Automatic classification of electrocardiogram (ECG) signals is important for diagnosing heart arrhythmias. A big challenge in automatic ECG classification is the variation in the waveforms and characteristics of ECG signals among different patients. To address this issue, this paper proposes adapting a patient-independent deep neural network (DNN) using the information in the patient-dependent identity vectors (i-vectors). The adapted networks, namely i-vector adapted patient-specific DNNs (iAP-DNNs), are tuned toward the ECG characteristics of individual patients. For each patient, his/her ECG waveforms are compressed into an i-vector using a factor analysis model. Then, this i-vector is injected into the middle hidden layer of the patient-independent DNN. Stochastic gradient descent is then applied to fine-tune the whole network to form a patient-specific classifier. As a result, the adaptation makes use of not only the raw ECG waveforms from the specific patient but also the compact representation of his/her ECG characteristics through the i-vector. Analysis on the hidden-layer activations shows that by leveraging the information in the i-vectors, the iAP-DNNs are more capable of discriminating normal heartbeats against arrhythmic heartbeats than the networks that use the patient-specific ECG only for the adaptation. Experimental results based on the MIT-BIH database suggest that the iAP-DNNs perform better than existing patient-specific classifiers in terms of various performance measures. In particular, the sensitivity and specificity of the existing methods are all under the receiver operating characteristic curves of the iAP-DNNs.

This paper proposes deep learning methods with signal alignment that facilitate the end-to-end classification of raw electrocardiogram (ECG) signals into heartbeat types, i.e., normal beat or different types of arrhythmias. Time-domain sample points are extracted from raw ECG signals, and consecutive vectors are extracted from a sliding time-window covering these sample points. Each of these vectors comprises the consecutive sample points of a complete heartbeat cycle, which includes not only the QRS complex but also the P and T waves. Unlike existing heartbeat classification methods in which medical doctors extract handcrafted features from raw ECG signals, the proposed end-to-end method leverages a deep neural network for both feature extraction and classification based on aligned heartbeats. This strategy not only obviates the need to handcraft the features but also produces optimized ECG representation for heartbeat classification. Evaluations on the MIT-BIH arrhythmia database show that at the same specificity, the proposed patient-independent classifier can detect supraventricular- and ventricular-ectopic beats at a sensitivity that is at least 10% higher than current state-of-the-art methods. More importantly, there is a wide range of operating points in which both the sensitivity and specificity of the proposed classifier are higher than those achieved by state-of-the-art classifiers. The proposed classifier can also perform comparable to patient-specific classifiers, but at the same time enjoys the advantage of patient independence.

It have been proved that LoRa networks are suitable to do the localization for outdoor environment [1] [2]. Through the performance investigation in simulation models and real experiments, it showed that the performance of RSSI-based LoRa localization algorithms in [1] is compatible to The Global Positioning System (GPS), the most popular outdoor localization system. However, in very noisy outdoor environment, the performance of the algorithms degrades significantly because the effect of noisy nodes (anchor nodes that are highly affected by noise) cannot be totally avoided in localization. Based on this observation, we propose two new RSSI-based LoRa localization algorithms to further improve the accuracy of the localization for very noisy outdoor environment. One new algorithm iteratively removes all noisy nodes and use the remaining anchor nodes to process the localization; while the other new algorithm uses density clustering to get the best estimation. Our performance investigation shows that the proposed algorithms outperform the algorithms in [1] significantly in terms of the localization error if the outdoor environment is very noisy.

LoRa-based (Long Range Communication based) localization systems make use of RSSI (Received Signal Strength Indicator) to locate an object properly in an outdoor environment for IoT (Internet of Things) applications in smart environment and urban networking. The accuracy of localization is highly degraded, however, by noisy environments (e.g., electronic interference, blocking). To address this issue, this paper proposes two new localization algorithms to improve localization accuracy. Furthermore, the paper develops a winner selection strategy to select a winner from the traditional localization algorithm and the two new algorithms to minimize localization errors. Our simulations and real experiments found that the two new algorithms can significantly improve localization accuracy. Additionally, the winner selection strategy effectively selects a winner from the three algorithms to improve localization accuracy further. Using our proposed algorithms in some real experiments, the localization error is only a few meters in a real measurement field longer than 100 m.

