Efficient Conversion of Deep Features to Compact Binary Codes Using Fourier Decomposition for Multimedia Big Data

Ahmad, Jamil,Muhammad, Khan,Lloret, Jaime,Baik, Sung Wook IEEE 2018 IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS - Vol.14 No.7

<P>Exponential growth of multimedia data has been witnessed in recent years from various industries, such as e-commerce, health, transportation, and social networks, etc. Access to desired data in such gigantic datasets require sophisticated and efficient retrieval methods. In the last few years, neuronal activations generated by a pretrained convolutional neural network (CNN) have served as generic descriptors for various tasks including image classification, object detection and segmentation, and image retrieval. They perform incredibly well compared to hand-crafted features. However, these features are usually high dimensional, requiring a lot of memory and computations for indexing and retrieval. For very large datasets, utilization of these high dimensional features in raw form becomes infeasible. In this paper, a highly efficient method is proposed to transform high dimensional deep features into compact binary codes using bidirectional Fourier decomposition. This compact bit code saves memory and eases computations during retrieval. Further, these codes can also serve as hash codes, allowing very efficient access to images in large datasets using approximate nearest neighbor (ANN) search techniques. Our method does not require any training and achieves considerable retrieval accuracy with short length codes. It has been tested on features extracted from fully connected layers of a pretrained CNN. Experiments conducted with several large datasets reveal the effectiveness of our approach for a wide variety of datasets.</P>

Secure Surveillance Framework for IoT Systems Using Probabilistic Image Encryption

Muhammad, Khan,Hamza, Rafik,Ahmad, Jamil,Lloret, Jaime,Wang, Haoxiang,Baik, Sung Wook IEEE 2018 IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS - Vol.14 No.8

<P>This paper proposes a secure surveillance framework for Internet of things (IoT) systems by intelligent integration of video summarization and image encryption. First, an efficient video summarization method is used to extract the informative frames using the processing capabilities of visual sensors. When an event is detected from keyframes, an alert is sent to the concerned authority autonomously. As the final decision about an event mainly depends on the extracted keyframes, their modification during transmission by attackers can result in severe losses. To tackle this issue, we propose a fast probabilistic and lightweight algorithm for the encryption of keyframes prior to transmission, considering the memory and processing requirements of constrained devices that increase its suitability for IoT systems. Our experimental results verify the effectiveness of the proposed method in terms of robustness, execution time, and security compared to other image encryption algorithms. Furthermore, our framework can reduce the bandwidth, storage, transmission cost, and the time required for analysts to browse large volumes of surveillance data and make decisions about abnormal events, such as suspicious activity detection and fire detection in surveillance applications.</P>

OBPF: Opportunistic Beaconless Packet Forwarding Strategy for Vehicular Ad Hoc Networks

( Kashif Naseer Qureshi ),( Abdul Hanan Abdullah ),( Jaime Lloret ),( Ayman Altameem ) 한국인터넷정보학회 2016 KSII Transactions on Internet and Information Syst Vol.10 No.5

In a vehicular ad hoc network, the communication links are unsteady due to the rapidly changing topology, high mobility and traffic density in the urban environment. Most of the existing geographical routing protocols rely on the continuous transmission of beacon messages to update the neighbors` presence, leading to network congestion. Source-based approaches have been proven to be inefficient in the inherently unstable network. To this end, we propose an opportunistic beaconless packet forwarding approach based on a modified handshake mechanism for the urban vehicular environment. The protocol acts differently between intersections and at the intersection to find the next forwarder node toward the destination. The modified handshake mechanism contains link quality, forward progress and directional greedy metrics to determine the best relay node in the network. After designing the protocol, we compared its performance with existing routing protocols. The simulation results show the superior performance of the proposed protocol in terms of packet delay and data delivery ratio in realistic wireless channel conditions.

IoTEC: IoT based Efficient Clustering Protocol for Wireless Sensor Network

Amjad Mehmood,S. Khan,Daqiang Zhang,Jaime Lloret,Syed Hassan Ahmed 한국산업정보학회 2014 한국산업정보학회 학술대회논문집 Vol.2014 No.1

Enhancing Security in Mobile IPv6

Hero Modares,Amirhossein Moravejosharieh,Rosli Bin Salleh,Jaime Lloret 한국전자통신연구원 2014 ETRI Journal Vol.36 No.1

In the Mobile IPv6 (MIPv6) protocol, a mobile node(MN) is a mobile device with a permanent home address(HoA) on its home link. The MN will acquire a care-ofaddress (CoA) when it roams into a foreign link. It thensends a binding update (BU) message to the home agent(HA) and the correspondent node (CN) to inform them ofits current CoA so that future data packets destined for itsHoA will be forwarded to the CoA. The BU message,however, is vulnerable to different types of security attacks,such as the man-in-the-middle attack, the sessionhijacking attack, and the denial-of-service attack. Thecurrent security protocols in MIPv6 are not able toeffectively protect the BU message against these attacks. The private-key-based BU (PKBU) protocol is proposed inthis research to overcome the shortcomings of someexisting MIPv6 protocols. PKBU incorporates a method toassert the address ownership of the MN, thus allowing theCN to validate that the MN is not a malicious node. Theresults obtained show that it addresses the securityrequirements while being able to check the addressownership of the MN. PKBU also incorporates a methodto verify the reachability of the MN.

