VFAST - Virtual Foundation for Advancement of Science and Technology (Pakistan)
Not a member yet
1255 research outputs found
Sort by
Brain Tumor Segmentation using Deep Learning
Get PDFIn addition to helping doctors discover and measure tumors, it also helps them develop better recovery and treatment plans. Recent MRI brain tumor segmentation algorithms have focused on U-Net design to combine high-level and low-level features for improved accuracy. Fully convolutional networks, which are also used for this purpose, are unable to successfully reconstruct the image through the decoder path because of the insufficient and low-level information from the encoder path. More effort needs to be done to optimise the low-level information flow from the encoder path to the decoder path in order to improve image reconstruction. In this study, we suggested a transfer learning residual U-Net model that combines the U-Net and VGG-16 architectures. To improve image reconstruction, VGG-16 is combined with the encoder. Additionally, a residual path in skipping connection is included to highlight key feature details while muting noisy and unnecessary feature replies. It is trained using The Cancer Imaging Achieve (TCIA) and Brats 2018 datasets, and It makes it easier to segment small brain tumors. When compared to previous brain tumor segmentation techniques, the suggested model performs competitively
An ensembling approach to predict hepatitis in patients with liver disease using machine learning
Get PDFWith a 3.5% mortality rate, liver disease is one of the worst diseases in existence. Pakistan is targeting this major health issue from several perspectives, to improve prevention, diagnosis, and treatment due to having the highest incidence of liver disorders in the world. For liver problem disease, also known as HEP C, Pakistan is now the second most prevalent country in the world. This is due to the rapid progression of HEP C, which can only be stopped by early diagnosis. If not, it progresses to the last stage of HEP C cirrhosis, which has no other treatment options besides liver transplantation. One and only machine learning algorithms like logistic regression, random forest, KNN, K-Means, and XGBoost can be used to predict liver illness utilizing modern methods like artificial intelligence. Data is gathered from Kaggle and subjected to several machine learning algorithms after pre-processing in order to quickly diagnose liver disease. Additionally, to improve accuracy, all of these algorithms are ensemble, and accuracy is 78.96%, along with precision, recall, and F1 score. In this work, liver disease is predicted early on using pre-processing, feature extraction, and classification techniques. Recall, precision, and f1score metrics are used to compare the accuracy of the six algorithms, and these algorithms are then combined to provide the most accurate diagnosis of liver disease
Exploring the themes for Quality Assurance at Secondary Level in Punjab: A Document Analysis
Get PDFQuality assurance (Q.A.) in education is the process of ensuring that educational programs and services meet established standards and expectations. This study aimed to explore themes for quality assurance in secondary schools at the Punjab level to enhance and evaluate the quality assurance process. In order to support in-depth realities, the exploration study is grounded in the interpretivism research paradigm. Data were collected by using the document analysis technique on quality assurance standards documents implemented in different countries around the world; In-depth qualitative analysis was performed with the use of NVivo 12 software. The study\u27s various themes have been confirmed via the use of numerous methods, including Coding Nodes, Word Trees, Word Tag Clouds, and Treemaps. Documents from eleven countries were selected to achieve the study’s objective; the most updated and relative themes were extracted and presented diagrammatically and in tabular form. A total of twelve themes were found through a thematic analysis process. Twelve themes were explored and named 1)assessment;2)community involvement; 3)curriculum; 4)early childhood education;5)school environments; 6)school ethos and value;.7)Facilities for schools;8)H)school administration and management, 9)school quality management and improvement. 10)School Mission, Vision, and Objectives ,11)Teacher Standards,12)Student Standards This research study is applicable at the secondary school level in the quality assurance process. The research finding highlighted the most relevant themes/factors used in quality assurance process; to enhance or evaluate the quality assurance practices. The outcome of this research study bridges the gap in the existing literature by offering empirical knowledge on the school quality assurance process at the secondary school level. This is the first research done in an Asian setting to focus specifically on quality assurance and its associated themes and processes. This study may eventually improve educational standards and student performance
