A novel hybrid machine-learning approach is proposed in this work to carry out robust multi-people tracking using a millimeter-wave (mmWave) radar in complex indoor environments. The proposed new system including the adaptive hybrid clustering technique leverages both density-based spatial clustering (DBSCAN) and expectation-maximization (EM) schemes over the received radar point-clouds to separate individual human trajectories reliably. Meanwhile, the Hungarian algorithm incorporation with the Kalman filter is employed for tracking of individual persons. Furthermore, a condition-number-based outlier detector is designed to filter error-prone radar data to improve the tracking accuracy. Realworld experiments are conducted in various indoor scenarios and the results demonstrate that our proposed new system can achieve an average Euclidean-distance error (EDE) of 38.19cm in the presence of a single person and that of 44.70cm in the presence of two persons in our laboratory with the area of 300cm×300cm. Our proposed new multi-subject tracking approach also outperforms the existing methods in terms of EDE.

Millimeter-wave (mmWave) radar has been deemed a key enabling technology for Internet of Things (IoT) applications and offers robust and non-invasive sensing capabilities of intelligent systems. However, conventional Fourier transform (FT)-based range estimation methods suffer from limited resolution, which can restrict performance, especially in dynamic IoT scenarios. To address this, we propose a fractional Fourier transform (FrFT)-based range estimation scheme that achieves higher resolution and accuracy. The proposed method incorporates a recursive clutter removal mechanism to enhance signal quality and employs a random forest regressor to dynamically determine the optimal FrFT angle parameter α for improved performance. Experimental results demonstrate that our proposed new FrFT-based approach achieves a mean absolute percentage error (MAPE) of 16.67%, which significantly outperforms the conventional FT-based method with a MAPE of 37.13%. Furthermore, we validate the effectiveness of our new approach by presenting its application to human height measurement to showcase its potential for real-world applications.

The utilization of face masks is an essential healthcare measure, particularly during times of pandemics, yet it can present challenges in communication in our daily lives. To address this problem, we propose a novel approach known as the human-in-the-loop StarGAN (HL–StarGAN) face-masked speech enhancement method. HL–StarGAN comprises discriminator, classifier, metric assessment predictor, and generator that leverages an attention mechanism. The metric assessment predictor, referred to as MaskQSS, incorporates human participants in its development and serves as a “human-in-the-loop” module during the learning process of HL–StarGAN. The overall HL–StarGAN model was trained using an unsupervised learning strategy that simultaneously focuses on the reconstruction of the original clean speech and the optimization of human perception. To implement HL–StarGAN, we created a face-masked speech database named “FMVD,” which comprises recordings from 34 speakers in three distinct face-masked scenarios and a clean condition. We conducted subjective and objective tests on the proposed HL–StarGAN using this database. The outcomes of the test results are as follows: (1) MaskQSS successfully predicted the quality scores of face-masked voices, outperforming several existing speech assessment methods. (2) The integration of the MaskQSS predictor enhanced the ability of HL–StarGAN to transform face-masked voices into high-quality speech; this enhancement is evident in both objective and subjective tests, outperforming conventional StarGAN and CycleGAN-based systems.

A novel robust package-height estimation and parcel-size classification scheme is proposed in this work. A pertinent prototype system consisting of a millimeter-wave radar, a shipment track, and a stepping motor has been built for proof of concept. Three new schemes using the range-profile data produced by the mmWave radar, namely, the detection based-on cumulative distribution (DBCD) scheme, the detection based-on peak-value clustering (DBPC) scheme, and the DBCD–DBPC hybrid scheme are introduced here. For benchmark evaluation of the proposed new system, two practical scenarios, namely, the undisturbed scenario (no people is close to the system) and the disturbed scenario (some people is close to the system), are tested. This new system can overcome the serious drawback of the existing camera-assisted systems, which have to rely on sufficient lighting conditions, and operate normally even in complete darkness. Meanwhile, the proposed new system can accommodate parcels/packages in arbitrary orientations, which cannot be allowed by the current camera-assisted systems, during the parcel-size measurements. According to the test experiments, the proposed DBCD–DBPC hybrid scheme can reach up to a very high average classification accuracy of 96.4% for both undisturbed and disturbed scenarios. The proposed novel package-height estimation and parcel-size classification technique in this work can be very useful for intelligent inventory management and smart logistics in the future.

