Automatic Number Plate Recognition (ANPR) is a computer vision technology using optical character recognition to identify and read vehicle number plates to obtain vehicle data. ANPR is closely related to our daily life, it is widely used in applications like parking lot management, automatic toll payment system, and traffic violation detection. In recent years ANPR has made great progress, thanks to the advancement of algorithms and techniques especially deep learning methods, which show great success in a wide range of tasks. To this, in the paper, we implement Macau ANPR system with deep learning-based methods. We create a new process: vehicle detection, and a new function: detecting number plate characters' color whether the vehicle is for commercial use. We provide complete and detailed explanations of these two new functions and the two main processes of ANPR: vehicle and number plate detection and character recognition. We make use of five state-of-the-art algorithms for detection, including four deep learning-based methods, and three tools for character recognition. To this, we holistically present the steps of character separation and recognition. Besides, we illustrate the comparison of different deep learning models and show all the outcomes of the sample pictures with all the mentioned methods. Moreover, at the end of this paper, we highlight merits and drawbacks of all these methods and tools. We believe that our study can help grow the community in a better way.

Text recognition in textures is a pressing need for effective contextual perception in our daily life. In OCR scope, deep learning methods can meet the needs of real-time scenarios. However, characters with different textures, such as printed and handwritten characters leads OCR to deal with different scenarios. To this, in this paper, we focus on the implementation and optimization of text recognition using deep learning methods. In particular, we go with a two-stage OCR approach based on deep learning methods to detect and recognize Traditional Chinese characters including handwritten and printed while improving the accuracy. In particular, DBNet [1] is used in the text detection stage and CRNN [2] (baseline) and ABINet [3] (advanced) models in the text recognition stage. For the ABINet, we modify fusion module by using attention mechanism. For the CRNN, we utillize combined loss function. The experiment results show that The CRNN model with the combined loss function improves nearly 4.2% compared with the baseline CRNN. The ABINet model with new fusion module achieves 92.30% on the Traditional Chinese recognition dataset, improves nearly 0.8% compared to the original ABINet. Notably, we also have our own Traditional Chinese handwritten datasets for text detection and recognition. In fine, we believe that our endeavour can help grow the community in a better way.

This paper proposes transferred initialization with modified fully connected layers for COVID-19 diagnosis. Convolutional neural networks (CNN) achieved a remarkable result in image classification. However, training a high-performing model is a very complicated and time-consuming process because of the complexity of image recognition applications. On the other hand, transfer learning is a relatively new learning method that has been employed in many sectors to achieve good performance with fewer computations. In this research, the PyTorch pre-trained models (VGG19_bn and WideResNet -101) are applied in the MNIST dataset for the first time as initialization and with modified fully connected layers. The employed PyTorch pre-trained models were previously trained in ImageNet. The proposed model is developed and verified in the Kaggle notebook, and it reached the outstanding accuracy of 99.77% without taking a huge computational time during the training process of the network. We also applied the same methodology to the SIIM-FISABIO-RSNA COVID-19 Detection dataset and achieved 80.01% accuracy. In contrast, the previous methods need a huge compactional time during the training process to reach a high-performing model. Codes are available at the following link: github.com/dipuk0506/Spina1Net

As an emulous alternative to deep neural networks, Deep Forest emerges with features like low complexity, fewer hyper-parameters, and good robustness, which are predominantly desired in distributed computing applications and ecosystems. Recently, an efficient distributed Deep Forest system, named ForestLayer, was proposed, designing a fine-grained sub-Forest-based task-parallel algorithm to improve the parallel computing efficiency of Deep Forest. However, the sub-Forest splitting of ForestLayer is static and one-off without adaptability to the computing environment, nevertheless, the size of splitting granularity has a significant impact on the system performance. To further improve the computing efficiency and scalability of the distributed Deep Forest, in this paper, we propose a novel distributed Deep Forest algorithm, named BLB-gcForest (Bag of Little Bootstraps-gcForest), which augments the gcForest (multi-Grained Cascade Forest) approach for constructing Deep Forest. BLB-gcForest carries out parallel computation for each tree in sub-Forests at a finer parallel granularity and integrates with the Bag of Little Bootstraps (BLB) mechanism to reduce massive transmitted feature instances for Cascade Forest Layers, utterly improving both computation efficiency and communication efficiency. Moreover, to solve the problem of the forest splitting granularity, we further design an adaptive sub-Forest splitting algorithm to ensure the maximum resource utilization for parallel computation of each sub-Forest. Experimental results on four well-known large-scale datasets, namely YEAST, LETTER, MNIST, CIFAR10, show that the training efficiency of BLB-gcForest achieves up to 20.3x and 1.64x speedups compared with the state-of-the-art gcForest and ForestLayer, respectively while guaranteeing higher accuracy and better robustness

In regression GUI testing for Android apps, test scripts often fail due to changes to, rather than faults in, those apps. To avoid such false positives while still retaining the value of the old test scripts as much as possible, programmers need an automatic way to maintain the tests after the corresponding GUI has evolved. In this paper, we propose the CHATEM approach to automate GUI test script maintenance for Android apps. Taking as input the models for the GUIs of the base and updated version app and the original test scripts, CHATEM automatically extracts the changes between the two GUIs and generates maintenance actions for each change, which are then combined to form the maintenance actions for affected test scripts. In an experimental evaluation on 16 Android apps, CHATEM was able to automatically maintain the test scripts so that overall more than 95% of the remaining behaviors tested before are still tested, and almost 80% of the reusable test actions are retained in the result tests.

