Multimedia Sensor Research Articles

Secure smart home architecture for ambient-assisted living using a multimedia Internet of Things based system in smart cities.

Recent advances in smartphones and remote monitoring based on the Internet of Things (IoT) have enabled improved multidimensional intelligent services. The advent of IoT-based wearable and multimedia sensors has prevented millions of mishapsthrough seamless and systematic monitoring. An IoT-based monitoring system is composed of several sensor devices to measure vital signs, fall detection, energy consumption, and visual recognition. As the data collected by the sensors are transmitted to cloud storage through the Internet, data security is a major concern when transmitting data from remote locations. To improve data security and prediction accuracy, in this study, we proposed a smart and secure multimedia IoT monitoring system for smart homes backed up by smart grid supervisory control and data acquisition (SCADA). The proposed system employs state-of-the-art IoT microcontrollers and hardware devices and integrates them in a manner that significantly affects the accuracy and speed of the entire system. Furthermore, the information gathered from IoT is securely transferred through private channels and stored on the cloud, which can be accessed authentically and reliably using an information system built into an IoT application. The output was extensively compared in terms of power consumption and delivery ratio, which were based on the values collected with sequence numbers. The comparative analysis demonstrated that the proposed approach provides increased prediction accuracy and better security. Hence, the proposed powerefficient prototype model monitors the entire smart home environment in real time and serves as an early warning system for critical situations.

Coverage and Energy Efficiency Optimization for Randomly Deployed Multi-Tier Wireless Multimedia Sensor Networks

In this study, a novel multi-tier framework is proposed for randomly deployed WMSNs. Low cost directional Passive Infrared Sensors (PIR sensors) are randomly deployed across a Region of Interest (RoI), which are activated according to the Differential Evolution (DE) algorithm proposed for coverage optimization. The proposed DE and the Genetic Algorithms are applied to optimize the coverage maximization using minimum sensors. Results obtained using the two approaches are tested and compared. Only the scalar sensors that are yielded by the coverage optimization process are kept active throughout the network lifetime while the multimedia sensors are kept in silent. When an event is detected by a scalar sensor, the corresponding multimedia sensor(s), in whose effective coverage field of view (FoV) that the target falls, is then activated to capture the event (target point/scene). The analysis of the network total energy expenditure and a comparison of the proposed framework to current approaches and frameworks is made. Simulation results show that the proposed architecture achieves a remarkable network lifetime prolongation while extending the coverage area.

Question Text Classification Method of Tourism Based on Deep Learning Model

The Internet of Things applications are diverse in nature, and a key aspect of it is multimedia sensors and devices. These IoT multimedia devices form the Internet of Multimedia Things (IoMT). Compared with the Internet of Things, it generates a large amount of text data with different characteristics and requirements. Aiming at the problems that machine learning and single structure deep learning model cannot effectively grasp the text emotional information in text processing, resulting in poor classification effect, this paper proposes a text classification method of tourism questions based on deep learning model. First, the corpus is trained with word2vec tool based on continuous word bag model to obtain the text word vector representation. Then, the attention mechanism is introduced into the long-short term network (LSTM), and the attention-based LSTM model is constructed for text feature extraction, which highlights the impact of different words in the input text on the text emotion category. Finally, the text features are input into the Softmax classifier to obtain the probability distribution of text categories, and the model is trained combined with the cross entropy loss function. The experimental results show that the average accuracy, recall, and F value are 0.943, 0.867, and 0.903, respectively, which has better classification effect than other methods.

An improved k-angle coverage algorithm for multimedia wireless sensor networks based on two-layer tabu search

An improved k-angle coverage algorithm for multimedia wireless sensor networks based on two-layer tabu search

Fuzzy Logic Based Clustering With Firefly Optimized Routing Protocol For Qos Aware Wireless Sensor Networks

Nowdays, Wireless sensor networks (WSN) becomes familiar due to its applicability in diverse areas of gathering and processing data from the physical environment. At the same time, the advanced applications and new multimedia sensors have raised the demand for highly sufficient management of their quality of service (QoS). The constraints and requirements for theQoS management entirely based on the application perspective. In this view, this paper presents a QoS aware cluster based routing (QoS-CR) technique for WSN. The proposed QoS-CR involves three main processes, namely clustering, routing and maintenance. At the earlier stage, fuzzy logic based clustering (FBC) technique gets executed to organize the nodes into clusters and selects cluster heads (CHs) effectively. Then, a firefly with a levy (FF-L) algorithm is employed for identifying the optimal paths between two CHs or CHs to BS. Finally, the maintenance process is invoked to balance the load and energy consumption throughout the network evenly. A detailed simulation analysis takes place to ensure the performance of the QoS-CR model, and the results are validated interms of several measures under a distinct number of nodes and simulation rounds. The outcome of the extensive simulation verified the superior characteristics of the proposed model over the compared methods.

