Search

We propose a novel generic trust management framework for crowdsourced IoT services. The framework exploits a multi-perspective trust model that captures the inherent characteristics of crowdsourced IoT services. Each perspective is defined by a set of attributes that contribute to the perspective's influence on trust. The attributes are fed into a machine-learning-based algorithm to generate a trust model for crowdsourced services in IoT environments. We demonstrate the effectiveness of our approach by conducting experiments on real-world datasets., Comment: 14 pages, accepted and to appear in IEEE Ttransactions on Services Computing

Finding influential members in social networks received a lot of interest in recent literature. Several algorithms have been proposed that provide techniques for extracting a set of the most influential people in a certain social network. However, most of these algorithms find influential nodes based solely on the topological structure of the network. In this paper, a new algorithm, namely NodeRank, is proposed that ranks every user in a given social network based on the topological structure as well as the interests of the users (nodes). Higher ranks are given to people with great influence on other members of the network. Furthermore, the paper investigates a MapReduce version of the algorithm that enables the algorithm to run on multiple machines simultaneously. Experiments showed that the MapReduce model is not suitable for the NodeRank algorithm since MapReduce is only applicable for batch processes and the NodeRank is highly iterative. For that reason, a parallel version of the algorithm is proposed that utilizes Hadoop Spark, a framework for parallel processes that supports batch operations as well as iterative and recursive algorithms. Several experiments have been carried out to test the accuracy as well as the scalability of the algorithm.

We propose a novel distributed integrity-preserving framework for storing trust information in crowdsourced IoT environments. The integrity and availability of the trust information is paramount to ensure accurate trust assessment. Our proposed framework leverages the blockchain to build a distributed storage medium for trust-related information that ensures its integrity. We propose a geo-scoping approach, which ensures that trust-related information is only available where needed, thus, enabling fast access and storage space preservation. We conduct several experiments using real datasets to highlight the effectiveness of our framework., Comment: 10 pages, Accepted and to appear in 2021 IEEE International Conference on Web Services (ICWS). Content may change prior to final publication

We develop a novel framework for efficiently and effectively discovering crowdsourced services that move in close proximity to a user over a period of time. We introduce a moving crowdsourced service model which is modelled as a moving region. We propose a deep reinforcement learning-based composition approach to select and compose moving IoT services considering quality parameters. Additionally, we develop a parallel flock-based service discovery algorithm as a ground-truth to measure the accuracy of the proposed approach. The experiments on two real-world datasets verify the effectiveness and efficiency of the deep reinforcement learning-based approach.

This work is devoted to capturing Emirati-accented speech database (Arabic United Arab Emirates database) in each of neutral and shouted talking environments in order to study and enhance text-independent Emirati-accented speaker identification performance in shouted environment based on each of First-Order Circular Suprasegmental Hidden Markov Models (CSPHMM1s), Second-Order Circular Suprasegmental Hidden Markov Models (CSPHMM2s), and Third-Order Circular Suprasegmental Hidden Markov Models (CSPHMM3s) as classifiers. In this research, our database was collected from fifty Emirati native speakers (twenty five per gender) uttering eight common Emirati sentences in each of neutral and shouted talking environments. The extracted features of our collected database are called Mel-Frequency Cepstral Coefficients (MFCCs). Our results show that average Emirati-accented speaker identification performance in neutral environment is 94.0%, 95.2%, and 95.9% based on CSPHMM1s, CSPHMM2s, and CSPHMM3s, respectively. On the other hand, the average performance in shouted environment is 51.3%, 55.5%, and 59.3% based, respectively, on CSPHMM1s, CSPHMM2s, and CSPHMM3s. The achieved average speaker identification performance in shouted environment based on CSPHMM3s is very similar to that obtained in subjective assessment by human listeners., Comment: 14 pages, 3 figures. arXiv admin note: text overlap with arXiv:1707.00686

We introduce the notion of Adaptive Trust in crowdsourced IoT services; a usage-based trust that represents a service's trustworthiness based on consumers' uses. A novel four-stage framework is proposed to assess the dynamic service trust by leveraging how the service is being used. The first stage uses an algorithm to predict different trust factors that affect the overall trustworthiness of an IoT service. Trust factors are fed to the second stage to build a service-to-factor model that predicts the trustworthiness of a service at each given trust factor. A usage-to-factor model is built at the third stage, which detects the importance of each factor for a specific usage scenario. The last stage utilizes the two models to compute a trust value specifically tailored for a particular usage. Several experiments have been conducted using real dataset to ensure the efficiency of the proposed approach.

Analyzing social networks has received a lot of reviews in the recent literature. Many papers have been proposed to provide new techniques for mining social networks to help further study this huge amount of data. However, to the best of our knowledge, none of them considered the 'semantic meaning' of the nodes interests while clustering the network. In this work, we propose a new algorithm, namely GeoSim, for clustering users in any social network site into communities based on the 'semantic meaning' of the nodes interests as well as their relationships with each other. Moreover, this paper proposes a parallel version of the GeoSim algorithm that utilizes the MapReduce model to run on multiple machines simultaneously and get faster results. The two versions of the algorithm (centralized and parallel) are examined thoroughly to test their performance. The experiments show that both versions of the GeoSim algorithm achieve high community detection accuracy and scale linearly with the size of the cluster.

