Mohammed Alhamid - Academia.edu (original) (raw)

Papers by Mohammed Alhamid

Computers & Electrical Engineering, 2021

Abstract Recently, great progress has been witnessed in the application of mobile cloud computing... more Abstract Recently, great progress has been witnessed in the application of mobile cloud computing in the field of health care such as online medical inquiries. However, due to the limitation of cognitive intelligence, QoE (Quality of Experience) is hampered by two problems, the first of which is that the traffic pressure of the core network cannot well meet the requirements of delay-sensitive emotional services, especially for users with different emergencies, while the second is that current applications cannot provide personalized service for different users. Based on the two problems, we propose an emotion-aware mobile edge computing architecture based on emotional task priority to guide the allocation of edge resources and to provide intelligent and personalized emotional services with higher QoE. Specifically, we first introduce the entities involved in the proposed architecture of emotion-aware mobile edge computing system. Next, we describe our optimal computing resource allocation strategy, including important concepts and a detailed algorithm. Finally, we build a test platform and conduct experiments, which show that the proposed architecture obtains better performance in terms of system utility compared with baseline methods.

Journal of Parallel and Distributed Computing, 2020

Early-stage disease risk prediction can be beneficial to improve the health of the mass and can r... more Early-stage disease risk prediction can be beneficial to improve the health of the mass and can reduce the economic burden of late treatment. Machine learning has played a pivotal role in predictive systems, which requires achieving a specific degree of accuracy for healthcare systems. Most recently researchers have found the necessity of bridging between epidemiology and machine learning classifications toward health risk prediction. This work proposes an epidemiology knowledgedriven unique model that follows the principle of association rule-based ontology to select features and classification techniques. The goal of this approach is to generalize a framework for future robust systems to predict the likelihood of diseases, which can be executed in the edge computing environment. The framework introduces epidemiological library and structured attribute set along with the library of precaution to derive the disease risk-prediction process. To investigate the adoption of the epidemiology knowledge-driven model, we considered a real dataset of early-stage likelihood prediction of diabetes and carried out a set of experiments for highlighting the significance of several epidemiological factors. The classification aspect of the framework is further compared with widely accepted approaches for machine learning based healthcare, which shows the novelty of the proposed model.

Sensors, 2020

The Internet of Things (IoT) has changed our lives drastically. Customers, regulatory bodies, and... more The Internet of Things (IoT) has changed our lives drastically. Customers, regulatory bodies, and industrial partners are driving us to use IoT. Although IoT provides new opportunities, security remains a key concern while providing various services. It is especially challenging how the data generated from IoT devices can be protected from potential security attacks and how to safeguard the exchange of these data while transiting through different nodes and gateways. In this research, we aim to ensure a safe IoT environment by proposing an efficient key management technique that uses a combination of symmetric and asymmetric cryptosystem to obtain the speed of the former as well as the security benefits of the latter. Our proposal considers a set of Smart Objects (SO) capable of key registration, generation and distribution for IoT data transmission. We used the open-source Message Queuing Telemetry Transport (MQTT) protocol to facilitate communications between the source and the de...

Mobile Networks and Applications, 2018

With the development of intelligent applications, more and more intelligent applications are comp... more With the development of intelligent applications, more and more intelligent applications are computation intensive, data intensive and delay sensitive. Compared with traditional cloud computing, edge computing can reduce communication delay by offloading computing tasks to edge cloud. Furthermore, with the complexity of computing scenarios in edge cloud, deep learning based on computation offloading scheme has attracted wide attention. However, all the learning-based offloading scheme does not consider the where and how to run the offloading scheme itself. Thus, in this paper, we consider the problem of running the learning-based computation offloading scheme for the first time and propose the learning for smart edge architecture. Then, we give the computation offloading optimization problem of mobile devices under multiuser and multi edge cloud scenarios. Furthermore, we propose cognitive learning-based computation offloading (CLCO) scheme for this problem. Finally, experimental results show that compared with other offloading schemes, the CLCO scheme has lower task duration and energy consumption.

Peer-to-Peer Networking and Applications, 2018

Authors and publishers use different metrics at various levels to estimate the impact of produced... more Authors and publishers use different metrics at various levels to estimate the impact of produced research, including the journallevel impact factor, the number of citations at an article-level and the H-index at an author-level. In this paper, we propose an approach to measure the Article Citation Impact (ACI) that will enable idenGEAtification of the impact of articles at their extended nearby citation network. We combine an article's content with its bibliometrics to evaluate the citation impact of articles in their surrounding citation network. Using the article metadata, we calculate the semantic similarity between two articles in the extended network. The articles' similarity and bibliometric scores are then used to assess the impact of the article among their extended nearby citation network. In our empirical studies, we use two datasets to validate the efficiency of our approach to evaluate the impact of articles on improving article recommendation processes. The experimental results highlight the effectiveness of the proposed approach to optimize the overall recommendation quality, compared to other baseline approaches.

