Availability is one of the three main goals of information security. This paper contributes to systems' availability by introducing an optimization model for the adaptation (controlling the capturing, coding, and ...
详细信息
Availability is one of the three main goals of information security. This paper contributes to systems' availability by introducing an optimization model for the adaptation (controlling the capturing, coding, and sending features of the video communication system) of live broadcasting of video to limited and varied network bandwidth and/or limited power sources such as wireless and mobile network cases. We first, analyzed the bitrate-accuracy and bitrate-power characteristics of various video transmission techniques for adapting video communication in Artificial Intelligence-based Systems. To optimize resources for live video streaming, we analyze various video parameter settings for adapting the stream to available resources. We consider the object detection accuracy, the bandwidth, and power consumption requirement. The results showed that setting SNR and spatial video encoding features (with upscaling the frames at the destination) are the best techniques that maximizing the object detection accuracy while minimizing the bandwidth and the consumed energy requirements. In addition, we analyze the effectiveness of combining SNR and spatial video encoding features with upscaling and find that we can increase the performance of the streaming system by combining these two techniques. We presented a multi-objective function for determining the parameter or parameters' pairing that provides the optimal object detection's accuracy, power consumption, and bit rate. Results are reported based on more than 15,000 experiments utilizing standard datasets for short video segments and a collected dataset of 300 videos from YouTube. We evaluated results based on the detection index, false-positive index, power consumption, and bandwidth requirements metrics. For a single adaptive parameter, the analysis of the experiment's outcome demonstrate that the multi-objective function achieves object detection accuracy as high as the best while drastically reducing bandwidth requirements
Workload balancing in cloud computing is not yet resolved, particularly considering Infrastructure as a Service (IaaS) in the cloud network. The problem of being underloaded or overloaded should not occur at the time ...
详细信息
Workload balancing in cloud computing is not yet resolved, particularly considering Infrastructure as a Service (IaaS) in the cloud network. The problem of being underloaded or overloaded should not occur at the time of the server or host accessing the cloud which may lead to create system crash problem. Thus, to resolve these existing problems, an efficient task scheduling algorithm is required for distributing the tasks over the entire feasible resources, which is termed load balancing. The load balancing approach assures that the entire Virtual Machines (VMs) are utilized appropriately. So, it is highly essential to develop a load-balancing model in a cloud environment based on machine learning and optimization strategies. Here, the computing and networking data is utilized for the analysis to observe the traffic as well as performance patterns. The acquired data is offered to the machine learning decision to select the right server by predicting the performance effectively by employing an Optimal Kernel-based Extreme Learning Machine (OK-ELM) and their parameter is tuned by the developed hybrid approach Population Size-based Mud Ring Tunicate Swarm Algorithm (PS-MRTSA). Further, effective scheduling is performed to resolve the load balancing issues by employing the developed model MR-TSA. Here, the developed approach effectively resolves the multi-objective constraints such as Response time, Resource cost, and energy consumption. Thus, the recommended load balancing model securesan enhanced performance rate than the traditional approaches over several experimental analyses.
In Taiwan, due to its relatively low development cost, groundwater has been the main source of water supply for most aquacultural industry in costal areas. The overdraft of groundwater has caused serious land-subsiden...
详细信息
In Taiwan, due to its relatively low development cost, groundwater has been the main source of water supply for most aquacultural industry in costal areas. The overdraft of groundwater has caused serious land-subsidence in many parts of Taiwan. In addition to providing enough surface water for aquaculture freshwater demand, revising the aquaculture structure is one approach to reduce the reliance on fresh groundwater. Due to the most serious land-subsidence in Tachen Village, Changhua County, Taiwan, which may be caused by overusing groundwater for mainly raising freshwater clams, alternative techniques, such as changing the method of water use or revising the kinds of fish with less freshwater demands and higher gross profits, were studied in the study to reduce the dependence on fresh groundwater. The fuzzy multi-objective function comprising three single-objectives, viz. reducing saltwater demand, reducing freshwater demand, and increasing the total fisheries gross profit, was coupled with a global optimization algorithm to find suitable aquaculture scenarios in the study area. Analytical results can be provided to the fisheries authorities as references for revising the aquaculture structure.
Wireless sensor networks (WSNs) are the networks which mainly focuses on the applications and are composed of considerable sensor nodes. The use of energy in a valuable way is considered as a feature for the design st...