Due to the growing need for bandwidth starving Multi-View Videos (MVV) in virtual reality, TV, and education, effectively allocating the resources of next-generation wireless technologies for MVV streams becomes increasingly crucial. To achieve high utility for MVV users, this article proposes a cross-layer resource allocation mechanism to leverage video synthesizing schemes (such as Depth-Image-Based Rendering (DIBR) for efficient MVV streaming with massive MIMO). First, we formulate a new problem,antenna allocation with video synthesis(AAVS), and prove its NP-hardness. Then, we design an approximation algorithm namedUtility-based Multi-View Synthesis(UMVS) with the analytical performance provided, and dynamic scenarios are addressed by augmenting UMVS with deep reinforcement learning. Data-driven simulation results show that UMVS outperforms existing antenna allocation schemes by at least 10%, and the DRL extension provides an additional 6% improvement in system utility under congested scenarios.

Currently, there are concerns regarding the impact of AI-generated fake sentences or artificially manipulated audio files on people’s lives and property. However, the public database for this purpose is very limited and the performance of algorithms is language dependent. The verification of the authenticity of audio files using other languages cannot completely determine whether experimental results can be replicated in Chinese sentences. Therefore, this article created an acoustic Chinese database, named YuanZe Mandarin Dataset (YZMD), by recording different tampered audio samples in a silent room using a microphone, minimizing external interference with the audio files. The text used was adjusted based on the hearing test for Taiwanese Mandarin in noise. The purpose of this database is to verify the effectiveness of detecting audio tampering and to provide it for future public use. We evaluated several algorithms, including two different features, CQCC (Constant Q Cepstral Coefficients) and MFCC (Mel-frequency Cepstral Coefficients), and two different learning models, ResNet (Deep Residual Networks) and GMM (Gaussian Mixture Model). This article also compared and evaluated a database called Automatic Speaker Verification Spoofing and Countermeasures Challenge. The experiments showed that YZMD had similar trends to the public database. The results showed that the CQCC feature was significantly superior to MFCC due to its higher dimensionality. Meanwhile, ResNet provided better performance than GMM. The results in both databases indicate that combining CQCC and ResNet can further improve the performance of detecting forged audio files, compared to all other feature-model combinations.

In this letter, we propose a novel automatic-segmentation technique for a dynamic human-posture learning system using skeletal-graph time-series. The focused problem is very challenging as no fixed segment-size is appropriate for capturing precise human postures. Our proposed novel dynamic-segmentation scheme will first estimate the number of segments and then the optimal segmentation can be determined using hidden logistic regression subject to the estimated number of segments. Experimental results from the realworld Kinect data are compared with the well-known dynamic-time-warping (DTW) segmentation method. Based on our experiments, our proposed new scheme greatly outperforms the DTW method in terms of miss-detection probability and miss-alignment percentage.

Due to the growing need for Multi-View Videos (MVV) in advertisement, TV, and education, effectively allocating the resources of next-generation wireless technologies to provide MVV streams is challenging. To achieve the high utility for MVV users, this paper proposes a cross-layer resource allocation mechanism to leverage video synthesizing schemes (such as Depth-Image-Based Rendering (DIBR)) for efficient MVV streaming with massive MIMO. We formulate a new problem Antenna Allocation with Video Synthesizing (AAVS) and prove its NP-hardness. Then, we design an algorithm, named Marginal Utility-Based Iteration (MUBI). The performance is evaluated by the data-driven simulations, and the results manifest that MUBI outperforms the baselines regarding the total utility of users.

The method is proposed to detect human body with frequency modulation continuous wave (FMCW) and millimeter-wave (mmWave) radar. Human detection is the first step before performing vital sign monitoring, which is one of the most important applications for mmWave radar. In this Abstract, we exploit the range profile (RP) variation within a certain distance to detect human. This requires less computational storage spaces than conventional approaches. First, we perform clutter removal processing to weak ranging signals, and then calculate the standard deviation of each chirp to identify whether there is human in radar’s field of view (Fov). The experimental results confirmed that the accuracy our proposed method is higher than 97% even if the received ranging signals are weak.

