Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and com...Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and complex model structures require more calculating resources.Since people generally can only carry and use mobile and portable devices in application scenarios,neural networks have limitations in terms of calculating resources,size and power consumption.Therefore,the efficient lightweight model MobileNet is used as the basic network in this study for optimization.First,the accuracy of the MobileNet model is improved by adding methods such as the convolutional block attention module(CBAM)and expansion convolution.Then,the MobileNet model is compressed by using pruning and weight quantization algorithms based on weight size.Afterwards,methods such as Python crawlers and data augmentation are employed to create a garbage classification data set.Based on the above model optimization strategy,the garbage classification mobile terminal application is deployed on mobile phones and raspberry pies,realizing completing the garbage classification task more conveniently.展开更多
The shipping industry is one of the biggest industries throughout the ages. Maritime transport plays a vital role in world economy; whereas competition between maritime companies is fierce [1], at the same time agreem...The shipping industry is one of the biggest industries throughout the ages. Maritime transport plays a vital role in world economy; whereas competition between maritime companies is fierce [1], at the same time agreements of co-operation have taken different forms including alliances and mergers between companies to increase their market share. But competitions still stand despite all alliances even in same market. This intense competition drives companies to attain high level of competitiveness, by monitoring ship＇s operating performance and operating cost, emphasis on improving performance and reduce cost. On other hand new environmental regulations come to light, expansion of ECA （emission control areas）, which lead to significant higher fuel cost when using low sulfur fuel. Since the fuel cost is the largest portion of the operating cost of the vessel, a saving in fuel usage can result in considerable saving in operational costs. Furthermore, fuel saving has environmental benefits in the reduction of greenhouse gas emissions. The aim of this paper is to investigate the role of trim optimization which considers one of the easiest and cheapest methods for ship performance optimization and fuel consumption reduction trim optimization.展开更多
文摘Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and complex model structures require more calculating resources.Since people generally can only carry and use mobile and portable devices in application scenarios,neural networks have limitations in terms of calculating resources,size and power consumption.Therefore,the efficient lightweight model MobileNet is used as the basic network in this study for optimization.First,the accuracy of the MobileNet model is improved by adding methods such as the convolutional block attention module(CBAM)and expansion convolution.Then,the MobileNet model is compressed by using pruning and weight quantization algorithms based on weight size.Afterwards,methods such as Python crawlers and data augmentation are employed to create a garbage classification data set.Based on the above model optimization strategy,the garbage classification mobile terminal application is deployed on mobile phones and raspberry pies,realizing completing the garbage classification task more conveniently.
文摘The shipping industry is one of the biggest industries throughout the ages. Maritime transport plays a vital role in world economy; whereas competition between maritime companies is fierce [1], at the same time agreements of co-operation have taken different forms including alliances and mergers between companies to increase their market share. But competitions still stand despite all alliances even in same market. This intense competition drives companies to attain high level of competitiveness, by monitoring ship＇s operating performance and operating cost, emphasis on improving performance and reduce cost. On other hand new environmental regulations come to light, expansion of ECA （emission control areas）, which lead to significant higher fuel cost when using low sulfur fuel. Since the fuel cost is the largest portion of the operating cost of the vessel, a saving in fuel usage can result in considerable saving in operational costs. Furthermore, fuel saving has environmental benefits in the reduction of greenhouse gas emissions. The aim of this paper is to investigate the role of trim optimization which considers one of the easiest and cheapest methods for ship performance optimization and fuel consumption reduction trim optimization.