详细信息
Wireless sensor networks (WSNs) are the networks which mainly focuses on the applications and are composed of considerable sensor nodes. The use of energy in a valuable way is considered as a feature for the design structure of WSNs. In the WSNs, the nodes power sources are limited. Moreover, because of this, there is a must for a different approach regarding the energy availability and this is mainly for long distance communication, for this multi-hop (MH) systems are chosen. Even though MH decreases the energy cost used by all node along the path, however, to obtain the best routing path among nodes is yet an interesting subject. In this article, we present a multi-objectivemulti-hop routing (MOMHR) protocol for optimal data routing to gain the network lifetime. In the first phase, the K-means algorithm is applied to split the nodes into k clusters. Next, the artificial bee colony optimisation algorithm is applied to obtain the best possible CH within each cluster then using a multi-objective functions finally the multi-hop routing protocol finds a multihop path with minimum communication cost from the node to the base station. Our proposed method is simulated in MATLAB platform and compared with two recent protocols such as low energy adaptive clustering hierarchy and energy efficient centroid-based routing protocol. The execution of the proposed MOMHR protocols using multi-objective function is evaluated using metrics such as energy efficiency and network lifetime.
A technique of automated segmentation has been introduced in this paper, which makes the tumour segmentation out of MRI images, apart from improving the effectiveness of segmentation as well as classification. Once th...
详细信息
A technique of automated segmentation has been introduced in this paper, which makes the tumour segmentation out of MRI images, apart from improving the effectiveness of segmentation as well as classification. Once the dataset of MRI dataset is collected from different public sources, the pre-processing of the image is performed by the median filtering and contrast enhancement. The segmentation of brain tumour is the main contribution of this paper, which concentrates on developing the Adaptive Influence Factor-based Elephant Herding Optimisation (AIF-EHO)-based FCM-UNet fusion segmentation with multi-objective function. Then, the feature extraction is performed using Completed Local Binary Pattern (CLBP) and Local Gradient Pattern (LGP). These extracted features are further used in deep learning using Enhanced Recurrent Neural Network (RNN) for brain tumour classification. Results demonstrated on public benchmarks described that this method attains competitive accuracy than the conventional techniques while being computationally effective.
In metropolitan cities, it provides better Terrestrial communication for transmitting the data. However, places like oceans, deserts, and mountains do not have a better network coverage. The terrestrial communication ...
详细信息
In metropolitan cities, it provides better Terrestrial communication for transmitting the data. However, places like oceans, deserts, and mountains do not have a better network coverage. The terrestrial communication network is utilized to transmit audio and videos based on the frequencies. Fifth-generation terrestrial networks have the ability to provide better coverage in the satellites. Here, the Software-Defined Networking (SDN) is designed to control the network using software programs. Without considering the underlying network technology, the managing of the network becomes a complicated issue. Still, satellite communication networks generally provide less data throughput, and also it shows high latency. The development of a successful Hybrid Satellite-Terrestrial Network (HSTN) faces several difficulties in the substantial distinctions between Terrestrial Communications (TerComs) and Satellite Communications (SatComs). Thus, it does not provide effective outcomes in terms of coverage performance, mobility, transmission delay, and channel fading. In Integrated Satellite-Terrestrial Networks (ISTNs), the satellite gateway placement becomes the challenging factor. Due to the placement of the wrong gateway, the demand arising for the network's service and coverage performance gets still affected. In order to alleviate such issues, an intelligent ISTN model is proposed for the controller placement and routing. The main intention of this approach is to determine the optimized value for placement and routing. Firstly, the gateway and controller placement are optimized using the objectivefunction, which includes constraints such as network reliability and network latency. Secondly, the optimal routing is accomplished using the Improved Rat Swarm Optimizer (I-RSO). Moreover, the designed I-RSO algorithm provides the optimal solutions to enhance the system performance. Also, the developed model is used to derive the multi-objection function with multiple constraints.
The effective and efficient optimization of Storm Water Management Model (SWMM) parameters is critical to improving the accuracy of the urban rainfall-runoff simulation. Therefore, it is necessary to investigate the a...
