Horizontal Kernels Research Articles

A Low-Cost Hardware Design of Learning-Based One-Dimensional Interpolation for Real-Time Video Applications at the Edge

Gradual advances have occurred in the design of micro-artificial intelligence for resource-limited hardware. A high-resolution (HR) image reconstruction module is indispensable for video analytics chips or devices at the edge. This paper proposes a low-cost and learning-based interpolation method for HR image reconstruction. The proposed method generates reconstructed pixels by processing reference pixels with optimal weights, which are pre-trained by solving the minimum mean square error problem for real images. To reduce the number of computation units and the usage of learned weights, a cross-directional interpolation architecture, which includes a vertical kernel and a horizontal kernel, is adopted. Moreover, a one-dimensional feature discriminator is proposed to improve the quality of up-scaled images efficiently. The main benefit of the proposed method is that it requires a small number of computation units but can still produce high-quality images. The hardware architecture of the proposed method was implemented on a field-programmable gate array (FPGA) by using Xilinx UltraScale+ ZCU102 and an application-specific integrated circuit (ASIC) by using TSMC’s 0.13-μm technology. On the ASIC, the proposed hardware required only approximately 60K gate counts and 50 KBytes of memory. The experimental results indicate that the average peak signal-to-noise ratio of the up-scaled images reached 35.92 dB for the Set-5 dataset. The throughput of the proposed hardware was at least 1000 Mpixels/s on the FPGA and 1200 Mpixels/s on the ASIC, which indicates that the proposed hardware can handle a target resolution higher than 4K in real time.

UnetDVH-Linear: Linear Feature Segmentation by Dilated Convolution with Vertical and Horizontal Kernels.

Linear feature extraction is crucial for special objects in semantic segmentation networks, such as slot marking and lanes. The objects with linear characteristics have global contextual information dependency. It is very difficult to capture the complete information of these objects in semantic segmentation tasks. To improve the linear feature extraction ability of the semantic segmentation network, we propose introducing the dilated convolution with vertical and horizontal kernels (DVH) into the task of feature extraction in semantic segmentation networks. Meanwhile, we figure out the outcome if we put the different vertical and horizontal kernels on different places in the semantic segmentation networks. Our networks are trained on the basis of the SS dataset, the TuSimple lane dataset and the Massachusetts Roads dataset. These datasets consist of slot marking, lanes, and road images. The research results show that our method improves the accuracy of the slot marking segmentation of the SS dataset by 2%. Compared with other state-of-the-art methods, our UnetDVH-Linear (v1) obtains better accuracy on the TuSimple Benchmark Lane Detection Challenge with a value of 97.53%. To prove the generalization of our models, road segmentation experiments were performed on aerial images. Without data argumentation, the segmentation accuracy of our model on the Massachusetts roads dataset is 95.3%. Moreover, our models perform better than other models when training with the same loss function and experimental settings. The experiment result shows that the dilated convolution with vertical and horizontal kernels will enhance the neural network on linear feature extraction.

Inferring Transcription Factor interactions using a novel HV-SVM classifier

Interactions between Transcription Factors (TFs) are necessary for deciphering the complex mechanisms of transcription regulation in eukaryotes. We proposed a novel HV-kernel based SVM classifier to classify TF-TF pairs based on their protein domains and GO annotations. Two types of pairwise kernels, namely, a horizontal kernel and a vertical kernel, were combined to evaluate the similarity between a pair of TFs, and a Genetic Algorithm was used to obtain kernel and feature weights to optimise the classifier's performance. We showed that our proposed HV-SVM method can make accurate predictions of TF-TF interactions even in the higher and more complex eukaryotes.

Diffusion of carbon dioxide through grain bulks

The diffusion coefficient of carbon dioxide (CO 2) through grain bulks was determined using a transient method with the following variables: (1) grain bulk (wheat, barley, and canola); (2) moisture content (m.c.) (dry, damp, and wet conditions); (3) temperature (5°C, 15°C, 25°C, and 40°C); (4) direction of gas flow (upwards, downwards, and horizontal); (5) porosity (two levels for each grain bulk); (6) grain kernel orientation (vertical and horizontal); (7) initial concentration in the gas chamber (20%, 40%, and 60%); and (8) dockage (0%, 4%, 8%, and 12%). The diffusion coefficients of CO 2 through wheat bulks ranged from 5.9×10 −6 to 7.6×10 −6 m 2 s −1, through barley bulks from 5.1×10 −6 to 8.4×10 −6 m 2 s −1, and through canola bulks from 3.7×10 −6 to 5.3×10 −6 m 2 s −1 for the test conditions studied. Increasing the m.c. decreased diffusion coefficients. An increase in temperature generally increased the diffusion coefficient of CO 2. Diffusion in the downward direction resulted in higher diffusion coefficients. No significant difference in diffusion coefficients was observed between the upward and horizontal directions of flow. An increase in porosity resulted in higher diffusion coefficients. The upward diffusion coefficient of CO 2 was higher for vertical grain kernel orientation than for horizontal kernel orientation for wheat and barley but for canola, the difference between the two kernel orientations was not significant. There was no significant difference in diffusion coefficients for different initial gas concentrations. The diffusion coefficient increased linearly as the dockage was increased. The amount of CO 2 absorbed by barley and canola increased with an increase in m.c. in polynomial fashion. There was no significant difference in the sorption of CO 2 by barley and canola when the temperature of the grain was changed from 15°C to 40°C.

Genotypic and Environmental Factors Affecting Seed Coat Durability of Field Peas

The diffusion coefficient of carbon dioxide (CO2) through grain bulks was determined using a transient method with the following variables: (1) grain bulk (wheat, barley, and canola); (2) moisture content (m.c.) (dry, damp, and wet conditions); (3) temperature (5°C, 15°C, 25°C, and 40°C); (4) direction of gas flow (upwards, downwards, and horizontal); (5) porosity (two levels for each grain bulk); (6) grain kernel orientation (vertical and horizontal); (7) initial concentration in the gas chamber (20%, 40%, and 60%); and (8) dockage (0%, 4%, 8%, and 12%). The diffusion coefficients of CO2 through wheat bulks ranged from 5.9×10−6 to 7.6×10−6 m2 s−1, through barley bulks from 5.1×10−6 to 8.4×10−6 m2 s−1, and through canola bulks from 3.7×10−6 to 5.3×10−6 m2 s−1 for the test conditions studied.Increasing the m.c. decreased diffusion coefficients. An increase in temperature generally increased the diffusion coefficient of CO2. Diffusion in the downward direction resulted in higher diffusion coefficients. No significant difference in diffusion coefficients was observed between the upward and horizontal directions of flow. An increase in porosity resulted in higher diffusion coefficients. The upward diffusion coefficient of CO2 was higher for vertical grain kernel orientation than for horizontal kernel orientation for wheat and barley but for canola, the difference between the two kernel orientations was not significant. There was no significant difference in diffusion coefficients for different initial gas concentrations. The diffusion coefficient increased linearly as the dockage was increased.The amount of CO2 absorbed by barley and canola increased with an increase in m.c. in polynomial fashion. There was no significant difference in the sorption of CO2 by barley and canola when the temperature of the grain was changed from 15°C to 40°C.