Auscultation is the most efficient way to diagnose cardiovascular and respiratory diseases. To reach accurate diagnoses, a device must be able to recognize heart and lung sounds from various clinical situations. However, the recorded chest sounds are mixed by heart and lung sounds. Thus, effectively separating these two sounds is critical in the pre-processing stage. Recent advances in machine learning have progressed on monaural source separations, but most of the well-known techniques require paired mixed sounds and individual pure sounds for model training. As the preparation of pure heart and lung sounds is difficult, special designs must be considered to derive effective heart and lung sound separation techniques. In this study, we proposed a novel periodicity-coded deep auto-encoder (PC-DAE) approach to separate mixed heart-lung sounds in an unsupervised manner via the assumption of different periodicities between heart rate and respiration rate. The PC-DAE benefits from deep-learning-based models by extracting representative features and considers the periodicity of heart and lung sounds to carry out the separation. We evaluated PC-DAE on two datasets. The first one includes sounds from the Student Auscultation Manikin (SAM), and the second is prepared by recording chest sounds in real-world conditions. Experimental results indicate that PC-DAE outperforms several well-known separation works in terms of standardized evaluation metrics. Moreover, waveforms and spectrograms demonstrate the effectiveness of PC-DAE compared to existing approaches. It is also confirmed that by using the proposed PC-DAE as a pre-processing stage, the heart sound recognition accuracies can be notably boosted. The experimental results confirmed the effectiveness of PC-DAE and its potential to be used in clinical applications.

Femtocells can extend the last-mile accessibility for the current cellular networks so as to serve more users indoors and improve the spectrum utility. However, since the indoor femtocell establishment can be ad hoc, HeNBs may also be inevitably vulnerable to the rogue-HeNB (uncoordinated or illegitimate HeNB) attack in practice. For detecting rogue-HeNBs, a two-dimensional received signal-to-interference-plus-noise ratio (SINR) map is exploited to construct a spatial radio-activity feature map (RAFM). Mathematical proof is derived to justify that the existence of any femtocell interference corresponds to a flat-bottom convex region in the RAFM. Advanced image processing techniques are designed here to localize the radio interference (rogue-HeNB) over the RAFM. Thus, a novel positioning scheme is proposed in this paper to undertake the accurate rogue-HeNB localization for the femtocell networks. Different indoor scenarios are evaluated through the real experiments for our proposed method. The average accuracy can be within one meter for a 6.75 meter by 8.1 meter laboratory.

We participate in the FEMH 2018 Challenge of a bigdata subproject of the IEEE. The goal of this Challenge is pathological voice detection, and classify the different diseases, including phono trauma, neoplasm and vocal paralysis. Final, this challenge uses sensitivity, specificity and UAR as a result. The database is recorded with 50 normal voice samples and 150 samples of common voice disorders in a tertiary teaching hospital (Far Eastern Memorial Hospital, FEMH). The paper proposes a Deep Neural Networks based (DNN-based) approach in this challenge. Data preprocessing used Mel-Frequency Cepstral Coefficients (MFCCs), which also have emotion specific information. Gradual spectral variations are captured using 13 MFCCs extracted from speech signal. In the disease detection section, we examine the performance among different DNN structures (ie, hidden layers and number of neurons). Then, In the disease classification section, examine the performance among different batch sizes and normalize or no normalize. Finally, the tested DNN structures have the best results at 5 hidden layers and 200 of neurons.

Intelligent inspection in the substation transformer using optical character recognizer has been developing rapidly. Character segmentation from the text line of data plate is an important step for localization and recognition of electrical equipment. However, on-site character segmentation is challenging if the data plate contains multiple languages, especially when the width between Chinese and non-Chinese character differs significantly and the complex environments cause the light reflection and fading. This paper proposes a new method, based on analyzing the connected component and Chinese character's structure, to segment characters from multi-language data plate of substations. The proposed method uses the combination of the HSV color space and multi-scale MSRCP to reduce the effect of illumination and complex background. The proposed method utilized the width of each kind character, the interval between characters and the relationship within the left-right structure Chinese character to improve the segmentation accuracy. Experimental results show that the text lines from the data plate in substation transformer, including Chinese, English, Roman numerals, Arabic numerals and symbols, can be segmented correctly. Results show that the proposed method outperforms two existing character segmentation methods and achieves 99.4% precision in the multi-language data plate dataset.

