List of Titles

A hierarchical method for finding optimal architecture and weights using evolutionary least square based learning

- Ghosh, Ranadhir, Verma, Brijesh

Authors: Ghosh, Ranadhir , Verma, Brijesh
Date: 2003
Type: Text , Journal article
Relation: International Journal of Neural Systems Vol. 13, no. 1 (2003), p. 13-24
Full Text: false
Reviewed:
Description: In this paper, we present a novel approach of implementing a combination methodology to find appropriate neural network architecture and weights using an evolutionary least square based algorithm (GALS).1 This paper focuses on aspects such as the heuristics of updating weights using an evolutionary least square based algorithm, finding the number of hidden neurons for a two layer feed forward neural network, the stopping criterion for the algorithm and finally some comparisons of the results with other existing methods for searching optimal or near optimal solution in the multidimensional complex search space comprising the architecture and the weight variables. We explain how the weight updating algorithm using evolutionary least square based approach can be combined with the growing architecture model to find the optimum number of hidden neurons. We also discuss the issues of finding a probabilistic solution space as a starting point for the least square method and address the problems involving fitness breaking. We apply the proposed approach to XOR problem, 10 bit odd parity problem and many real-world benchmark data sets such as handwriting data set from CEDAR, breast cancer and heart disease data sets from UCI ML repository. The comparative results based on classification accuracy and the time complexity are discussed.
Description: 2003004100

An AI-enabled lightweight data fusion and load optimization approach for internet of things

- Jan, Mian, Zakarya, Muhammad, Khan, Muhammad, Mastorakis, Spyridon, Balasubramanian, Venki

Authors: Jan, Mian , Zakarya, Muhammad , Khan, Muhammad , Mastorakis, Spyridon , Balasubramanian, Venki
Date: 2021
Type: Text , Journal article
Relation: Future Generation Computer Systems Vol. 122, no. (2021), p. 40-51
Full Text: false
Reviewed:
Description: In the densely populated Internet of Things (IoT) applications, sensing range of the nodes might overlap frequently. In these applications, the nodes gather highly correlated and redundant data in their vicinity. Processing these data depletes the energy of nodes and their upstream transmission towards remote datacentres, in the fog infrastructure, may result in an unbalanced load at the network gateways and edge servers. Due to heterogeneity of edge servers, few of them might be overwhelmed while others may remain less-utilized. As a result, time-critical and delay-sensitive applications may experience excessive delays, packet loss, and degradation in their Quality of Service (QoS). To ensure QoS of IoT applications, in this paper, we eliminate correlation in the gathered data via a lightweight data fusion approach. The buffer of each node is partitioned into strata that broadcast only non-correlated data to edge servers via the network gateways. Furthermore, we propose a dynamic service migration technique to reconfigure the load across various edge servers. We assume this as an optimization problem and use two meta-heuristic algorithms, along with a migration approach, to maintain an optimal Gateway-Edge configuration in the network. These algorithms monitor the load at each server, and once it surpasses a threshold value (which is dynamically computed with a simple machine learning method), an exhaustive search is performed for an optimal and balanced periodic reconfiguration. The experimental results of our approach justify its efficiency for large-scale and densely populated IoT applications. © 2021 Elsevier B.V. *Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Venki Balasubramanian” is provided in this record**.

Decoupled modeling of gene regulatory networks using Michaelis-Menten kinetics

- Youseph, Ahammed, Chetty, Madhu, Karmakar, Gour

Authors: Youseph, Ahammed , Chetty, Madhu , Karmakar, Gour
Date: 2015
Type: Text , Conference proceedings
Full Text: false
Description: A set of genes and their regulatory interactions are represented in a gene regulatory network (GRN). Since GRNs play a major role in maintaining the cellular activities, inferring these networks is significant for understanding biological processes. Among the models available for GRN reconstruction, our recently developed nonlinear model [1] using Michaelis-Menten kinetics is considered to be more biologically relevant. However, the model remains coupled in the current form making the process computationally expensive, especially for large GRNs. In this paper, we enhance the existing model leading to a decoupled form which not only speeds up the computation, but also makes the model more realistic by representing the strength of each regulatory arc by a distinct Michaelis-Menten constant. The parameter estimation is carried out using differential evolution algorithm. The model is validated by inferring two synthetic networks. Results show that while the accuracy of reconstruction is similar to the coupled model, they are achieved at a faster speed. Â© Springer International Publishing Switzerland 2015.

Multimodal memetic framework for low-resolution protein structure prediction

- Nazmul, Rumana, Chetty, Madhu, Chowdhury, Ashan

Authors: Nazmul, Rumana , Chetty, Madhu , Chowdhury, Ashan
Date: 2020
Type: Text , Journal article
Relation: Swarm and Evolutionary Computation Vol. 52, no. (Feb 2020), p. 14
Full Text: false
Reviewed:
Description: In this paper, we propose a systematic design of evolutionary optimization, namely Multimodal Memetic Framework (MMF), to effectively search the vast complex energy landscape. Our proposed memetic framework is implemented in hierarchical stages with the optimization of each stage performed in parallel in three different states: Exploratory, Exploitative and Central. Each state, with its own set of sub-populations, either explores or exploits by beneficial mixing of potential solutions to direct the search towards a global solution. Instead of implementing identical genetic operators, the proposed approach employs different selection and survival criteria in each state according to their designated task. The Exploratory state employs a knowledge-based initial population generation technique with appropriately tuned genetic operators to guide the search to the "nearest peak". The Exploitative state fine-tunes the individuals representing different regions by applying a building block based local search. Finally, by utilizing the imbibed knowledge from different peaks, the Central state carries out information-exchange among the highly fit solutions for exploring the undiscovered regions. The information exchange employs a novel non-random parental selection technique to distribute the reproduction opportunity intelligently among the individuals for making cross-over more effective. The method has been tested on a set of various benchmark protein sequences for 2D and 3D lattice models. The experimental results demonstrate the superiority of the proposed method over other state-of-the-art algorithms.

Convergence of elitist clonal selection algorithm based on martingale theory

- Hong, Lu, Kamruzzaman, Joarder

Authors: Hong, Lu , Kamruzzaman, Joarder
Date: 2013
Type: Text , Journal article
Relation: Engineering Letters Vol. 21, no. 4 (2013), p. 181-184
Full Text: false
Reviewed:
Description: In recent years, progress has been made in the analysis of global convergence of clonal selection algorithms (CSA), but most analyses are based on the theory of Markov chain, which depend on the description of the transition matrix and eigenvalues. However, such analyses are very complicated, especially when the population size is large, and are presented for particular implementations of CSA. In this paper, instead of the traditional Markov chain theory, we introduce martingale theory to prove the convergence of a class of CSA, called elitist clonal selection algorithm (ECSA). Using the submartingale convergence theorem, the best individual affinity evolutionary sequence is described as a submartingale, and the almost everywhere convergence of ECSA is derived. Particularly, the algorithm is proved convergent with probability 1 in finite steps when the state space of population is finite. This new proof of global convergence analysis of ECSA is more simplified and effective, and not implementation specific.

Showing items 1 - 5 of 5