JUSPN, volume-15 , Issue 2 (2021), PP 33 - 41
Published: 24 Mar 2021
by Wendy Osborn from Department of Mathematics and Computer Science, University of Lethbridge, Lethbridge, Alberta, Canada, T1K 3M4
Abstract: In this paper, the problem of query processing in spatial data streams is explored, with a focus on the spatial join operation. Although the spatial join has been utilized in many proposed centralized and distributed query processing strategies, for its application to spatial data streams the spatial join operation has received very little attention. One identified limitation with existing strategies is that a bounded region of space (i.e., spatial extent) from which the spatial objects are generated needs to be known in advance. However, this information may not be available. Therefore, two strategies for spatial data stream join processing are proposed where the spatial extent of the spatial object stream is not required to be known in advance. Both strategies estimate the common region that is shared by two or more spatial data streams in order to process the spatial join. An evaluation of both strategies includes a comparison with a recently proposed approach in which the spatial extent of the data set is known. Experimental results show that one of the strategies performs very well at estimating the common region of space using only incoming objects on the spatial data streams. Other limitations of this work are also identified. read more... read less...
Keywords: spatial data streams, stream query processing, spatial join, performance
JUSPN, volume-15 , Issue 2 (2021), PP 25 - 31
Published: 21 Mar 2021
by Karim Haricha, Azeddine Khiat, Yassine Issaoui, Ayoub Bahnasse, Hassan Ouajji from Lab SSDIA, University Hassan II of Casablanca, Morocco, ENSAM Casablanca, University Hassan II of Casablanca, Morocco
Abstract: Production activities is generating a large amount of data in different types (i.e., text, images), that is not well exploited. This data can be translated easily to knowledge that can help to predict all the risks that can impact the business, solve problems, promote efficiency of the manufacture to the maximum, make the production more flexible and improving the quality of making smart decisions, however, implementing the Smart Manufacturing(SM) concept provides this opportunity supported by the new generation of the technologies. Internet Of Things (IoT) for more connectivity and getting data in real time, Big Data to store the huge volume of data and Deep Learning algorithms(DL) to learn from the historical and real time data to generate knowledge, that can be used, predict all the risks, problem solving, and better decision-making. In this paper, we will introduce SM and the main technologies to success the implementation, the benefits, and the challenges. read more... read less...
Keywords: Smart Manufacturing (SM), Industry 4.0, Internet Of Things (IoT), Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL).
JUSPN, volume-15 , Issue 2 (2021), PP 19 - 24
Published: 22 Mar 2021
by Vishv Patel, Devansh Shah, Nishant Doshi from Pandit Deendayal Energy University, Gandhinagar, India, Gujarat-382426
Abstract: The large deployment of the Internet of Things (IoT) is empowering Smart City tasks and activities everywhere throughout the world. Items utilized in day-by-day life are outfitted with IoT devices and sensors to make them interconnected and connected with the internet. Internet of Things (IoT) is a vital piece of a smart city that tremendously impact on all the city sectors, for example, governance, healthcare, mobility, pollution, and transportation. This all connected IoT devices will make the cities smart. As different smart city activities and undertakings have been propelled in recent times, we have seen the benefits as well as the risks. This paper depicts the primary challenges and weaknesses of applying IoT innovations dependent on smart city standards. Moreover, this paper points the outline of the technologies and applications of the smart cities. read more... read less...
Keywords: Internet of Things (IoT), Smart Cities, IoT Devices and Sensors, Technologies of Smart Cities, Applications of Smart Cities
JUSPN, volume-15 , Issue 2 (2021), PP 11 - 17
Published: 24 Mar 2021
by Meryem Elmoulat, Olivier Debauche, Saïd Mahmoudi, Sidi Ahmed Mahmoudi, Adriano Guttadauria, Pierre Manneback, Frédéric Lebeau from University Mohammed V, Faculty of Sciences, Research Unit GeoRisk: Geological Risks, Battouta Avenue, Rabat, Morocco, 10140, University of Mons, Faculty of Engineering - ILIA/Infortech, Place du Parc 20, Mons, Belgium, 7000, University of Liège - GxABT, TERRA, Passage des déportés 2, Gembloux, Belgium, 5030, University of Liège - GxABT, BioDynE, Gembloux, Belgium, 5030
Abstract: Landslides are phenomena that cause significant human and economic losses. Researchers have investigated the prediction of high landslides susceptibility with various methodologies based upon statistical and mathematical models, in addition to artificial intelligence tools. These methodologies allow to determine the areas that could present a serious risk of landslides. Monitoring these risky areas is particularly important for developing an Early Warning Systems (EWS). As matter of fact, the variety of landslides’ types make their monitoring a sophisticated task to accomplish. Indeed, each landslide area has its own specificities and potential triggering factors; therefore, there is no single device that can monitor all types of landslides. Consequently, Wireless Sensor Networks (WSN) combined with Internet of Things (IoT) allow to set up large-scale data acquisition systems. In addition, recent advances in Artificial Intelligence (AI) and Federated Learning (FL) allow to develop performant algorithms to analyze this data and predict early landslides events at edge level (on gateways). These algorithms are trained in this case at fog level on specific hardware. The novelty of the work proposed in this paper is the integration of Federated Learning based on Fog-Edge approaches to continuously improve prediction models. read more... read less...