Multi-Objective Evolutionary Algorithm based on decomposition (MOEA/D) has been proposed for a decade in solving complex multi-objective problems (MOP) by decomposing it into a set of single-objective problems. MOEA/D-AGR is one of the improved algorithm introduced recently to substitute the original replacement scheme in MOEA/D with a new adaptive global replacement (GR) scheme so that the neighborhood replacement size Tris increased among the generation to achieve the shifting of focus from solution diversity to convergence. However, the new replacement scheme only considers the one-way convergence of the objective solutions among all sub-problems. It is hard to re-achieve the solution diversity once the algorithm reaches another steeper landscape of solution from a flatten one while it is focusing on convergence. This paper proposes a new adaptive GR scheme to prolong the period of Trincrement so that it can fit the re-increment of fitness landscape. To compensate the shorten period for solution convergence, local searching is adapted for those individuals which has stopped improving its solution value by Simulated Annealing (SA) algorithm. In order to suppress the degree of local searching at the early stage of focusing solution diversity, Fuzzy Logic is used here to coordinate the frequency of local searching according to the average change of objective solution values. To demonstrate the performance of the proposed algorithm, several common benchmark MOPs are used in this paper for comparing with the several state-of-the-art MOEA/D algorithms in terms of IGD. The performance investigation found that the performance of the proposed algorithm was generally better than the other compared algorithms.

A learning process is easily trapped into a local minimum when training multi-layer feed-forward neural networks. An algorithm called Wrong Output Modification (WOM) was proposed to help a learning process escape from local minima, but WOM still cannot totally solve the local minimum problem. Moreover, there is no performance analysis to show that the learning has a higher probability of converging to a global solution by using this algorithm. Additionally, the generalization performance of this algorithm was not investigated when the early stopping method of training is applied. Based on these limitations of WOM, we propose a new algorithm to ensure the learning can escape from local minima, and its performance is analyzed. We also test the generalization performance of this new algorithm when the early stopping method of training is applied.

This paper presents a new Multi-Objective Particle Swarm Optimization (MOPSO) algorithm that has two new components: leader selection and crossover. The new leader selection algorithm, called Space Expanding Strategy (SES), guides particles moving to the boundaries of the objective space in each generation so that the objective space can be expanded rapidly. Besides, crossover is adopted instead of mutation to enhance the convergence and maintain the stability of the generated solutions (exploitation). The performance of the proposed MOPSO algorithm was compared with three popular multi-objective algorithms in solving fifteen standard test functions. Their performance measures were hypervolume, spread and inverse generational distance. The performance investigation found that the performance of the proposed algorithm was generally better than the other three, and the performance of the proposed crossover was generally better than three popular mutation operators.

Multi-layer feed-forward neural networks are commonly used in supervised learning, for which data training is required. One popular way to check whether the training is completed is to monitor the mean square error. It is expected that the learning is completed when the mean square error is less than or equal to an error threshold, which is usually a very small positive real number (e.g., 0.001). However, this terminating condition does not always work very effectively. This paper proposes a new terminating condition to identify the convergence of the learning process in multi-layer feed-forward neural networks. The new termination condition is called Threshold of Output Differences (TOD), which is the difference between an ouput value and its corresponding desired (target) output value to identify the convergence of the learning process. It proposes that the learning is completed when the difference for each output is less than a threshold. The performance investigation showed that the convergence rate of a learning algorithm with this new terminating condition is generally faster than the original one. Moreover, the classification rate (generalization) of a learning algorithm with TOD is usually better than the original one.