The performance, dependability, and security of cloud service systems are vital for the ongoing operation, control, and support. Thus, controlled improvement in service requires a comprehensive analysis and systematic identification of the fundamental underlying constituents of cloud using a rigorous discipline. In this paper, we introduce a framework which helps identifying areas for potential cloud service enhancements. A cloud service cannot be completed if there is a failure in any of its underlying resources. In addition, resources are kept offline for scheduled maintenance. We use redundant resources to mitigate the impact of failures/maintenance for ensuring performance and dependability; which helps enhancing security as well. For example, at least 4 replicas are required to defend the intrusion of a single instance or a single malicious attack/fault as defined by Byzantine Fault Tolerance (BFT). Data centers with high performance, dependability, and security are outsourced to the cloud computing environment with greater flexibility of cost of owing the computing infrastructure. In this paper, we analyze the effectiveness of redundant resource usage in terms of dependability metric and cost of service deployment based on the priority of service requests. The trade-off among dependability, cost, and security under different redundancy schemes are characterized through the comprehensive analytical models.

Public cloud providers, such as Amazon EC2, offer idle computing resources known as spot instances at a much cheaper rate compared to On-Demand instances. Spot instance prices are set dynamically according to market demand. Cloud users request spot instances by submitting their bid, and if user's bid price exceeds current spot price then a spot instance is assigned to that user. The problem however is that while spot instances are executing their jobs, they can be revoked whenever the spot price rises above the current bid of the user. In such scenarios and to complete jobs reliably, we propose a set of improvements for the cloud spot market which benefits both the provider and users. Typically, the new framework allows users to bid different prices depending on their perceived urgency and nature of the running job. Hence, it practically allow them to negotiate the current bid price in a way that guarantees the timely completion of their jobs. To complement our intuition, we have conducted an empirical study using real cloud spot price traces to evaluate our framework strategies which aim to achieve a resilient deadline-aware auction framework.

Virtual machines (VMs) are used in cloud computing systems to handle user requests for service. Failure of VMs cause that the user's request not being completed. Replication mechanisms can be used to mitigate the impact of VM failures. In this paper, we are primarily interested in characterizing the failure-recovery behavior of a VM in cloud with different replication schemes. We use a service-oriented dependability metric called Defects Per Million (DPM) defined as the number of user requests dropped out of a million, due to VM failures. We present an analytical modeling approach for computing the DPM metric in different replication schemes on the basis of structure-state process and checkpointing method. The effectiveness of replication schemes are demonstrated through experimental results. To verify the validity of the proposed analytical models, we extend the widely used cloud simulator CloudSim and compare the simulation results with analytical solutions.

Traditional system-oriented dependability metrics like reliability and availability do not fully reflect the impact of system failure-repair behavior in service-oriented environments. The telecommunication systems community prefers to use Defects Per Million (DPM), defined as the number of calls dropped out of a million calls due to failures, as a user-perceived dependability metric. In this paper, we provide new formulation for the computation of the DPM metric for a system supporting Voice over IP functionality using the Session Initiation Protocol (SIP). We evaluate different replication schemes that can be used at the SIP application server. They include the effects of software failure, failure detection, recovery mechanisms, and imperfect coverage for recovery mechanisms. We derive closed-form expressions for the DPM taking into account the transient behavior of recovery after a failure. Our approach and underlying models can be readily extended to other types of service-oriented environments.

In cloud computing systems, a user request goes through several cloud service provider specific processing steps from the instant it is submitted until the service is completed. In this paper, we use service-oriented metrics to characterize the dependability of cloud computing systems in order to find the pitfalls and improve the service. We find that it is not possible to fully reflect the impact of a cloud-service's dependability behavior through traditional dependability metrics like availability or reliability. We use a user-perceived dependability metric called Defects Per Million (DPM), defined as the number of user requests dropped out of a million. We demonstrate a new formulation for computing DPM metric in cloud computing systems. We incorporate check pointing scheme for job execution in the cloud to mitigate the impact of virtual machine failures, and compute DPM in order to characterize the improvement in the DPM due to the check pointing scheme compared to no-check pointing scheme.

Virtual machines (VM) are used in cloud computing systems to handle user requests for service. A typical user request goes through several cloud service provider specific processing steps from the instant it is submitted until the service is completed. In the process of providing the service, VM failures cause the user's request to be dropped. To mitigate the adverse impact of VM failure, replication mechanisms, either using cold, warm or hot replication, can be used. In this paper, we model the system behavior with a structure-state process to characterize the failure-recovery behavior of a VM in a cloud that uses one of the aforementioned replication schemes. We use a service-oriented dependability metric called Defects Per Million (DPM), defined as the number of user requests dropped out of a million. The structure-state process approach is used to analyze the job completion time distribution and subsequently we compute the DPM by counting the number of requests exceed the specified deadline. The effectiveness of replication schemes are demonstrated through numerical results.