Smartphone-Based Unconstrained Step Detection Fusing a Variable Sliding Window and an Adaptive Threshold

At present, indoor location-based service has become a hot topic. The traditional approaches that rely on professional equipment and expertise to collect indoor maps has limited the rapid development of indoor location-based services. Adopting low-cost crowdsourcing methods to construct and maintain indoor maps with various sensors integrated in smart phones by common users is a development trend of constructing indoor map. The existing crowdsourcing-based indoor topology construction methods mostly use the pedometer based PDR (Pedestrian Dead Reckoning) to infer user trajectories, which suffers from the problem of accumulated estimation errors. To reduce the error of pedestrian dead reckoning and improve the accuracy of the indoor topology construction, we propose a novel indoor topology construction algorithm based on the user closed trajectory fusion. The algorithm requires the user to start and end a trajectory loop at the same location when collecting data. Based on this trajectory loop, we can perform the forward and backward dead reckoning starting from the starting and the ending point of the path, respectively. For instance, after completing the forward path inference, we can swap the starting point with the ending point, and then perform the reverse path inference. Last, we aggregate the coordinates obtained from the forward and reverse path inferences with the different weight. The weight is defined to be proportional to the confidence of the PDR, i.e., inversely proportional to the walking time from the starting location of path inference. Compared to the traditional unidirectional trajectory inference method, our proposed algorithm can greatly reduce the accumulated error of dead reckoning by aggregating the bidirectional trajectory inference. To improve the accuracy of heading estimation of each step, we Ieverage a radial Gaussian function to filter the compass noise, and adopt the multi-strategy fusion mechanism based on the difference of direction estimation using the gyroscope and compass. The paper further introduces the external contour of the building to calibrate the direction of the indoor topological path, and improves the accuracy of the indoor topological path construction. The experimental results shows that our proposed crowdsourcing-based indoor topology construction algorithm using the bidirectional trajectory fusion scheme outperforms the traditional indoor topology construction algorithm that uses only the forward PDR and can obtain an average map accuracy of 0.40-meter.

Currently, pedestrian dead reckoning (PDR) is widely used in indoor positioning. Its principle is to recursively update the location of pedestrians by using the step count, step length and heading. To estimate the pedestrian heading, a common method in PDR is to utilize magnetometer measurements to estimate the heading of a smartphone. However, magnetometer is extremely vulnerable to magnetic interferences in indoor environments, resulting that magnetometer measurements are unreliable for heading estimation. Moreover, there is an offset angle between the device heading and the pedestrian heading, and the device heading may continuously change while the pedestrian heading keeps fixed. Therefore, the pedestrian heading cannot be simply replaced by the device heading. In this paper, we propose a step-wise method to accurately estimate the heading of a pedestrian who carries a smartphone at different positions. To be specific, the proposed method fuses the signals from the accelerometer, gyroscope and magnetometer of the smartphone to transform the device reference frame to the Earth reference frame, and then utilizes the horizontal angular velocities to establish an optimization problem, the analytical solution of which is obtained. Extensive simulations are carried out and confirm that the proposed method is more robust and more accurate than the existing algorithms.

Having recently become an important research topic, indoor tracking in a multi-floor building delivers comprehensive and efficient location-based services. In this paper, we present a deep learning (DL)-based indoor multi-floor tracking scheme, that is independent of infrastructure and only uses the smartphone as a terminal device to measure and analyze the user’s mobility information. Our method detects the floor transition according to changes in barometer readings. We compiled the time-series barometer data to train the DL model, and applied the data augmentation method to avoid overfitting and data imbalances during model training. Furthermore, we developed a floor decision algorithm to process the DL model’s output and generate the floor detection result. In the proposed scheme, the smartphone’s inertial measurement unit sensors are used to measure the user’s mobility information, and pedestrian dead reckoning (PDR) is exploited to update the user’s 2D location. We implemented the multi-floor tracking by combining the floor detection algorithm with PDR. To avoid the accumulated error problem that commonly arises in the infrastructure-free approach, the calibration nodes (CN) were configured in the floor plan to correct the estimated location by matching the possible CNs during the floor transition. We conducted several experiments in multi-floor buildings to evaluate our scheme’s performance, and found that our floor detection method achieves a 99.6% average floor number accuracy, with all floor transition types (i.e., stairs, elevator) being successfully recognized. Furthermore, we compared localization performance with the conventional methods to validate the effectiveness of our approach.