IEEE Access, 2018

Nowadays, the mobile healthcare industry is prospering due to the increase in computer processing... more Nowadays, the mobile healthcare industry is prospering due to the increase in computer processing power, improvement of next-generation communication technologies, and high storage capacity. Mobile multimedia sensors can acquire healthcare data, which can be processed to make decisions on the health status of users. In line with this, we propose a mobile multimedia healthcare framework in this paper, where an automatic seizure detection system is embedded as a case study. In the proposed system, electroencephalogram signals from a head-mounted set are recorded and processed using convolutional neural networks. A classification module determines whether the signals exhibit seizure. Experimental results show that the proposed system can achieve high levels of accuracy and sensitivity. The Children's Hospital Boston-Massachusetts Institute of Technology database indicates the system accuracy and sensitivity to be 99.02% and 92.35% in a cross-patient scenario, respectively.

IEEE Transactions on Vehicular Technology, 2019

IEEE Access, 2019

The rapidly increasing number of potential academic venues for research publication and commentar... more The rapidly increasing number of potential academic venues for research publication and commentary has made sourcing the venue that would best contribute to promoting effective scientific cooperation more challenging. In this paper, we propose a similarity learning approach to determine the most appropriate venue to publish an article. We first analyze the article metadata and cited articles to build the citation network matrices of the given article and then apply these to learn and build similarity matrices between academic objects (i.e., articles, authors, and venues) at an extended nearby article citation network. Using the formed matrices, we estimate a collaborative anticipation confidence score of a relationship between the venues in the extended network. For our empirical studies, we used an actual academic dataset to validate the efficiency of our approach and recommend an appropriate academic venue. The experimental results highlight the effectiveness of our proposed approach to optimize overall recommendation quality, compared with other baseline approaches.

IEEE Access, 2019

In this paper, we propose a Blockchain-based infrastructure to support security-and privacy-orien... more In this paper, we propose a Blockchain-based infrastructure to support security-and privacy-oriented spatio-temporal smart contract services for the sustainable Internet of Things (IoT)-enabled sharing economy in mega smart cities. The infrastructure leverages cognitive fog nodes at the edge to host and process offloaded geo-tagged multimedia payload and transactions from a mobile edge and IoT nodes, uses AI for processing and extracting significant event information, produces semantic digital analytics, and saves results in Blockchain and decentralized cloud repositories to facilitate sharing economy services. The framework offers a sustainable incentive mechanism, which can potentially support secure smart city services, such as sharing economy, smart contracts, and cyber-physical interaction with Blockchain and IoT. Our unique contribution is justified by detailed system design and implementation of the framework. INDEX TERMS Sharing economy, cognitive processing at the edge, mobile edge computing, Blockchain, smart city.

Future Generation Computer Systems, 2018

This paper presents results of a user study of the effects of virtual reality technology on VR Si... more This paper presents results of a user study of the effects of virtual reality technology on VR Sickness and User Experience. In our study the participants watched two different panoramic (360) videos, one with relaxing content (beach clip) and second one with action content (roller coaster video clip). Videos were watched on four different head mounted displays (HMDs) and on the 2D television as a reference display. To assess VR Sickness discomfort levels, we have used the Simulator Sickness Questionnaire (SSQ), and for user experience the User Experience Questionnaire (UEQ) was used. For quick assessments of VR Sickness discomfort levels, we have also used Subjective Units of Distress Scale (SUDS). We have found a strong correlation between SUDS and total SSQ score and between total SSQ score and SSQ-D score. Shown negative correlation between VR Sickness discomfort levels (assessed by SSQ and UEQ Questionnaire), and user experience (assessed by UEQ Questionnaire), indicates that presence of VR Sickness symptoms affects the user experience.