This paper presents a new algorithm that extends Particle Swarm Optimization (PSO) to deal with multi-objective problems. It makes two main contributions. The first is that the square root distance (SRD) computation among particles and leaders is proposed to be the criterion of the local best selection. This new criterion can make all swarms explore the whole Pareto-front more uniformly. The second contribution is the procedure to update the archive members. When the external archive is full and a new member is to be added, an existing archive member with the smallest SRD value among its neighbors will be deleted. With this arrangement, the non-dominated solutions can be well distributed. Through the performance investigation, our proposed algorithm performed better than two well-known multi-objective PSO algorithms, MOPSO-σ and MOPSO-CD, in terms of different standard measures.

Minimizing power consumption in the area of ICT (Information and Communication Technologies) is becoming a hot topic. In computer networks, traffic measurements have indicated that the network utilization may become very low (less than 10%) during non-peak hours, which provides the opportunity to power off some routers and links in a network to conserve energy consumption without causing network performance deterioration. This paper formulates an optimization problem for power saving in backbone networks during non-peak hours and proposes a heuristic algorithm for the optimization problem. The performance investigation shows that the proposed heuristic can save up to 50% more power than a popular power saving algorithm for backbone networks.

Backpropagation (BP) algorithm is very popular in supervised learning for feed-forward neural networks. However, it is sometimes slow and easily trapped into a local minimum or a flat-spot area (known as the local minimum and flat-spot area problem respectively). Many modifications have been proposed to speed up its convergence rate but they seldom improve the global convergence capability. Some fast learning algorithms have been proposed recently to solve these two problems: Wrong Output Modification (WOM) is one new algorithm that can improve the global convergence capability significantly. However, some limitations exist in WOM so that it cannot solve the local minimum and flat-spot problem effectively. In this paper, some enhancements are proposed to further improve the performance of WOM by (a) changing the mechanism to escape from a local minimum or a flat-spot area and (b) adding a fast checking procedure to identify the existence of a local minimum or a flat-spot area. The performance investigation shows that the proposed enhancements can improve the performance of WOM significantly when it is applied into different fast learning algorithms. Moreover, WOM with these enhancements is also applied to a very popular second-order gradient descent learning algorithm, Levenberg-Marquardt (LM) algorithm. The performance investigation shows that it can significantly improve the performance of LM.

Backpropagation (BP) algorithm, which is very popular in supervised learning, is extensively applied in training feed-forward neural networks. Many modifications have been proposed to speed up the convergence process of the standard BP algorithm. However, they seldom focus on improving the global convergence capability. This paper proposes a new algorithm called Wrong Output Modification (WOM) to improve the global convergence capability of a fast learning algorithm. When a learning process is trapped by a local minimum or a flat-spot area, this algorithm looks for some outputs that go to other extremes when compared with their target outputs, and then it modifies such outputs systemically so that they can get close to their target outputs and hence some weights of neurons are changed accordingly. It is hoped that these changes make the learning process escape from such local minima or flat-spot areas and then converge. The performance investigation shows that the proposed algorithm can be applied into different fast learning algorithms, and their global convergence capabilities are improved significantly compared with their original algorithms. Moreover, some statistical data obtained from this algorithm can be used to identify the difficulty of a learning problem.

Backpropagation (BP) learning algorithm is the most widely used supervised learning technique that is extensively applied in the training of multi-layer feed-forward neural networks. Although many modifications of BP have been proposed to speed up the learning of the original BP, they seldom address the local minimum and the flat-spot problem. This paper proposes a new algorithm called Local-minimum and Flat-spot Problem Solver (LFPS) to solve these two problems. It uses a systematic approach to check whether a learning process is trapped by a local minimum or a flat-spot area, and then escape from it. Thus, a learning process using LFPS can keep finding an appropriate way to converge to the global minimum. The performance investigation shows that the proposed algorithm always converges in different learning problems (applications) whereas other popular fast learning algorithms sometimes give very poor global convergence capabilities.

