VFAST - Virtual Foundation for Advancement of Science and Technology (Pakistan)
Not a member yet
1255 research outputs found
Sort by
Notion of Beauty in the Selected Pakistani Advertisements: A Multimodal Critical Discourse Analysis
Get PDFBeauty advertisement is one of the most potent and successful tools for significantly influencing consumer purchasing behavior as it modifies individuals’ views of beauty, social conventions, and gender roles. From a Multimodal Critical Discourse Analysis standpoint, this study looks at the beauty advertisements in a few chosen social media (Instagram) posts. The study’s goal is to concentrate on how the idea of beauty is used in these Pakistani advertisements to control and influence consumers through both language as well as images. For this particular reason, four ads from different Instagram pages have been chosen via purposive sampling and they have undergone both linguistic and visual analysis. Fairclough’s Three-Dimensional Model (1995) serves as the foundation for the linguistic examination while Kress and van Leeuwen’s Grammar of Visual Design (2006) is applied for the visual analysis of these ads. The nature of this study is qualitative. The findings reveal that advertisers have employed a variety of discursive techniques like surreal representation, scientific evidence, celebrity endorsement, & self-representation etc., and linguistic devices, such as pronouns, catchy phrases, adjectives, repetitions, etc. in addition to visual tactics, e.g., modality, gaze, social distance, salience, and camera angles etc. to influence women by portraying an idealized version of beauty in the chosen advertisements. Additionally, it shows how advertisers—who are essentially powerful people with vested interests—marginalize and restrict the status of women in society to propagate the ideology of beauty just for boosting the sales of their products. Thus, the companies and creators of these commercials employ images and language as a means of controlling Pakistan’s female consumer base by luring them to get on their items. It is anticipated that this study will increase awareness of the usefulness of multimodal critical discourse analysis and open the door for future researchers to investigate the language and pictures used in advertisements for a variety of other products
2DCNN_CLA: Accurate prediction of Clathrin proteins using hyperparameter optimization in deep learning and DDE profiles
Get PDFBackground and Objectives: The adaptor protein clathrin is the major component of the vesicle-coating complex, and it plays a role in the cleavage of the membrane of invaginated vesicles. Clathrin malfunction has been associated with a extensive range of human diseases, including cancer, Alzheimer\u27s disease, and neurodegenerative disorders. A detailed model must be constructed to define its functions in order to gain insight into human diseases and to design pharmacological targets for treatment.
Methods: Before we analyze the data, it would be wise to understand the two-dimensional convolutional neural network (2DCNN). The data provide convincing evidence against the hypothesis that (2DCNN) and additional features were derived from DDE (PSSM) profiles, clathrin proteins may be detected from high-throughput sequencing. When fed into 2D CNNs, the PSSM profile\u27s 20 x 20 matrix was interpreted as a 20 × 20 pixel image. After that, we fed the data into a 2D convolutional neural network (CNN), where we tweaked a few settings to get the best possible results from the model. Based on the findings of the 10-fold cross-validation, we utilized a hyper-parameter optimization procedure to determine the optimal model for our data. After all that, the current model\u27s prediction abilities was tested on an external dataset.
Results: Our model had an MCC of 0.83% and a sensitivity of 0.90% in detecting clathrin proteins in the independent sample. In all of the standard criteria, our technique surpassed even the most advanced classical neural networks. This work provides a practical approach to studying clathrin proteins, and the application of deep learning to biological research has the potential to have far-reaching consequences. At https://github.com/Rahu001/2DCNN-CLA, you may find our open-source scripts and dataset.