In the mobile industrial human-machine interaction (HMI), to establish the data connection, the engineer has to manually select the target machine from a long list, which may lead to wrong connection and waste of time. We observe that the engineer should face to the machine during the interaction to ensure that the machine works accurately, and this characteristic makes the proximity estimation algorithm suitable to simplify the data connection. However, due to the densely deployed machines, the existing algorithms cannot provide sufficient accuracy with limited latency. In this paper, we implement a testbed to evaluate the performance in the mobile industrial HMI. Based on the experimental results, we propose the definition of received signal strength indicator (RSSI) difference and then use it to design the face-to-machine proximity estimation (FaceME) algorithm. The experimental results prove that FaceME can provide guaranteed estimation accuracy and low-time complexity.

In the mobile industrial human machine interaction (HMI) based on wireless sensor networks, the engineer has to manually select the target machine from a long list which may lead to wrong connection and waste of time. We observe that the engineer should face to the machine during the interaction to ensure that the machine works accurately, and this characteristic makes the proximity estimation algorithm suitable to simplify the data connection. However, due to the densely deployed machines and the frequent HMI in the industrial plant, the existing algorithms can not provide sufficient accuracy with limited latency. In this paper, we implement a mobile industrial HMI testbed to evaluate the characteristics of wireless communication in the face-to-machine HMI, and then propose the face-to-machine proximity estimation (FaceME) algorithm based on the analytical results. The experimental results prove that FaceME can provide guaranteed estimation accuracy and low time complexity that satisfies the requirements of the face-to-machine HMI.

To establish data connection in industrial wireless networks, the engineer has to enter the address of the target machine or manually select it from a list. Since the machines are densely deployed in the plant, the manual data connection becomes a non-trivial issue which may lead to connection error and waste of time. The existing technologies, such as QR code scanning and proximity estimation, simplify the process of data connection to the closest node. However, they can not be used to connect with any node located in line-of-sight of the engineer, and thus limits their application. In this paper, we propose a scheme called LightCon which controls the display module (LCD screen or LED light) of nodes to display different visible symbols such as colors and numbers, thus the engineer can select the corresponding symbol on the mobile device to establish connection. Moreover, symbol assignment algorithms are proposed to reduce the complexity of symbol selection when the number of nodes are greater than the number of symbols. The theoretical and experimental results prove that LightCon reduces the complexity of line-of-sight connection with guaranteed accuracy.

In this study, the authors tackle the problem of carrier aggregation (CA) in downlink of long‐term evolution advanced (LTE‐A) femtocell networks. They propose a novel approach in a new perspective: namely, user navigation, to improve the CA performance of an LTE‐A system in the indoor environment. The proposed indoor user navigation (IUN) algorithm exploits the a priori knowledge of radio interferences between femtocells to build a geometric quality‐of‐service (QoS) map, which can be utilised to navigate users toward the locations suitable for performing CA to satisfy the QoS requirements. The simulations demonstrate the effectiveness of the proposed IUN algorithm to improve the CA performance in terms of the aggregate throughput for the LTE‐A femtocell networks.

Nowadays, the sufficient quality-of-service (QoS) provision for mobile applications remains a major challenge in any wireless network. Conventional sufficient QoS provision techniques using resource allocation, data scheduling, and cross-layer optimization have been proposed to tackle this problem. Nevertheless, due to the unpredictable nature of wireless channel conditions, the QoS improvements resulting from the aforementioned approaches are often unsatisfactory. In this paper, we would like to follow our previous concept, namely user-placement ushering (UPU), by use of the user's mobility. A mobile user can be relocated to an optimal, or at least a better place to boost the QoS for a particular application. Novel fast algorithms are devised here to usher (guide) the mobile user to an appropriate spot with sufficient QoS, which is nearby. We address the UPU problem to accommodate realistic complex indoor environments, where obstacles are present. Our simulation results have demonstrated that our new fast UPU algorithms are capable of finding new appropriate locations satisfying the required QoSs for different wireless network applications.

This study proposes an accurate and calibration-free mobile device localization algorithm in cellular networks. By exploiting the mutual received signal strength (RSS) between base stations, the proposed algorithm creates an accurate RSS-distance mapping using multivariable regression approaches. Unlike traditional methods, the generated mapping is not fixed but rather dynamic to reflect current environments, thus, better characterizing the RSS-distance relationship in the target area and achieving more accurate location estimations without additional calibration effort. Furthermore, this study adopts singular value decomposition to enhance the robustness of our system. Experiments were conducted in a realistic GSM network. Results demonstrated that our approach apparently improves the positioning accuracy, as compared to three existing cellular-based methods, Cell-ID, enhanced Cell-ID, and propagation-model approaches.

