Early diagnosis of chronic diseases represents one of the most significant challenges and opportunities in modern healthcare, with profound implications for improving patient outcomes and alleviating the substantial financial burdens placed on healthcare systems globally. An emerging technological paradigm that promises to address this challenge involves the development of “smart” biosensors. These biosensors are sophisticated analytical devices that integrate advanced machine learning algorithms, particularly artificial neural networks (ANNs), directly with sensing hardware to process complex, multivariate electrochemical and chemiresistive data in real-time. This review critically evaluates ANN-based biosensing systems for chronic disease management, conducting a comprehensive comparison of model architectures across various diagnostic and predictive applications and also highlighting persistent research gaps. While ANNs offer formidable pattern recognition capabilities, their practical performance and clinical utility remain fundamentally constrained by a series of challenges related to data availability, quality, security, and the inherent complexities of biological systems. Our analysis reveals that while substantial progress has been made, particularly in diabetes management and cancer screening via breath analysis, critical hurdles persist in sensor stability, model generalizability, and system integration. Ultimately, this review provides not merely a catalogue of technologies but a comprehensive, critical analysis aimed at equipping researchers with the insights needed to overcome the interdisciplinary barriers to achieving reliable, accessible, and early diagnosis of chronic diseases through next-generation intelligent biosensing platforms. We argue that the path forward requires a concerted focus on generating robust clinical validation data, developing interpretable and trustworthy models, and creating standardized frameworks for system evaluation and deployment.

High-resolution automotive radars, which are widely used nowadays, yield multiple measurements per frame from a single target. Clustering these measurements accurately and finding the tight bounding boxes are two challenging problems. In this work, the shape is estimated using a rectangular bounding box using the position and range rate measurements from the radar. While the Doppler (or range rate) measurements provide extra information about the target velocity, the presence of micro-Doppler (for example, returns from tires of a car) can significantly degrade the clustering, bounding box and heading estimates. It is necessary to cluster the measurements corresponding to different targets, as well as those that occur due to micro-Doppler. A clustering method is developed that can effectively use the Doppler information to differentiate closely spaced targets while avoiding the drawbacks of microDoppler. The bounding box estimate is refined by using only the measurements corresponding to the target bulk and, in turn, further aids in clustering iteratively. The effectiveness of the proposed approach is verified using simulations for different scenarios.

Autonomous vehicle technology is rapidly becoming the driving force in the automobile industry. As such, the interest in high-resolution radio detection and ranging (radar) for autonomous vehicle applications is increasing due to its affordability and high angular resolution. However, for Advanced Driver Assistance Systems (ADAS), the challenge of azimuth ambiguity caused by a large physical distance between radar antennas is prevalent. This causes false measurements in a direction different from the target’s true angle due to grating lobes. This challenge increases when extended targets are considered. This paper proposes a Pseudo-3D Assignment (P3DA) method based on a Pseudo Measurement Set (PMS) to resolve azimuth ambiguity in multiple extended target tracking. The proposed method can resolve mono (single) and split (duplicated) azimuth ambiguities common in extended target tracking. The proposed solution uses Lagrangian Relaxation based on a Flexible Search (LR-FS) algorithm to solve the P3DA-PMS problem efficiently. The performance of the proposed algorithm in a typical traffic scenario simulated in Unreal Engine 4, with an ego vehicle mounted with both 2D (unambiguous) and 3D (ambiguous) radars, is evaluated. Simulation and experiment results suggest that the proposed P3DA-PMS-based tracking algorithm can perform better than conventional methods.

This paper analyses the track-level detection of ghost tracks in multitarget tracking with a known reflection surface. In a real-world target tracking problem, the number of targets in surveillance is unknown to the platform. Thus, the tracker will be inadequate to distinguish the direct target return from the multipath return during the track initialization. Therefore, ghost tracks can be created with multipath measurements when they are considered direct path measurements. Even though the possible multipath measurement could be predicted for the existing tracks at a given instance, it is hard to decide whether the detected track is a multipath or a new target. Thus, a sequence of time instances needs to be considered to determine the track status. In this work, we propose a classification model to classify a track as either a multipath or direct path using an LSTM network with sequential data. Additionally, the performance of the proposed approach is compared with four other algorithms using a simulation-based dataset.