Investigating the Role of English as a Second Language in Supporting Career Development at Tertiary Level Education in Pakistan
Get PDFThis study has taken the initiation to focus on the interrelatedness and discontinuity of ESL among the students of four leading International universities: Punjab University, Lahore College for Women University, University of Management and Technology, and the University of Central Punjab. To observe the usage of ESL competencies in information searching, contrivance treatment, and construction for research purposes, and for applied intercultural professionalism, communication accommodation theory with career development indicators has been applied. A questionnaire (α = .702), comprising 37 statements based upon six domains was administered. The data was collected from 850 students of different degree programs in journalism and mass communication discipline. ANOVA (one-way) and t-tests (Independent Samples) were brought into play to find out the relationship between the study’s variables. Both government-regulated and non-government varsities bespoke similarities feting positive treatment of ESL’s functions while managing its impact according to their atmospheric obligations. The students of PU and LCWU proportionately adjudged second language more as confluent, dispenser, endorser, broker, liaison, and facilitator to be the source of providence for media in Pakistan as compared to the students of UMT and UCP. Overall results show that students took more precedence over practice patterns of ESL in their career building
Impact of American Literature on Behaviour of the Students of Public Sector Colleges of Kotli AJ&K
Get PDFThe study investigates the impact of American literature taught to the students of Intermediate 1st year from their Book 1 syllabus at Public sector colleges of Kotli Azad Jammu and Kashmir. Most of the themes of the syllabus are established on tolerance, mutual respect, sacrifice and love for humanity, and this is hypothesized that key elements of the literature put positive impact on the behaviour of the learners. In this respect, the students of 1st year were selected to discover the impact of American literature on their social attitudes. To validate the research endeavour, 500 male students and 210 female students were selected from 20 public sector colleges of Kotli as a sample by using convenient sampling technique. Close-ended questionnaire was used as the tool of data collection which was developed on five-point Likert Scale. To determine the validity of the research tool, the value of internal consistency (Cronbach Alpha) was found 0.823. The obtained data was analysed through simple statistical tools. The findings indicate that the students showed lack of tolerance and forgiveness to others which is an indication that some other factors are influencing their social attitude. Moreover, they represented excessive self- priority and at a greater scale, they justified their personal point of view instead of giving a proportionate space to others
Problems in Early Identification of Children with Hearing Loss: A Narrative Review of Research
Get PDFEarly identification of hearing loss in children is crucial for their cognitive and linguistic development. So, the major objectives of this research were to identify the common practices, problems and challenges in early identification of children with hearing loss discussed in various studies. The research design was qualitative and narrative review was conducted to explore the challenges associated with the early detection of hearing loss in children. The study involved a comprehensive search of academic databases, medical journals, and credible sources to collect relevant studies focusing on the obstacles and limitations in identifying hearing loss at an early stage. After the literature search, the selected studies were critically evaluated. Key information was extracted from each study to identify common themes and patterns related to the challenges in early detection. Results highlighted the regional variations in the causes of hearing loss, highlighting the need for targeted interventions and screening programs in different parts of the country. Consanguinity, particularly first cousin marriages, emerged as a significant risk factor for childhood deafness in Pakistan. The prevalence of parental consanguinity was found to be high in certain regions, contributing to the increased risk of congenital hearing impairment in children. However, beyond consanguinity, other factors such as infectious diseases, genetic factors, and environmental influences can also lead to hearing loss in children. To overcome these challenges, several key recommendations can be proposed. Implementing universal newborn hearing screening programs is crucial to identify hearing impairment in infants before critical language and communication development stages. This requires collaboration between healthcare providers, policymakers, and advocacy organizations to ensure equitable access to screening services across all regions
Detection of Crackle and Wheeze in Lung Sound using Machine Learning Technique for Clinical Decision Support System
