algorithm. The performance of the modified Bat-BP algorithm is compared with simple Bat-BP algorithm on XOR and OR datasets. The simulation results show that the convergence rate to global minimum in modified Bat-BP is highly enhanced and the oscillations are greatly reduced in the gradient path.

Hybrid Bat-BP: A New Intelligent Tool for Diagnosing Noise-Induced Hearing Loss (NIHL) in Malaysian Industrial Workers

Applied Mechanics and Materials, 2013

Noise-Induced Hearing Loss (NIHL) has become a major health threat to the Malaysian industrial wo... more Noise-Induced Hearing Loss (NIHL) has become a major health threat to the Malaysian industrial workers in the recent era due to exposure to high frequency noise produced by the heavy machines. Recently, many studies have been conducted to diagnose the NIHL in industrial workers but unfortunately they neglected some factors that can play a major role in speeding-up NIHL. In this paper, a new Hybrid Bat-BP algorithm which is based on the trio combination of BAT based metaheuristic optimization, back-propagation neural network, and fuzzy logic is proposed to diagnose NIHL in Malaysian industrial workers. The proposed Hybrid Bat-BP will use heat, body mass index (BMI), diabetes, and smoking along with the century old audiometric variables (i.e. age, frequency, and duration of exposure) to better predict NIHL in Malaysian workers. The results obtained through Hybrid Bat-BP will be able to help us identify and reduce the NIHL rate in the workers with high accuracy.

Improving the Accuracy of Gradient Descent Back Propagation Algorithm (GDAM) on Classification Problems

International Journal of New Computer Architectures and their Applications (IJNCAA), Sep 7, 2012

The traditional Back-propagation Neural Network (BPNN) Algorithm is widely used in solving many r... more The traditional Back-propagation Neural Network (BPNN) Algorithm is widely used in solving many real time problems in world. But BPNN possesses a problem of slow convergence and convergence to local minima. Previously, several modifications are suggested to improve the convergence rate of Gradient Descent Back-propagation algorithm such as careful selection of initial weights and biases, learning rate, momentum, network topology, activation function and 'gain'value in the activation function. This research ...

The Effect of Data Pre-processing on Optimized Training of Artificial Neural Networks

Procedia Technology, 2013

Recently, the popularity of artificial neural networks (ANN) is increasing since its capacity to ... more Recently, the popularity of artificial neural networks (ANN) is increasing since its capacity to model very complex problems in the area of Machine Learning, Data Mining and Pattern Recognition. Improving training efficacy of ANN based algorithm is a dynamic area of research and several papers have been reviewed in the literature. The performance of Multi-layer Perceptrons (MLP) trained with Back Propagation Artificial Neural Network (BP-ANN) method is highly influenced by the size of the datasets and the data-preprocessing techniques used. This work analyses the benefits of using pre-processing datasets using different techniques in-order to improve the ANN convergence. Specifically Min-Max, Z-Score and Decimal Scaling Normalization preprocessing techniques were evaluated. The simulation results show that the computational efficiency of ANN training process is highly enhanced when coupled with different preprocessing techniques.

Patterns of trade among Muslim countries

Pide Working Papers, 1977

Impact of Employment Agglomeration on Patented Innovation in U.S. Manufacturing Industries from 1986 to 2008

International Journal of Business and Social Research, Oct 30, 2014

This paper examines impact of employment agglomeration in fifteen U.S. manufacturing industries o... more This paper examines impact of employment agglomeration in fifteen U.S. manufacturing industries on their innovation activities measured by patent count. A count data model is employed in regressing patent count on employment agglomeration measures, measure of scale, and some control variables. Measures of employment agglomeration and market concentration are found to have negative impacts on innovation in U.S. manufacturing industries. Two agglomeration proxies -Gini index and Ellison-Glaeser index have a negative influence on U.S. patented innovation for the study period. This result implies that the external benefit of spatial agglomeration of similar firms has waned down. The impact of market concentration is also found to be a negative factor for innovation. This result implies that firms with larger plant size are less innovative than those with smaller plant size. Impact of 'share of workers with post graduate degrees' on innovation was found to be a positive but statistically not significant factor for innovation. The 'goods pooling' determinant displayed negative influence on innovation. These results are mostly consistent across fifteen manufacturing subsectors. Rising energy cost is found to be one of the most significant deterrents of innovation whereas, ethnic diversity is found to be a significant facilitator of it. Results of this research lend support in favor of regional economic development policies that promote coagglomeration of various interdependent and complementary industries and small scale industries, and supports ethnic diversity to spur innovation in U.S. manufacturing industries.