In the literature, the problem of point target tracking with multipath detections has been studied. However, the case of extended target tracking in a multipath environment (e.g., tracking a submarine using a high resolution sonar, tracking a vehicle in an urban environment using an imaging radar) has not been adequately addressed. If the multipath detections from a single target can be modeled and used properly, better tracking performance can be obtained in terms of accuracy, false tracks and computing time. By integrating the Random Matrix (RM) theory and the random finite set (RFS) theory, an extension of the Probability Hypothesis Density (PHD) filter, called MP-ET-PHD, is proposed in this paper to address the multitarget tracking problem with an unknown number of targets in an uncertain multipath environment with clutter. In the proposed framework, a novel multipath measurement update equation is formulated and derived. Also, a Gaussian Mixture (GM) implementation of the proposed MP-ET-PHD is presented for practical applications. Simulation results show that the proposed MP-ET-PHD can effectively handle multipath detections and yield improved tracking performance over the traditional single-path extended target trackers.

To address the problem of extended target tracking (ETT) with measurement-origin uncertainty in a multipath environment with terrain-constrained motion model, a new generalized version of the standard probabilistic data association (PDA) filter, called MP-ET-PDA, based on random matrices (RM) is proposed in this paper. In the MP-ET-PDA filter, we assume that multipath detections and clutter are possible in the extended target tracking problem, which are prevalent in practical systems but barely addressed in the literature. Further, a clustering-aided MP-ET-PDA algorithm with a reduced computational complexity that makes use of the Variational Bayesian (VB) technique, called MP-ET-PDA-VB, is presented to provide near real-time processing capability in ETT problems with an uncertain multipath environment. In addition to using a constant velocity motion model, a new terrain-constrained motion model is presented for scenarios where terrain-following is required by motion-constrained autonomous vehicles. The posterior Cramér-Rao lower bound (PCRLB), which quantifies the best possible accuracy in realistic ETT problems with multipath detections and measurement-origin uncertainty, is derived as the benchmark for performance evaluation. Simulations results demonstrate the improved performance of the proposed algorithms.

A study was conducted to examine the operational use of multi-sensor data fusion for military airborne intelligence, surveillance and reconnaissance. Participants performed a simulated picture compilation task wherein they had to identify all ships and planes in their area of operation using various sensors. One group performed the task using only native sensor data. The second group had imperfect data fusion to help them resolve the kinematic information, but they still had to identify each contact. The results indicated that data fusion automation improved the identification of ships and planes over the native sensor group. However, over time, map clutter continually increased for the group with fusion automation, surpassing the clutter for the native sensor group. The results suggest that while multi-sensor data fusion has benefits for picture compilation, dealing with plot clutter from false and spurious tracks is a key concern. Interface suggestions are provided to mitigate the effects.

Detecting dynamic vehicles is of great significance in the field of autonomous vehicles. In the literature, a few vehicle detection methods are proposed to detect vehicles within 50 m from the Lidar, where the point clouds are relatively dense. It is a great challenge to detect vehicles that are far from the Lidar because of sparse point clouds. Fewer returned point clouds will result in a larger fitting randomness and lower detection rate. To tackle this issue, a dynamic vehicle detection method based on likelihood-field-based model combined with coherent point drift (CPD), which includes the steps of dynamic object detection and dynamic vehicle confirmation, is proposed in this paper. An adaptive threshold based on the distance and grid angular resolution is applied to detect the dynamic objects. The pose estimation based on CPD (PE-CPD) is proposed to estimate the vehicle pose. The scaling series algorithm coupled with a Bayesian filter that is improved by PE-CPD is utilized for updating the vehicle states. Finally, comparative experiments of vehicle detection based on KITTI data sets are conducted. The results show that the proposed method improves the detection rate, especially the detection in the radius of 40-80 m, which is termed as distant area, compared with the method based on pose estimation with modified scaling series.