Face Recognition from Video by Matching Images Using Deep Learning-Based Models
Get PDFThis paper explores the intersection of video recognition, computer vision, and artificial intelligence, highlighting its broad applicability across various fields. The research focuses on the applications, challenges, ethical dilemmas, and outcomes of artificial intelligence, which continues to grow in significance in the 21st century. We propose a systematic approach that incorporates models for face detection, feature extraction, and recognition. Our methodology includes the accurate segmentation of 100 human faces from video frames, with each face averaging 150x150 pixels. The feature extraction process yielded 1,000 face feature vectors, with an average size of 128, representing key characteristics for recognition. By applying a cosine similarity threshold of 0.7, we filtered irrelevant data and determined whether the two images matched. Our recognition system achieved 85% accuracy, demonstrating the effectiveness of the models and techniques employed. Additionally, ethical considerations were addressed, emphasizing the importance of data privacy, informed consent, cybersecurity, and transparency. This research advances the understanding of face recognition from video data and highlights the need for further exploration in this domain
Pakistan Quest for security An Analysis of Internal and External Security
Get PDFMany times, people think of terrorism as a premeditated, harsh response to perceived injustices. Unfortunately, reports on the repercussions of terrorism frequently lack a clear understanding of the psychological and societal reasons that underlie these kinds of acts. Pakistan has been at the forefront of both the global counterterrorism effort and the experience of terrorism since the events of 9/11. This essay examines the security issues that Pakistan faces as a result of terrorism, which feeds a vicious cycle of radicalization. Pakistan is suffering greatly as a result of the aftermath of terrorism, which has affected its political, social, economic, and physical infrastructure. Terrorism has cost the nation dearly on the social, economic, and human fronts. Despite playing a significant role in the global campaign against terrorism, Pakistan has received unjust labels as a financier of global terrorism. Pakistani terrorism is a complicated problem shaped by many variables, with psychological aspects being one of the most important ones. Since 9/11, countries with a majority of Muslims, especially Pakistan, have felt emotionally threatened by the term "terrorism," frequently connecting it to crimes committed by extreme groups wrongly classified as Musli
Machine Learning Approaches for In-Vehicle Failure Prognosis in Automobiles: A Review
Get PDFThe automobile industry has a growing need for reliable and safe health monitoring systems equipped with low-cost sensor networks and intelligent algorithms. This paper provides an overview of approaches already exist, used in on-board health monitoring systems for vehicles. It focuses on the methodologies, theories, and applications employed in the data measurement and data analysis systems of vehicle (cars) on-board health monitoring systems. A fault detection and diagnosis system, which is accurate, plays a vital role in ensuring the safety of autonomous vehicles by preventing potentially dangerous situations. This study focuses on emphasizing a fault diagnosis system that utilizes hybrid methods. Among the various options considered in this analysis, internal sensors emerge as the preferred choice due to their numerous benefits, including affordability, durability, widespread availability, ease of access, and low energy consumption. Model-based methods require various techniques that may introduce errors to estimation results, while signal-based methods necessitate a time-consuming process of including all possible conditions in a pre-built database. Based on this review, future development trends in designing new low-cost health monitoring systems for vehicles are also discussed
Intrusion Detection Using Machine Learning and Deep Learning Models on Cyber Security Attacks
Get PDFTo detect and stop harmful activity in computer networks, network intrusion detection is an essential part of cybersecurity defensive systems. It is becoming more difficult for traditional rule-based techniques to identify new attack vectors in the face of the increasing complexity and diversity of cyber threats. Machine learning (ML) and deep learning (DL) models can analyze vast amounts of network traffic data and automatically identify patterns and anomalies, there has been a surge in interest in using these models for network intrusion detection. This paper examines the approaches, algorithms, and real-world applications of machine learning and deep learning techniques for network intrusion detection in order to present a thorough review of the state-of-the-art in countering cyber threats. We assess ML and DL-based intrusion detection systems\u27 effectiveness, strengths, and weaknesses in a range of attack scenarios and network environments by synthesizing current literature and empirical research. Additionally, we talk about new developments, obstacles, and paths forward in the areas of transfer learning, adversarial robustness, and ensemble learning. The understanding gained from this investigation clarifies the potential of ML and DL models in strengthening defenses against changing cyber threats, reducing risks, and protecting vital assets. In deep learning autoencode accuracy 68\% less than other models. The performance of the CNN and LSTM algorithm is impressive and outperformed with 100\% accuracy on cyber security attacks datasets. Machine learning algorithm accuracy rate of SVM and KNN 100\% while logistic regression accuracy is 99\% GNB accuracy 80\% with training data of the models. The overall models perforamance deep learning increadible accuracy with 100\% on the training and testing data