Primary perisplenic hydatid cyst

Journal of the College of Physicians and Surgeons Pakistan Jcpsp, Jul 1, 2009

1. J Coll Physicians Surg Pak. 2009 Jun;19(6):380-2. Primary perisplenic hydatid cyst. Sharif MA,... more

Access to Health CareA Conceptual Framework and its Relevance to Health Care Planning

Eval Health Prof, 1994

Despite some serious past efforts to clarify its multiple dimensions and meanings, access to heal... more Despite some serious past efforts to clarify its multiple dimensions and meanings, access to health care has remained a rather elusive concept, hampering the work of health care policymakers and professionals as they endeavor to effect meaningful health care reform. This article provides perhaps the most detailed clarification of the access concept, especially the crucial linkages among the various access dimensions, and presents a comprehensive conceptual framework for evaluation and planning activities as they relate to people&#39;s access to health care services. The proposed conceptual model recognizes access as the outcome of a process involving the interplay between the characteristics of the health care service system and of potential users in a specified area, and moderated by health care related public policy and planning efforts. An elaborate typology of access, incorporating four pairs of access dimensions, is also derived. This atomization of the concept allows us to focus on specific aspects of the access to health care problem, and to develop precise outcome indicators of health system performance for evaluative purposes. Further, it enables the access concept and its pertinent dimensions to be put into proper perspective when assessing the health care access situation in a specific national or regional context. The relevance of the proposed access model and the typology to health care planning in general, and to spatial planning of health care service systems in particular, is also discussed.

Weight Optimization in Recurrent Neural Networks with Hybrid Metaheuristic Cuckoo Search Techniques for Data Classification

Mathematical Problems in Engineering, 2015

Recurrent neural network (RNN) has been widely used as a tool in the data classification. This ne... more Recurrent neural network (RNN) has been widely used as a tool in the data classification. This network can be educated with gradient descent back propagation. However, traditional training algorithms have some drawbacks such as slow speed of convergence being not definite to find the global minimum of the error function since gradient descent may get stuck in local minima. As a solution, nature inspired metaheuristic algorithms provide derivative-free solution to optimize complex problems. This paper proposes a new metaheuristic search algorithm called Cuckoo Search (CS) based on Cuckoo bird's behavior to train Elman recurrent network (ERN) and back propagation Elman recurrent network (BPERN) in achieving fast convergence rate and to avoid local minima problem. The proposed CSERN and CSBPERN algorithms are compared with artificial bee colony using BP algorithm and other hybrid variants algorithms. Specifically, some selected benchmark classification problems are used. The simulation results show that the computational efficiency of ERN and BPERN training process is highly enhanced when coupled with the proposed hybrid method.

Allergic broncho-pulmonary aspergillosis presenting as flitting opacities on chest radiograph

Journal of the College of Physicians and Surgeons--Pakistan: JCPSP

A aspergilose broncopulmonar alérgica é uma doença pulmonar que ocorre em pacientes com asma ou f... more A aspergilose broncopulmonar alérgica é uma doença pulmonar que ocorre em pacientes com asma ou fibrose cística, desencadeada pela reação de hipersensibilidade à presença do fungo Aspergilus fumigatus nas vias aéreas. Relatamos aqui um caso em que uma paciente com quadro clínico sugestivo de asma apresentou critérios clínicos, laboratoriais e radiológicos compatíveis com o diagnóstico de aspergilose broncopulmonar alérgica. A importância de tais achados deve-se ao fato de que quanto mais precocemente for feito o diagnóstico, menores serão os riscos de agravamento do quadro respiratório e de aparecimento de fibrose.

Bio-inspired Algorithm Optimization of Neural Network for the Prediction of Dubai Crude Oil Price

Previous studies proposed several bio-inspired algorithms for the optimization of Neural Network ... more Previous studies proposed several bio-inspired algorithms for the optimization of Neural Network (NN) to avoid local minima and to improve accuracy and convergence speed. To advance the performance of NN, a new bio-inspired algorithm called Flower Pollination Algorithm (FPA) is used to optimize the weights and bias of NN due to its ability to explore very large search space and frequent chosen of similar solution. The FPA optimized NN (FPNN) was applied to build a model for the prediction of Dubai crude oil price unlike previous studies that mainly focus on the West Texas Intermediate and Brent crude oil price benchmarks. Results suggested that the FPNN was found to improve the convergence speed and accuracy of the cuckoo search algorithm and artificial bee colony optimized NN in the prediction of Dubai crude oil price. The Middle East region that produces a significant amount of crude oil relies on the Dubai crude oil price to benchmark prices for exporting crude oil to Asian count...