IEEE Access, 2017

Human facial expressions change with different states of health; therefore, a facial-expression r... more Human facial expressions change with different states of health; therefore, a facial-expression recognition system can be beneficial to a healthcare framework. In this paper, a facial-expression recognition system is proposed to improve the service of the healthcare in a smart city. The proposed system applies a bandlet transform to a face image to extract sub-bands. Then, a weighted, center-symmetric local binary pattern is applied to each sub-band block by block. The CS-LBP histograms of the blocks are concatenated to produce a feature vector of the face image. An optional feature-selection technique selects the most dominant features, which are then fed into two classifiers: a Gaussian mixture model and a support vector machine. The scores of these classifiers are fused by weight to produce a confidence score, which is used to make decisions about the facial expression's type. Several experiments are performed using a large set of data to validate the proposed system. Experimental results show that the proposed system can recognize facial expressions with 99.95% accuracy.

IEEE Access, 2018

This paper presents the analysis of real-life medical big data obtained from a hospital in centra... more This paper presents the analysis of real-life medical big data obtained from a hospital in central China from 2013 to 2015 for risk assessment of cerebral infarction disease. We propose a new recurrent convolutional neural network (RCNN)-based disease risk assessment multimodel by utilizing structured and unstructured text data from the hospital. In the proposed model, the convolutional layer becomes a bidirectional recurrent neural network by utilizing the intra-layer recurrent connection within the convolutional layer. Each neuron within convolutional layer receives feedforward and recurrent inputs from the previous unit and neighborhood, respectively. In addition to step-by-step recurrent operation, the region of context capture increases, thereby facilitating fine-grain feature extraction. Furthermore, we use a data parallelism approach over multimodel data during training and testing of the proposed model. Results show that the data parallelism approach leads to fast conversion speed. The RCNN-based model works differently from the traditional convolutional neural network and other typical methods. The proposed model exhibits a prediction accuracy of 96.02%, which is higher than those of typical existing methods. INDEX TERMS Convolutional neural network, feature learning, medical big data, disease risk assessment.

IEEE Transactions on Circuits and Systems for Video Technology, 2017

With the irruption of inexpensive Depth sensor devices, hand gesture tracking has become again on... more With the irruption of inexpensive Depth sensor devices, hand gesture tracking has become again one topic of great interest. The problems to face respect other tracking algorithms are mainly two: the high complexity of the hand structure which translate in a very large amount of possible gestures, and the rapidness of the movements we are able to make when moving the hand or just the fingers. Recent approaches try to fit a 3D hand model to the observed RGB-D data by an optimization function that minimizes the error between the model and the data. However, these algorithms are very dependent of the initialization point, being unpractical to run in a natural environment. To solve these kind of problems, it is common to use an offline dataset with pre-learnt gestures that will serve as a first rough estimate. In concrete, we present an algorithm that uses an articulated ICP minimization function, that is initialized by the parameters obtained from a dataset of hand gestures trained through deep learning framework. This set up has two strong points. First, deep learning provides a very fast and accurate estimate of performed hand gesture. Second, the articulated ICP algorithm allows to capture the possible variability of a gesture performed by different person or slightly different gesture. Our proposed algorithm is evaluated and validated in several ways. Independent evaluations for deep learning framework and articulated ICP are performed. Moreover, different real sequences are recorded to validate our approach, and finally quantitative and qualitative comparisons are conducted with state-of-the-art algorithms.

Future Generation Computer Systems, 2017

This is a PDF file of an unedited manuscript that has been accepted for publication. As a service... more This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. Highlights  Collaborative Analysis Model for Trending Images in Online Social Networks  Trending image authentication using steerable pyramid transform  Search-based computational Intelligence algorithm for optimal computation  Analysis of descriptive tags and trending contents on Twitter dataset. Highlights (for review)

IEEE Access, 2017

With the continuous rise in ingenious forgery, a wide range of digital audio authentication appli... more With the continuous rise in ingenious forgery, a wide range of digital audio authentication applications are emerging as a preventive and detective control in real-world circumstances, such as forged evidence, breach of copyright protection, and unauthorized data access. To investigate and verify, this paper presents a novel automatic authentication system that differentiates between the forged and original audio. The design philosophy of the proposed system is primarily based on three psychoacoustic principles of hearing, which are implemented to simulate the human sound perception system. Moreover, the proposed system is able to classify between the audio of different environments recorded with the same microphone. To authenticate the audio and environment classification, the computed features based on the psychoacoustic principles of hearing are dangled to the Gaussian mixture model to make automatic decisions. It is worth mentioning that the proposed system authenticates an unknown speaker irrespective of the audio content i.e., independent of narrator and text. To evaluate the performance of the proposed system, audios in multienvironments are forged in such a way that a human cannot recognize them. Subjective evaluation by three human evaluators is performed to verify the quality of the generated forged audio. The proposed system provides a classification accuracy of 99.2% ± 2.6. Furthermore, the obtained accuracy for the other scenarios, such as text-dependent and text-independent audio authentication, is 100% by using the proposed system. INDEX TERMS Digital audio authentication, audio forensics, forgery, machine learning algorithm, human psychoacoustic principles.