In recent years pedestrian dead reckoning (PDR) has been a popular indoor localization technique that takes advantage of inertial navigation sensors (INS) of smartphones due to its availability. Despite the convenience of INS, noise has been a recurring problem in PDR which encourages many researches on noise filtering. This paper proposes a model that utilizes empirical mode decomposition (EMD) as the noise filter. EMD is an unconventional filter being applied in PDR to remove noise by processing the raw signal before implementing step counts, step lengths and heading estimation. The experiment made using the proposed model was able to perform the standard PDR technique without overlaps in heading estimation.

This paper presents a hybrid pedestrian navigation algorithm based on investigation of different combinations of pedestrian dead-reckoning (PDR), WiFi fingerprinting, and magnetic matching (MM). A multilevel quality-control mechanism is developed based on the interaction between different techniques. The algorithms were evaluated by walking in two indoor environments, with two smartphones, and under four motion conditions (i.e., handheld, at an ear, dangling with hand, and in a pants pocket). It was found that 2D accuracy of WiFi fingerprinting and MM is related with received signal strength and magnetic distribution, respectively. MM results had small errors on some occasions but suffered from significant mismatches. WiFi-aided MM provided better results than either WiFi or MM, but still had a risk of mismatching. Furthermore, integration of PDR, WiFi, and MM reduced dependency on both navigation environment and motion condition. The proposed algorithm provided more reliable solutions than both PDR/WiFi and PDR/MM, especially in areas with poor WiFi signal distribution or indistinctive magnetic features.

Diabetic retinopathy (DR) is the retinal disease caused by diabetes that involves damage to the small blood vessels in the posterior of the eye. Early stage of DR may not cause symptoms. But the progression of the disease leads to the proliferative stage. This causes leakage of protein and blood in the retina. Blood vessel segmentation is a helpful tool in the treatment of diabetic retinopathy. Many studies have been carried out in the last decade in order to derive an accurate blood vessel detection and segmentation in retinal images because vascular anomalies are one of the strongest signs of DR. An user friendly graphical user interface (GUI) which is MATLAB based that segments the blood vessels by means of adaptive median thresholding is proposed in this paper. From the segmented image, various features of blood vessels like area, mean, standard deviation, energy, entropy and histogram are calculated, in order to distinguish the image as normal or abnormal. With respect to the ground truth, performance measures like accuracy, specificity and sensitivity are calculated. The GUI is implemented using MATLAB and the feature parameters are calculated. The average accuracy, specificity and sensitivity were found to be 0.95, 0.99 and 0.77 respectively for drive images using Adaptive median thresholding.

Eliminating tissue-fold artifacts in histopathological whole-slide images for improved image-based prediction of cancer grade

This paper presents the design and implementation of mmRipple, which empowers commodity mmWave radars with the communication capability through smartphone vibrations. In mmRipple, a smartphone (transmitter) sends messages by modulating smartphone vibrations, while a mmWave radar (receiver) receives the messages by detecting and decoding the smartphone vibrations with mmWave signals. By doing so, a smartphone user can not only be passively sensed by a mmWave radar, but also actively send messages to the radar using her smartphone without any hardware modifications to either the smartphone or the mmWave radar. mmRipple addresses a series of unique technical challenges, including vibration signal generation, tiny vibration sensing, multiple object separation, and movement interference mitigation. We implement and evaluate mmRipple using commodity mmWave radars and smartphones in different practical conditions. Experimental results show that mmRipple achieves an average vibration pattern recognition accuracy of 98.60% within a 2m communication range, and 97.74% within 3m on 11 different types of smartphones. The communication range can be further extended up to 5m with an accuracy of 91.67% with line-of-sight path. To our best knowledge, mmRipple is the first work that allows smartphones to send data to COTS mmWave radars via smartphone vibrations and will enable many new applications such as vibration-based near field communication and pedestrian-to-sensing-infrastructure communication.