A novel vector-space-based adaptive filtering (VAF) algorithm for acoustic echo cancellation (AEC) is presented. The proposed VAF algorithm can be divided into two phases: offline and online. In the offline phase, VAF constructs a vector space to incorporate the prior knowledge of adaptive filter coefficients from a wide range of different channel characteristics. Then, in the online phase, a mapping function is derived to estimate the adaptive filter for the testing condition using the constructed vector space. By using the vector space, VAF can effectively and efficiently estimate the parameters of the adaptive filter for the unknown testing condition. The experimental results for three designed AEC tasks demonstrate that VAF provides notably faster convergence rates compared to conventional adaptive filtering methods.

Received signal strength (RSS) in Wi-Fi networks is commonly employed in indoor positioning systems; however, variations in hardware challenge robustness of this approach. This paper proposes a novel positioning feature, which is called delta-fused principal strength (DFPS), to enhance the robustness of Wi-Fi localization against the problem of heterogeneous hardware. The proposed algorithm computes the pairwise delta RSS and then integrates with RSS using principal component analysis. This paper makes two principal contributions: First, the fused positioning feature embeds discriminative power within delta RSS to compensate for the problem of heterogeneous devices in a unified framework, and second, DFPS provides increased flexibility in determining the number of required components and achieves better computational efficiency. We applied DFPS to location fingerprinting systems in a realistic indoor Wi-Fi environment. Experimental results demonstrate the effectiveness of proposed algorithm, where DFPS outperforms previous robust positioning features for heterogeneous and homogeneous devices.

This study investigates the performance of Wi-Fi-based fingerprinting location estimation in an unmodified factory environments of Hon-Hai Precision Industry. The positioning system contains four components: temporal filter, dynamic clustering, access point selection, and pattern-matching. We evaluated the performance using realistic Wi-Fi power measurements. Results show that, although reasonable accuracy is achieved (around 72-percentil error is smaller than 7 meter), there always exist much large errors (e.g., over 13 meter). We argue that for a large factory environment, sufficient number of the-same-floor APs is required for many indoor location-based applications such as labor tracking.

This study proposes a clustering-based Wi-Fi fingerprinting localization algorithm. The proposed algorithm first presents a novel support vector machine based clustering approach, namely SVM-C, which uses the margin between two canonical hyperplanes for classification instead of using the Euclidean distance between two centroids of reference locations. After creating the clusters of fingerprints by SVM-C, our positioning system embeds the classification mechanism into a positioning task and compensates for the large database searching problem. The proposed algorithm assigns the matched cluster surrounding the test sample and locates the user based on the corresponding cluster's fingerprints to reduce the computational complexity and remove estimation outliers. Experimental results from realistic Wi-Fi test-beds demonstrated that our approach apparently improves the positioning accuracy. As compared to three existing clustering-based methods, K-means, affinity propagation, and support vector clustering, the proposed algorithm reduces the mean localization errors by 25.34%, 25.21%, and 26.91%, respectively.

Received power in cellular networks is commonly employed in mobile localization systems. However, uncertainties in power-distance mapping and dynamics of propagation models challenge the performance of the positioning system. Although collecting realistic data in the target area may reduce the uncertainties, it requires a time-consuming site survey and high-cost labor efforts. This study proposes a novel algorithm to enhance the performance of mobile localization without the need of additional calibration effort. The proposed algorithm utilizes the pairwise information between base stations (BSs), which is assumed to be available, and then localizes the user based on multidimensional scaling. Unlike traditional methods, the proposed approach further considers the geometric structure between BSs to compensate for the problem of distance estimation, thus achieving more accurate location estimations. We applied this approach in a realistic GSM network and experimental results demonstrate the effectiveness of our approach. The proposed algorithm outperforms previous calibration-free positioning methods, including Cell-ID and enhanced Cell-ID, in reducing the mean error by 16.74%-38.56% and 18.22%-20.96%, respectively.