In this paper, the multi-vehicle tracking problem is revisited, with greater consideration being given to the interactions between vehicles. Traditionally, algorithms for tracking multiple vehicles in the multi-lane case assume that vehicles move independently of one another and that longitudinal and lateral vehicle dynamics are mutually independent. However, due to traffic volume, limited lane resources, and traffic heterogeneity, vehicles have to interact with neighboring vehicles for the purposes of maintaining a safe distance from the leading vehicle or improving their navigability by passing slower vehicles. To address the limitations in the literature, this paper proposes a novel multi-vehicle tracking algorithm that integrates the microscopic traffic models (MTM) for modeling interaction behaviors among vehicles in a 2-D road coordinate system. Due to the dependence between the longitudinal and later motions, their corresponding estimates are updated sequentially in a recursive manner. An adaptive deferred decision logic is proposed to improve the accuracy of lateral state estimates and thus improve overall performance. Simulation results show that the proposed MTM-based tracking algorithm can achieve better performance than a conventional multi-lane vehicle tracking algorithm with extension to multi-vehicle tracking, which does not consider interactions among vehicles but updates the longitudinal and lateral motion estimates independently.

In the last five years, the state-of-the-art in computer vision has improved greatly thanks to an increased use of deep convolutional neural networks (CNNs), advances in graphical processing unit (GPU) acceleration and the availability of large labelled datasets such as ImageNet. Obtaining datasets as comprehensively labelled as ImageNet for ship classification remains a challenge. As a result, we experiment with pre-trained CNNs based on the Inception and ResNet architectures to perform ship classification. Instead of training a CNN using random parameter initialization, we use transfer learning. We fine-tune pre-trained CNNs to perform maritime vessel image classification on a limited ship image dataset. We achieve a significant improvement in classification accuracy compared to the previous state-of-the-art results for the Maritime Vessel (Marvel) dataset.

Multi-vehicle tracking is crucial in many applications, such as traffic surveillance, intelligent transportation systems, and advanced driver assistance systems. Most conventional multi-target tracking algorithms are not ideal for multi-vehicle tracking, since they assume that the targets move independently of one another. However, due to traffic volume and limited lane resources, vehicles have to interact with their neighbors, resulting in highly dependent motions. To address this limitation, this paper proposes a novel multi-vehicle tracking algorithm for the single-lane case that considers motion dependence across vehicles by integrating the car-following model (CFM) into the tracking process with on-road constraints. A new CFM-based motion model that describes the dependent motion of vehicles in the single-lane case is proposed, and the notion of car-following clusters is defined. In order to exploit all available information in sensor measurements, the proposed algorithm updates the state estimates of car-following clusters by utilizing a stacked-update strategy. Furthermore, the variable structure interacting multiple model estimator is modified and integrated into the proposed algorithm to handle maneuvers that may violate the CFM. Simulation results demonstrate the superiority of the proposed multi-vehicle tracking algorithm over other state-of-the-art multi-vehicle tracking algorithms.

This paper considers the localization performance of MIMO radars with widely-separated antennas. A Multiple-Hypothesis (MH) based algorithm is proposed for multiple target localization problems where targets become unobservable in certain pairs of transmitters and receivers. In addition, the performance of MIMO radars in localizing multiple-scatterer targets is compared to that of multistatic radar systems. Finally, simulation results are provided in order to demonstrate the capability of MIMO radars in localizing multiple-scatterer targets.

In this paper we present a multisensor-multitarget tracking testbed for large-scale distributed scenarios. The objective is to develop a testbed capable of handling multiple, heterogeneous sensors in a hierarchical architecture for maritime surveillance. The testbed consists of a scenario generator that can generate simulated data from multiple sensors including radar, sonar, IR and ESM as well as a tracker framework into which different tracking algorithms can be integrated. In the current stage of the project, the IMM/Assignment tracker, and the Particle Filter (PF) tracker are implemented in a distributed architecture and some preliminary results are obtained. Other trackers like the Multiple Hypothesis Tracker (MHT) are also planned for the future.

