Just-in-time connectivity for large spiking networks

The scale of large neuronal network simulations is memory limited due to the need to store connectivity information: connectivity storage grows as the square of neuron number up to anatomically relevant limits. Using the NEURON simulator as a discrete-event simulator (no integration), we explored the consequences of avoiding the space costs of connectivity through regenerating connectivity parameters when needed: just in time after a presynaptic cell fires. We explored various strategies for automated generation of one or more of the basic static connectivity parameters: delays, postsynaptic cell identities, and weights, as well as run-time connectivity state: the event queue. Comparison of the JitCon implementation to NEURON's standard NetCon connectivity method showed substantial space savings, with associated run-time penalty. Although JitCon saved space by eliminating connectivity parameters, larger simulations were still memory limited due to growth of the synaptic event queue. We therefore designed a JitEvent algorithm that added items to the queue only when required: instead of alerting multiple postsynaptic cells, a spiking presynaptic cell posted a callback event at the shortest synaptic delay time. At the time of the callback, this same presynaptic cell directly notified the first postsynaptic cell and generated another self-callback for the next delay time. The JitEvent implementation yielded substantial additional time and space savings. We conclude that just-in-time strategies are necessary for very large network simulations but that a variety of alternative strategies should be considered whose optimality will depend on the characteristics of the simulation to be run.     

Detection of COVID-19 and its pulmonary stage using Bayesian hyperparameter optimization and deep feature selection methods

Since the first case of COVID-19 was reported in December 2019, many studies have been carried out on artificial intelligence for the rapid diagnosis of the disease to support health services. Therefore, in this study, we present a powerful approach to detect COVID-19 and COVID-19 findings from computed tomography images using pre-trained models using two different datasets. COVID-19, influenza A (H1N1) pneumonia, bacterial pneumonia and healthy lung image classes were used in the first dataset. Consolidation, crazy-paving pattern, ground-glass opacity, ground-glass opacity and consolidation, ground-glass opacity and nodule classes were used in the second dataset. The study consists of four steps. In the first two steps, distinctive features were extracted from the final layers of the pre-trained ShuffleNet, GoogLeNet and MobileNetV2 models trained with the datasets. In the next steps, the most relevant features were selected from the models using the Sine–Cosine optimization algorithm. Then, the hyperparameters of the Support Vector Machines were optimized with the Bayesian optimization algorithm and used to reclassify the feature subset that achieved the highest accuracy in the third step. The overall accuracy obtained for the first and second datasets is 99.46% and 99.82%, respectively. Finally, the performance of the results visualized with Occlusion Sensitivity Maps was compared with Gradient-weighted class activation mapping. The approach proposed in this paper outperformed other methods in detecting COVID-19 from multiclass viral pneumonia. Moreover, detecting the stages of COVID-19 in the lungs was an innovative and successful approach.     

Mobility-Aware RSVP: A framework for improving the performance of multimedia services over wireless IP-based mobile networks

This paper proposes the Mobility-Aware Resource Reservation Protocol (MARSVP) in which mobility and QoS signaling are performed as a single functional block. The key concept of MARSVP is to convey mobility-specific information (binding updates and their associated acknowledgments) by using newly defined RSVP objects embedded in existing RSVP messages. An appealing feature of MARSVP is that it adheres to the current RSVP standard (RFC 2205) and thus requires minimal changes to end nodes without affecting any of the conventional RSVP routers in between. The proposed mechanism is evaluated using a simulation model for application-level performance and an analytical model for network-level signaling cost. Simulation results indicate a 27.9% improvement in QoS interruption when using Mobile IPv6 (MIPv6), 12.5% when using Hierarchical Mobile IPv6 (HMIPv6), and no improvement when using Fast Handovers for MIPv6 (FMIPv6). On the network-level, signaling cost savings of 9.4% and 11.9% are achieved for MIPv6 and HMIPv6, respectively, while FMIPv6 achieves savings of 17.9% when using Voice-over-IP traffic and 26.7% for Video-over-IP traffic. The results of the conducted studies indicate MARSVP’s superiority to conventional RSVP when deployed over wireless networks.     

Medical application of information gain based artificial immune recognition system (AIRS): Diagnosis of thyroid disease

In this paper, we have made medical application of a new artificial immune system named the information gain based artificial immune recognition system (IG-AIRS) which minimizes the negative effects of taking into account all attributes in calculating Euclidean distance in shape–space representation which is used in many artificial immune systems. For medical data, thyroid disease data set was applied in the performance analysis of our proposed system. Our proposed system reached 95.90% classification accuracy with 10-fold CV method. This result ensured that IG-AIRS would be helpful in diagnosing thyroid function based on laboratory tests, and would open the way to various ill diagnoses support by using the recent clinical examination data, and we are actually in progress.     

The modeling of mode choices of intercity freight transportation with the artificial neural networks and adaptive neuro-fuzzy inference system

Mode choice modeling is probably the most important element of transportation planning. It affects the general efficiency of travel and the allocation of resources. The development of mode choice models has recently witnessed significant advances in many fields, such as passenger and freight transport. A large number of mathematical models have been used to model the traveler’s choice of mode and destination and the shipper’s choice of mode, shipment size and supply market, among others. Such models are not only becoming almost intractable but also data intensive, difficult to calibrate and update, and intransferable. These models cover a wide range of mathematical complexity and accuracy. This paper describes a new approach to mode choice of intercity freight transport modeling using artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS) models. The new approach combines the learning ability of artificial neural networks and the transparent nature of fuzzy logic. The approach is found to be highly adaptive and efficient in investigating non-linear relationships among different variables. The adaptive neuro-fuzzy inference system model is tested on the freight transport market in Turkey, Germany, France and Austria by using information on the freight flows and their attributes. The ANNs and ANFIS models are more successful in the representation of the non-linear behavior of mode choice of intercity freight transport compared to the classical models.     

