http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
LDCSIR: Lightweight Deep CNN-based Approach for Single Image Super-Resolution
Muhammad, Wazir,Shaikh, Murtaza Hussain,Shah, Jalal,Shah, Syed Ali Raza,Bhutto, Zuhaibuddin,Lehri, Liaquat Ali,Hussain, Ayaz,Masrour, Salman,Ali, Shamshad,Thaheem, Imdadullah International Journal of Computer ScienceNetwork S 2021 International journal of computer science and netw Vol.21 No.spc12
Single image super-resolution (SISR) is an image processing technique, and its main target is to reconstruct the high-quality or high-resolution (HR) image from the low-quality or low-resolution (LR) image. Currently, deep learning-based convolutional neural network (CNN) image super-resolution approaches achieved remarkable improvement over the previous approaches. Furthermore, earlier approaches used hand designed filter to upscale the LR image into HR image. The design architecture of such approaches is easy, but it introduces the extra unwanted pixels in the reconstructed image. To resolve these issues, we propose novel deep learning-based approach known as Lightweight deep CNN-based approach for Single Image Super-Resolution (LDCSIR). In this paper, we propose a new architecture which is inspired by ResNet with Inception blocks, which significantly drop the computational cost of the model and increase the processing time for reconstructing the HR image. Compared with the other state of the art methods, LDCSIR achieves better performance in terms of quantitively (PSNR/SSIM) and qualitatively.
Wazir Muhammad,Asad Ullah,Amjad Hussain,Nawab Ali,Khan Alam,Gulzar Khan,Matiullah,뱅수진,이상훈 한국물리학회 2015 THE JOURNAL OF THE KOREAN PHYSICAL SOCIETY Vol.67 No.3
A medical linear accelerator (LINAC) room must be properly shielded to limit the outside radiation exposure to an acceptable safe level defined by individual state and international regulations. However, along with this prime objective, some additional issues are also important. The current case-study was designed to unfold the issues related to over-shielded and unplanned treatment rooms for LINACs. In this connection, an apparently unplanned and over-shielded treatment room of 610 × 610 cm2 in size was compared with a properly designed treatment room of 762 × 762 cm2 in size (i.e., by following the procedures and recommendations of the IAEA Safety Reports Series No. 47 and NCRP 151). Evaluation of the unplanned room indicated that it was over-shielded and that its size was not suitable for total body irradiation (TBI), although the license for such a treatment facility had been acquired for the installed machine. An overall 14.96% reduction in the total shielding volume (i.e., concrete) for an optimally planned room as compared to a non-planned room was estimated. Furthermore, the inner room’s dimensions were increased by 25%, in order to accommodate TBI patients. These results show that planning and design of the treatment rooms are imperative to avoid extra financial burden to the hospitals and to provide enough space for easy and safe handling of the patients. A spacious room is ideal for storing treatment accessories and facilitates TBI treatment.
Muhammad, Wazir,Hussain, Ayaz,Shah, Syed Ali Raza,Shah, Jalal,Bhutto, Zuhaibuddin,Thaheem, Imdadullah,Ali, Shamshad,Masrour, Salman International Journal of Computer ScienceNetwork S 2021 International journal of computer science and netw Vol.21 No.11
Recently, image super-resolution techniques used in convolutional neural networks (CNN) have led to remarkable performance in the research area of digital image processing applications and computer vision tasks. Convolutional layers stacked on top of each other can design a more complex network architecture, but they also use more memory in terms of the number of parameters and introduce the vanishing gradient problem during training. Furthermore, earlier approaches of single image super-resolution used interpolation technique as a pre-processing stage to upscale the low-resolution image into HR image. The design of these approaches is simple, but not effective and insert the newer unwanted pixels (noises) in the reconstructed HR image. In this paper, authors are propose a novel single image super-resolution architecture based on synchronized depthwise separable convolution with Dense Skip Connection Block (DSCB). In addition, unlike existing SR methods that only rely on single path, but our proposed method used the synchronizes path for generating the SISR image. Extensive quantitative and qualitative experiments show that our method (SDCN) achieves promising improvements than other state-of-the-art methods.