MF-Ledger: Blockchain Hyperledger Sawtooth-Enabled Novel and Secure Multimedia Chain of Custody Forensic Investigation Architecture

IEEE Access, 2021

Due to globalization and worldwide connectivity, multimedia data exchange has increased significa... more Due to globalization and worldwide connectivity, multimedia data exchange has increased significantly over the Internet in the last decade. The life cycle of multimedia content is also getting more multifaceted as more people are accessing, sharing, modifying and re-using multimedia information. This poses serious challenges for the multimedia industry to provide integrity, reliability and trustworthiness for multimedia investigations against the growing cybersecurity threats. This paper bridges this gap by enabling a secure and transparent digital forensic investigations process using blockchain technology. MF-Ledger a Blockchain Hyperledger sawtooth-enabled novel, secure and efficient digital forensic investigation architecture is proposed where participating stakeholders create a private network to exchange and agree on different investigation activities before being stored on the blockchain ledger. We have created digital contracts (smart contracts) and implemented them using sequence diagrams to handle the stakeholders' secure interaction in the investigation process. The proposed architectural solution delivers robust information integrity, prevention, and preservation mechanism to permanently and immutably store the evidence (chain of custody) in a private permissioned encrypted blockchain ledger. INDEX TERMS Blockchain, hyperledger sawtooth, smart contracts, digital signatures, digital forensics, evidence chain of custody.

Dynamics of Watermark Position in Audio Watermarked Files using Neural Networks

Applied Mathematics & Information Sciences, 2017

Studying the Effect of Training Levenberg Marquardt Neural Network by Using Hybrid Meta-Heuristic Algorithms

Journal of Computational and Theoretical Nanoscience, 2016

Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the gr... more Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the group of meta-heuristic nature inspired algorithms which provides derivative-free solutions to solve complex problems. Meanwhile, the Levenberg Marquardt Back propagation (LMBP) still it is not able to avoid local minimum. To deal with this problem, global search optimization technique has the ability to adjust the weight for NN (Neural Network) to avoid the local minima problem. This paper proposes an accelerated particle swarm optimization (APSO) is implemented in conjunction with Levenberg Marquardt back propagation (LMBP) algorithms to achieve faster convergence rate and to avoid local minima problem. The performances of the proposed Accelerated Particle Swarm Optimization Levenberg Marquardt (APSO_LM) algorithms compared by means of simulations on 7-Bit Parity and six UCI benchmark classification datasets. The simulation results show that the APSO-LM algorithm shows better performance than baseline algorithms in terms of convergence speed and Mean Squared Error (MSE).

A New Cuckoo Search Based Levenberg-Marquardt (CSLM) Algorithm

Lecture Notes in Computer Science, 2013

ABSTRACT Back propagation neural network (BPNN) algorithm is a widely used technique in training ... more ABSTRACT Back propagation neural network (BPNN) algorithm is a widely used technique in training artificial neural networks. It is also a very popular optimization procedure applied to find optimal weights in a training process. However, traditional back propagation optimized with Levenberg marquardt training algorithm has some drawbacks such as getting stuck in local minima, and network stagnancy. This paper proposed an improved Levenberg-Marquardt back propagation (LMBP) algorithm integrated and trained with Cuckoo Search (CS) algorithm to avoided local minima problem and achieves fast convergence. The performance of the proposed Cuckoo Search Levenberg-Marquardt (CSLM) algorithm is compared with Artificial Bee Colony (ABC) and similar hybrid variants. The simulation results show that the proposed CSLM algorithm performs better than other algorithm used in this study in term of convergence rate and accuracy.