Organizations have come to realize that storing their databases in the Cloud rather than in-house data centers is cheaper and more flexible. However, companies are still concerned about the privacy and the security of their data. Encrypting the whole database before uploading it to the Cloud solves the security issue. But querying the database requires downloading and decrypting the entire dataset, which is impractical. This paper proposes a new scheme for protecting the privacy and integrity of spatial data stored in the Cloud while being able to execute range queries efficiently. Data objects are encrypted and sorted using Z-order space-filling curve. An index is built on top of the encrypted data to be utilized by the Service Provider to identify and retrieve a superset of data objects that contains the answers to the query. Many simulation experiments have been carried out to measure the performance of the proposed scheme in terms of the redundancy in data retrieved. The experimental results show that the proposed scheme outperforms the most recent scheme by Kim et al. in terms of data redundancy.

This work is aimed at exploiting Second-Order Circular Suprasegmental Hidden Markov Models (CSPHMM2s) as classifiers to enhance talking condition recognition in stressful and emotional talking environments (completely two separate environments). The stressful talking environment that has been used in this work uses Speech Under Simulated and Actual Stress (SUSAS) database, while the emotional talking environment uses Emotional Prosody Speech and Transcripts (EPST) database. The achieved results of this work using Mel-Frequency Cepstral Coefficients (MFCCs) demonstrate that CSPHMM2s outperform each of Hidden Markov Models (HMMs), Second-Order Circular Hidden Markov Models (CHMM2s), and Suprasegmental Hidden Markov Models (SPHMMs) in enhancing talking condition recognition in the stressful and emotional talking environments. The results also show that the performance of talking condition recognition in stressful talking environments leads that in emotional talking environments by 3.67% based on CSPHMM2s. Our results obtained in subjective evaluation by human judges fall within 2.14% and 3.08% of those obtained, respectively, in stressful and emotional talking environments based on CSPHMM2s.

Social networks have gained a lot of interest in recent literature due to the huge amount of data that can be extracted from them. With this ever growing data, emerged the need for techniques to handle it and analyze it. Several papers have proposed many techniques to analyze a given social network from several aspects. Communities are a crucial property in social networks and community detection is considered one of the most important problems in these networks. For this, many papers have devised algorithms for detecting communities. The issue with these algorithms is that they only take into consideration the relation (or distance) between the nodes for detecting communities. In this paper, a new algorithm is proposed to detect communities based on the interests of the nodes rather than their distances from each other. The paper carries out some experiments to test how well is the clustering algorithm in terms of the accuracy and the execution time.

As the amount of spatial data gets bigger, organizations realized that it is cheaper and more flexible to keep their data on the Cloud rather than to establish and maintain in-house huge data centers. Though this saves a lot for IT costs, organizations are still concerned about the privacy and security of their data. Encrypting the whole database before uploading it to the Cloud solves the security issue. But querying the database requires downloading and decrypting the data set, which is impractical. In this paper, we propose a new scheme for protecting the privacy and integrity of spatial data stored in the Cloud while being able to execute range queries efficiently. The proposed technique suggests a new index structure to support answering range query over encrypted data set. The proposed indexing scheme is based on the Z-curve. The paper describes a distributed algorithm for answering range queries over spatial data stored on the Cloud. We carried many simulation experiments to measure the performance of the proposed scheme. The experimental results show that the proposed scheme outperforms the most recent schemes by Kim et al. in terms of data redundancy.

Finding the optimal path in multi-hop wireless networks has gained considerable interest in the recent literature. Standard routing methods such as Ad-hoc On-Demand Distance Vector Routing (AODV) and Dynamic Source Routing (DSR) are based on link-level abstraction of the network without fully considering the impact of the physical layer. Recent studies have introduced spectrum-efficient routing algorithms that take into consideration the physical layer characteristics of the wireless network. These studies, however, focused on algorithmic development and theoretical optimality analysis based on generic network settings. This paper closes the gap between algorithm development and protocol implementation by developing a full spectrum-efficient routing protocol implementation for real-world IEEE 802.11 multi-hop networks. Our ns-2 simulation results illustrate the efficiency of the proposed protocol and its superiority over existing routing protocols.

Routing in multi-hop wireless networks is a vital aspect to sustain acceptable performance. Standard routing schemes, such as ad-hoc on-demand vector routing (AODV) and dynamic source routing (DSR), use the number of hops from source to destination as the routing metric without paying attention to the physical layer properties of the wireless links. This paper, however, presents a new routing protocol for finding the path with maximum end-to-end spectral efficiency in real-world IEEE 802.11s networks. In contrast to previous work, our protocol fully considers the physical layer characteristics of the wireless channel, the interaction between network layer route computation and medium access control (MAC) contention resolution, in addition to all necessary information gathering and exchange performed by the wireless nodes. Furthermore, we provide a full NS-2 simulation comparison between spectrum-efficient routing and standard routing protocols using various performance metrics such as end-to-end data rate, delay, packet loss and overhead time.

In this work we focus on Emarati speaker identification systems in neutral talking environments based on each of Vector Quantization (VQ), Gaussian Mixture Models (GMMs), and Hidden Markov Models (HMMs) as classifiers. These systems have been tested on our collected Emarati speech database which is composed of 25 male and 25 female Emarati speakers using Mel-Frequency Cepstral Coefficients (MFCCs). Our results yield an average text-dependent Emarati speaker identification performance of 100.00%, %99.81, and 99.69% based on VQ, GMMs, and HMMs, respectively. For text-independent systems, the average Emarati speaker identification performance based on VQ, GMMs, and HMMs is 94.48%, 86.55%, and 74.83%, respectively. The achieved results based on VQ are close to those obtained in subjective assessment by human listeners.