International Journal of High Performance Computing and Networking (7 papers in press)

Regular Issues

• Infinite impulse response system identification using antlion optimisation algorithm  
  by Sandeep Singh, Alpana Shekhar, Chakshu Kalra, Shubham Kaushik, Tarun Kumar Rawat, Alaknanda Ashok 
  Abstract: This paper focuses on infinite impulse response (IIR) system identification using a recent nature-inspired algorithm called antlion optimisation (ALO). The system identification problem concerns determining the viable parameters by minimising the cost function. Generally, gradient-based techniques are mostly used for IIR system identification. However, these traditional algorithms face the problem of getting trapped in local solution. So to get rid of this problem, a novel ALO algorithm is used for IIR system identification. The ALO is inspired by the preying process of antlions on the ants. The algorithm is free of the issues faced by the traditional techniques. The performance of the ALO algorithm is measured using two measures, the mean square error, which is taken as cost function, and the convergence profile. The results obtained using ALO are compared with that of the particle swarm optimisation algorithm and cat swarm optimisation algorithm. The obtained results confirmed that the ALO algorithm surpasses the performance of the existing algorithms.
  Keywords: antlion algorithm; system identification; mean square error; convergence profile.
  
  
• A survey of blockchain as a service platform  
  by Samer Muneer Alshurafa, Derar Eleyan, Amna Eleyan 
  Abstract: Blockchain provides more security and decentralised systems. However, it is difficult for startups and small companies to build and deploy their blockchain networks. So, cloud computing providers make it easy for those to work with blockchain using their networks and cloud infrastructure through using blockchain as a service platform. There are many blockchain as a service providers and platforms. This survey provides an overview of 23 such platforms and provides a comparison based on provider, blockchain protocol, blockchain type, cost, security, and support of smart contract.
  Keywords: blockchain; blockchain as a service; cloud computing; distributed ledger technology.
  DOI: 10.1504/IJHPCN.2021.10042153
   
  
• Benchmarking the Keras API on GPU: the use of Tensorflow and CNTK Libraries as Back-end  
  by Felipe Florencio, Edward David Moreno 
  Abstract: With the popularisation of Convolutional Neural Networks (CNNs), many tools were developed to facilitate the development of models. One of the main tools developed is the Keras API, which is a high-level API for creating and training models. The Keras API acts as a high-level layer to facilitate the implementation of neural networks while other CNN libraries can run as backend. There is a demand for studies that compare the performance of a CNN implemented with the Keras API and the performance of CNNs implemented only with native methods to CNN libraries. Objective: To evaluate the impact of the Keras API on the performance of TensorFlow 1, TensorFlow 2 and CNTK libraries in relation to the execution time in GPUs. Conducting an experiment for measuring the execution time of the LeNet-5 model, it was implemented with the aid of the Keras API and implemented without it. Models implemented with Keras API methods showed longer execution times than models implemented only with native methods from CNTK libraries. The performance difference can be significant for some applications. The Keras API sacrifices library performance up to four times when compared with native methods.
  Keywords: convolutional neural network; GPU; benchmarking; evaluation performance; Keras; Tensorflow; CNTK.
  
  
• Machine and federated learning for high-performance computing: a survey  
  by Akshat Gaurav, Konstantinos Psannis 
  Abstract: A paradigm shift in machine learning application models has occurred in recent years owing to privacy and deep learning aspirations. The recently created decentralised paradigm of machine learning is known as federated learning (FL). This is a machine learning technique in which many dispersed nodes use their locally stored data to train a common prediction model. Through FL, better data privacy is possible because training data is not routed to a central server. However, FL is a new field that has yet to achieve mainstream acceptance and is still in the development phase. In this context, the purpose of our study is to provide a more comprehensive overview of the most important protocols and platforms of FL. Additionally, this study includes real-world examples of how diverse architectures and protocols that use FL may work to achieve the necessary objectives.
  Keywords: federated learning; blockchain; machine learning; internet of things.
  
  
• A split and merge video cryptosystem technique based on dual hash functions and Lorenz system  
  by Obaida M. Al-Hazaimeh, Ashraf Abu-Ein, Ma'moun Al-Smadi, Monther H. Al-Bsool 
  Abstract: Chaos-based cryptosystems and their behaviour in cryptography has attracted attention from many scientists and researchers in physics and computer science in recent decades. A new dynamic cryptosystem for video sequence based on the combination of chaotic Lorenz map and dual hash functions is proposed in this paper to improve the security level of the video applications. First, split up the video sequence into video frames and audio samples. Then, the initial conditions for both video and audio are generated using SHA-256 and MD5, respectively. Next, a higher dimensional Lorenz chaotic system is adopted to confuse and diffuse the audio samples and video frames components. Moreover, to improve the security level of the proposed cryptosystem against different types of cryptanalytic attack, the concept of multi-key is employed. The security analysis is conducted and the results indicate that the presented cryptosystem satisfies the security requirements against various attacks and can be directly applied in the real life video applications.
  Keywords: video encryption; Lorenz chaotic map; differential attack; statistical test suite; randomness.
  
  
• A survey of node localisation algorithms in wireless sensor networks  
  by Amanpreet Kaur, Govind P. Gupta, Sangeeta Mittal 
  Abstract: Wireless sensor networks (WSN) have gained a lot of attention due to wide variety of applications. The main task of WSN is to detect various physical attributes from the environment, convert the observation into information and send the required information through wireless links to base station/sink. In most of applications of WSNs, location of source node which has generated sensor reading is also required for better deduction of the sensor readings. This estimation of an accurate location of a node called node localization, is one of the crucial challenges in the field of wireless sensor networks. As this research area is in trend from last two decades, in this paper, we present a review of existing literature related to WSN node localization problem. Firstly, an introduction on wireless sensor networks and its challenges are mentioned. Then, issues of localization algorithms are discussed. This paper also presents different localization algorithms and also discusses different categories of localization algorithms. Based on precision/hardware requirement, localization algorithms can be categorized into two groups such as range-based and range-free algorithms. Next, a comprehensive study of range-based and range-free algorithms for localization process is reviewed. Various range-based and range-free algorithms with their merits and demerits are explored. Finally, a list of research gaps is discussed.
  Keywords: node localisation; range-free localisation; range-based localisation; wireless sensor networks; localisation error; energy; accuracy.
  
  
• Analysis of various versions of You Only Look Once: a comparative analysis  
  by Ritika Dhiman, Sunil K. Singh, Gurkanwal Singh Kang, Nandini Sidana 
  Abstract: You Only Look Once (YOLO) is the best-in-class real-time object detection algorithm that uses convolutional neural networks (CNN) to detect an object. YOLO has been very popular among the computer vision research community and has gradually improved through various iterations. It is used in a wide range of applications: to detect animals, people, objects on road, etc. YOLO accomplishes high accuracy and can provide results run in real-time where other object detection algorithms do not. The main purpose of this paper is to discuss all the various versions of the YOLO family and do a comparative performance analysis. The content of this paper includes several stages, such as summarising the development of the YOLO family, introducing their methodology, and discussing differences in their different versions. Further, YOLOv5 being the best among all other versions based on speed and accuracy has been used to experimentally detect wildfire smoke from images.
  Keywords: object detection; computer vision; YOLO; deep learning; image processing; convolutional neural networks; smoke detection.