A New Back-Propagation Neural Network Optimized with Cuckoo Search Algorithm

Lecture Notes in Computer Science, 2013

Back-propagation Neural Network (BPNN) algorithm is one of the most widely used and a popular tec... more Back-propagation Neural Network (BPNN) algorithm is one of the most widely used and a popular technique to optimize the feed forward neural network training. Traditional BP algorithm has some drawbacks, such as getting stuck easily in local minima and slow speed of convergence. Nature inspired meta-heuristic algorithms provide derivative-free solution to optimize complex problems. This paper proposed a new meta-heuristic search algorithm, called cuckoo search (CS), based on cuckoo bird's behavior to train BP in achieving fast convergence rate and to avoid local minima problem. The performance of the proposed Cuckoo Search Back-Propagation (CSBP) is compared with artificial bee colony using BP algorithm, and other hybrid variants. Specifically OR and XOR datasets are used. The simulation results show that the computational efficiency of BP training process is highly enhanced when coupled with the proposed hybrid method.

The Effect of Bat Population in Bat-BP Algorithm

Lecture Notes in Electrical Engineering, 2014

ABSTRACT A new metaheuristic based back-propagation algorithm known as Bat-BP is presented in thi... more ABSTRACT A new metaheuristic based back-propagation algorithm known as Bat-BP is presented in this paper. The proposed Bat-BP algorithm successfully solves the problems like slow convergence to global minima and network stagnancy in back-propagation neural network (BPNN) algorithm. In this paper, the bat population is increased from 10 to 500 bats to detect the performance decline or incline in the Bat-BP algorithm by performing simulations on XOR and OR datasets. The simulation results show that the convergence rate to global minimum in Bat-BP is directly proportional with an increase in bats on 2-bit XOR dataset. In case of 3-bit XOR and 4-bit OR datasets, the results deteriorated with an increase in the bat population.

A New Optimized Cuckoo Search Recurrent Neural Network (CSRNN) Algorithm

Lecture Notes in Electrical Engineering, 2014

ABSTRACT Selecting the optimal topology of neural network for a particular application is a diffi... more ABSTRACT Selecting the optimal topology of neural network for a particular application is a difficult task. In case of recurrent neural networks (RNN), most methods only introduce topologies in which their neurons are fully connected. However, recurrent neural network training algorithm has some drawbacks such as getting stuck in local minima, slow speed of convergence and network stagnancy. This paper propose an improved recurrent neural network trained with Cuckoo Search (CS) algorithm to achieve fast convergence and high accuracy. The performance of the proposed Cuckoo Search Recurrent Neural Network (CSRNN) algorithm is compared with Artificial Bee Colony (ABC) and similar hybrid variants. The simulation results show that the proposed CSRNN algorithm performs better than other algorithms used in this study in terms of convergence rate and accuracy.

A New Levenberg Marquardt based Back Propagation Algorithm Trained with Cuckoo Search

Procedia Technology, 2013

Back propagation training algorithm is widely used techniques in artificial neural network and is... more Back propagation training algorithm is widely used techniques in artificial neural network and is also very popular optimization task in finding an optimal weight sets during the training process. However, traditional back propagation algorithms have some drawbacks such as getting stuck in local minimum and slow speed of convergence. This research proposed an improved Levenberg Marquardt (LM) based back propagation (BP) trained with Cuckoo search algorithm for fast and improved convergence speed of the hybrid neural networks learning method. The performance of the proposed algorithm is compared with Artificial Bee Colony (ABC) and the other hybridized procedure of its kind. The simulation outcomes show that the proposed algorithm performed better than other algorithm used in this study in term of convergence speed and rate.

CSLM: Levenberg Marquardt based Back Propagation Algorithm Optimized with Cuckoo Search

Journal of ICT Research and Applications, 2013

Training an artificial neural network is an optimization task, since it is desired to find optima... more Training an artificial neural network is an optimization task, since it is desired to find optimal weight sets for a neural network during training process. Traditional training algorithms such as back propagation have some drawbacks such as getting stuck in local minima and slow speed of convergence. This study combines the best features of two algorithms; i.e. Levenberg Marquardt back propagation (LMBP) and Cuckoo Search (CS) for improving the convergence speed of artificial neural networks (ANN) training. The proposed CSLM algorithm is trained on XOR and OR datasets. The experimental results show that the proposed CSLM algorithm has better performance than other similar hybrid variants used in this study.