Backpropagation (BP) algorithm is the most popular supervised learning algorithm that is extensively applied in training feed-forward neural networks. Many BP modifications have been proposed to increase the convergence rate of the standard BP algorithm, and Quickprop is one the most popular fast learning algorithms. The convergence rate of Quickprop is very fast; however, it is easily trapped into a local minimum and thus it cannot converge to the global minimum. This paper proposes a new fast learning algorithm modified from Quickprop. By addressing the drawbacks of the Quickprop algorithm, the new algorithm has a systematic approach to improve the convergence rate and the global convergence capability of Quickprop. Our performance investigation shows that the proposed algorithm always converges with a faster learning rate compared with Quickprop. The improvement in the global convergence capability is especially large. In one learning problem (application), the global convergence capability increased from 4% to 100%.

Backpropagation (BP) learning algorithm is the most widely supervised learning technique which is extensively applied in the training of multi-layer feed-forward neural networks. Many modifications of BP have been proposed to speed up the learning of the original BP. However, these modifications sometimes cannot converge properly due to the local minimum problem. This paper proposes a new algorithm, which provides a systematic approach to make use of the characteristics of different fast learning algorithms so that the convergence of a learning process is promising with a fast learning rate. Our performance investigation shows that the proposed algorithm always converges with a fast learning rate in two popular complicated applications whereas other popular fast learning algorithms give very poor global convergence capabilities in these two applications.

Backpropagation (BP) learning algorithm is the most widely supervised learning technique which is extensively applied in the training of multi-layer feed-forward neural networks. Many modifications of BP have been proposed to speed up the learning of the original BP. However, the performance of these modifications is still not promising due to the existence of the local minimum problem and the error overshooting problem. This paper proposes an Enhanced Two-Phase method to solve these two problems to improve the performance of existing fast learning algorithms. The proposed method effectively locates the existence of the above problems and assigns appropriate fast learning algorithms to solve them. Throughout our investigation, the proposed method significantly improves the performance of different fast learning algorithms in terms of the convergence rate and the global convergence capability in different problems. The convergence rate can be increased up to 100 times compared with the existing fast learning algorithms.

Backpropagation (BP) learning algorithm is the most widely supervised learning technique which is extensively applied in the training of multi-layer feed-forward neural networks. Many modifications that have been proposed to improve the performance of BP have focused on solving the ldquoflat spotrdquo problem to increase the convergence rate. However, their performance is limited due to the error overshooting problem. A novel approach called BP with two-phase magnified gradient function (2P-MGFPROP) was introduced to overcome the error overshooting problem and hence speed up the convergence rate of MGFPROP. In this paper, this approach is further enhanced by proposing to divide the learning process into multiple phases, and different fast learning algorithms are assigned in different phases to improve the convergence rate in different adaptive problems. Through the performance investigation, it is found that the convergence rate can be increased up to two times, compared with existing fast learning algorithms.

Backpropagation (BP) learning algorithm is the most widely supervised learning technique which is extensively applied in the training of multi-layer feed-forward neural networks. Many modifications have been proposed to improve the performance of BP, and BP with Magnified Gradient Function (MGFPROP) is one of the fast learning algorithms which improve both the convergence rate and the global convergence capability of BP [19]. MGFPROP outperforms many benchmarking fast learning algorithms in different adaptive problems [19]. However, the performance of MGFPROP is limited due to the error overshooting problem. This paper presents a new approach called BP with Two-Phase Magnified Gradient Function (2P-MGFPROP) to overcome the error overshooting problem and hence speed up the convergence rate of MGFPROP. 2P-MGFPROP is modified from MGFPROP. It divides the learning process into two phases and adjusts the parameter setting of MGFPROP based on the nature of the phase of the learning process. Through simulation results in two different adaptive problems, 2P-MGFPROP outperforms MGFPROP with optimal parameter setting in terms of the convergence rate, and the improvement can be up to 50%.