ABSTRACTThe objective of our venture is to actualize a lane detection framework considering expanding the usability of driver assistance system functions, attempting to overcome the problems of the generalized method. It is tuned to detect mountainous roads on the Indian hilly terrain. The proposed technique acquires a video sequence as input and performs operation on each frame to extract the candidate lane lines. The novelty of this work is that a unique method is used to decide upon whether the lane is on the straight or curved roads and adaptive thresholding is used as it can adjust its value for various environmental conditions. Kalman filter is used in the lane tracking stage where the feasible results obtained for the present frame are compared with the results in the previous video frames. Comparison of the presented algorithm with the conventional method is carried out and attained an average detection accuracy of 93%.

Motion trajectory tracing in indoor environment has become increasingly important, has the potential to support a broad array of applications including elder care, business analysis, pedestrian navigation. Traditional approaches involve wearable sensors, specialized hardware installations. This paper presents SmartMTra, an infrastructure-free, inertial sensor based motion trajectory tracing system in indoor environment through the use of smartphone. SmartMTra exploits various scenarios in daily activity. It figures out common feature states both in pedestrian's motion mode, smartphone carrying pattern, which can be uniquely identified by adapting domain-divided statistics model techniques. Pedestrian Dead Reckoning (PDR) is applied to trace the pedestrian's real-time motion trajectory with the detected step counts, step-length, heading information. Our experimental evaluation in a campus building demonstrates that errors during 150m travelled distance were 5.2m horizontally, 0.2m during up-down stairs with robustness to scenarios.

Pedestrian dead reckoning (PDR) uses built-in sensors in smartphones to track user positions, offering both versatility and portability. However, diversities among individuals and their behavior patterns decrease positioning accuracy. In this study, a two-stage personalized pedestrian dead reckoning based on neural networks (P2Net) is proposed. The first stage employs a human activity and smartphone location recognition (HSR) module, integrating a convolutional neural network with focal loss (FLCNN) to recognize nine modes, which constrains the subsequent optimized PDR procedure. In the second stage, a hybrid feature temporal attention network (HFTAN) is constructed to achieve generalized step length estimation across individual diversities. Temporal features via temporal convolutional network (TCN) and physical features are combined to generate hybrid features with time-series modeling capability and interpretability, which are then fed into a bi-directional long short-term memory (BiLSTM) model with a feature attention mechanism to estimate pedestrian step length. Experimental results demonstrate that P2Net achieves a class average accuracy of 92.75% for nine modes, and the total traveled distance error (TTDE) under various states is within 10%, outperforming other mentioned positioning methods.

Abstract. In this work, a new method is developed for the automatic and accurate detection and labelling of signalized, un-coded circular targets for the purpose of automated camera calibration in a test field. The only requirements of this method are the approximate height of the camera, an approximate range of orientations of the camera, and the object-space coordinates of the targets. In each image, circular targets are detected using adaptive thresholding and robust ellipse fitting. Labelling of those targets is performed next. First, the exterior orientation parameters of the image are estimated using a one-point pose-estimation approach, where a list of possible orientation and target labels are used, along with height, to calculate the camera position. The estimated position and orientation of the camera combined with the interior orientation parameters (IOPs) are then used to back-project the known object-space coordinates of the targets into the image space. These targets are then matched against the targets detected in the image, and the list entry with the best fit is chosen as the solution. This resolves both the detection and labelling of the targets, without the need for any coded targets or their associated software packages, and each image is solved independently allowing for parallel processing. This process accurately labels 92–97% of images, with average accuracy rates of 97% or better, and average completeness rates of 70–95% in imagery from the three cameras tested. The cameras were calibrated using observations from the detection and labelling process, which resulted in sub-pixel root mean square (RMS) values determined for the pixel space residuals.