Pitch angle control in wind turbines above the rated wind speed by multi-layer perceptron and radial basis function neural networks

In wind energy conversion systems, one of the operational problems is the changeability and discontinuity of wind. In most cases, wind speed can fluctuate rapidly. Hence, quality of produced energy becomes an important problem in wind energy conversion plants. Several control techniques have been applied to improve the quality of power generated from wind turbines. Pitch control is the most efficient and popular power control method, especially for variable-speed wind turbines. It is a useful method for power regulation above the rated wind speed. This paper proposes an artificial neural network-based pitch angle controller for wind turbines. In the simulations, a variable-speed wind turbine is modeled, and its operation is observed by using two types of artificial neural network controllers. These are multi-layer perceptrons with back propagation learning algorithm and radial basis function network. It is shown that the power output was successfully regulated during high wind speed, and as a result overloading or outage of the wind turbine was prevented.     

Prediction of performance and exhaust emissions of a diesel engine fueled with biodiesel produced from waste frying palm oil

Biodiesel is receiving increasing attention each passing day because of its fuel properties and compatibility with the petroleum-based diesel fuel (PBDF). Therefore, in this study, the prediction of the engine performance and exhaust emissions is carried out for five different neural networks to define how the inputs affect the outputs using the biodiesel blends produced from waste frying palm oil. PBDF, B100, and biodiesel blends with PBDF, which are 50% (B50), 20% (B20) and 5% (B5), were used to measure the engine performance and exhaust emissions for different engine speeds at full load conditions. Using the artificial neural network (ANN) model, the performance and exhaust emissions of a diesel engine have been predicted for biodiesel blends. According to the results, the fifth network is sufficient for all the outputs. In the fifth network, fuel properties, engine speed, and environmental conditions are taken as the input parameters, while the values of flow rates, maximum injection pressure, emissions, engine load, maximum cylinder gas pressure, and thermal efficiency are used as the output parameters. For all the networks, the learning algorithm called back-propagation was applied for a single hidden layer. Scaled conjugate gradient (SCG) and Levenberg–Marquardt (LM) have been used for the variants of the algorithm, and the formulations for outputs obtained from the weights are given in this study. The fifth network has produced R² values of 0.99, and the mean % errors are smaller than five except for some emissions. Higher mean errors are obtained for the emissions such as CO, NO_x and UHC. The complexity of the burning process and the measurement errors in the experimental study can cause higher mean errors.     

An Objective Deghosting Quality Metric for HDR Images

Reconstructing high dynamic range (HDR) images of a complex scene involving moving objects and dynamic backgrounds is prone to artifacts. A large number of methods have been proposed that attempt to alleviate these artifacts, known as HDR deghosting algorithms. Currently, the quality of these algorithms are judged by subjective evaluations, which are tedious to conduct and get quickly outdated as new algorithms are proposed on a rapid basis. In this paper, we propose an objective metric which aims to simplify this process. Our metric takes a stack of input exposures and the deghosting result and produces a set of artifact maps for different types of artifacts. These artifact maps can be combined to yield a single quality score. We performed a subjective experiment involving 52 subjects and 16 different scenes to validate the agreement of our quality scores with subjective judgements and observed a concordance of almost 80%. Our metric also enables a novel application that we call as hybrid deghosting, in which the output of different deghosting algorithms are combined to obtain a superior deghosting result.     

Modeling discrete event scalable network systems

Scalability in simulation tools is one of the most important traits to measure performance of software. The reason is that today’s Internet is the main instance of a large-scale and highly complex system. Simulation of Internet-scale network systems has to be supported by any simulation tool. Despite this fact, many network simulators lacks support for building large models. In this work, in order to propose a new approach for scalability issue in network simulation tools, a network simulator is developed based on behavior of honeybees and high performance DEVS, modular and hierarchical system theoretic approach. A biologically-inspired discrete event modeling approach is described for studying networks’ scalability and performance traits. Since natural systems can offer important concepts for modeling network systems, key adaptive and emergent attributes of honeybees and their societal properties are incorporated into a set of simulation models that are developed using the discrete event system specification approach. Large-scale network models are simulated and evaluated to show the benefits of nature-inspired network models.     

An adaptive least squares channel estimation based on conjugate gradient approach for multipath fading CDMA systems

Multiple access interference (MAI) is the main factor affecting the performance of channel estimation techniques for code division multiple access (CDMA) systems. Although, several multi-user channel estimation algorithms have been proposed to mitigate MAI, these algorithms require high computational complexities. In this paper, we address the problem of iterative least squares (LS) mobile channel estimation at high channel efficiency that requires a short training sequence along with the spreading sequences. We employ an efficient iterative method based on conjugate gradient (CG) algorithm to reduce the computational complexity of the estimation method. Computer simulations illustrate that the proposed method performs almost identical to the exact LS estimate for reasonable training lengths.