Feature selection for semi-supervised multi-target regression using genetic algorithm

Multi-target regression (MTR) is an exciting area of machine learning where the challenge is to predict the values of more than one target variables which can take on continuous values. These variables may or may not be correlated. Such problems commonly occur in real life scenarios, and therefore, interest and research in this area has increased in recent times. Some examples of applications include analyzing brain-activity data gathered using multimedia sensors, stock information from continuous web data, data related to characteristics of the vegetation at a certain site, etc. For a real-world multi-target learning system, the problem can be further complicated when new issues emerge with very little data available. In such cases, a semi-supervised approach can be adopted. This paper proposes a Genetic Algorithm (GA) based semi-supervised technique on multi-target regression problems to predict new targets, using very small number of labelled examples by incorporating GA with MTR-SAFER. Experiments are carried out on real world MTR data sets. The proposed method isexplored with different variations and also compared with the state of the art MTR methods. Results have indicated a significantly better performance with the further benefit of having a reduced feature set.

Distributed aerial processing for IoT-based edge UAV swarms in smart farming

This work addresses the challenges of a decentralized and heterogeneous Unmanned Aerial Vehicle (UAV) swarm deployment – some fitted with multimedia sensors, while others armed with scalar sensors – in resource-constrained and challenging environments, typically associated with farming. Subsequently, we also address the resulting problem of sensing and processing resource-intensive data aerially within the Edge swarm in the fastest and most efficient manner possible. The heterogeneous nature of the Edge swarm results in under-utilization of the available computation resources due to unequal data generation within its members. To address this, we propose a Nash bargaining-based weighted intra-Edge processing offload scheme to mitigate the problem of heavy processing in some of the swarm members. We do this by distributing the data to be processed to all the swarm members. Real-life hardware tuned simulation of a large UAV swarm shows that by increasing the number of UAVs in the swarm, our scheme achieves better scalability and reduced processing delays for intensive processing tasks. Additionally, in comparison to regular star and mesh topologies, our scheme achieves an increase in collective available network processing speeds by 100% for only 25% of the number of UAVs in a star topology.

An Application-Aware Clustering Protocol for Wireless Sensor Networks to Provide QoS Management

Wireless sensor networks (WSNs) have long been established as a suitable technology for gathering and processing information from the environment. However, recent applications and new multimedia sensors have increased the demand for a more adequate management of their quality of service (QoS). The constraints and demands for this QoS management greatly depend on each individual network’s purpose or application. Low-Energy Adaptive Clustering Hierarchy (LEACH) is arguably the most well-known routing protocol for WSNs, but it is not QoS-aware. In this paper, we propose LEACH-APP, a new clustering protocol based on LEACH that takes the network’s application into account and is aimed at providing a better overall QoS management. We thoroughly describe our proposal and provide a case study to explain its operation. Then, we evaluate its performance in terms of two significant QoS metrics—throughput and latency—and compare it to that of the original protocol. Our experiments show that LEACH-APP increases the throughput by roughly 250% and reduces the latency by almost 80%, overall providing a more flexible and powerful QoS management.

An adaptive IoT platform on budgeted 3G data plans

Abstract In this paper, we design and implement an Internet-of-Things (IoT) based platform for developing cities using environmental sensing as a driving application. Since ubiquitous and free WiFi access is not available in most developing cities, IoT deployments must leverage 3G cellular connections that are metered and expensive. In order to best utilize the limited 3G data plan, we propose two adaptation strategies to drive sensing and data collection. The first technique is an infrastructure-level adaptation approach where we adjust sensing intervals of periodic sensors so that the data volume remains bounded within the allocated data budget. The second approach is at the information-level where application-specific analytics are deployed on-board devices. This use case focuses on multimedia sensors that process captured raw media data to lower volume semantic data that is communicated. We implement the two adaptation strategies on the EnviroSCALE (Environmental Sensing and Community Alert Network) platform, which is an inexpensive Raspberry Pi based environmental sensing system that employs air quality sensors and periodically publishes sensor data over a 3G connection with a limited data plan. We outline our deployment experience of EnviroSCALE in Dhaka city, the capital of Bangladesh, particularly in the direction of infrastructure-level adaptation. For information-level adaptation, our testbed experiment results demonstrate the practicality of adaptive sensing and triggering rich sensing analytics via user-specified criteria over budgeted 3G connections.

