Search Results (409)

With the growing prevalence of large-scale intelligent surveillance camera systems, the burden on real-time video analytics pipelines has significantly increased due to continuous video transmission from numerous cameras. To mitigate this strain, recent approaches focus on filtering irrelevant video frames early in the pipeline, at the camera or edge device level. In this paper, we propose Wi-Filter, an innovative filtering method that leverages Wi-Fi signals from wireless edge devices, such as Wi-Fi-enabled cameras, to optimize filtering decisions dynamically. Wi-Filter utilizes channel state information (CSI) readily available from these wireless cameras to detect human motion within the field of view, adjusting the filtering threshold accordingly. The motion-sensing models in Wi-Filter (Wi-Fi assisted Filter) are trained using a self-supervised approach, where CSI data are automatically annotated via synchronized camera feeds. We demonstrate the effectiveness of Wi-Filter through real-world experiments and prototype implementation. Wi-Filter achieves motion detection accuracy exceeding 97.2% and reduces false positive rates by up to 60% while maintaining a high detection rate, even in challenging environments, showing its potential to enhance the efficiency of video analytics pipelines. Full article

The fusion of multiple sensor data to improve positioning accuracy and robustness is an important research direction in indoor positioning systems. In this paper, a Wi-Fi- and vision-based Fusion Adaptive Kalman Filter (FAKF) method is proposed for improving the accuracy of indoor positioning. To improve the accuracy of Wi-Fi positioning, a random forest algorithm with added region restriction is proposed. For visual positioning, YOLOv7 target detection and Deep SORT target tracking algorithms are combined in order to improve the stability of visual positioning. The fusion positioning method proposed in this study uses Kalman filtering for state estimation and updating by combining measurements from camera and Wi-Fi sensors, and it adaptively adjusts the parameters and weights of the filters by monitoring the residuals of the camera and Wi-Fi measurements in real time in order to optimize the accuracy and stability of the position estimation. In the experimental section, the real trajectory data and the predicted trajectory data generated using different positioning methods are compared. The experimental results show that the fused positioning method can significantly reduce positioning errors and the fused data can more accurately reflect the actual position of a target compared with single-sensor data. Full article

Indoor positioning systems have become increasingly important due to the rapid expansion of Internet of Things (IoT) technologies, especially for providing precise location-based services in complex environments such as multi-floor campus buildings. This paper presents a WiFi fingerprint indoor localization system based on AdaBoost, combined with a new access point (AP) filtering technique. The system comprises offline and online phases. During the offline phase, a fingerprint database is created using received signal strength (RSS) values for two four-floor campus buildings. In the online phase, the AdaBoost classifier is used to accurately estimate locations. To improve localization accuracy, APs that always appear in the measurement data are selected for applying the AdaBoost algorithm, aiming to eliminate noise from the fingerprint database. The performance of the proposed method is compared with other well-known machine learning-based positioning algorithms in terms of positioning accuracy and error distances. The results indicate that the average positioning accuracy of the proposed scheme reaches 95.55%, which represents an improvement of 5.55% to 16.21% over the other methods. Additionally, the two-dimensional positioning error can be reduced to 0.25 m. Full article

Wireless Fidelity (Wi-Fi) based positioning has gained popularity for accurate indoor robot positioning in indoor navigation. In daily life, it is a low-cost solution because Wi-Fi infrastructure is already installed in many indoor areas. In addition, unlike the Global Navigation Satellite System (GNSS), Wi-Fi is more suitable for use indoors because signal blocking, attenuation, and reflection restrictions create a unique pattern in places with many Wi-Fi transmitters, and more precise positioning can be performed than GNSS. This paper proposes a machine learning-based method for Wi-Fi-enabled robot positioning in indoor environments. The contributions of this research include comprehensive 3D position estimation, utilization of existing Wi-Fi infrastructure, and a carefully collected dataset for evaluation. The results indicate that the AdaBoost algorithm attains a notable level of accuracy, utilizing the dBm signal strengths from Wi-Fi access points distributed throughout a four-floor building. The mean average error (MAE) values obtained in three axes with the Adaptive Boosting algorithm are 0.044 on the x-axis, 0.063 on the y-axis, and 0.003 m on the z-axis, respectively. In this study, the importance of various Wi-Fi access points was examined with explainable artificial intelligence methods, and the positioning performances obtained by using data from a smaller number of access points were examined. As a result, even when positioning was conducted with only seven selected Wi-Fi access points, the MAE value was found to be 0.811 for the x-axis, 0.492 for the y-axis, and 0.134 for the Z-axis, respectively. Full article