IEEE Access, 2017

Recent advances in wireless sensor networks for ubiquitous health and activity monitoring systems... more Recent advances in wireless sensor networks for ubiquitous health and activity monitoring systems have triggered the possibility of addressing human needs in smart environments through recognizing human real-time activities. While the nature of streams in such networks requires efficient recognition techniques, it is also subject to suspicious inference-based privacy attacks. In this paper, we propose a framework that efficiently recognizes human activities in smart homes based on spatiotemporal mining technique. In addition, we propose a technique to enhance the privacy of the collected human sensed activities using a modified version of micro-aggregation approach. An extensive validation of our framework has been performed on benchmark data sets yielding quite promising results in terms of accuracy and privacy-utility tradeoff. INDEX TERMS Internet of Things, data mining, data privacy, healthcare, smart home.

Sensors, 2017

A large number of the population around the world suffers from various disabilities. Disabilities... more A large number of the population around the world suffers from various disabilities. Disabilities affect not only children but also adults of different professions. Smart technology can assist the disabled population and lead to a comfortable life in an enhanced living environment (ELE). In this paper, we propose an effective voice pathology assessment system that works in a smart home framework. The proposed system takes input from various sensors, and processes the acquired voice signals and electroglottography (EGG) signals. Co-occurrence matrices in different directions and neighborhoods from the spectrograms of these signals were obtained. Several features such as energy, entropy, contrast, and homogeneity from these matrices were calculated and fed into a Gaussian mixture model-based classifier. Experiments were performed with a publicly available database, namely, the Saarbrucken voice database. The results demonstrate the feasibility of the proposed system in light of its high accuracy and speed. The proposed system can be extended to assess other disabilities in an ELE.

Multimedia Tools and Applications, 2016

The use of social networks has grown exponentially in recent years. The large amount of data avai... more The use of social networks has grown exponentially in recent years. The large amount of data available in these networks can be effectively utilized in many machine learning applications. This paper proposes a framework of an emotion recognition system that fetches huge amount of face images from the social networks into a cloud. In the cloud, the problem of the unlabeled facial images is handled by applying an active learning approach. For the feature extraction, an interlaced derivative pattern is used, while for a base classifier, an extreme learning machine is utilized. Once the emotion is recognized in the cloud, it can be shared with the end users to meet their interests. Several experiments were performed using some publicly available databases and heterogeneous images from the social networks. Experimental results showed that the proposed framework may effectively be used in the emotion recognition.

Mobile Networks and Applications, 2016

With the advent of future generation mobile communication technologies (5G), there is the potenti... more With the advent of future generation mobile communication technologies (5G), there is the potential to allow mobile users to have access to big data processing over different clouds and networks. The increasing numbers of mobile users come with additional expectations for personalized services (e.g., social networking, smart home, health monitoring) at any time, from anywhere, and through any means of connectivity. Because of the expected massive amount of complex data generated by such services and networks from heterogeneous multiple sources, an infrastructure is required to recognize a user’s sentiments (e.g., emotion) and behavioral patterns to provide a high quality mobile user experience. To this end, this paper proposes an infrastructure that combines the potential of emotion-aware big data and cloud technology towards 5G. With this proposed infrastructure, a bimodal system of big data emotion recognition is proposed, where the modalities consist of speech and face video. Experimental results show that the proposed approach achieves 83.10 % emotion recognition accuracy using bimodal inputs. To show the suitability and validity of the proposed approach, Hadoop-based distributed processing is used to speed up the processing for heterogeneous mobile clients.

Multimedia Tools and Applications, 2015

Users of ambient intelligence environments have been overwhelmed by the huge numbers of social me... more Users of ambient intelligence environments have been overwhelmed by the huge numbers of social media available, thus identifying the social media tailored to the user's need is becoming an important question to be discussed. This paper adapts the Katz proximity measure, for the use in social tagging system, to help users in ambient environment find relevant media suited to their interests. The method models the ternary relations among user, resource and tag as a weighted, undirected tripartite graph, then apply the Katz proximity measure to tripartite graph. Experiments on two real datasets are implemented and compared with many state-of-the-art algorithms. The experimental results prove that the adaptation of the Katz algorithm with the tripartite structure yields a significant improvement, and successfully ranks relevant search results according to the user's interests.