NAO Robot\u27s Vision Control and Kick Motion Generation
Get PDFThis case study explores the enhancement of the Nao robot’s soccer-playing capabilities in the Standard Platform League (SPL) by integrating a vision-based system. Robots’ computer vision capabilities such as ball recognition, ball tracking, and motion capabilities like kicking and shooting are explored. The bottom camera tracks a red ball, and the top camera detects the goal. The robot navigates towards the ball, adapting its position for a precise kick to the left or right. Safety measures are embedded, ensuring the robot refrains from movement or kicking if the ball is not visible. The process of kick generation and execution is also discussed; whereas, the kick motion of the robot is controlled by setting the ball’s boundary conditions. This study highlights the feasibility of the Nao robot as a soccer player and provides insights into integrating robotics and programming in sports
Remote Power Management System for Cellular Sites with Enhanced Features and Redundant Connectivity
Get PDFIn today\u27s world, telecommunications infrastructure holds a significance to that of roadways in the early 19th century, serving as a vital link for governments and individuals alike. With heightened market competition and decreasing calling rates, coupled with rising expectations for Quality of Service (QoS), operators are striving to enhance QoS while optimizing resources to manage operational costs. However, challenges such as power shortages and fuel theft persist, leading to frequent network outages. To address these issues, a remote monitoring systems is proposed to prevent fuel theft and report electrical parameters remotely. This system proposes a redundant communication pathway using existing cell site’s physical alarms, eliminating the need for additional servers and SIM cards. Notably, it enhances fault detection capabilities, particularly in detecting gradual fuel theft and addressing voltage fluctuations. These advancements promise to significantly reduce operational expenditure and increase network availability, thereby positively impacting cellular operators\u27 revenue streams
A Model for Wheat Yield Prediction to Reduce the Effect of Climate Change Using Support Vector Regression
Get PDFRecent changes in the climatic conditions have significantly threatened the food security globally. Increasing in temperature adversely affected different crops in Pakistan particularly Wheat crop. Mostly farmer’s crop wheat in District Khairpur but yield is not predicted yet. Therefore, famers are unable to estimate the effects of climate changes. This research work introduces a novel framework for the development of wheat yield prediction model using Support Vector Regression. The model incorporates four predictor variables: temperature, rainfall, humidity and pH value of soil. The essential wheat yield data obtained from official departments, websites, and scholarly publications. Five datasets are created from the gathered data in order evaluate the suggested wheat prediction model. For the creation of dataset, some preprocessing operations such as handling missing values and outlier’s detection are applied to the collected raw data. Experiments performed using simple linear and multiple linear regression models. By dividing the dataset in 70% and 30%, model training and testing performed respectively. The conducted research illustrated that multiple linear regression model provide desired outcomes
IoT-Driven Approaches for Early Detection and Monitoring of Heart Disease: Current Trends and Future Directions
Get PDFCardiovascular disease (CVD) is a serious disease having a widespread effect on individuals across the world. Early and accurate detection of cardiac disease is crucial in healthcare, especially in the domain of cardiology. Currently, a non-invasive ultrasound imaging method is used that evaluates the structure, performance, and blood, allowing for the precise identification of a number of cardiac ailments, such as valve problems, heart failure, and congenital anomalies. These traditional techniques have some limitations, including high cost, the need for medical expertise and equipment, and the fact that they often create incorrect results due to human involvement. Furthermore, the traditional method takes more time to predict heart disease. Electrocardiogram (ECG) signals play a critical role in reducing death rates caused by CVDs, and they provide details regarding the heart patient’s health to a medical expert by employing an automated heart failure detection system. Recent developments in deep learning-based health care systems, such as ECG signal analysis, include CNN, LSTM, and other neural networks. In this research, we provide a hybrid deep learning based approach for the timely and accurate diagnosis of cardiovascular disease. The proposed system uses a hybrid of convolutional neural networks (CNN) and long short-term memory (LSTM) and utilizes the MIT-BIH ECG signal dataset for heart disease diagnosis. This study uses two different approaches with MIT-BIH arrhythmia imbalanced and balanced datasets. The first approach uses CNN and CNN-LSTM with an imbalanced dataset, and the second approach uses CNN and CNN-LSTM with a balanced dataset. The performance of both approaches was analyzed. The experimental outcomes show that the overall performance of both CNN, CNN-LSTM was excellent on a balanced dataset compared to imbalanced dataset. The proposed system achieved a better result than the previous suggested methods. Additionally, it is easy to adopt the suggested technique in the field of healthcare in order to identify heart disease