Received signal strength (RSS) in Wi-Fi networks is commonly employed in indoor positioning systems; however, device diversity is a fundamental problem in such systems. This problem becomes more important in recent years due to the tremendous growth of new Wi-Fi devices, which perform differently in respect to the RSS values and degrade localization performance significantly. Several studies have proposed methods to improve the robustness of positioning systems against device diversity. This paper is primarily concerned with the performance of calibration-free approaches, including signal strength difference (SSD), hyperbolic location fingerprinting (HLF), and DIFF. The performance comparison is based on two Wi-Fi positioning systems in a 3-D indoor building, including a zero-configuration and a fingerprinting-based system. The results show that these calibration-free techniques perform much better than the original RSS with heterogeneous devices. However, the improvement in robustness is gained at the expense of losing some discriminative information. When the testing and training data are both measured from the same device, the performance of HLF and SSD is clearly below that of RSS in both systems. Although DIFF performs the best, it has to suffer from dealing with a space of large dimensions.

Wireless positioning is vulnerable to malicious attacks due to the nature of its open medium. This study proposes an attack-resistant fingerprinting localization algorithm based on a probabilistic inclusive disjunction model. This model allows an attacked observation to play a less significant role during the localization process, thus achieving more robust location estimations under security threats. This study included experiments conducted in an actual Wi-Fi network. Experimental results demonstrated that this approach apparently achieves more robust estimation than cluster-based, median-based, and sensor-selection methods under various attacks on RSS.

This paper presents a novel approach to building a WLAN-based location fingerprinting system. Our algorithm intelligently transforms received signal strength (RSS) into principal components (PCs) such that the information of all access points (APs) is more efficiently utilized. Instead of selecting APs, the proposed technique replaces the elements with a subset of PCs to simultaneously improve the accuracy and reduce the online computation. Our experiments are conducted in a realistic WLAN environment. The results show that the mean error is reduced by 33.75 percent, and the complexity by 40 percent, as compared to the existing methods. Moreover, several benefits of our algorithm are demonstrated, such as requiring fewer training samples and enhancing the robustness to RSS anomalies.

This paper proposes a dynamic fingerprinting combination (DFC) algorithm that improves mobile localization by dynamically weighting the spatial correlation from multiple location fingerprinting systems. This DFC algorithm first extracts the complementary advantages of fingerprinting functions to construct a fusion profile, and then dynamically combines individual outputs based on the fusion profile surrounding the test sample. The proposed algorithm generates more accurate location estimates and reduces the risk of selecting a poorly-performing fingerprinting approach. This study applies DFC to an actual GSM network with realistic measurements. Experimental results show that DFC improves the positioning accuracy of base fingerprinting algorithms, including the Bayesian approach and a neural network model.

This study focuses on indoor localization in Wireless Local Area Networks (WLANs). We investigate the unequal contribution of each access point (AP) on location estimation. The main contribution is two parts. First, a novel mechanism is proposed to measure the degrees of the AP importance. The importance of each AP is quantified by the signal discrimination between distinct locations. We utilize such numerical relevancies to select important APs for positioning. Second, the importance is further embedded into our positioning system. We provide a weighted kernel function where the effect of APs is differentiated. That is, the larger weights are assigned to the more important APs. Moreover, we develop a quasi-entropy function to avoid an abrupt change on the weights. Our positioning system is developed in a real-worldWLAN environment, where the realistic measurement of receive signal strength (RSS) is collected. Experimental results show that the positioning accuracy is significantly improved by taking the different importance into consideration.

This paper presents a novel approach to placing access points (APs) in wireless local area networks (WLAN). Unlike the traditional methods focusing on coverage maximization, we investigate how to place APs from the perspective of an indoor location system. We present a framework for linking the placement of APs and the positioning performance. Our algorithm, namely maximizing SNR (signal-to-noise ratio), aims at choosing a proper set of APs' locations so that the signal is maximized and the noise is minimized simultaneously. The proposed algorithm regards the location discriminant information as the signal and the degree of unstable measurements as the noise. Such numerical values provide a good theoretical formulation to measure the influence of the AP deployment. In our location system, we utilize such SNR ratio to deploy APs so as to reduce the positioning errors. Our location system is developed in a real-world WLAN environment, where the realistic measurements were collected. The experimental results show that the positioning accuracy is improved based on our deployment approach in different scenarios.

This study focuses on the localization using Received Signal Strength (RSS) in dense multipath indoor environments. A dynamic system approach is proposed in the fingerprinting module, where the location is estimated from the state instead from RSS directly. The state is reconstructed from a temporal sequence of RSS samples by incorporating a proper memory structure based on Taken's embedded theory. Then, a more accurate state-location correlation is estimated because the impact of the temporal variation due to multipath is considered. An indoor experiment in Wireless Local Area Networks (WLAN) shows the effectiveness of our approach.