Computers & Electrical Engineering, 2021

Abstract Recently, great progress has been witnessed in the application of mobile cloud computing... more Abstract Recently, great progress has been witnessed in the application of mobile cloud computing in the field of health care such as online medical inquiries. However, due to the limitation of cognitive intelligence, QoE (Quality of Experience) is hampered by two problems, the first of which is that the traffic pressure of the core network cannot well meet the requirements of delay-sensitive emotional services, especially for users with different emergencies, while the second is that current applications cannot provide personalized service for different users. Based on the two problems, we propose an emotion-aware mobile edge computing architecture based on emotional task priority to guide the allocation of edge resources and to provide intelligent and personalized emotional services with higher QoE. Specifically, we first introduce the entities involved in the proposed architecture of emotion-aware mobile edge computing system. Next, we describe our optimal computing resource allocation strategy, including important concepts and a detailed algorithm. Finally, we build a test platform and conduct experiments, which show that the proposed architecture obtains better performance in terms of system utility compared with baseline methods.

Journal of Parallel and Distributed Computing, 2020

Early-stage disease risk prediction can be beneficial to improve the health of the mass and can r... more Early-stage disease risk prediction can be beneficial to improve the health of the mass and can reduce the economic burden of late treatment. Machine learning has played a pivotal role in predictive systems, which requires achieving a specific degree of accuracy for healthcare systems. Most recently researchers have found the necessity of bridging between epidemiology and machine learning classifications toward health risk prediction. This work proposes an epidemiology knowledgedriven unique model that follows the principle of association rule-based ontology to select features and classification techniques. The goal of this approach is to generalize a framework for future robust systems to predict the likelihood of diseases, which can be executed in the edge computing environment. The framework introduces epidemiological library and structured attribute set along with the library of precaution to derive the disease risk-prediction process. To investigate the adoption of the epidemiology knowledge-driven model, we considered a real dataset of early-stage likelihood prediction of diabetes and carried out a set of experiments for highlighting the significance of several epidemiological factors. The classification aspect of the framework is further compared with widely accepted approaches for machine learning based healthcare, which shows the novelty of the proposed model.

Sensors, 2020

The Internet of Things (IoT) has changed our lives drastically. Customers, regulatory bodies, and... more The Internet of Things (IoT) has changed our lives drastically. Customers, regulatory bodies, and industrial partners are driving us to use IoT. Although IoT provides new opportunities, security remains a key concern while providing various services. It is especially challenging how the data generated from IoT devices can be protected from potential security attacks and how to safeguard the exchange of these data while transiting through different nodes and gateways. In this research, we aim to ensure a safe IoT environment by proposing an efficient key management technique that uses a combination of symmetric and asymmetric cryptosystem to obtain the speed of the former as well as the security benefits of the latter. Our proposal considers a set of Smart Objects (SO) capable of key registration, generation and distribution for IoT data transmission. We used the open-source Message Queuing Telemetry Transport (MQTT) protocol to facilitate communications between the source and the de...

Mobile Networks and Applications, 2018

With the development of intelligent applications, more and more intelligent applications are comp... more With the development of intelligent applications, more and more intelligent applications are computation intensive, data intensive and delay sensitive. Compared with traditional cloud computing, edge computing can reduce communication delay by offloading computing tasks to edge cloud. Furthermore, with the complexity of computing scenarios in edge cloud, deep learning based on computation offloading scheme has attracted wide attention. However, all the learning-based offloading scheme does not consider the where and how to run the offloading scheme itself. Thus, in this paper, we consider the problem of running the learning-based computation offloading scheme for the first time and propose the learning for smart edge architecture. Then, we give the computation offloading optimization problem of mobile devices under multiuser and multi edge cloud scenarios. Furthermore, we propose cognitive learning-based computation offloading (CLCO) scheme for this problem. Finally, experimental results show that compared with other offloading schemes, the CLCO scheme has lower task duration and energy consumption.

Peer-to-Peer Networking and Applications, 2018

Authors and publishers use different metrics at various levels to estimate the impact of produced... more Authors and publishers use different metrics at various levels to estimate the impact of produced research, including the journallevel impact factor, the number of citations at an article-level and the H-index at an author-level. In this paper, we propose an approach to measure the Article Citation Impact (ACI) that will enable idenGEAtification of the impact of articles at their extended nearby citation network. We combine an article's content with its bibliometrics to evaluate the citation impact of articles in their surrounding citation network. Using the article metadata, we calculate the semantic similarity between two articles in the extended network. The articles' similarity and bibliometric scores are then used to assess the impact of the article among their extended nearby citation network. In our empirical studies, we use two datasets to validate the efficiency of our approach to evaluate the impact of articles on improving article recommendation processes. The experimental results highlight the effectiveness of the proposed approach to optimize the overall recommendation quality, compared to other baseline approaches.

