Special Issue "Deep Learning and Parallel Computing for Intelligent and Efficient IoT"

Submission Deadline: 29 January 2021 (closed)
Guest Editors
Dr. Irfan Uddin, Kohat University of Science and Technology, Pakistan.
Dr. Jia-Bao Liu, Anhui Jianzhu University, China.
Dr. Furqan Aziz, University of Birmingham, UK.
Dr. Shamsul Huda, Deakin University, Australia.
Dr. Muhammad Asif Manzoor, University of Regina, Canada.

Summary

Artificial Intelligence (AI) is recently becoming very popular mainly because of advancements in Machine Learning (ML), more specifically in Deep Learning (DL) and Reinforcement Learning (RL). A wide range of applications are using these techniques. Internet of Things (IoT) is the future generation system. The complex, heterogeneous and distributed nature of IoT devices has inspired many researchers and practitioners to explore the usage of AI/ML/DL techniques to make intelligent IoT. Parallel computing techniques are used to make these devices more efficient and reliable. As a result of this massive adaption and growth, smart cities, smart grid, smart healthcare and smart industries are emerged.

A large number of distributed heterogeneous devices are interconnected in IoT and a huge amount of data is generated. This data is increasing in size and heterogeneity. The network of IoT devices is diverse and complex in nature. These devices contain limited computational power, memory and energy resources. Therefore, AI/ML/DL based devices are important to develop intelligent IoT systems and efficient management of resource and network. The objective is to improve the overall performance of IoT systems.

This special issue aims to bring together the academic and industrial researchers to explore the opportunities of DL and parallel computing for IOT, study its impact on the solution of the aforementioned challenges and propose viable solutions.

We solicit papers covering various topics of interest that include but not limited to the following topics:

• Architecture and technologies for intelligent IoT using Deep Learning and Parallel Computing

• Services for smart systems based on Deep Learning (smart building, smart cities, smart grids, smart transportation, smart healthcare)

• Big data mining and analytics for intelligent IOT based on Deep Learning

• Applications for intelligent IoT based on Deep Learning

• Transport protocols for intelligent IoT based on Deep Learning

• Data management for IoT based on Deep Learning

• Application for energy efficient IOT systems based on Deep Learning


Keywords
Deep Learning, Parallel Computing, GPUs, IoT and Performance improvements.

Published Papers
  • Adaptive Power Control Aware Depth Routing in Underwater Sensor Networks
  • Abstract Underwater acoustic sensor network (UASN) refers to a procedure that promotes a broad spectrum of aquatic applications. UASNs can be practically applied in seismic checking, ocean mine identification, resource exploration, pollution checking, and disaster avoidance. UASN confronts many difficulties and issues, such as low bandwidth, node movements, propagation delay, 3D arrangement, energy limitation, and high-cost production and arrangement costs caused by antagonistic underwater situations. Underwater wireless sensor networks (UWSNs) are considered a major issue being encountered in energy management because of the limited battery power of their nodes. Moreover, the harsh underwater environment requires vendors to design and deploy energy-hungry… More
  •   Views:384       Downloads:345        Download PDF

  • Deep-Learning-Empowered 3D Reconstruction for Dehazed Images in IoT-Enhanced Smart Cities
  • Abstract With increasingly more smart cameras deployed in infrastructure and commercial buildings, 3D reconstruction can quickly obtain cities’ information and improve the efficiency of government services. Images collected in outdoor hazy environments are prone to color distortion and low contrast; thus, the desired visual effect cannot be achieved and the difficulty of target detection is increased. Artificial intelligence (AI) solutions provide great help for dehazy images, which can automatically identify patterns or monitor the environment. Therefore, we propose a 3D reconstruction method of dehazed images for smart cities based on deep learning. First, we propose a fine transmission image deep convolutional… More
  •   Views:555       Downloads:479        Download PDF