Safe semi supervised multi-target regression (MTR-SAFER) for new targets learning

Multi-target regression (MTR) is a challenging research problem which aims to predict more than one continuous variable as output in a pattern. In recent time, a number of novel applications have increased interest and research in this area. Applications include predicting brain activity from multimedia sensors, different values for stocks from continuous web data, condition of various attributes of the vegetation at a given site, etc. In contrast to conventional regression problems where each instance only belongs to single target from a set of disjoint targets, in multi-target regression, each instance may belong to more than one continuous variable as output. Multi-target regression problems are concerned with problems where there are more than one continuous variables to output. These output variables may or may not be related. A number of approaches have been proposed for this problem. However, for a dynamic multi-target learning system, a pre-trained multi-target system shall be revised as new targets emerge with very few instances. The objective of this paper is to investigate semi-supervised techniques on multi-target regression problems to predict new target using very limited amount of examples. Experiments are then conducted on real world multi-target regression (MTR) data sets. The proposed methodology is then compared with state of the art MTR methods. Promising results are obtained using proposed safe semi-supervised regressor with binary relevance.

Prison Perimeter Surveillance System Using WSN

The aim of this paper is to introduce a prison hybrid surveillance system using two main technologies; Wireless Sensor Network (WSN) and Unmanned Aerial Vehicles (UAVs). The system consists of three tiers; Wireless Underground Sensor Network (WUSN) in tier 0, Wireless Ground Sensor Network (WGSN) in tier 1 and Wireless Vision Sensor Network (WVSN) in tier 2 that consists of surveillance towers and Unmanned Aerial Vehicles (UAVs) equipped with multimedia sensors. Those three tiers are independent in operation and can complement one another in functionality. Such a design that utilizes the most advanced technologies proves performance in flexibility, scalability and hierarchical surveillance for a high security prison or any other military site.

Research on the Color Temperature & White Balance for Multimedia Sensor

With Internet of Things development, multimedia sensors have been employed in lots of applications, such as in smart grid, intelligent transportation etc. How to improve the function of camera becomes an important issue, especially on the color temperature and white balance. White balance is a very important concept in image processing. The so-called white balance, white object is to restore. Since humans from birth after the growth process, the human brain has been the reduction of the adaptability of colored objects under different light. However, as the imaging devices such as digital cameras, cannot adaptability in a different light, since the Charge-coupled Device (CCD) output imbalance, resulting in a digital camera color reproduction distortion. This paper analyzes the principles and characteristics of white balance and color temperature to study the environmental impact of shooting on the captured image and find the most appropriate white balance method.

XMDR-DAI-based USN multimedia MetaData management agent for sensor networks

In a ubiquitous sensor network (USN) environment, it is necessary to define and manage a single metadata between the multimedia sensor and multimedia sensor node for interoperability purposes. One method to resolve this issue is the SensorML (Sensor Model Language), which is standard language that can be applied to sensor modeling. SensorML describes the model for data processing between multimedia sensors and provides a framework that can describe the information of each sensor. In this paper, an XMDR-DAI-based USN multimedia metadata is defined to describe the application of sensor devices, sensor nodes and sensor network information. And then an agent technology is used for effective storing and search of XMDR-DAI-based USN multimedia metadata. Sensor multimedia metadata can maintain interoperability in a USN multimedia environment based on SensorML, and the metadata management system can be directly used for metadata management in USN multimedia middleware or applications.

Real-time routing protocols for (m,k)-firm streams based on multi-criteria in wireless sensor networks

Even though some velocity based routing protocols for (m,k)-firm stream have been recently proposed in multimedia wireless sensor networks, there are still many perspective parameters to be considered for forwarding procedure. Moreover, since they are not correlated with each other, multi-criteria system for forwarding is desirable to select next hop. However, current existing protocols apply these parameters sequentially without any prioritization. To address this issue, in this paper, we propose two (m,k)-firm specific routing protocols based on fuzzy interference system and analytical hierarchical process in conjunction with the gray relational analysis. In each protocol, delivery ratio, energy, speed, (m,k)-firm stream requirement as well as current stream status are used to select the best appropriate next hop while considering given node's constraints. Through the simulation results, we demonstrate that the proposed scheme gracefully maintains (m,k)-firm requirement while extending the network lifetime. Finally, superiority of the proposed approach to existing velocity based routing protocols is also proven through diverse simulation scenarios.