Get PDFThis study aims to develop a computer-based clinical decision support system that will help clinicians and healthcare personnel to make an early and correct decision to prevent the patient from nontransmissible respiratory diseases. The main contribution of this study is to analyze, investigate, and extraction of the useful feature of pathological respiration and Classification of Crackle and Wheeze from recorded lungs sound by using machine learning techniques. In the particular spectrogram, Time-frequency and Mel-Frequency cepstral coefficient (MFCC)technique is applied for feature analysis and data conversion into a format that can be useful for feature extraction and training models. PCA dimensional reduction technique is used to reduce the dimensionality of the extracted feature. In order to apply various machine learning techniques a widely used dataset freely available dataset ICBHI-2017 is used. The respiratory lungs sound is comprised of 126 patients with 920 Chest sound annotations that include adventitious sounds such as “Crackle” and “Wheeze”. Machine learning algorithms such as MusicANN, VGGish, and OpenL3 were applied for testing the better accuracy of the classification model. The accuracy of the utilized classifier with the extracted feature set is determined as 72%, 81%, and 69% respectively
Detection of Malware Attacks using Artificial Neural Network
Get PDFMalware attacks are increasing rapidly as the technology continues to become prevalent. These attacks have become extremely difficult to detect as they continuously change their mechanism for exploitation of vulnerabilities in software. The conventional approaches to malware detection become ineffective due to a large number of varying patterns and sequences, thereby requiring artificial intelligence-based approaches for the detection of malware attacks. In this paper, we propose an artificial neural network-based model for malware detection. Our proposed model is generic as it can be applied to multiple datasets. We have compared our model with different machine-learning approaches. The experimentation results show that the proposed model can outperform other well-known approach as it achieves 99.6\% , 98.9\% and 99.9\% accuracy on the Windows API call dataset, Top PE Imports Dataset and Malware Dataset, respectively
A Modified Hybrid Method For Solving Non-Linear Equations With Computational Efficiency
Get PDFThis paper proposes a modified hybrid method for solving non-linear equations that improves computational efficiency while maintaining accuracy. The proposed method combines the advantages of the traditional Halley’s and mean-based methods, resulting in a more efficient algorithm. The modified hybrid method starts with Halley’s method and then switches to the mean-based method for rapid convergence. To further improve the efficiency of the algorithm, the proposed method incorporates a dynamic selection criterion to choose the appropriate method at each iteration. Numerical experiments are performed to evaluate the performance of the proposed method in comparison to other existing methods. The results show that the modified hybrid method is computationally efficient and can achieve high accuracy in a shorter time than other commonly used methods having similar features. The proposed method is applicable to a wide range of non-linear equations and can be used in various fields of science and engineering where non-linear equations arise. The modified hybrid method provides an effective tool for solving non-linear equations, offering significant improvements in computational efficiency over existing methods
The Grooming the beard According to Muhadiseen and Jurists and Its Impact on Legal Rulings
Get PDFWearing Leaving beard in the eyes according to Muhaddithin and jurists and its effect on the Shari\u27ah rulings" is an inductive study, which is of special importance, its The objectives, and its written approach are fully mentioned in the elements Introduction. The topic and its subtopics have been described in the light of logical arguments, so for it is concluded that: Ummah unanimously regards wearing beard obligatory to According to Ummah It is obligatory to leave the beard unanimously, and if there is no just righteus person other than the shaved man One, his testimony will be accepted on the basis of necessity. Shaving beard was not popular among the Salafis predecessors, so there is no mention of punishment for the same reasons. However, the reformation of such persons is the duty of law enforcement agencies. It is always better to correct such persons with Dawa’h( innvitation). Thus, it is permissible to cut one\u27s beard to the extent of one\u27s handful, or to leave it as it is; but cutting it beyond the handful is preferable. There is no absolute prohibition in either of them in acquiring knowledge. However, caution should be exercised in learning religious studies by the person to leave beard. It is highly recommended that in the presence of a good person, avoiding even a minor deviated is better