An Indoor Pedestrian Positioning Method Using HMM with a Fuzzy Pattern Recognition Algorithm in a WLAN Fingerprint System.

In this paper, an indoor real-time location tracking system is proposed using ultra-high frequency passive radio frequency identification technology. A dynamic k nearest neighbor driven hidden Markov model is developed to track subsequent positions of moving objects by combining static localization with dynamic tracking. Statistically validated regression models are developed to relate the tags’ received signal strength indicator and distance, which are iteratively updated over time to accommodate environmental changes. These models are utilized to generate a fingerprint database, which is used by the dynamic k nearest neighbor to estimate the set of potential locations for targeted tagged objects. The probabilistic likelihoods of tags’ potential locations based on the current location and the received signal strength indicator(s) are used to construct the hidden Markov model’s transition and emission matrixes, respectively. Finally, the performance of the proposed framework is evaluated by a set of experiments given different factors, such as movement pattern and speed. Results reveal that our proposed framework can track objects with an average tracking error as low as 0.36m.

Since GPS (Global Positioning System) cannot meet accuracy requirements indoors, indoor Location-Based Services (LBSs) have become increasingly important. BLE (Bluetooth Low Energy) offers cost and accuracy advantages. Typically, the position fingerprinting method is used for indoor positioning. However, due to irregular reflection and absorption, the indoor environment introduces various offsets in Bluetooth RSSI (Received Signal Strength Indicator). This study analyzed the RSSI space and proposed a pre-processing workflow to improve position estimation accuracy by correcting offsets in RSSI space for BLE fingerprinting methods using machine learning. Experiments performed using different position estimation methods showed that the corrected data achieved a 6% improvement over the filter-only result. This study also evaluated the effects of different pre-processing and post-processing filters on positioning accuracy. Experiments were also conducted using a published dataset and showed similar results.

Wireless networks, and in particular Wireless Fidelity ( WiFi ) networks, present important problems of connectivity among wireless terminals. These problems lead to inefficiencies in the Application level. For localization algorithms in wireless networks, efficient handover protocols and multimedia delivery information, these problems must be solved. A figure used to control the connectivity of terminals to other terminals or to an Access Point ( AP ) is the well known Received Signal Strength Indicator ( RSSI ). Managing this figure it is possible to control the availability of a service in the wireless terminal. But the problem with RSSI is the fact that it exhibits high variability in space and time. Thus it is important to filter those values in order to efficiently manage the availability of the service in the mobile terminal. For that reason in this paper we present the experimental validation of a filter and a predictor of availability of a service in the wireless terminal based on the RSSI. We test the performance of the filter and the predictor that improves significantly other filters that are also presented in the paper. The significance of our work is that our filter allows simplifying a lot of network algorithms and protocols. As an example we present a simple protocol of handover in presence of multimedia information using our filter and predictor based on RSSI.

The deployment of a fingerprint positioning method consists of an offline phase and a real-time phase. During the offline phase, a fingerprint database is built. This process is tedious and time consuming. Even so, the majority of WiFi-based indoor positioning methods implemented in practical indoor location–based service (ILBS) systems are the fingerprint method, because this method is accurate enough, whereas other WiFi-based indoor positioning methods are too inaccurate. During the real-time phase, the fingerprint method obtains a test fingerprint (a set of WiFi signals collected at that moment). Then, for each fingerprint, i f , in the fingerprint database, it compares i f with the test fingerprint in order to find the most similar i f . This paper introduces a novel method of comparing two fingerprints in order to improve the accuracy of the fingerprint method. This method assigns weights to received signal strength indications (RSSIs) based on the variance of the RSSIs.

Results of a study of the influence of manufacturing environment factors on wireless personal networks are presented in the paper. A classification of such factors is proposed, and the noise immunity of wireless personal networks is determined using a real production as an example. A method for evaluating noise immunity based on a received signal strength indicator (RSSI) is proposed. RSSI values can be obtained natively from almost any receiver and transmitter, which makes this method affordable compared to using network analyzers and other specialized equipment. In the conducted experiment the receiver and transmitter were located at a distance ranging from 0.5 to 25 m from each other. The act of signal transfer was carried out alternately under the influence of each production environment factor. Then measured RSSI values were analyzed and converted into the maximum permissible distance between the receiver and the transmitter in accordance with the proposed method. As a result, data on the influence of a production environment on the noise immunity of wireless personal networks was obtained. Nevertheless, it is concluded that the influence is not significant enough to decide against the use of wireless personal networks, since the influence of many factors can be offset by the use of mesh topology and a dense arrangement of receivers and transmitters. The results are particularly interesting in the context of manufacturing digitalization, where the wireless method of data transmission from field level sensors becomes preferable to the wired due to the requirement for flexibility and mobility of a production process.