Since inexpensive passive sensors have become available, it is possible to deploy a large number of them for tracking purposes in Anti-Submarine Warfare (ASW). However, modern submarines are quiet and difficult to track with passive sensors alone. Multistatic sensor networks, which have few transmitters (e.g., dipping sonars) in addition to passive receivers (e.g., sonobouys), have the potential to improve the tracking performance. The performance can be improved further by moving the transmitters according to existing target states and any possible new target states. Even though a large number of passive sensors are available, due to frequency, processing power and other physical limitations, only a few of them can be used at any one time. Then the problems are to decide the path of the transmitters and select a subset from the available passive sensors in order to optimize the tracking performance. In this paper, the Posterior Cramer-Rao Lower Bound (PCRLB), which gives a lower bound on estimation uncertainty, is used as the performance measure. An algorithm is presented to decide jointly the optimal path of the movable transmitters, by considering transmitters' operational constraints, and the optimal subset of passive sensors that should be used at each time steps for tracking multiple, possibly time-varying, number of targets. The effect of sensor location uncertainties, due to deployment error and possible sensor drifting, on the tracking performance is addressed in the sensor management algorithm. Simulation results illustrating the performance of the proposed algorithm are presented.

Passive Coherent Location (PCL), which uses commercial signals (e.g., FM broadcast, digital TV) as illuminators of opportunity, is an emerging technology in air defense systems. The advantages of PCL are low cost, low vulnerability to electronic counter measures, early detection of stealthy targets and low-altitude detection. However, limitations of PCL include lack of control over illuminators, limited observability and poor detection due to low Signal-to-Noise Ratio (SNR). This leads to high clutter with low probability of detection of target of interest. In this paper, multiple target tracking algorithms for PCL systems are analyzed to handle low probability of detection and high nonlinearity in the measurement model due to high measurement error. The converted measurement Kalman filter, unscented Kalman filter and particle filter based PHD filter are implemented and compared for PCL radar systems. The feasibility of using transmitters of opportunity for tracking airborne targets is shown on simulated and real data sets.

In this paper, the general problem of dynamic assignment of sensors to local fusion centers (LFCs) in a distributed tracking framework is considered. With technological advances, a large number of sensors can be deployed for multitarget tracking purposes. However, due to physical limitations such as frequency, power, bandwidth, and fusion center capacity, only a limited number of them can be used by each LFC. The transmission power of future sensors is anticipated to be software controllable within certain lower and upper limits. Thus, the frequency reusability and the sensor reachability can be improved by controlling transmission powers. Then, the problem is to select the sensor subsets that should be used by each LFC and to find their transmission frequencies and powers in order to maximize the tracking accuracies and minimize the total power consumption. The frequency channel limitation and the advantage of variable transmitting power have not been discussed in the literature. In this paper, the optimal formulation for the aforementioned sensor management problem is provided based on the posterior Cramer-Rao lower bound. Finding the optimal solution to the aforementioned NP-hard multiobjective mixed-integer optimization problem in real time is difficult in large-scale scenarios. An algorithm is presented to find a suboptimal solution in real time by decomposing the original problem into subproblems, which are easier to solve, without using simplistic clustering algorithms that are typically used. Simulation results illustrating the performance of sensor array manager are also presented.

In this paper, we are concerned with the problem of utilizing a large network of sensors in order to track multiple targets. Large-scale sensor array management has applications in a number of target tracking domains. For example, in ground target tracking, hundreds or even thousands of unattended ground sensors may be dropped over a large surveillance area. At any one time, it may then only be possible to utilize a very small number of the available sensors at the fusion center because of physical limitations, such as available communications bandwidth. A similar situation may arise in tracking sea-surface or underwater targets using a large network of sonobuoys. The general problem is then to select a small subset of the available sensors in order to optimize tracking performance. In a practical scenario with hundreds of sensors, the number of possible sensor combinations would make it infeasible to use enumeration in order to find the optimal solution. Motivated by this consideration, in this paper we use an efficient search technique in order to determine near-optimal sensor utilization strategies in real-time. This search technique consists of convex optimization followed by greedy local search. We consider several problem formulations and the posterior Cramer-Rao lower bound is used as the basis for network management. Simulation results illustrate the performance of the algorithms, both in terms of their real-time capability and the resulting estimation accuracy. Furthermore, in comparisons it can also be seen that the proposed solutions are near-optimal.