Ibrar Ahmad

Ibrar Ahmad

Auto-generated profile, based on publicly available information

Ibrar Ahmad

Center for Intelligence of Science and Technology, Beijing University of Posts and Telecommunications, Beijing, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 May 2017 in IEEE Access
Verified
Journal Article
Open access
IAIbrar Ahmad
Ibrar Ahmad
XWXiaojie Wang
Xiaojie Wang
Ruifan LiRuifan Li
Ruifan Li
MAManzoor Ahmed
Manzoor Ahmed
RURahat Ullah
Rahat Ullah
The recognition accuracy of ligature-based Urdu language optical character recognition (OCR) systems highly depends on the accuracy of segmentation that converts Urdu text into lines and ligatures. In general, lines and ligatures-based Urdu language OCRs are more successful as compared to characters-based. This paper presents the techniques for segmenting Urdu Nastaleeq text images into lines and subsequently to ligatures. Classical horizontal projection-based segmentation method is augmented with a curved-line-split algorithm for successfully overcoming the problems, such as text line split position, overlapping, merged ligatures, and ligatures crossing line split positions. Ligature segmentation algorithm extracts connected components from text lines, categorizes them into primary and secondary classes, and allocates secondary components to the primary class by examining width, height, coordinates, overlapping, centroids, and baseline information. The proposed line segmentation algorithm is tested on 47 pages with 99.17% accuracy. The proposed ligature segmentation algorithm is mainly tested on a large Urdu-printed text images data set. The proposed algorithm segmented Urdu-printed text images data set to 189 000 ligatures from 10 063 text lines having 332 000 connected components. A total of about 142 000 secondary components have been successfully allocated to more than 189 000 primary ligatures with accuracy rate of 99.80%. Thus, both of the proposed segmentation algorithms outperform the existing algorithms employed for Urdu Nastaleeq text segmentation. Moreover, the proposed line segmentation algorithm is also tested on Arabic, for which it also extracted lines correctly.

22 June 2017 in Cluster Computing
Verified
Journal Article
Closed access
PDF file
IAIbrar Ahmad
Ibrar Ahmad
XWXiaojie Wang
Xiaojie Wang
YMYuz Hao Mao
Yuz Hao Mao
GLGuang Liu
Guang Liu
HAHaseeb Ahmad
Haseeb Ahmad
RURahat Ullah
Rahat Ullah

7 December 2017 in IEEE Microwave and Wireless Components Letters
Verified
Journal Article
Closed access
MKMuhammad Saad Khan
Muhammad Saad Khan
HZHongxin Zhang
Hongxin Zhang
XWXueli Wang
Xueli Wang
RURahat Ullah
Rahat Ullah
IAIbrar Ahmad
Ibrar Ahmad
MTMuhammad Zahid Tunio
Muhammad Zahid Tunio
Broadband and highly efficient amplifiers are of great interest in modern wireless communication systems. In this paper, we present a novel two-stage broadband Doherty power amplifier (DPA), which is able to maintain high efficiency at saturated output power and at backoff output power levels over a wide bandwidth. The amplifier uses a novel and simple approach to achieve bandwidth enhancement and at the same time uses a driver amplifier. We employ Klopfenstein taper to deliver wide bandwidth. The measurement results show that the proposed broadband two-stage DPA is able to deliver 31%–35% drain efficiency at 6-dB output power backoff while at the saturation it achieves 40%–55% drain efficiency over the designed bandwidth of 1.5 to 2.6 GHz. The amplifier can deliver above 35-dBm output power with substantial gain of around 20 dB. The proposed DPA is a promising candidate for wideband and high gain requirements in modern wireless systems.

25 May 2017 in Cluster Computing
Verified
Journal Article
Closed access
PDF file
HAHaseeb Ahmad
Haseeb Ahmad
ADAli Daud
Ali Daud
LWLicheng Wang
Licheng Wang
IAIbrar Ahmad
Ibrar Ahmad
Muhammad HafeezMuhammad Hafeez
Muhammad Hafeez
YYYixian Yang
Yixian Yang

1 July 2017
Verified
Conference Paper
Closed access
Ruifan LiRuifan Li
Ruifan Li
YMYuzhao Mao
Yuzhao Mao
IAIbrar Ahmad
Ibrar Ahmad
FFFangxiang Feng
Fangxiang Feng
XWXiaojie Wang
Xiaojie Wang
Clothing images are abundant especially from the ecommercial platform, due to the rapid development of e-business. Recognizing and retrieving those images is of importance for commercial and social applications, which has recently been received tremendous attention from multimedia processing and computer vision. However, the large variations in clothing of their appearance and style, and even the large quantity of multiple categories and attributes make those problems challenging. Furthermore, the labels provided by shop retailers for real world images are largely erroneous or incomplete. Even worse, the imbalance problem among those image categories prevents the effective learning. To overcome those problems, we adopt a multi-task deep learning framework to learn effective representation. And we propose multi-weight convolutional neural networks for imbalance learning. The topology of this network is composed of two kinds of layers, shared layers at the bottom and task dependent ones at the top. Furthermore, category-relevant parameters are incorporated to regularize the learning procedure of backward gradients for different categories. We collect a large-scale dataset for those two problems containing about one million shop photos from four different Chinese retailers. Experiments on this dataset demonstrate that our proposed joint framework and multi-weight neural networks can effectively learn robust representation and achieve better performance.

23 June 2022 in American Journal of Health, Medicine and Nursing Practice
Verified
Journal Article
Open access
PDF file
IAIbrar Ahmad
Ibrar Ahmad
HKHoor Maab Kaifi
Hoor Maab Kaifi
Fahim UllahFahim Ullah
Fahim Ullah
AJAdan Javed
Adan Javed
HTHira Tahir
Hira Tahir
MRMujeeb ur Rahman
Mujeeb ur Rahman
Purpose: To figure out the prevalence of malnutrition among patients with Type-2 Diabetes Mellitus (T2DM) in tertiary care hospital Methodology: The study adopted a cross-sectional study. The study took place in Endocrine and Medicine Departments of Lady Reading Hospital, Peshawar, Pakistan from September 2019 to March 2020. A total number of 259 patients of T2DM were screened for screened for nutritional assessment with the help of nurse and supporting staff. The data was recorded with the help of question are and Subjective Global Assessment form (SGA). The nutritional risk parameters and malnutrition status was figured out and the data collected was statistically analyzed with the help of MS Excel and SPSS 22.0. Findings: The results of the current findings revealed that 123 patients out of 259 were at moderate risk of malnutrition, while 136 patients were highly at malnutrition risk. Similarly, 162 patients were sorted out to have the status of moderate malnutrition while 97 patients were severely mal-nourished. Among various categories of BMI the highest frequency has been shown by Obese Class-I with highest risk malnutrition risk and severe malnourished frequency. The Correlation Coefficient R2 value of 0.923. The Chi-Square value of 187.69 and p-value (1.214e-38) nullifies the Null hypothesis. Conclusion: Based on the findings of this study, it may be concluded that a wholesome ratio of T2DM are at nutritional risk or having the status of malnutrition in hospitalized patients. Secondly, it may also be inferred that the largest number of T2DM could be assumed at Obese Class-I of BMI distribution.