Wireless networks are abundant throughout public spaces and medical facilities. Health monitoring systems may employ the use of wireless communication for data observation and collection in a Dynamic Data Driven Application System (DDDAS). Receive Signal Strength Indicator (RSSI) is a metric to evaluate the performance of two wireless devices and it can be leveraged as a medium for a covert channel. This paper proposes a novel approach in utilizing the observation of RSSI measurements at a wireless receiver as a covert channel. By fluctuating the transmitting power of a wireless emitter, the peak and troughs of an observation can be evaluated as a message. Additionally, RSSI as a metric is significantly hindered by noise and interference. Thus, the hindrance presents a challenge when RSSI is employed as a covert channel. To address such a challenge, we apply wavelet transforms to denoise the measurements of RSSI for when we fluctuate the transmitting power. Our realworld evaluation demonstrates the applicability, accuracy, and performance of the proposed approach in DDDAS

Wireless Sensor Networks have attracted many researchers all over the world. Wireless sensor networks have become a kind of sub field including data fusion, data aggregation, remote environmental monitoring, sensing (temperature, pressure speed) and a variety of military applications. The Received Signal Strength Indicator (RSSI) is used for distance measurement between sensor nodes. This paper proposes both average and adaptive fuzzy logic algorithms to compute monitoring area temperature. The main advantages of these methods are simplicity and accuracy in area temperature monitoring. We compare the mean square of error of these two methods. Using the RMSE results, it is shown that the adaptive fuzzy logical algorithm with RSSI is better than the average fuzzy logical algorithm at computing monitoring area temperature.

Expansion of wireless body area networks applications, such as health-care, m-banking, and others has lead to vulnerability of privacy and personal data. An effective and unobtrusive natural method of authentication is therefore a necessity in such applications. Accelerometer-based gait recognition has become an attractive solution, however, continuous sampling of accelerometer data reduces the battery life of wearables. This paper investigates the usage of received signal strength indicator (RSSI) as a source of gait recognition. Unlike the accelerometer-based method, the RSSI approach does not require additional sensors (hardware) or sampling of them, but uses the RSSI values already available in all radio devices. Three radio channel features namely, the time series, auto-correlation function, and level crossing rate were extracted from unique signature of the RSSI in relation to the corresponding subject. The extracted features were then used together with four different classification learners, namely decision tree, support vector machine, $k$ -nearest neighbors, and artificial neural network, to evaluate the method. The best performance was achieved utilizing artificial neural network with 95% accuracy when the features were extracted from one on-body radio channel (right wrist to waist), and 98% when the features were extracted from two on-body radio channels (right wrist to waist, and left wrist to waist). The developed RSSI-based gait authentication approach can complement high-level authentication methods for increased privacy and security, without additional hardware, or high energy consumption existing in accelerometer-based solutions.

In Wireless Sensor Networks (WSN), localization system is required in order to provide position information to sensor nodes. The cost and limited energy resource associated with common, mobile nodes prohibits them from carrying relatively expensive devices such as Global Positioning System (GPS). This paper proposes a mechanism that allows non-GPS-equipped nodes in the network to derive their approximated locations from a limited number of GPS-equipped nodes. A Non-GPS equipped node uses Received Signal Strength Indicator (RSSI) to know the position of the node using Hidden Markov Model (HMM). To enhance lifetime, an efficient clustering scheme is used for localizing the nodes of HMM with Random Walk Mobility (RWM) model. Coverage Preserving Clustering Protocol (CPCP) approach is compared with existing LEACH protocol for localization with HMM combined mobility through NS2 simulation. Simulation analysis shows that our cluster localization out performs well with Learning Movement Patterns.