IEEE Access, 2018

Nowadays, the mobile healthcare industry is prospering due to the increase in computer processing... more Nowadays, the mobile healthcare industry is prospering due to the increase in computer processing power, improvement of next-generation communication technologies, and high storage capacity. Mobile multimedia sensors can acquire healthcare data, which can be processed to make decisions on the health status of users. In line with this, we propose a mobile multimedia healthcare framework in this paper, where an automatic seizure detection system is embedded as a case study. In the proposed system, electroencephalogram signals from a head-mounted set are recorded and processed using convolutional neural networks. A classification module determines whether the signals exhibit seizure. Experimental results show that the proposed system can achieve high levels of accuracy and sensitivity. The Children's Hospital Boston-Massachusetts Institute of Technology database indicates the system accuracy and sensitivity to be 99.02% and 92.35% in a cross-patient scenario, respectively.

IEEE Transactions on Vehicular Technology, 2019

IEEE Access, 2019

The rapidly increasing number of potential academic venues for research publication and commentar... more The rapidly increasing number of potential academic venues for research publication and commentary has made sourcing the venue that would best contribute to promoting effective scientific cooperation more challenging. In this paper, we propose a similarity learning approach to determine the most appropriate venue to publish an article. We first analyze the article metadata and cited articles to build the citation network matrices of the given article and then apply these to learn and build similarity matrices between academic objects (i.e., articles, authors, and venues) at an extended nearby article citation network. Using the formed matrices, we estimate a collaborative anticipation confidence score of a relationship between the venues in the extended network. For our empirical studies, we used an actual academic dataset to validate the efficiency of our approach and recommend an appropriate academic venue. The experimental results highlight the effectiveness of our proposed approach to optimize overall recommendation quality, compared with other baseline approaches.

IEEE Access, 2019

In this paper, we propose a Blockchain-based infrastructure to support security-and privacy-orien... more In this paper, we propose a Blockchain-based infrastructure to support security-and privacy-oriented spatio-temporal smart contract services for the sustainable Internet of Things (IoT)-enabled sharing economy in mega smart cities. The infrastructure leverages cognitive fog nodes at the edge to host and process offloaded geo-tagged multimedia payload and transactions from a mobile edge and IoT nodes, uses AI for processing and extracting significant event information, produces semantic digital analytics, and saves results in Blockchain and decentralized cloud repositories to facilitate sharing economy services. The framework offers a sustainable incentive mechanism, which can potentially support secure smart city services, such as sharing economy, smart contracts, and cyber-physical interaction with Blockchain and IoT. Our unique contribution is justified by detailed system design and implementation of the framework. INDEX TERMS Sharing economy, cognitive processing at the edge, mobile edge computing, Blockchain, smart city.

Future Generation Computer Systems, 2018

This paper presents results of a user study of the effects of virtual reality technology on VR Si... more This paper presents results of a user study of the effects of virtual reality technology on VR Sickness and User Experience. In our study the participants watched two different panoramic (360) videos, one with relaxing content (beach clip) and second one with action content (roller coaster video clip). Videos were watched on four different head mounted displays (HMDs) and on the 2D television as a reference display. To assess VR Sickness discomfort levels, we have used the Simulator Sickness Questionnaire (SSQ), and for user experience the User Experience Questionnaire (UEQ) was used. For quick assessments of VR Sickness discomfort levels, we have also used Subjective Units of Distress Scale (SUDS). We have found a strong correlation between SUDS and total SSQ score and between total SSQ score and SSQ-D score. Shown negative correlation between VR Sickness discomfort levels (assessed by SSQ and UEQ Questionnaire), and user experience (assessed by UEQ Questionnaire), indicates that presence of VR Sickness symptoms affects the user experience.