Duration of stay based weighted scheduling framework for mobile phone sensor data collection in opportunistic crowd sensing

Advancement of mobile phone based new sensing paradigm like opportunistic and participatory crowd sensing has lead to increase in both multimedia and scalar sensor data traffic over wireless networks. In opportunistic crowd sensing, there are more chances of missing required mobile phones sensor data due to unpredictable mobility nature of users. Analysis of scheduling schemes under realistic human mobility models has become an important issue for pervasive sensing applications specifically for mobile phone based crowd sensing. This paper refers to a weighted scheduling framework for collecting mobile phone sensor data under Levy Walk mobility model. The proposed method uses duration of stay of mobile phone users as one of the important parameter to improve the scheduling performance in terms of reducing the rate of missing of mobile nodes and thereby increasing the rate of collection of required sensor data. The simulation results show that for improving the scheduling performance in opportunistic crowd sensing, high weight value should be given for duration of stay parameter, when mobile nodes stay within the data collection region for more than schedule iteration time with high probability.

Optimal Viterbi Based Total Variation Sequence Detection (TVSD) For Robust Image/Video Decoding In Wireless Sensor Networks

In this letter, we propose a novel scheme for robust reconstruction, based on total variation regularization, towards image/video communication in multimedia wireless sensor networks. We derive the optimal joint source channel decoder as the combination of a maximum likelihood cost function and an anisotropic total variation norm based regularization factor. The proposed scheme exploits the bounded variation (BV) property of images and is thus ideally suited for reconstruction. Subsequently, it is demonstrated that the trellis based Viterbi decoder can be employed for robust image reconstruction using modified total variation state and branch metrics. Simulation results for BTC and JPEG encoded image transmission demonstrate a superior reconstruction performance for the proposed scheme in comparison to conventional methods.

Design and Realization of Virtual Experimental System for Computer

With the modernization of the society and improvement of technologies, people have new requirement for the communication mode between human and computer. And it leads to the appearance of Virtual Reality technology. The Virtual Reality technology is an integration of computer graphics technique, multi media technique, sensor technique, display techniques, simulation technique, and Internet technologies and so on. It builds virtual scenes on the network to implement a platform that multi-users from different places can immerse into and communicate with each other with no bound.

Routing Protocols for Wireless Multimedia Sensor Network: A Survey

Multimedia applications have become an essential part of our daily lives, and their use is flourishing day by day. The area of wireless sensor network is not an exception where the multimedia sensors are attracting the attention of the researchers increasingly, and it has shifted the focus from traditional scalar sensors to sensors equipped with multimedia devices. The multimedia sensors have the ability to capture video, image, audio, and scalar sensor data and deliver the multimedia content through sensors network. Due to the resource constraints nature of WSN introducing multimedia will add more challenges, so the protocols designed for multimedia wireless sensor network should be aware of the resource constraints nature of WSN and multimedia transmission requirement. This paper discusses the design challenges of routing protocols proposed for WMSN. A survey and comprehensive discussion are given for proposed protocols of WMSN followed by their limitations and features.

Delay-Jitter aware slot assignment for Real-Time applications in wireless multimedia ad hoc sensor networks

This paper presents a distributed time slot assignment algorithm which adopts TDMA as medium access control, specially suited to support applications with tight delay, jitter and throughput requirements in convergecast traffic network, e.g. wireless multimedia surveillance sensor network. The proposed algorithm basically consists of two parts. The first part is the slot assignment for single node, which minimizes delay and jitters for dynamically arrived message streams and optimizes stream acceptation ratio. The second part is the slot assignment for multi-hop network, which guarantees every node having a path to the base station for its data delivery. In the path, sufficient resource is reserved and QoS can be guaranteed. For different applications, we use a dynamic programming technique to optimize TDMA frame length in accordance with their QoS requirements. The proposed algorithm is further optimized for dealing with unreliable links and dynamic traffic demands. It is evaluated and compared with existing slot assignment algorithms. The results show that our algorithm provides lower end-to-end delay and jitter, but higher throughput.

Nonpreemptive priority scheme for the S-MAC protocol in multimedia mobile sensor networks

S-MAC is a well-known medium access control (MAC) protocol designed for wireless sensor networks (WSNs). S-MAC uses a few novel techniques to reduce energy consumption and support self-configuration. Besides, S-MAC also achieves good scalability and collision avoidance by utilizing a combined scheduling and contention scheme. However, S-MAC does not have any priority scheme, making it unsuitable for multimedia applications and suffering from varying degree of starvation and fairness problems. In this paper, we propose a simple, efficient, but yet well-performing sliding contention window control mechanism to modify the S-MAC protocol such that priority can be supported along with the multimedia applications in multimedia mobile sensor networks. Furthermore, the proposed scheme could solve the starvation problem and alleviate the fairness problem. An analytic model is carried out to study the saturation throughput of proposed scheme. In addition, simulations were also conducted to analyze the proposed scheme and the results show that the proposed scheme is able to carry the prioritized traffic and mitigate the starvation and fairness problems.