Countering the Problem of Oscillations in Bat-BP Gradient Trajectory by Using Momentum

Lecture Notes in Electrical Engineering, 2013

Metaheuristic techniques have been recently used to counter the problems like slow convergence to... more Metaheuristic techniques have been recently used to counter the problems like slow convergence to global minima and network stagnancy in backpropagation neural network (BPNN) algorithm. Previously, a meta-heuristic search algorithm called Bat was proposed to train BPNN to achieve fast convergence in the neural network. Although, Bat-BP algorithm achieved fast convergence but it had a problem of oscillations in the gradient path, which can lead to sub-optimal solutions. In-order to remove oscillations in the BAT-BP algorithm, this paper proposed the addition of momentum coefficient to the weights update in the Bat-BP algorithm. The performance of the modified Bat-BP algorithm is compared with simple Bat-BP algorithm on XOR and OR datasets. The simulation results show that the convergence rate to global minimum in modified Bat-BP is highly enhanced and the oscillations are greatly reduced in the gradient path.

Hybrid Bat-BP: A New Intelligent Tool for Diagnosing Noise-Induced Hearing Loss (NIHL) in Malaysian Industrial Workers

Applied Mechanics and Materials, 2013

Noise-Induced Hearing Loss (NIHL) has become a major health threat to the Malaysian industrial wo... more Noise-Induced Hearing Loss (NIHL) has become a major health threat to the Malaysian industrial workers in the recent era due to exposure to high frequency noise produced by the heavy machines. Recently, many studies have been conducted to diagnose the NIHL in industrial workers but unfortunately they neglected some factors that can play a major role in speeding-up NIHL. In this paper, a new Hybrid Bat-BP algorithm which is based on the trio combination of BAT based metaheuristic optimization, back-propagation neural network, and fuzzy logic is proposed to diagnose NIHL in Malaysian industrial workers. The proposed Hybrid Bat-BP will use heat, body mass index (BMI), diabetes, and smoking along with the century old audiometric variables (i.e. age, frequency, and duration of exposure) to better predict NIHL in Malaysian workers. The results obtained through Hybrid Bat-BP will be able to help us identify and reduce the NIHL rate in the workers with high accuracy.

Improving the Accuracy of Gradient Descent Back Propagation Algorithm (GDAM) on Classification Problems

International Journal of New Computer Architectures and their Applications (IJNCAA), Sep 7, 2012

The traditional Back-propagation Neural Network (BPNN) Algorithm is widely used in solving many r... more The traditional Back-propagation Neural Network (BPNN) Algorithm is widely used in solving many real time problems in world. But BPNN possesses a problem of slow convergence and convergence to local minima. Previously, several modifications are suggested to improve the convergence rate of Gradient Descent Back-propagation algorithm such as careful selection of initial weights and biases, learning rate, momentum, network topology, activation function and 'gain'value in the activation function. This research ...

The Effect of Data Pre-processing on Optimized Training of Artificial Neural Networks

Procedia Technology, 2013

Recently, the popularity of artificial neural networks (ANN) is increasing since its capacity to ... more Recently, the popularity of artificial neural networks (ANN) is increasing since its capacity to model very complex problems in the area of Machine Learning, Data Mining and Pattern Recognition. Improving training efficacy of ANN based algorithm is a dynamic area of research and several papers have been reviewed in the literature. The performance of Multi-layer Perceptrons (MLP) trained with Back Propagation Artificial Neural Network (BP-ANN) method is highly influenced by the size of the datasets and the data-preprocessing techniques used. This work analyses the benefits of using pre-processing datasets using different techniques in-order to improve the ANN convergence. Specifically Min-Max, Z-Score and Decimal Scaling Normalization preprocessing techniques were evaluated. The simulation results show that the computational efficiency of ANN training process is highly enhanced when coupled with different preprocessing techniques.

Patterns of trade among Muslim countries

Pide Working Papers, 1977

Impact of Employment Agglomeration on Patented Innovation in U.S. Manufacturing Industries from 1986 to 2008