Keywords: Landslides Susceptibility, IoT, Artificial Intelligence, Early Warning System, Landslides Monitoring, Edge AI, Edge IoT
AI’S Contribution to Ubiquitous Systems and Pervasive Networks Security – Reinforcement Learning vs Recurrent Networks
JUSPN, volume-15 , Issue 2 (2021), PP 01 - 09
Published: 22 Mar 2021
by Christophe Feltus from Luxembourg Institute of Science and Technology (LIST), Esch-sur-Alzette, Luxembourg, L-4362
Abstract: Reinforcement learning and recurrent networks are two emerging machine-learning paradigms. The first learns the best actions an agent needs to perform to maximize its rewards in a particular environment and the second has the specificity to use an internal state to remember previous analysis results and consider them for the current one. Research into RL and recurrent network has been proven to have made a real contribution to the protection of ubiquitous systems and pervasive networks against intrusions and malwares. In this paper, a systematic review of this research was performed in regard to various attacks and an analysis of the trends and future fields of interest for the RL and recurrent network-based research in network security was complete. read more... read less...
Keywords: Artificial Intelligence, Reinforcement Learning, Recurrent Networks, RNN, GRU, LSTM, RL, Security, Network Security, Malware Detection, Literature Review, Machine learning, Intrusion Detection, State of the Art.
An Enhanced Deep Learning Model to Network Attack Detection, by using Parameter Tuning, Hidden Markov Model and Neural Network
JUSPN, volume-15 , Issue 1 (2021), PP 35 - 41
Published: 21 Mar 2021
by Choukri Djellali, Mehdi adda from Department of Mathematics, Computer Science and Engineering University of Quebec At Rimouski 300 Allée des Ursulines, Rimouski, QC G5L 3A1 Rimouski, Canada
Abstract: In recent years, Deep Learning has become a critical success factor for Machine Learning. In the present study, we introduced a Deep Learning model to network attack detection, by using Hidden Markov Model and Artificial Neural Networks. We used a model aggregation technique to find a single consolidated Deep Learning model for better data fitting. The model selection technique is applied to optimize the bias-variance trade-off of the expected prediction. We demonstrate its ability to reduce the convergence, reach the optimal solution and obtain more cluttered decision boundaries. Experimental studies conducted on attack detection indicate that our proposed model outperformed existing Deep Learning models and gives an enhanced generalization. read more... read less...
Keywords: Deep Learning, Data Mining, HMM, Neural Network, Pattern Recognition, Model aggregation, Model selection, Network Security.
JUSPN, volume-15 , Issue 1 (2021), PP 27 - 34
Published: 21 Mar 2021
by Redouane Marhoum, Chaimaa Fouhad, Mohamed El Khaili, Hassan Ouajji from SSDIA laboratory, ENSET, Hassan 2nd University of Casablanca, BP 159, Mohammedia, Morocco
Abstract: Global demand for primary fossil energy continues to increase. However, the production of energy from fossil fuels, in addition to depleting available reserves, releases millions of tons of Greenhouse Gas (GHG) into the atmosphere. Thus, it is obvious that the high concentration of GHGs in the air disrupts the natural greenhouse effect and consequently causes global warming. The implementation of action plans aimed at reducing greenhouse gas emissions has led all countries to use clean energy sources (sun, earth, wind) called renewable energies and also to rationalize the use of energies whether based on fossil fuels or renewable. Our paper presents a modeling of the demand and its management to ensure an optimization of the energy consumption and the reduction of its bill read more... read less...
