MSMuhammad Asif Saleem

Muhammad Asif Saleem

*This is an algorithmically generated author record based on publicly available information.

Muhammad Asif Saleem has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Challenges in Integration of Heterogeneous Internet of Things

    by Muhammad Noaman, Muhammad Sohail Khan, Muhammad Faisal Abrar, Sikandar Ali, Atif Alvi, Muhammad Asif Saleem

    Internet of Things (IoT) is considered the upcoming industrial and academic revolution in the technological world having billions of things and devices connected to the Internet. These connected devices are heterogeneous. They have different standards and technologies which communicate through different protocols. Therefore, the implementation of IoT on a large scale is difficult due to these heterogeneity challenges. This motivated us to overcome the scaling problem of IoT by identifying the challenges from the literature and providing solutions. This study is based on the identification of the heterogeneous challenges with solutions via a systematic literature review. A total of 81 primary sources were selected. After extracting and synthesizing the data, we identified 14 different IoT heterogeneity challenges. Some of the identified challenges are “heterogeneity of devices,” “heterogeneity in formats of data,” “heterogeneity in communication,” and “interoperability issue due to heterogeneity.” The identified challenges have been analyzed from digital libraries and timeframe perspectives. Furthermore, we have found a total of 81 solutions for those challenges, with at least 5 unique solutions for each challenge. In the future, we will categorize the challenges and prioritize the solutions by using a multi-criteria decision-making problem.


  • Open Access

    Comparative Analysis of Recent Architecture of Convolutional Neural Network

    by Muhammad Asif Saleem, Norhalina Senan, Fazli Wahid, Muhammad Aamir, Ali Samad, Mukhtaj Khan

    Convolutiona neural network (CNN) is one of the best neural networks for classification, segmentation, natural language processing (NLP), and video processing. The CNN consists of multiple layers or structural parameters. The architecture of CNN can be divided into three sections: convolution layers, pooling layers, and fully connected layers. The application of CNN became most demanding due to its ability to learn features from images automatically, involving massive amount of training data and high computational resources like GPUs. Due to the availability of the above-stated resources, multiple CNN architectures have been reported. This study focuses on the working of convolution, pooling, and the fully connected layers of CNN architecture, origin of architectures, limitation, benefits of reported architectures, and comparative analysis of contemporary architecture concerning the number of parameters, architectural depth, and significant contribution.