Realistic and Efficient Radio Propagation Model for V2X Communications

( Rashid Hafeez Khokhar ),( Tanveer Zia ),( Kayhan Zrar Ghafoor ),( Jaime Lloret ),( Muhammad Shiraz ) 한국인터넷정보학회 2013 KSII Transactions on Internet and Information Syst Vol.7 No.8

Multiple wireless devices are being widely deployed in Intelligent Transportation System (ITS) services on the road to establish end-to-end connection between vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) networks. Vehicular ad hoc networks (VANETs) play an important role in supporting V2V and V2I communications (also called V2X communications) in a variety of urban environments with distinct topological characteristics. In fact, obstacles such as big buildings, moving vehicles, trees, advertisement boards, traffic lights, etc. may block the radio signals in V2X communications. Their impact has been neglected in VANET research. In this paper, we present a realistic and efficient radio propagation model to handle different sizes of static and moving obstacles for V2X communications. In the proposed model, buildings and large moving vehicles are modeled as static and moving obstacles, and taken into account their impact on the packet reception rate, Line-of-sight (LOS) obstruction, and received signal power. We use unsymmetrical city map which has many dead-end roads and open faces. Each dead-end road and open faces are joined to the nearest edge making a polygon to model realistic obstacles. The simulation results of proposed model demonstrates better performance compared to some existing models, that shows proposed model can reflect more realistic simulation environments.

An intelligent monitoring of greenhouse using wireless sensor networks

Achouak Touhami,Khelifa Benahmed,Lorena Parra,Fateh Bounaama,Jaime Lloret 국제구조공학회 2020 Smart Structures and Systems, An International Jou Vol.26 No.1

Over recent years, the interest for vegetables and fruits in all seasons and places has much increased, from where diverse countries have directed to the commercial production in greenhouse. In this article, we propose an algorithm based on wireless sensor network technologies that monitor the microclimate inside a greenhouse and linear equations model for optimization plant production and material cost. Moreover, we also suggest a novel design of an intelligent greenhouse. We validate our algorithms with simulations on a benchmark based on experimental data made at lNRA of Montfavet in France. Finally, we calculate the statistical estimators RMSE, TSSE, MAPE, EF and R². The results obtained are promising, which shows the efficiency of our proposed system.

CODIE: Controlled Data and Interest Evaluation in Vehicular Named Data Networks

Ahmed, Syed Hassan,Bouk, Safdar Hussain,Yaqub, Muhammad Azfar,Kim, Dongkyun,Song, Houbing,Lloret, Jaime IEEE 2016 IEEE Transactions on Vehicular Technology VT Vol.65 No.6

<P>Recently, named data networking (NDN) has been proposed as a promising architecture for future Internet technologies. NDN is an extension to the content-centric network (CCN) and is expected to support various applications in vehicular communications [ vehicular NDN (VNDN)]. VNDN basically relies on naming the content rather than using end-to-end device names. In VNDN, a vehicle broadcasts an 'Interest' packet for the required 'content,' regardless of end-to-end connectivity with servers or other vehicles and known as a 'consumer.' In response, a vehicle with the content replies to the Interest packet with a 'Data' packet and named as a 'provider.' However, the simple VNDN architecture faces several challenges such as consumer/provider mobility and Interest/Data packet(s) forwarding. In VNDN, for the most part, the Data packet is sent along the reverse path of the related Interest packet. However, there is no extensive simulated reference available in the literature to support this argument. In this paper, therefore, we first analyze the propagation behavior of Interest and Data packets in the vehicular ad hoc network (VANET) environment through extensive simulations. Second, we propose the 'CODIE' scheme to control the Data flooding/broadcast storm in the naive VNDN. The main idea is to allow the consumer vehicle to start hop counter in Interest packet. Upon receiving this Interest by any potential provider, a data dissemination limit (DDL) value stores the number of hops and a data packet needs to travel back. Simulation results show that CODIE forwards fewer copies of data packets processed (CDPP) while achieving similar interest satisfaction rate (ISR), as compared with the naive VNDN. In addition, we also found that CODIE also minimizes the overall interest satisfaction delay (ISD), respectively.</P>

Grey wolf optimization based clustering algorithm for vehicular ad-hoc networks

Fahad, Muhammad,Aadil, Farhan,Rehman, Zahoor-ur-,Khan, Salabat,Shah, Peer Azmat,Muhammad, Khan,Lloret, Jaime,Wang, Haoxiang,Lee, Jong Weon,Mehmood, Irfan Elsevier 2018 Computers & electrical engineering Vol.70 No.-

<P>In vehicular ad-hoc network (VANETs), frequent topology changes occur due to fast moving nature of mobile nodes. This random topology creates instability that leads to scalability issues. To overcome this problem, clustering can be performed. Existing approaches for clustering in VANETs generate large number of cluster-heads which utilize the scarce wireless resources resulting in degraded performance. In this article, grey wolf optimization based clustering algorithm for VANETs is proposed, that replicates the social behaviour and hunting mechanism of grey wolfs for creating efficient clusters. The linearly decreasing factor of grey wolf nature enforces to converge earlier, which provides the optimized number of clusters. The proposed method is compared with well-known meta-heuristics from literature and results show that it provides optimal outcomes that lead to a robust routing protocol for clustering of VANETs, which is appropriate for highways and can accomplish quality communication, confirming reliable delivery of information to each vehicle. (C) 2018 Elsevier Ltd. All rights reserved.</P>