Keywords: Energy efficiency, energy hub, renewable energy, smart house, Energy storage, IoT
JUSPN, volume-15 , Issue 1 (2021), PP 17 - 25
Published: 21 Mar 2021
by Ramin Firouzi, Rahim Rahmani, Theo Kanter from Department of Computer and Systems Science, Stockholm University, Kista, Sweden, SE-164 07
Abstract: With the advent of edge computing, the Internet of Things (IoT) environment has the ability to process data locally. The complexity of the context reasoning process can be scattered across several edge nodes that are physically placed at the source of the qualitative information by moving the processing and knowledge inference to the edge of the IoT network. This facilitates the real-time processing of a large range of rich data sources that would be less complex and expensive compare to the traditional centralized cloud system. In this paper, we propose a novel approach to provide low-level intelligence for IoT applications through an IoT edge controller that is leveraging the Fuzzy Logic Controller along with edge computing. This low-level intelligence, together with cloud-based intelligence, forms the distributed IoT intelligence. The proposed controller allows distributed IoT gateway to manage input uncertainties; besides, by interacting with its environment, the learning system can enhance its performance over time, which leads to improving the reliability of the IoT gateway. Therefore, such a controller is able to offer different context-aware reasoning to alleviate the distributed IoT. A simulated smart home scenario has been done to prove the plausibility of the low-level intelligence concerning reducing latency and more accurate prediction through learning experiences at the edge. read more... read less...
Keywords: Internet of Things (IoT), context-awareness, edge computing, reasoning, type two fuzzy controller
JUSPN, volume-15 , Issue 1 (2021), PP 11 - 15
Published: 24 Mar 2021
by Tariq Abu Hilal, Hasan Abu Hilal, Ala’ Abu Hilal from Higher Colleges of Technology, Abu Dhabi, UAE, 41012, Zayed University, Abu Dhabi, UAE, 41012
Abstract: Turkish lossless text compression was proposed by converting the character’s from UTF-8 to ANSI system for space-preserving. Likewise, we present a decoding method that transforms the encoded ANSI string back to its original format. Unlike the one-byte ANSI characters, some of the Turkish alphabets are being stored in 2 bytes size. All that space comes at a price. The developed sequential encoding technique will reduce the size of the text file up to 9%. Moreover, the Turkish encoded text will retain its original form after decoding. According to our proposal, it is considered as a lossless text compression, where it’s a common concern today. Thus, many parties have become interested in Unicode compression. Basically, our algorithm is mapping Unicode Turkish characters into ANSI, by using the available 8-bit legacy. For Arabic Text Compression, a sequential encoding technique was suggested that efficiently converts Arabic characters string from UTF-8 to ANSI characters coding. The encoding algorithm presented in this paper significantly reduces the file size. The decoding method transforms the encoded ANSI string back to its original format. Unlike the one-byte ANSI characters, Arabic alphabets are currently being stored in 2 bytes size which leads to inefficient space utilization. The newly developed sequential encoding technique reduces the space required for storage up to fifty percent. In addition, the proposed technique will retain the Arabic encoded text to its original form after decoding, which is leading to a lossless text compression. Thus, addressing the common concern of the currently available Arabic characters compression techniques. In this research, a multistage compression process was implemented on Turkish and Arabic languages, by using the new encoding technique, in addition to the 7-Zip application, which has shown a significant file size reduction. read more... read less...
Keywords: Unicode; ANSI, UTF-8 Encoding, Turkish Text Compression, Arabic Text Compression, 7-Zip Application
JUSPN, volume-15 , Issue 1 (2021), PP 01 - 09
Published: 22 Mar 2021
by Bo Liu, Yingying Chen, Hongbo Liu, Yudong Yao from ECE Department, Stevens Instituted of Technology, Hoboken, NJ, USA, 07030, ECE Department, Rutgers University, New Brunswick, NJ, 08901, University of Electronic Science and Technology of China, Chengdu, Sichuan, 610015, China
Abstract: This paper explores a low-cost portable visible light communication (VLC) system to support the increasing needs of lightweight mobile applications. VLC grows rapidly in the past decade for many applications (e.g., indoor data transmission, human sensing, and visual MIMO) due to its RF interference immunity and inherent high security. However, most existing VLC systems heavily rely on fixed infrastructures with less adaptability to emerging lightweight mobile applications. This work proposes Light Storage, a portable VLC system takes the advantage of commercial smartphone flashlights as the transmitter and a solar panel equipped with both data reception and energy harvesting modules as the receiver. Light Storage can achieve concurrent data transmission and energy harvesting from the visible light signals. It develops multi-level light intensity data modulation to increase data throughput and integrates the noise reduction functionality to allow portability under various lighting conditions. The system supports synchronization together with adaptive error correction to overcome both the linear and non-linear signal offsets caused by the low time-control ability from the commercial smartphones. Finally, the energy harvesting capability in Light Storage provides sufficient energy support for efficient short range communication. Light Storage is validated in both indoor and outdoor environments and can achieve over 98% data decoding accuracy, demonstrating the potential as an important alternative to support low-cost and portable short range communication. read more... read less...
Keywords: Visible Light Communication; Energy Harvesting; Solar Panel.