This paper presents a unified performance metric for evaluating the chronological wild geese optimization (CWGO) algorithm in wireless sensor networks (WSNs). The metric combines key performance factors—energy consumption, delay, distance, and trust—into a single measure using Lagrange interpolation, providing a more comprehensive assessment of WSN algorithms. We evaluate CWGO against E-CERP, EECHIGWO, DUCISCA, and DE-SEP across static and dynamic sensor node configurations in various wireless technologies, including LoRa, Wi-Fi, Zigbee, and Bluetooth low energy (BLE). The results show that CWGO consistently outperforms the other algorithms, especially in larger node configurations, demonstrating its scalability and robustness in static and dynamic environments. Moreover, the unified metric reveals significant performance gaps with EECHIGWO, which underperforms all wireless technologies. DUCISCA and DE-SEP show moderate and fluctuating results, underscoring their limitations in larger networks. While E-CERP performs competitively, it generally lags behind CWGO. The unified metric offers a holistic view of algorithm performance, conveying clearer comparisons across multiple factors. This study emphasized the importance of a unified evaluation approach for WSN algorithms and positions CWGO as a superior solution for efficient cluster head selection and routing optimization in diverse WSN scenarios. While CWGO demonstrates superior performance in simulation, future research should validate these findings in real-world deployments, accounting for hardware limitations and in a highly dynamic environment. Further optimization of the unified metrics’ computational efficiency could enhance its real-time applicability in larger, energy-resource-constrained WSNs. Full article

Background: Indoor Positioning Systems (IPS) have gained increasing relevance in logistics, offering solutions for safety enhancement, intralogistics management, and material flow control across various environments such as industrial facilities, offices, hospitals, and supermarkets. This study aims to evaluate IPS technologies’ performance and applicability to guide practitioners in selecting systems suited to specific contexts. Methods: The study systematically reviews key IPS technologies, positioning methods, data types, filtering methods, and hybrid technologies, alongside real-world examples of IPS applications in various testing environments. Results: Our findings reveal that radio-based technologies, such as Radio Frequency Identification (RFID), Ultra-wideband (UWB), Wi-Fi, and Bluetooth (BLE), are the most commonly used, with UWB offering the highest accuracy in industrial settings. Geometric methods, particularly multilateration, proved to be the most effective for positioning and are supported by advanced filtering techniques like the Extended Kalman Filter and machine learning models such as Convolutional Neural Networks. Overall, hybrid approaches that integrate multiple technologies demonstrated enhanced accuracy and reliability, effectively mitigating environmental interferences and signal attenuation. Conclusions: The study provides valuable insights for logistics practitioners, emphasizing the importance of selecting IPS technologies suited to specific operational contexts, where precision and reliability are critical to operational success. Full article

High-precision indoor positioning is essential for various applications, such as the Internet of Things, robotics, and smart manufacturing, requiring accuracy better than 1 m. Conventional indoor positioning methods, like Wi-Fi or Bluetooth fingerprinting, typically provide low accuracy within a range of several meters, while techniques such as laser or visual odometry often require fusion with absolute positioning methods. Ultra-wideband (UWB) and Wi-Fi Round-Trip Time (RTT) are emerging radio positioning technologies supported by industry leaders like Apple and Google, respectively, both capable of achieving high-precision indoor positioning. This paper offers a comprehensive survey of UWB and Wi-Fi positioning, beginning with an overview of UWB and Wi-Fi RTT ranging, followed by an explanation of the fundamental principles of UWB and Wi-Fi RTT-based geometric positioning. Additionally, it compares the strengths and limitations of UWB and Wi-Fi RTT technologies and reviews advanced studies that address practical challenges in UWB and Wi-Fi RTT positioning, such as accuracy, reliability, continuity, and base station coordinate calibration issues. These challenges are primarily addressed through a multi-sensor fusion approach that integrates relative and absolute positioning. Finally, this paper highlights future directions for the development of UWB- and Wi-Fi RTT-based indoor positioning technologies. Full article

Indoor positioning based on Wi-Fi signals has gained a lot of attention lately. There are many advantages related to the use of Wi-Fi signals for positioning, including the availability of Wi-Fi access points in indoor environments and the integration of Wi-Fi transceivers into consumer devices. However, since Wi-Fi uses an unlicensed spectrum, anyone can create their own access points. Therefore, it is possible to affect the function of the localization system by spoofing signals from access points and thus alter positioning accuracy. Previously published works focused mainly on the evaluation of spoofing on localization systems and the detection of anomalies when updating the radio map. Spoofing mitigation solutions were proposed; however, their application to systems that use off-the-shelf items is not straightforward. In this paper filtering algorithms are proposed to minimize the impact of access point spoofing. The filtering was applied with a combination of the widely used K-Nearest Neighbours (KNN) localization algorithm and their performance is evaluated using the UJIIndoorLoc dataset. During the evaluation, the spoofing of Access Points was performed in two different scenarios and the number of spoofed access points ranged from 1 to 10. Based on the achieved results proposed SFKNN provided good detection of the spoofing and helped to reduce the mean localization error by 2–5 m, especially when the number of spoofed access points was higher. Full article