详细信息
The effective and efficient optimization of Storm Water Management Model (SWMM) parameters is critical to improving the accuracy of the urban rainfall-runoff simulation. Therefore, it is necessary to investigate the applicability of the dynamic system response curve (DSRC) method in optimizing SWMM model parameters, which is newly proposed to solve the nonlinear problems encountered by current widely used optimization methods. A synthetic case, free of data and model errors, was used to examine the applicability of the DSRC with single-objective or multi-objective functions in finding the optimum parameter values known by assumption. A real watershed case was selected for the optimization of SWMM parameters by use of DSRC with the most suitable objectivefunction, which was determined by a synthetic case. In addition, the advantages of the DSRC in SWMM parameter optimization over the Particle Swarm Optimization(PSO) and multiple objective Particle Swarm Optimization(MOPSO) algorithms were analyzed in terms of NSE, REv, REp, and EPt. The results revealed that the DSRC with multi-objective function could find the global optima of all SWMM model parameters in the synthetic case, but it could only attain part of them with a single-objectivefunction. In the real watershed case, the DSRCS-optimized SWMM performed better than MOPSO-optimized one with an increase of average NSE by 5.8% and a reduction of average vertical bar REv vertical bar, vertical bar REp vertical bar and vertical bar EPt vertical bar by -53.7%, -67.9%, and -34.6% respectively during the study period. The outputs of this paper could provide a promising approach for the optimization of SWMM parameters and the improvement of urban flooding simulation accuracy, and a scientific support for urban flood risk control and mitigation.
multiscale retinex is one of the most popular image enhancement methods. However, its control parameters, such as Gaussian kernel sizes, gain, and offset, should be tuned carefully according to the image contents. In ...
详细信息
multiscale retinex is one of the most popular image enhancement methods. However, its control parameters, such as Gaussian kernel sizes, gain, and offset, should be tuned carefully according to the image contents. In this letter, we propose a new method that optimizes the parameters using practical swarm optimization and multi-objective function. The method iteratively verifies the visual quality (i.e. brightness, contrast, and colorfulness) of the enhanced image using a multi-objective function while subtly adjusting the parameters. Experimental results shows that the proposed method achieves better image quality qualitatively and quantitatively compared with other image enhancement methods.
One of the infrastructure-free networks is mobile ad hoc networks (MANETs) that are built with limited battery life using wireless mobile devices. This restricted battery capability in MANETs creates the necessity of ...
详细信息
One of the infrastructure-free networks is mobile ad hoc networks (MANETs) that are built with limited battery life using wireless mobile devices. This restricted battery capability in MANETs creates the necessity of considering the energy-awareness constraint in designing them. As routing protocols, the major aim of MANETs is to create the energy awareness in the network;it improves the network's lifetime through effectively utilizing the available restricted energy. Moreover, it creates some limitations like the mobility constraint, wireless link's sensitivity to environmental impacts, and restricted transmission range and residual energy of nodes that causes rapid modifications in the network topology and frequent link failure. By taking those problems, this paper plans to develop a new multipath routing protocol, where the hybrid optimization algorithm with the integration of cuckoo search optimization (CSO) and butterfly optimization algorithm (BOA) is proposed and named sensory modality-based cuckoo search butterfly optimization (SM-CSBO) for determining the optimal path between the source and destination. The main goal is to select the path with better link quality and more stable links to guarantee reliable data transmission. The multi-objective function is considered with the factors regarding distance, normalized energy, packet delivery ratio, and control overhead to develop an effective routing protocol in MANET. The proposed model of SM-CSBO algorithm has superior than 5.8%, 30.4%, 36.7%, and 39.3%, correspondingly maximized than PSO, SFO, CSO, and SFO algorithms while considering the number of nodes as 150. The simulation outcomes proved that it enhances network performance when compared with the other traditional protocols.
Genetic algorithms applied to structural damage detection have broad application prospects. Based on the traditional genetic algorithms, this paper conducts the improvement research of the objectivefunction with the ...
详细信息
Genetic algorithms applied to structural damage detection have broad application prospects. Based on the traditional genetic algorithms, this paper conducts the improvement research of the objectivefunction with the incorporation of multi-objective function optimization. On the basis of three typical structural damage scenarios, we took a comprehensive study using different multi-objective function of the genetic algorithm from the standpoint of both convergence speed and accuracy. Data analysis obtained the corresponding optimal portfolio of weight coefficient in three typical scenarios, further fitted a universal formula for the weight coefficient value choice (WCCF). And an example to demonstrate the reliability of the formula is provided, which is supposed to provide more reference for quadratic optimization based on preliminary analysis for practical application.
暂无评论