  • Machine Learning Approach for COVID-19 Detection on Twitter
  • Abstract Social networking services (SNSs) provide massive data that can be a very influential source of information during pandemic outbreaks. This study shows that social media analysis can be used as a crisis detector (e.g., understanding the sentiment of social media users regarding various pandemic outbreaks). The novel Coronavirus Disease-19 (COVID-19), commonly known as coronavirus, has affected everyone worldwide in 2020. Streaming Twitter data have revealed the status of the COVID-19 outbreak in the most affected regions. This study focuses on identifying COVID-19 patients using tweets without requiring medical records to find the COVID-19 pandemic in Twitter messages (tweets). For this… More
  •   Views:670       Downloads:428        Download PDF


  • Automatic Surveillance of Pandemics Using Big Data and Text Mining
  • Abstract COVID-19 disease is spreading exponentially due to the rapid transmission of the virus between humans. Different countries have tried different solutions to control the spread of the disease, including lockdowns of countries or cities, quarantines, isolation, sanitization, and masks. Patients with symptoms of COVID-19 are tested using medical testing kits; these tests must be conducted by healthcare professionals. However, the testing process is expensive and time-consuming. There is no surveillance system that can be used as surveillance framework to identify regions of infected individuals and determine the rate of spread so that precautions can be taken. This paper introduces a… More
  •   Views:488       Downloads:359        Download PDF

  • COVID-19 Infected Lung Computed Tomography Segmentation and Supervised Classification Approach
  • Abstract The purpose of this research is the segmentation of lungs computed tomography (CT) scan for the diagnosis of COVID-19 by using machine learning methods. Our dataset contains data from patients who are prone to the epidemic. It contains three types of lungs CT images (Normal, Pneumonia, and COVID-19) collected from two different sources; the first one is the Radiology Department of Nishtar Hospital Multan and Civil Hospital Bahawalpur, Pakistan, and the second one is a publicly free available medical imaging database known as Radiopaedia. For the preprocessing, a novel fuzzy c-mean automated region-growing segmentation approach is deployed to take an… More
  •   Views:599       Downloads:386        Download PDF

  • Systematic Analysis of Safety and Security Risks in Smart Homes
  • Abstract The revolution in Internet of Things (IoT)-based devices and applications has provided smart applications for humans. These applications range from healthcare to traffic-flow management, to communication devices, to smart security devices, and many others. In particular, government and private organizations are showing significant interest in IoT-enabled applications for smart homes. Despite the perceived benefits and interest, human safety is also a key concern. This research is aimed at systematically analyzing the available literature on smart homes and identifying areas of concern or risk with a view to supporting the design of safe and secure smart homes. For this systematic review… More
  •   Views:492       Downloads:591        Download PDF

  • Pashto Characters Recognition Using Multi-Class Enabled Support Vector Machine
  • Abstract During the last two decades significant work has been reported in the field of cursive language’s recognition especially, in the Arabic, the Urdu and the Persian languages. The unavailability of such work in the Pashto language is because of: the absence of a standard database and of significant research work that ultimately acts as a big barrier for the research community. The slight change in the Pashto characters’ shape is an additional challenge for researchers. This paper presents an efficient OCR system for the handwritten Pashto characters based on multi-class enabled support vector machine using manifold feature extraction techniques. These… More
  •   Views:490       Downloads:442        Download PDF

  • Feasibility-Guided Constraint-Handling Techniques for Engineering Optimization Problems
  • Abstract The particle swarm optimization (PSO) algorithm is an established nature-inspired population-based meta-heuristic that replicates the synchronizing movements of birds and fish. PSO is essentially an unconstrained algorithm and requires constraint handling techniques (CHTs) to solve constrained optimization problems (COPs). For this purpose, we integrate two CHTs, the superiority of feasibility (SF) and the violation constraint-handling (VCH), with a PSO. These CHTs distinguish feasible solutions from infeasible ones. Moreover, in SF, the selection of infeasible solutions is based on their degree of constraint violations, whereas in VCH, the number of constraint violations by an infeasible solution is of more importance. Therefore,… More
  •   Views:525       Downloads:447        Download PDF

  • Machine Learning-based USD/PKR Exchange Rate Forecasting Using Sentiment Analysis of Twitter Data
  • Abstract This study proposes an approach based on machine learning to forecast currency exchange rates by applying sentiment analysis to messages on Twitter (called tweets). A dataset of the exchange rates between the United States Dollar (USD) and the Pakistani Rupee (PKR) was formed by collecting information from a forex website as well as a collection of tweets from the business community in Pakistan containing finance-related words. The dataset was collected in raw form, and was subjected to natural language processing by way of data preprocessing. Response variable labeling was then applied to the standardized dataset, where the response variables were… More
  •   Views:1015       Downloads:511        Download PDF