This study presents the analysis and comparison of Wi-Fi coverage modeling for a hotspot using deterministic and empirical propagation models developed by researchers from the Universidad de Las Américas in Quito, Ecuador. Signal intensity measurements were taken from both the hotspot and the repeater at various locations within the Checa parish using a Raspberry Pi and a Global Positioning System (GPS). To assess the accuracy of the models, heat maps were generated using Matlab (R2023A). The results showed that the adjusted model, comparing the received signal levels of the hotspot with the Stanford University Interim Propagation Model (SUI), exhibited a significant error margin, especially at distances below 60 m. However, starting at −70 dBm and beyond 60 m, the sampled data aligned better with the adjusted model. The discrepancy in the heatmaps was explained by the hotspot’s higher transmission power compared to the Wi-Fi repeater. Furthermore, the reception levels of the hotspot were low near the transmitter, which led to new measurements being taken with the Wi-Fi repeater (Raspberry Pi 3). With the new measurements, the adjusted model using logarithmic regression showed a better fit, particularly in the range from −40 dBm to −98 dBm, with a path loss exponent of 8.96. This demonstrated a significant improvement in prediction accuracy, particularly at short distances. The results emphasize the importance of using tools such as Matlab and reference models to optimize network planning, providing the Universidad de Las Américas with a valuable tool to generate heat maps in areas with characteristics similar to those of Checa in the context of their community outreach programs. This approach could be crucial for future research and optimization of community Wi-Fi networks in similar environments. Full article

The scope of this work is to propose a distributed RF sensing architecture that interconnects and utilizes a cyber security operations center (SOC) to support long-term RF threat monitoring, alerting, and further centralized processing. For the purpose of this work, RF threats refer mainly to RF jamming, since this can jeopardize multiple wireless systems, either directly as a Denial of Service (DoS) attack, or as a means to force a cellular or WiFi wireless client to connect to a malicious system. Furthermore, the possibility of the suggested architecture to monitor signals from malicious drones in short distances is also examined. The work proposes, develops, and examines the performance of RF sensing sensors that can monitor any frequency band within the range of 1 MHz to 8 GHz, through selective band pass RF filtering, and subsequently these sensors are connected to a remote SOC. The proposed sensors incorporate an automatic calibration and time-depended environment RF profiling algorithm and procedure for optimizing RF jamming detection in a dense RF spectrum, occupied by heterogeneous RF technologies, thus minimizing false-positive alerts. The overall architecture supports TCP/IP interconnections of multiple RF jamming detection sensors through an efficient MQTT protocol, allowing the collaborative operation of sensors that are distributed in different areas of interest, depending on the scenario of interest, offering holistic monitoring by the centralized SOC. The incorporation of the centralized SOC in the overall architecture allows also the centralized application of machine learning algorithms on all the received data. Full article

“Smart” devices, such as contemporary smartphones and PDAs (Personal Digital Assistance), play a significant role in our daily live, be it for navigation or location-based services (LBSs). In this paper, the use of Ultra-Wide Band (UWB) and Wireless Fidelity (Wi-Fi) based on RTT (Round-Trip Time) measurements is investigated for pedestrian user localization. For this purpose, several scenarios are designed either using real observation or simulated data. In addition, the localization of user groups within a neighborhood based on collaborative navigation (CP) is investigated and analyzed. An analysis of the performance of these techniques for ranging the positioning estimation using different fusion algorithms is assessed. The methodology applied for CP leverages the hybrid nature of the range measurements obtained by UWB and Wi-Fi RTT systems. The proposed approach stands out due to its originality in two main aspects: (1) it focuses on developing and evaluating suitable models for correcting range errors in RF-based TWR (Two-Way Ranging) technologies, and (2) it emphasizes the development of a robust CP engine for groups of pedestrians. The results obtained demonstrate that a performance improvement with respect to position trueness for UWB and Wi-Fi RTT cases of the order of 74% and 54%, respectively, is achieved due to the integration of these techniques. The proposed localization algorithm based on a P2I/P2P (Peer-to-Infrastructure/Peer-to-Peer) configuration provides a potential improvement in position trueness up to 10% for continuous anchor availability, i.e., UWB known nodes or Wi-Fi access points (APs). Its full potential is evident for short-duration events of complete anchor loss (P2P-only), where an improvement of up to 53% in position trueness is achieved. Overall, the performance metrics estimated based on the extensive evaluation campaigns demonstrate the effectiveness of the proposed methodologies. Full article

