http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Step towards the Improvement in the Performance of Text Classification
( Shahid Hussain ),( Muhammad Rafiq Mufti ),( Muhammad Khalid Sohail ),( Humaira Afzal ),( Ghufran Ahmad ),( Arif Ali Khan ) 한국인터넷정보학회 2019 KSII Transactions on Internet and Information Syst Vol.13 No.4
The performance of text classification is highly related to the feature selection methods. Usually, two tasks are performed when a feature selection method is applied to construct a feature set; 1) assign score to each feature and 2) select the top-N features. The selection of top-N features in the existing filter-based feature selection methods is biased by their discriminative power and the empirical process which is followed to determine the value of N. In order to improve the text classification performance by presenting a more illustrative feature set, we present an approach via a potent representation learning technique, namely DBN (Deep Belief Network). This algorithm learns via the semantic illustration of documents and uses feature vectors for their formulation. The nodes, iteration, and a number of hidden layers are the main parameters of DBN, which can tune to improve the classifier’s performance. The results of experiments indicate the effectiveness of the proposed method to increase the classification performance and aid developers to make effective decisions in certain domains.
Association of the CYP17-34T/C Polymorphism with Pancreatic Cancer Risk
Hussain, Shahid,Bano, Raisa,Khan, Muhammad Tahir,Khan, Mohammad Haroon Asian Pacific Journal of Cancer Prevention 2016 Asian Pacific journal of cancer prevention Vol.17 No.no.sup3
Pancreatic cancer is a leading cause of fatality worldwide. Several population studies have been conducted on genetic diagnosis of pancreatic cancer but the results from epidemiologic studies are very limited. CYP17A gene has a role in disease formation but its influence on pancreatic cancer is unclear. A polymorphism in the 5'UTR promoter region of CYP17A1-34T/C (A1/A2) has been associated with multiple cancers. The aim of the current study was to assess associations of this polymorphism and socio-demographic risk factors with pancreatic cancer. A total of 255 and 320 controls were enrolled in the study, and were genetically analyzed through PCR-RFLP. Statistical analysis was conducted with observed genotype frequencies and odds ratios (ORs) and 95% CIs were estimated using unconditional logistic regression. The impact of socio-demographic factors was accessed through Kaplen-Meir analysis. According to our results, the A2/A2 genotype was significantly associated with pancreatic cancer (OR=2.1, 95%CI = 1.3-3.5). Gender female (OR=2.6, 95%CI=1.8-3.7), age group 80s/80+ years (OR=2.2, 95% CI=1.2-4), smoking both former (OR=4.6, 95% CIs=2.5-8.8) and current (OR=3.6, 95% CI=2-6.7), and family history (OR=7.1; 95%CI = 4.6-11.4) were also found associated with increased risk. Current study suggests that along with established risk factors for pancreatic cancer CYP17A1-34T/C may play a role. However, on the basis of small sample size the argument cannot be fully endorsed and larger scale studies are recommended.
Implications of deep learning for the automation of design patterns organization
Hussain, Shahid,Keung, Jacky,Khan, Arif Ali,Ahmad, Awais,Cuomo, Salvatore,Piccialli, Francesco,Jeon, Gwanggil,Akhunzada, Adnan Elsevier 2018 Journal of parallel and distributed computing Vol.117 No.-
<P><B>Abstract</B></P> <P>Though like other domains such as email filtering, web page classification, sentiment analysis, and author identification, the researchers have employed the text categorization approach to automate organization and selection of design patterns. However, there is a need to bridge the gap between the semantic relationship between design patterns (i.e. Documents) and the features which are used for the organization of design patterns. In this study, we propose an approach by leveraging a powerful deep learning algorithm named Deep Belief Network (DBN) which learns on the semantic representation of documents formulated in the form of feature vectors. We performed a case study in the context of a text categorization based automated system used for the classification and selection of software design patterns. In the case study, we focused on two main research objectives: 1) to empirically investigate the effect of feature sets constructed through the global filter-based feature selection methods besides the proposed approach, and 2) to evaluate the significant improvement in the classification decision (i.e. Pattern organization) of classifiers using the proposed approach. The adjustment of DBN parameters such as a number of hidden layers, nodes and iteration can aid a developer to construct a more illustrative feature set. The experimental promising results suggest the significance of the proposed approach to construct a more representative feature set and improve the classifier’s performance in terms of organization of design patterns.</P> <P><B>Highlights</B></P> <P> <UL> <LI> There is a need to bridge the gap between the semantic relationship between patterns. </LI> <LI> We propose an approach by leveraging a powerful deep learning algorithm named Deep Belief Network (DBN). </LI> <LI> The DBN learns on the semantic representation of documents formulated in the form of feature vectors. </LI> <LI> We performed a case study in the context of a text categorization based automated system. </LI> <LI> The experimental promising results suggest the significance of the proposed approach to construct a more representative feature set. </LI> </UL> </P>
Hussain Shahid,Jamwal Prashant K,Van Vliet Paulette 한국CDE학회 2021 Journal of computational design and engineering Vol.8 No.6
Neuroplasticity allows the human nervous system to adapt and relearn motor control following stroke. Rehabilitation therapy, which enhances neuroplasticity, can be made more effective if assisted by robotic tools. In this paper, a novel 4-SPS parallel robot has been developed to provide recovery of wrist movements post-stroke. The novel mechanism presented here was inspired by the forearm anatomy and can provide the rotational degrees of freedom required for all wrist movements. The robot design has been discussed in detail along with the necessary constructional, kinematic, and static analyses. The spatial workspace of the robot is estimated considering various dimensional and application-specific constraints besides checking for singular configurations. The wrist robot has been further evaluated using important performance indices such as condition number, actuator forces, and stiffness. The pneumatic artificial muscles exhibit varying stiffness, and therefore, workspace points are reached with different overall stiffness of the robot. It is essential to assess robot workspace points that can be reached with positive forces in actuators while maintaining a positive definite overall stiffness matrix. After the above analysis, design optimization has been carried out using an evolutionary algorithm whereby three critical criteria are optimized simultaneously for optimal wrist robot design.