International Journal of Business and Social Research, Oct 30, 2014

This paper examines impact of employment agglomeration in fifteen U.S. manufacturing industries o... more This paper examines impact of employment agglomeration in fifteen U.S. manufacturing industries on their innovation activities measured by patent count. A count data model is employed in regressing patent count on employment agglomeration measures, measure of scale, and some control variables. Measures of employment agglomeration and market concentration are found to have negative impacts on innovation in U.S. manufacturing industries. Two agglomeration proxies -Gini index and Ellison-Glaeser index have a negative influence on U.S. patented innovation for the study period. This result implies that the external benefit of spatial agglomeration of similar firms has waned down. The impact of market concentration is also found to be a negative factor for innovation. This result implies that firms with larger plant size are less innovative than those with smaller plant size. Impact of 'share of workers with post graduate degrees' on innovation was found to be a positive but statistically not significant factor for innovation. The 'goods pooling' determinant displayed negative influence on innovation. These results are mostly consistent across fifteen manufacturing subsectors. Rising energy cost is found to be one of the most significant deterrents of innovation whereas, ethnic diversity is found to be a significant facilitator of it. Results of this research lend support in favor of regional economic development policies that promote coagglomeration of various interdependent and complementary industries and small scale industries, and supports ethnic diversity to spur innovation in U.S. manufacturing industries.

Primary perisplenic hydatid cyst

Journal of the College of Physicians and Surgeons Pakistan Jcpsp, Jul 1, 2009

1. J Coll Physicians Surg Pak. 2009 Jun;19(6):380-2. Primary perisplenic hydatid cyst. Sharif MA,... more

Access to Health CareA Conceptual Framework and its Relevance to Health Care Planning

Eval Health Prof, 1994

Despite some serious past efforts to clarify its multiple dimensions and meanings, access to heal... more Despite some serious past efforts to clarify its multiple dimensions and meanings, access to health care has remained a rather elusive concept, hampering the work of health care policymakers and professionals as they endeavor to effect meaningful health care reform. This article provides perhaps the most detailed clarification of the access concept, especially the crucial linkages among the various access dimensions, and presents a comprehensive conceptual framework for evaluation and planning activities as they relate to people&#39;s access to health care services. The proposed conceptual model recognizes access as the outcome of a process involving the interplay between the characteristics of the health care service system and of potential users in a specified area, and moderated by health care related public policy and planning efforts. An elaborate typology of access, incorporating four pairs of access dimensions, is also derived. This atomization of the concept allows us to focus on specific aspects of the access to health care problem, and to develop precise outcome indicators of health system performance for evaluative purposes. Further, it enables the access concept and its pertinent dimensions to be put into proper perspective when assessing the health care access situation in a specific national or regional context. The relevance of the proposed access model and the typology to health care planning in general, and to spatial planning of health care service systems in particular, is also discussed.

Weight Optimization in Recurrent Neural Networks with Hybrid Metaheuristic Cuckoo Search Techniques for Data Classification

Mathematical Problems in Engineering, 2015

Recurrent neural network (RNN) has been widely used as a tool in the data classification. This ne... more Recurrent neural network (RNN) has been widely used as a tool in the data classification. This network can be educated with gradient descent back propagation. However, traditional training algorithms have some drawbacks such as slow speed of convergence being not definite to find the global minimum of the error function since gradient descent may get stuck in local minima. As a solution, nature inspired metaheuristic algorithms provide derivative-free solution to optimize complex problems. This paper proposes a new metaheuristic search algorithm called Cuckoo Search (CS) based on Cuckoo bird's behavior to train Elman recurrent network (ERN) and back propagation Elman recurrent network (BPERN) in achieving fast convergence rate and to avoid local minima problem. The proposed CSERN and CSBPERN algorithms are compared with artificial bee colony using BP algorithm and other hybrid variants algorithms. Specifically, some selected benchmark classification problems are used. The simulation results show that the computational efficiency of ERN and BPERN training process is highly enhanced when coupled with the proposed hybrid method.

Allergic broncho-pulmonary aspergillosis presenting as flitting opacities on chest radiograph

Journal of the College of Physicians and Surgeons--Pakistan: JCPSP

A aspergilose broncopulmonar alérgica é uma doença pulmonar que ocorre em pacientes com asma ou f... more A aspergilose broncopulmonar alérgica é uma doença pulmonar que ocorre em pacientes com asma ou fibrose cística, desencadeada pela reação de hipersensibilidade à presença do fungo Aspergilus fumigatus nas vias aéreas. Relatamos aqui um caso em que uma paciente com quadro clínico sugestivo de asma apresentou critérios clínicos, laboratoriais e radiológicos compatíveis com o diagnóstico de aspergilose broncopulmonar alérgica. A importância de tais achados deve-se ao fato de que quanto mais precocemente for feito o diagnóstico, menores serão os riscos de agravamento do quadro respiratório e de aparecimento de fibrose.