Weighted k-nearest neighbor (WKNN)-based Wi-Fi fingerprinting is popular in indoor location-based services due to its ease of implementation and low computational cost. KNN-based methods rely on distance metrics to select the nearest neighbors. However, traditional metrics often fail to capture the complexity of indoor environments and have limitations in identifying non-linear relationships. To address these issues, we propose a novel WKNN-based Wi-Fi fingerprinting method that incorporates distance metric learning. In the offline phase, our method utilizes a Siamese network with a triplet loss function to learn a meaningful distance metric from training fingerprints (FPs). This process employs a unique triplet mining strategy to handle the inherent noise in FPs. Subsequently, in the online phase, the learned metric is used to calculate the embedding distance, followed by a signal-space distance filtering step to optimally select neighbors and estimate the user’s location. The filtering step mitigates issues from an overfitted distance metric influenced by hard triplets, which could lead to incorrect neighbor selection. We evaluate the proposed method on three benchmark datasets, UJIIndoorLoc, Tampere, and UTSIndoorLoc, and compare it with four WKNN models. The results show a mean positioning error reduction of 3.55% on UJIIndoorLoc, 16.21% on Tampere, and 16.49% on UTSIndoorLoc, demonstrating enhanced positioning accuracy. Full article

This study addresses the challenges of human–robot interactions in real-time environments with adaptive field-programmable gate array (FPGA)-based accelerators. Predicting human posture in indoor environments in confined areas is a significant challenge for service robots. The proposed approach works on two levels: the estimation of human location and the robot’s intention to serve based on the human’s location at static and adaptive positions. This paper presents three methodologies to address these challenges: binary classification to analyze static and adaptive postures for human localization in indoor environments using the sensor fusion method, adaptive Simultaneous Localization and Mapping (SLAM) for the robot to deliver the task, and human–robot implicit communication. VLSI hardware schemes are developed for the proposed method. Initially, the control unit processes real-time sensor data through PIR sensors and multiple ultrasonic sensors to analyze the human posture. Subsequently, static and adaptive human posture data are communicated to the robot via Wi-Fi. Finally, the robot performs services for humans using an adaptive SLAM-based triangulation navigation method. The experimental validation was conducted in a hospital environment. The proposed algorithms were coded in Verilog HDL, simulated, and synthesized using VIVADO 2017.3. A Zed-board-based FPGA Xilinx board was used for experimental validation. Full article

Smartphone-based location estimation technology is becoming increasingly important across various fields. Accurate location estimation plays a critical role in life-saving efforts during emergency rescue situations, where rapid response is essential. Traditional methods such as GPS often face limitations in indoors or in densely built environments, where signals may be obstructed or reflected, leading to inaccuracies. Similarly, fingerprinting-based methods rely heavily on existing infrastructure and exhibit signal variability, making them less reliable in dynamic, real-world conditions. In this study, we analyzed the strengths and weaknesses of different types of wireless signal data and proposed a new deep learning-based method for location estimation that comprehensively integrates these data sources. The core of our research is the introduction of a ‘matching-map image’ conversion technique that efficiently integrates LTE, WiFi, and BLE signals. These generated matching-map images were applied to a deep learning model, enabling highly accurate and stable location estimates even in challenging emergency rescue situations. In real-world experiments, our method, utilizing multi-source data, achieved a positioning success rate of 85.27%, which meets the US FCC’s E911 standards for location accuracy and reliability across various conditions and environments. This makes the proposed approach particularly well-suited for emergency applications, where both accuracy and speed are critical. Full article

The IEEE 802.11bf-based wireless fidelity (WiFi) indoor positioning system has gained significant attention recently. It is important to recognize that multi-user online positioning occurs in real wireless environments. This paper proposes an indoor positioning sensing strategy that includes an optimized preprocessing process and a new machine learning (ML) method called NKCK. The NKCK method can be broken down into three components: neighborhood component analysis (NCA) for dimensionality reduction, K-means clustering, and K-nearest neighbor (KNN) classification with cross-validation (CV). The KNN algorithm is particularly suitable for our dataset since it effectively classifies data based on proximity, relying on the spatial relationships between points. Experimental results indicate that the NKCK method outperforms traditional methods, achieving reductions in error rates of $82.4\%$ compared to naive Bayes (NB), $85.0\%$ compared to random forest (RF), $72.1\%$ compared to support vector machine (SVM), $64.7\%$ compared to multilayer perceptron (MLP), $50.0\%$ compared to density-based spatial clustering of applications with noise (DBSCAN)-based methods, $42.0\%$ compared to linear discriminant analysis (LDA)-based channel state information (CSI) amplitude fingerprinting, and $33.0\%$ compared to principal component analysis (PCA)-based approaches. Due to the sensitivity of CSI, our multi-user online positioning system faces challenges in detecting dynamic human activities, such as human tracking, which requires further investigation in the future. Full article