  • Quality of Service Aware Cluster Routing in Vehicular Ad Hoc Networks
  • Abstract In vehicular ad hoc networks (VANETs), the topology information (TI) is updated frequently due to vehicle mobility. These frequent changes in topology increase the topology maintenance overhead. To reduce the control message overhead, cluster-based routing schemes are proposed. In cluster-based routing schemes, the nodes are divided into different virtual groups, and each group (logical node) is considered a cluster. The topology changes are accommodated within each cluster, and broadcasting TI to the whole VANET is not required. The cluster head (CH) is responsible for managing the communication of a node with other nodes outside the cluster. However, transmitting real-time data… More
  •   Views:483       Downloads:415        Download PDF

  • Adaptation of Vehicular Ad hoc Network Clustering Protocol for Smart Transportation
  • Abstract Clustering algorithms optimization can minimize topology maintenance overhead in large scale vehicular Ad hoc networks (VANETs) for smart transportation that results from dynamic topology, limited resources and non-centralized architecture. The performance of a clustering algorithm varies with the underlying mobility model to address the topology maintenance overhead issue in VANETs for smart transportation. To design a robust clustering algorithm, careful attention must be paid to components like mobility models and performance objectives. A clustering algorithm may not perform well with every mobility pattern. Therefore, we propose a supervisory protocol (SP) that observes the mobility pattern of vehicles and identifies the… More
  •   Views:800       Downloads:507        Download PDF

  • PeachNet: Peach Diseases Detection for Automatic Harvesting
  • Abstract To meet the food requirements of the seven billion people on Earth, multiple advancements in agriculture and industry have been made. The main threat to food items is from diseases and pests which affect the quality and quantity of food. Different scientific mechanisms have been developed to protect plants and fruits from pests and diseases and to increase the quantity and quality of food. Still these mechanisms require manual efforts and human expertise to diagnose diseases. In the current decade Artificial Intelligence is used to automate different processes, including agricultural processes, such as automatic harvesting. Machine Learning techniques are becoming… More
  •   Views:1255       Downloads:471        Download PDF

  • Liver-Tumor Detection Using CNN ResUNet
  • Abstract Liver tumor is the fifth most occurring type of tumor in men and the ninth most occurring type of tumor in women according to recent reports of Global cancer statistics 2018. There are several imaging tests like Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and ultrasound that can diagnose the liver tumor after taking the sample from the tissue of the liver. These tests are costly and time-consuming. This paper proposed that image processing through deep learning Convolutional Neural Network (CNNs) ResUNet model that can be helpful for the early diagnose of tumor instead of conventional methods. The existing studies… More
  •   Views:842       Downloads:453        Download PDF

  • Detecting Information on the Spread of Dengue on Twitter Using Artificial Neural Networks
  • Abstract Social media platforms have lately emerged as a promising tool for predicting the outbreak of epidemics by analyzing information on them with the help of machine learning techniques. Many analytical and statistical models are available to infer a variety of user sentiments in posts on social media. The amount of data generated by social media platforms, such as Twitter, that can be used to track diseases is increasing rapidly. This paper proposes a method for the classification of tweets related to the outbreak of dengue using machine learning algorithms. An artificial neural network (ANN)-based method is developed using Global Vector… More
  •   Views:819       Downloads:571        Download PDF

  • Smart Object Detection and Home Appliances Control System in Smart Cities
  • Abstract During the last decade the emergence of Internet of Things (IoT) based applications inspired the world by providing state of the art solutions to many common problems. From traffic management systems to urban cities planning and development, IoT based home monitoring systems, and many other smart applications. Regardless of these facilities, most of these IoT based solutions are data driven and results in small accuracy values for smaller datasets. In order to address this problem, this paper presents deep learning based hybrid approach for the development of an IoT-based intelligent home security and appliance control system in the smart cities.… More
  •   Views:810       Downloads:755        Download PDF