IEEE Access, 2017

Human facial expressions change with different states of health; therefore, a facial-expression r... more Human facial expressions change with different states of health; therefore, a facial-expression recognition system can be beneficial to a healthcare framework. In this paper, a facial-expression recognition system is proposed to improve the service of the healthcare in a smart city. The proposed system applies a bandlet transform to a face image to extract sub-bands. Then, a weighted, center-symmetric local binary pattern is applied to each sub-band block by block. The CS-LBP histograms of the blocks are concatenated to produce a feature vector of the face image. An optional feature-selection technique selects the most dominant features, which are then fed into two classifiers: a Gaussian mixture model and a support vector machine. The scores of these classifiers are fused by weight to produce a confidence score, which is used to make decisions about the facial expression's type. Several experiments are performed using a large set of data to validate the proposed system. Experimental results show that the proposed system can recognize facial expressions with 99.95% accuracy.

IEEE Access, 2018

This paper presents the analysis of real-life medical big data obtained from a hospital in centra... more This paper presents the analysis of real-life medical big data obtained from a hospital in central China from 2013 to 2015 for risk assessment of cerebral infarction disease. We propose a new recurrent convolutional neural network (RCNN)-based disease risk assessment multimodel by utilizing structured and unstructured text data from the hospital. In the proposed model, the convolutional layer becomes a bidirectional recurrent neural network by utilizing the intra-layer recurrent connection within the convolutional layer. Each neuron within convolutional layer receives feedforward and recurrent inputs from the previous unit and neighborhood, respectively. In addition to step-by-step recurrent operation, the region of context capture increases, thereby facilitating fine-grain feature extraction. Furthermore, we use a data parallelism approach over multimodel data during training and testing of the proposed model. Results show that the data parallelism approach leads to fast conversion speed. The RCNN-based model works differently from the traditional convolutional neural network and other typical methods. The proposed model exhibits a prediction accuracy of 96.02%, which is higher than those of typical existing methods. INDEX TERMS Convolutional neural network, feature learning, medical big data, disease risk assessment.

IEEE Transactions on Circuits and Systems for Video Technology, 2017

With the irruption of inexpensive Depth sensor devices, hand gesture tracking has become again on... more With the irruption of inexpensive Depth sensor devices, hand gesture tracking has become again one topic of great interest. The problems to face respect other tracking algorithms are mainly two: the high complexity of the hand structure which translate in a very large amount of possible gestures, and the rapidness of the movements we are able to make when moving the hand or just the fingers. Recent approaches try to fit a 3D hand model to the observed RGB-D data by an optimization function that minimizes the error between the model and the data. However, these algorithms are very dependent of the initialization point, being unpractical to run in a natural environment. To solve these kind of problems, it is common to use an offline dataset with pre-learnt gestures that will serve as a first rough estimate. In concrete, we present an algorithm that uses an articulated ICP minimization function, that is initialized by the parameters obtained from a dataset of hand gestures trained through deep learning framework. This set up has two strong points. First, deep learning provides a very fast and accurate estimate of performed hand gesture. Second, the articulated ICP algorithm allows to capture the possible variability of a gesture performed by different person or slightly different gesture. Our proposed algorithm is evaluated and validated in several ways. Independent evaluations for deep learning framework and articulated ICP are performed. Moreover, different real sequences are recorded to validate our approach, and finally quantitative and qualitative comparisons are conducted with state-of-the-art algorithms.

Future Generation Computer Systems, 2017

This is a PDF file of an unedited manuscript that has been accepted for publication. As a service... more This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. Highlights  Collaborative Analysis Model for Trending Images in Online Social Networks  Trending image authentication using steerable pyramid transform  Search-based computational Intelligence algorithm for optimal computation  Analysis of descriptive tags and trending contents on Twitter dataset. Highlights (for review)

IEEE Access, 2017

With the continuous rise in ingenious forgery, a wide range of digital audio authentication appli... more With the continuous rise in ingenious forgery, a wide range of digital audio authentication applications are emerging as a preventive and detective control in real-world circumstances, such as forged evidence, breach of copyright protection, and unauthorized data access. To investigate and verify, this paper presents a novel automatic authentication system that differentiates between the forged and original audio. The design philosophy of the proposed system is primarily based on three psychoacoustic principles of hearing, which are implemented to simulate the human sound perception system. Moreover, the proposed system is able to classify between the audio of different environments recorded with the same microphone. To authenticate the audio and environment classification, the computed features based on the psychoacoustic principles of hearing are dangled to the Gaussian mixture model to make automatic decisions. It is worth mentioning that the proposed system authenticates an unknown speaker irrespective of the audio content i.e., independent of narrator and text. To evaluate the performance of the proposed system, audios in multienvironments are forged in such a way that a human cannot recognize them. Subjective evaluation by three human evaluators is performed to verify the quality of the generated forged audio. The proposed system provides a classification accuracy of 99.2% ± 2.6. Furthermore, the obtained accuracy for the other scenarios, such as text-dependent and text-independent audio authentication, is 100% by using the proposed system. INDEX TERMS Digital audio authentication, audio forensics, forgery, machine learning algorithm, human psychoacoustic principles.