Pattern recognition for measuring the flame stability of gas-fired combustion based on the image processing technology

Indoor localization is an enabling technology for pervasive and mobile computing applications. Although different technologies have been proposed for indoor localization, Wi-Fi fingerprinting is one of the most used techniques due to the pervasiveness of Wi-Fi technology. Most Wi-Fi fingerprinting localization methods presented in the literature are discriminative methods. We present a generative method for indoor localization based on Wi-Fi fingerprinting. The Received Signal Strength Indicator received from a Wireless Access Point is modeled by a hidden Markov model. Unlike other algorithms, the use of a hidden Markov model allows ours to take advantage of the temporal autocorrelation present in the Wi-Fi signal. The algorithm estimates the user’s location based on the hidden Markov model, which models the signal and the forward algorithm to determine the likelihood of a given time series of Received Signal Strength Indicators. The proposed method was compared with four other well-known Machine Learning algorithms through extensive experimentation with data collected in real scenarios. The proposed method obtained competitive results in most scenarios tested and was the best method in 17 of 60 experiments performed.

The location method based on Received Signal Strength Indication (RSSI) ranging has the advantages of low development cost and simple implementation mechanism, and is the mainstream indoor location method nowadays. However, at present, there is a lack of systematic research on the characteristics of Access Point (AP) received signal strength, which cannot meet the signal strength characteristics required by specific indoor positioning environment. Detailedly, in this study, the indoor distribution characteristics of 2.4 GHz RSSI were analyzed experimentally from three influencing factors including antenna orientation of the receiver, type of wireless network card of the receiver and height difference of the transmitting and receiving antenna. The experimental results show that: (1) The RSSI value measured is the strongest When the antenna of the receiver is vertically oriented to the antenna of the transmitter, while the antenna is vertically backward to the transmitter, it is the opposite. The difference between the strongest signal and the weakest signal is 20%–25% at the same test point. (2) The network card with a large measurement range should be selected for data collection on the premise that the quantization step size is 1 and the smoothness is small. Avoiding using the network card for positioning with the maximum limit of measurement range is proposed also. (3) The path loss index of the ranging model is affected by the height difference of the antenna, resulting in a deviation of 0.1–0.2.

Today is an era of technology and computing. This technological revolution has created a need for anything and everything to be connected to each other in order to achieve a better communication and utilisation of resources. An isolated computer becomes an information island and may not be able to achieve the optimum use of power and resources. To connect computer systems, there are two options available: one is the installation of LAN (local area networking) cables which may be cumbersome at first but it ensures security and the other one is wireless media. Wireless networking, apart from being simple and efficient, poses serious challenges of security breach by rogue nodes and compromise in performance due to dynamic nature of mobile nodes. Extensive research has been carried out so far and several algorithms and protocols have been formulated to incorporate the location and energy aware characteristics for routing. The technique proposed in this paper considers various factors like energy, distance, vulnerability and battery power while propagating the packet information between the nodes in a sensor networks implementing the heterogeneity in terms of nodes. The ultimate aim is to enhance the longevity of the sensor network while ensuring the security of the network. This is achieved by considering RSSI (Received Signal Strength Indicator) factor in accord with other factors in a multi-hop routing. Extensive simulation results and analysis demonstrate that the proposed technique outperforms other security mechanisms and protocols in the literature in terms of energy awareness, security and routing efficiency.

The emergence of wireless body area networks (WBANs) has paved the way for real-time sensing of human biometrics in addition to remote control of smart medical devices, which in turn is revolutionising the smart healthcare industry. However, the limited power and computational capabilities of WBAN sensors make them vulnerable to a myriad of security attacks, thus securing them is paramount to their success and wider adoption. Received signal strength indicator (RSSI) secure key extraction (SKE) methods are used for securing WBAN sensors. However, such methods may suffer from stagnant RSSI values, significantly increasing the secret keys construction time. To remedy this, we propose a new method that involves one of the two sensors being mobile and thus can be picked up and moved around. This results in the stimulation of RSSI values which in turn improves the quality of the generated keys and thus shortening the execution times of the SKE process. The evaluation results highlighted the effectiveness of our method.

This paper presents a new robot system consisting of plural small size rovers for an asteroid wide-area exploration. After the rovers land and scatter on an asteroid, they communicate each other using radio and make a wireless mesh network on the asteroid's surface. When the rover communicates another ones, RSSI (Received Signal Strength Indicator) can be obtained at the same time. Although a CPU installed in the rovers cannot perform complex calculation, all the RSSI values are sent to Earth and relative distances among the rovers are estimated based on the RSSIs. Our proposed system has the following three advantages against a conventional exploration system using one or two rovers: (1) It is possible to explore a wider area of an asteroid. (2) Since the mesh network has redundant communication paths, it has more robustness against some troubles. (3) The relative distance estimation is useful for asteroid analyses using sensors that rovers have. In this paper, we describe that the concept of our proposed robot system, the relative distance estimation method based on the genetic algorithm and some simulation results.