This paper considers hybrid classification architectures for gender and ethnic classification of human faces and shows their feasibility using a collection of 3006 face images corresponding to 1009 subjects from the FERET database. The hybrid approach consists of an ensemble of RBF networks and inductive decision trees (DT). Experimental cross validation (CV) results yield an average accuracy rate of (a) 96% on the gender classification task and (b) 94% on the ethnic classification task. The benefits of our hybrid architecture include: (i) robustness via query by consensus provided by the ensembles of RBF networks, and (ii) flexible and adaptive thresholds as opposed to ad hoc and hard thresholds provided by using only DT.

Medical image processing has become an integral part of disease diagnosis, where technological advancements have brought significant changes to this approach. In this review, a comprehensive comparison between Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) in processing medical images is conducted. Automated medical analysis is becoming increasingly important due to issues of subjectivity in manual diagnosis and potential treatment delays. This research aims to compare the performance of Machine Learning (ML) in medical contexts using MRI, CT scan, and X-ray data. The comparison includes the accuracy rates of CNN and SVM algorithms, sourced from various studies conducted between 2018 and 2022. The results of the comparison show that CNN has higher average accuracy in processing MRI and X-ray data, with average values of 98.05% and 97.27%, respectively. On the other hand, SVM exhibits higher average accuracy for CT scan data, reaching 91.78%. However, overall, CNN achieves an average accuracy of 95.58%, while SVM's average accuracy is at 94.72%. These findings indicate that both algorithms perform well in processing medical data with high accuracy. Although based on these average accuracy rates, CNN demonstrates slightly better capabilities than SVM. Further research and development of more complex models are expected to continue improving the effectiveness of both approaches in disease diagnosis and patient care in the future.

Abstract. With the continuous improvement of the hardware level of the inertial measurement unit (IMU), indoor pedestrian dead reckoning (PDR) using an inertial device has been paid more and more attention. Typical PDR system position estimation is based on acceleration obtained from accelerometers to measure the step count, estimate step length and generate the position with the heading received from angular sensors (magnetometers and gyroscopes). Unfortunately, collected signals are very responsive to the alignment of sensor devices, built-in instrumental errors and distortions from the surrounding environment. In our work, a pedestrian positioning method using step detection based on a shoe-mounted inertial unit is arranged and put to the test, and the final results are analyzed. The extended Kalman filter (EKF) provides estimation of the errors which are acquired by the XSENS IMU sensor biases. The EKF is revised with acceleration and angular rate computations by the ZUPT (zero velocity update) and ZARU (zero angular rate update) algorithms. The step detection associated with these two solutions is the perfect choice to calculate the current position and distance walked and to estimate the IMU sensors' collected errors by using EKF. The test with a shoe-mounted IMU device was performed and analyzed in order to check the performance of the recommended method. The combined PDR final results were compared to GPS/Beidou postprocessing kinematic results (outdoor environment) and to a real route which was prepared and calculated for an indoor environment. After the comparison, the results show that the accuracy of the regular-speed walking under ZUPT and ZARU combination in the case of outdoor positioning did not go beyond 0.19 m (SD) and for indoor positioning accuracy did not exceed 0.22 m (SD). The authors are conscious that built-in drift errors coming from accelerometers and gyroscopes, as well as the final position obtained by XSENS IMU, are only stable for a short time period. Based on this consideration, our future work will be focused on supporting the methods presented with radio technologies (WiFi) or image-based solutions to correct all IMU imperfections.