IEEE Access, 2017

Recent advances in wireless sensor networks for ubiquitous health and activity monitoring systems... more Recent advances in wireless sensor networks for ubiquitous health and activity monitoring systems have triggered the possibility of addressing human needs in smart environments through recognizing human real-time activities. While the nature of streams in such networks requires efficient recognition techniques, it is also subject to suspicious inference-based privacy attacks. In this paper, we propose a framework that efficiently recognizes human activities in smart homes based on spatiotemporal mining technique. In addition, we propose a technique to enhance the privacy of the collected human sensed activities using a modified version of micro-aggregation approach. An extensive validation of our framework has been performed on benchmark data sets yielding quite promising results in terms of accuracy and privacy-utility tradeoff. INDEX TERMS Internet of Things, data mining, data privacy, healthcare, smart home.

Sensors, 2017

A large number of the population around the world suffers from various disabilities. Disabilities... more A large number of the population around the world suffers from various disabilities. Disabilities affect not only children but also adults of different professions. Smart technology can assist the disabled population and lead to a comfortable life in an enhanced living environment (ELE). In this paper, we propose an effective voice pathology assessment system that works in a smart home framework. The proposed system takes input from various sensors, and processes the acquired voice signals and electroglottography (EGG) signals. Co-occurrence matrices in different directions and neighborhoods from the spectrograms of these signals were obtained. Several features such as energy, entropy, contrast, and homogeneity from these matrices were calculated and fed into a Gaussian mixture model-based classifier. Experiments were performed with a publicly available database, namely, the Saarbrucken voice database. The results demonstrate the feasibility of the proposed system in light of its high accuracy and speed. The proposed system can be extended to assess other disabilities in an ELE.

Multimedia Tools and Applications, 2016

The use of social networks has grown exponentially in recent years. The large amount of data avai... more The use of social networks has grown exponentially in recent years. The large amount of data available in these networks can be effectively utilized in many machine learning applications. This paper proposes a framework of an emotion recognition system that fetches huge amount of face images from the social networks into a cloud. In the cloud, the problem of the unlabeled facial images is handled by applying an active learning approach. For the feature extraction, an interlaced derivative pattern is used, while for a base classifier, an extreme learning machine is utilized. Once the emotion is recognized in the cloud, it can be shared with the end users to meet their interests. Several experiments were performed using some publicly available databases and heterogeneous images from the social networks. Experimental results showed that the proposed framework may effectively be used in the emotion recognition.

Mobile Networks and Applications, 2016

With the advent of future generation mobile communication technologies (5G), there is the potenti... more With the advent of future generation mobile communication technologies (5G), there is the potential to allow mobile users to have access to big data processing over different clouds and networks. The increasing numbers of mobile users come with additional expectations for personalized services (e.g., social networking, smart home, health monitoring) at any time, from anywhere, and through any means of connectivity. Because of the expected massive amount of complex data generated by such services and networks from heterogeneous multiple sources, an infrastructure is required to recognize a user’s sentiments (e.g., emotion) and behavioral patterns to provide a high quality mobile user experience. To this end, this paper proposes an infrastructure that combines the potential of emotion-aware big data and cloud technology towards 5G. With this proposed infrastructure, a bimodal system of big data emotion recognition is proposed, where the modalities consist of speech and face video. Experimental results show that the proposed approach achieves 83.10 % emotion recognition accuracy using bimodal inputs. To show the suitability and validity of the proposed approach, Hadoop-based distributed processing is used to speed up the processing for heterogeneous mobile clients.

Multimedia Tools and Applications, 2015

Users of ambient intelligence environments have been overwhelmed by the huge numbers of social me... more Users of ambient intelligence environments have been overwhelmed by the huge numbers of social media available, thus identifying the social media tailored to the user's need is becoming an important question to be discussed. This paper adapts the Katz proximity measure, for the use in social tagging system, to help users in ambient environment find relevant media suited to their interests. The method models the ternary relations among user, resource and tag as a weighted, undirected tripartite graph, then apply the Katz proximity measure to tripartite graph. Experiments on two real datasets are implemented and compared with many state-of-the-art algorithms. The experimental results prove that the adaptation of the Katz algorithm with the tripartite structure yields a significant improvement, and successfully ranks relevant search results according to the user's interests.