We develop a very simple mathematical model to investigate the upper bound of the size of limited choices in our proposed QoS path selection algorithm called the largest widest shortest path among limited choices (LWSP-LC) for engineering design. The LWSP-LC can achieve load balancing effectively and reduce path searching complexity significantly. However, its performance is highly related to many factors, including the network environment and traffic condition. Our simulation results show that the size of limited choices is highly dependent on both the network size and network connectivity. By considering a fully connected network, we derive a simple mathematical model on the upper bound of the size of limited choices based on the network size only.

This paper presents a new approach using deterministic weight modification (DWM) to speed up the convergence rate effectively and improve the global convergence capability of the standard and modified back-propagation (BP) algorithms. The main idea of DWM is to reduce the system error by changing the weights of a multi-layered feed-forward neural network in a deterministic way. Simulation results show that the performance of DWM is better than BP and other modified BP algorithms for a number of learning problems.

This paper presents two novel approaches, backpropagation (BP) with magnified gradient function (MGFPROP) and deterministic weight modification (DWM), to speed up the convergence rate and improve the global convergence capability of the standard BP learning algorithm. The purpose of MGFPROP is to increase the convergence rate by magnifying the gradient function of the activation function, while the main objective of DWM is to reduce the system error by changing the weights of a multilayered feedforward neural network in a deterministic way. Simulation results show that the performance of the above two approaches is better than BP and other modified BP algorithms for a number of learning problems. Moreover, the integration of the above two approaches forming a new algorithm called MDPROP, can further improve the performance of MGFPROP and DWM. From our simulation results, the MDPROP algorithm always outperforms BP and other modified BP algorithms in terms of convergence rate and global convergence capability.

This paper presents a modified back-propagation algorithm using magnified gradient function (MGFPROP), which can effectively speed up the convergence rate and improve the global convergence capability of back-propagation. The purpose of MGFPROP is to increase the convergence rate by magnifying the gradient function of the activation function. From the convergence analysis, it is shown that the new algorithm retains the gradient descent property but gives faster convergence than that of the back-propagation algorithm. Simulation results show that, in terms of the convergence rate and the percentage of global convergence, the new algorithm always outperforms the standard back-propagation algorithm and other competing techniques.

A service scheduling scheme is to control the order of servicing cells within an ATM node and maintain their quality of service (QoS). Recent researchers have focused on the efficient ways of isolation among different incoming traffic, or the different approach to improve the overall QoS. However they seldom try to achieve both objectives simultaneously. In this paper, we propose a new service scheduling scheme with fuzzy logic design to achieve these two goals. We use a fuzzy controller to choose an appropriate service scheduling scheme from the two traditional methods for the current input traffic environment. Numerical results show that this approach not only can achieve both objectives, but also show better performance as compared with traditional methods.

In this paper, we investigate the dynamic multicast routing problem for single rate loss network and briefly discuss the dynamic multicast routing algorithm called least load multicast routing (LLMR). We propose a new multicast routing algorithm called maximum mean number of new calls accepted before blocking multicast routing (MCBMR), which can more accurately capture the current and future loading of a network. Simulation results show that this algorithm, compared with LLMR, not only has a smaller network revenue loss, but also results in smaller call blocking probabilities for all classes of traffic. We also discuss the implementation issues of our proposed algorithm and develop two approximation methods, state approximation and curve fitting, which can reduce the measurement complexity significantly with only a slight performance degradation.

We investigate a state dependent multicast routing algorithm called least load multicast routing (LLMR), for single rate loss networks. The algorithm is based on least load routing (LLR) concept and the approach is to select the least load links for establishing connections. The networks considered are assumed fully connected. In addition, connection requests are Poisson arrival and the holding times of accepted calls are exponentially distributed. The analytical model that we developed for calculating the blocking probabilities is based on the link independence assumption and the reduced load approximation (RLA). Analytical results are compared with simulation results and the agreement is surprisingly good. We find that the effect of link independence assumption is insignificant for the analytical model.