Automated techniques for Arabic content recognition are at a beginning period contrasted with their partners for the Latin and Chinese contents recognition. There is a bulk of handwritten Arabic archives available in libraries, data centers, historical centers, and workplaces. Digitization of these documents facilitates (1) to preserve and transfer the country’s history electronically, (2) to save the physical storage space, (3) to proper handling of the documents, and (4) to enhance the retrieval of information through the Internet and other mediums. Arabic handwritten character recognition (AHCR) systems face several challenges including the unlimited variations in human handwriting and the leakage of large and public databases. In the current study, the segmentation and recognition phases are addressed. The text segmentation challenges and a set of solutions for each challenge are presented. The convolutional neural network (CNN), deep learning approach, is used in the recognition phase. The usage of CNN leads to significant improvements across different machine learning classification algorithms. It facilitates the automatic feature extraction of images. 14 different native CNN architectures are proposed after a set of try-and-error trials. They are trained and tested on the HMBD database that contains 54,115 of the handwritten Arabic characters. Experiments are performed on the native CNN architectures and the best-reported testing accuracy is 91.96%. A transfer learning (TF) and genetic algorithm (GA) approach named “HMB-AHCR-DLGA” is suggested to optimize the training parameters and hyperparameters in the recognition phase. The pre-trained CNN models (VGG16, VGG19, and MobileNetV2) are used in the later approach. Five optimization experiments are performed and the best combinations are reported. The highest reported testing accuracy is 92.88%.
This paper presents the results of an investigation of induced residual stress, induced strain, and induced subsurface energy
in machined surfaces due to the machining process. The influence of tool wear on residual stress, strain, and energy is also
reported. The exact elasticity solution for a split ring was extended and used to calculate the residual stress in the machined
surface by using ring dimension changes caused by the electrochemical removal of a thin layer of residually stressed surface.
The strain distribution beneath the machined surface was determined by using the grid technique. The subsurface energy stored
in the machined surface was then obtained from the data of residual stress and strain. For the materials studied, this investigation
showed that such energy could not be neglected when establishing the total energy needed for machining a unit volume of material.
Tool coatings having different surface roughness and tools having various magnitudes of flank wear were investigated. The
experimental results show that tool wear is a dominant factor affecting the values of induced residual stress, strain, subsurface
energy, and the quality of the machined surface. The increase of tool wear caused an increase of residual stress and strain
beneath the machined surface. It was also found that the overall energy stored in the machined subsurface increases as the
tool wear increases and as the tool surface gets rougher. When the cutting tool is severely worn, the machined surface not
only becomes very rough, but also contains many partially fractured laps or cracks. This makes tool wear a key factor in controlling
the quality of the machined surface. 相似文献
Haptic technologies and applications have received enormous attention in the last decade. The incorporation of haptic modality into multimedia applications adds excitement and enjoyment to an application. It also adds a more natural feel to multimedia applications, that otherwise would be limited to vision and audition, by engaging as well the user’s sense of touch, giving a more intrinsic feel essential for ambient intelligent applications. However, the improvement of an application’s Quality of Experience (QoE) by the addition of haptic feedback is still not completely understood. The research presented in this paper focuses on the effect of haptic feedback and what it potentially adds to the experience of the user as opposed to the traditional visual and auditory feedback. In essence, it investigates certain issues regarding stylus-based haptic education applications and haptic-enhanced entertainment videos. To this end, we used two haptic applications: the haptic handwriting learning tool to experiment with force feedback haptic interaction and the tactile YouTube application for tactile haptic feedback. In both applications, our analysis shows that the addition of haptic feedback will increase the QoE in the absence of fatigue or discomfort for this category of applications. This implies that the incorporation of haptic modality (both force feedback as well as tactile feedback) has positively contributed to the overall QoE for the users. 相似文献
Moving target detection (MTD) technique is designed to filtering out the clutters. The basis of the MTD digital signal processor is a bank of Doppler filters designed using FFT algorithm. For high pulse repetition frequency (HPRF), it leads to a long time calculations and great complexity in hardware implementation. Frequency domain detector is represented by Welch method Realized Doppler filters bank which will reduce the time calculation. The proposed method enhances the target detection capabilities by p... 相似文献
In this paper, load frequency control is performed for a two-area power system incorporating a high penetration of renewable energy sources. A droop controller for a type 3 wind turbine is used to extract the stored kinetic energy from the rotating masses during sudden load disturbances. An auxiliary storage controller is applied to achieve effective frequency response. The coot optimization algorithm (COA) is applied to allocate the optimum parameters of the fractional-order proportional integral derivative (FOPID), droop and auxiliary storage controllers. The fitness function is represented by the summation of integral square deviations in tie line power, and Areas 1 and 2 frequency errors. The robustness of the COA is proven by comparing the results with benchmarked optimizers including: atomic orbital search, honey badger algorithm, water cycle algorithm and particle swarm optimization. Performance assessment is confirmed in the following four scenarios: (i) optimization while including PID controllers; (ii) optimization while including FOPID controllers; (iii) validation of COA results under various load disturbances; and (iv) validation of the proposed controllers under varying weather conditions. 相似文献
The Journal of Supercomputing - Power consumption is likely to remain a significant concern for exascale performance in the foreseeable future. In addition, graphics processing units (GPUs) have... 相似文献