Recent advances in mobile devices and ubiquity of wireless infrastructures create the opportunity to utilize heterogeneous wireless networks (HWNs) for localization. To efficiently exploit the spatial correlation embedded in the measurements from HWNs, we proposed two algorithms via a cooperative approach, called Direct Multi-Radio Fusion and Cooperative Eigen- Radio Positioning. The former discovers the spatial correlation after the information of measurements is reorganized to minimize the redundancy. The latter takes a further step to incorporate the spatial discrimination to estimate the location. We have implemented our algorithms for different wireless technologies involving the cellular GSM, DVB, FM and WLAN in realistic outdoor/indoor environments. The results show that the proposed algorithm reduces 44.19-48.88% of the mean error, as compared to the conventional approaches.

We present a novel approach to the problem of the indoor localization in wireless environments. The main contribution of this paper is fourfold: 1) we show that by projecting the measured signal into a decorrelated signal space, the positioning accuracy is improved, since the cross correlation between each AP is reduced, 2) we demonstrate that this novel approach achieves a more efficient information compaction and provides a better scheme to reduce online computation (the drawback of AP selection techniques is overcome, since we reduce the dimensionality by combing features, and each component in the decorrelated space is the linear combination of all APs; therefore, a more efficient mechanism is provided to utilize information of all APs while reducing the computational complexity), 3) experimental results show that the size of training samples can be greatly reduced in the decorrelated space; that is, fewer human efforts are required for developing the system, and 4) we carry out comparisons between RSS and three classical decorrelated spaces, including Discrete Cosine Transform (DCT), Principal Component Analysis (PCA), and Independent Component Analysis (ICA) in this paper. Two AP selection criteria proposed in the literature, MaxMean and InfoGain are also compared. Testing on a realistic WLAN environment, we find that PCA achieves the best performance on the location fingerprinting task.

This brief paper presents a novel localization algorithm, named discriminant-adaptive neural network (DANN), which takes the received signal strength (RSS) from the access points (APs) as inputs to infer the client position in the wireless local area network (LAN) environment. We extract the useful information into discriminative components (DCs) for network learning. The nonlinear relationship between RSS and the position is then accurately constructed by incrementally inserting the DCs and recursively updating the weightings in the network until no further improvement is required. Our localization system is developed in a real-world wireless LAN WLAN environment, where the realistic RSS measurement is collected. We implement the traditional approaches on the same test bed, including weighted kappa-nearest neighbor (WKNN), maximum likelihood (ML), and multilayer perceptron (MLP), and compare the results. The experimental results indicate that the proposed algorithm is much higher in accuracy compared with other examined techniques. The improvement can be attributed to that only the useful information is efficiently extracted for positioning while the redundant information is regarded as noise and discarded. Finally, the analysis shows that our network intelligently accomplishes learning while the inserted DCs provide sufficient information.

Positioning in indoor wireless environments is growing rapidly in importance and gains commercial interests in context-awareness applications. The essential challenge in localization is the severe fluctuation of receive signal strength (RSS) for the mobile client even at a fixed location. This work explores the major noisy source resulted from the multipath in an indoor wireless environment and presents an advanced positioning architecture to reduce the disturbance. Our contribution is to propose a novel approach to extract the robust signal feature from measured RSS which is provided by IEEE 802.11 MAC software so that the multipath effect can be mitigated efficiently. The dynamic multipath behavior, which can be modeled by a convolution operation in the time domain, can be transformed into an additive random variable in the logarithmic spectrum domain. That is, the convolution process becomes a linear and separable operation in the logarithmic spectrum domain and then can be effectively removed. To our best knowledge, this work is the first to enhance the robustness to a multipath fading condition, which is common in the environments of an indoor wireless LAN (WLAN) location fingerprinting system. Our approach is conceptually simple and easy to be implemented for practical applications. Neither a new hardware nor an extra sensor network installation is required. Both analytical simulation and experiments in a real WLAN environment demonstrate the usefulness of our approach to significant performance improvements. The numerical results show that the mean and the standard deviation of estimated error are reduced by 42% and 29%, respectively, as compared to the traditional maximum likelihood based approach. Moreover, the experimental results also show that fewer training samples are required to build the positioning models. This result can be attributed to that the location related information is effectively extracted by our algorithm.