LDCSIR: Lightweight Deep CNN-based Approach for Single Image Super-Resolution
Muhammad, Wazir,Shaikh, Murtaza Hussain,Shah, Jalal,Shah, Syed Ali Raza,Bhutto, Zuhaibuddin,Lehri, Liaquat Ali,Hussain, Ayaz,Masrour, Salman,Ali, Shamshad,Thaheem, Imdadullah International Journal of Computer ScienceNetwork S 2021 International journal of computer science and netw Vol.21 No.12
Single image super-resolution (SISR) is an image processing technique, and its main target is to reconstruct the high-quality or high-resolution (HR) image from the low-quality or low-resolution (LR) image. Currently, deep learning-based convolutional neural network (CNN) image super-resolution approaches achieved remarkable improvement over the previous approaches. Furthermore, earlier approaches used hand designed filter to upscale the LR image into HR image. The design architecture of such approaches is easy, but it introduces the extra unwanted pixels in the reconstructed image. To resolve these issues, we propose novel deep learning-based approach known as Lightweight deep CNN-based approach for Single Image Super-Resolution (LDCSIR). In this paper, we propose a new architecture which is inspired by ResNet with Inception blocks, which significantly drop the computational cost of the model and increase the processing time for reconstructing the HR image. Compared with the other state of the art methods, LDCSIR achieves better performance in terms of quantitively (PSNR/SSIM) and qualitatively.
Azeem Umair,Younis Hannan,ullah Niamat,Mehboob Khurram,Ajaz Muhammad,Ali Mushtaq,Hidayat Abdullah,Muhammad Wazir 한국원자력학회 2024 Nuclear Engineering and Technology Vol.56 No.1
This study focuses on measuring the levels of naturally occurring radioactivity in the soil of Swabi, Khyber Pakhtunkhwa, Pakistan, as well as the associated health hazard. Thirty (30) soil samples were collected from various locations and analyzed for 226Ra, 232Th, and 40K radioactivity levels using a High Purity Germanium detector (HPGe) gamma-ray spectrometer with a photo-peak efficiency of approximately 52.3%. The average values obtained for these radionuclides are 35.6 ± 5.7 Bqkg 1, 47 ± 12.5 Bqkg 1, and 877 ± 153 Bqkg 1, respectively. The level of 232Th is slightly higher and 40K is 2.2 times higher than the internationally recommended limit of 30 Bqkg 1 and 400 Bqkg 1, respectively. Various parameters were calculated based on the results obtained, including Radium Equivalent (Raeq), External Hazard (Hex), Absorbed Dose Rate (D), Annual Gonadal Equivalent Dose (AGDE), Annual Effective Dose Rate, and Excess Lifetime Cancer Risk (ELCR), which are 170.3 ± 24 Bqkg 1, 0.46 ± 0.06 Bqkg 1, 81.4 ± 2.04 nGy h 1, 582 ± 78.08 μSvy 1, 99.8 ± 13.5 μSv Gy 1, and 0.349 ± 0.04, respectively. These values are below the limits recommended by the United Nations Scientific Committee on the Effects of Atomic Radiation (UNSCEAR) in 2002. This study highlights the potential radiation threats associated with natural radioactivity levels in the soil of Swabi and provides valuable information for public health and safety
Hannan Younis,Sumbilah Shafique,Zahida Ehsan,Aleena Ishfaq,Khurram Mehboob,Muhammad Ajaz,Abdullah Hidayat,Wazir Muhammad Korean Nuclear Society 2023 Nuclear Engineering and Technology Vol.55 No.7
The radioactivity concentrations of Naturally Occurring Radioactive Materials (NORM) i.e., <sup>226</sup>Ra, <sup>232</sup>Th, and <sup>4</sup>K in various chemical fertilizers being used in the agricultural soil of Pakistan were determined utilizing gamma spectrometry by employing a High Purity Germanium (HPGe) detector. The radioactivity concentrations of <sup>226</sup>Ra, <sup>232</sup>Th, and <sup>4</sup>K extended from 2.58 ± 0.8-265.7 ± 8.8 Bq kg<sup>-1</sup>, 1.53 ± 0.14-76.6 ± 1.07 Bq kg<sup>-1</sup> and 36.5 ± 1.34-15606.7 ± 30.2 Bq kg<sup>-1</sup> respectively. The radiological hazard parameters such as internal and external indices and annual effective dose rates were calculated, while excessive lifetime cancer risk factors for the indoor and outdoor areas were found in the range from 0.3×10<sup>-3</sup> to 10.723×10<sup>-3</sup> and 0.03×10<sup>-3</sup> to 2.7948×10<sup>-3</sup> of most fertilizers, however, some values were slightly higher than the UNSCEAR (The United Nations Scientific Committee on the Effects of Atomic Radiation) recommended values for potash-containing fertilizers such as MOP (Muriate of Potash).