Myocardium segmentation is critical for remote diagnosis and intelligent monitoring of cardiac disease in e-Health systems. Existing deep-learning methods struggle with class imbalance, anatomical heterogeneity, and blurred boundaries in medical images. Standard cross-entropy loss weight all pixels equally and cannot adapt to rare but important regions. Focal loss tend to overly emphasize difficult-to-classify samples and lose edge information. A shape-aware adaptive weighted cross-entropy (AWCE) loss is introduced, which combines a global shape prior with per-pixel uncertainty to focus learning on rare in the dataset but critical regions for each samples. On the ACDC dataset, the proposed AWCE loss achieves stable training convergence, recovers thin-wall structures in qualitative evaluations, and outperforms both cross-entropy and focal loss on key metrics. This shape-guided loss promises to accelerate the adoption of AI-driven cardiac analysis in future digital health applications.

Accurate segmentation of the left ventricular myocardium in cardiac CT images is essential for diagnosing and treating cardiovascular diseases. This is considered particularly critical in clinical workflows enabled by the Internet of Medical Things (IoMT), where real-time remote monitoring and rapid analysis of cardiac function are fundamental to timely and effective intervention. Deep learning techniques have achieved significant progress in automatically outlining target objects with reduced human effort. However, most of the deep learning approaches focus on pixel-level loss minimization in model training, and fail to capture the global shape characteristics of anatomical structures, resulting in inconsistent segmentation. In this paper, we propose an end-to-end deep learning framework, which incorporates shape priors derived using kernel principal component analysis (KPCA) to address such limitation. A shape loss function is introduced to enforce anatomical shape consistency by integrating shape prior of myocardial structures during model training. Comprehensive experiments on both convolutional and transformer-based architectures demonstrate that the proposed method significantly enhances segmentation accuracy and anatomical fidelity, particularly in regions critical for diagnosis, such as mitral valve, interventricular septum and papillary muscles. Moreover, we show that integration of learnable Gaussian kernel parameters in KPCA enhances adaptability, outperforming that with fixed kernel parameters. We believe that the improved segmentation accuracy helps doctors make more precise assessments of the heart. This is especially useful in IoMT-based healthcare systems, where reliable segmentation supports quick diagnosis, remote monitoring, and smarter medical decisions, leading to better care and outcomes for patients with heart disease.

Coronary artery segmentation is critical for coronary artery disease diagnosis but challenging due to its tortuous course with numerous small branches and inter-subject variations. Most existing studies ignore important anatomical information and vascular topologies, leading to less desirable segmentation performance that usually cannot satisfy clinical demands. To deal with these challenges, in this paper we propose an anatomy- and topology-preserving two-stage framework for coronary artery segmentation. The proposed framework consists of an anatomical dependency encoding (ADE) module and a hierarchical topology learning (HTL) module for coarse-to-fine segmentation, respectively. Specifically, the ADE module segments four heart chambers and aorta, and thus five distance field maps are obtained to encode distance between chamber surfaces and coarsely segmented coronary artery. Meanwhile, ADE also performs coronary artery detection to crop region-of-interest and eliminate foreground-background imbalance. The follow-up HTL module performs fine segmentation by exploiting three hierarchical vascular topologies, i.e., key points, centerlines, and neighbor connectivity using a multi-task learning scheme. In addition, we adopt a bottom-up attention interaction (BAI) module to integrate the feature representations extracted across hierarchical topologies. Extensive experiments on public and in-house datasets show that the proposed framework achieves state-of-the-art performance for coronary artery segmentation.

Follicular thyroid carcinoma (FTC) is the second most common type of thyroid cancer and is highly aggressive, with a tendency to hematogenous metastasis. A definite diagnosis of FTC requires pathological examination after complete excision of the mass, and preoperative diagnosis of FTC is a challenge for both surgeons and imaging physicians. In this study, we aim to develop a multimodal deep learning model that combines grey scale ultrasound images, color doppler ultrasound images, and patient clinical data to predict the risk of FTC. This retrospective study include a dataset of 323 patients who underwent surgery. We develop and compare different models, including single modal, bimodal, and multi-modal models. The multimodal model performs the best, with an area under the curve (AUC) of 0.97. The results of the study demonstrate that the deep learning multimodal fusion method using grey scale ultrasound images, color doppler ultrasound images, and patient clinical data achieves better prediction performance.

Assessment of the left ventricle segmentation in cardiac magnetic resonance imaging (MRI) is of crucial importance for cardiac disease diagnosis. However, conventional manual segmentation is a tedious task that requires excessive human effort, which makes automated segmentation highly desirable in practice to facilitate the process of clinical diagnosis. The Internet of Medical Things (IoMT) and artificial intelligence (AI) for efficient medical data collection and analysis have been deemed effective approaches to remote and automatic diagnosis. In this article, we propose a novel reinforcement-learning-based framework for left ventricle contouring, which mimics how a cardiologist outlines the left ventricle in a cardiac image. Since such a contour drawing process is simply moving a paintbrush along a specific trajectory, it is thus analogized to a path finding problem. Following the algorithm of proximal policy optimization (PPO), we train a policy network, which makes a stochastic decision on the agent’s movement according to its local observation such that the generated trajectory matches the true contour of the left ventricle as much as possible. Moreover, we design a deep learning model with a customized loss function to generate the agent’s landing spot (or coordinate of its initial position on a cardiac image). We further propose an alternative approach for generating the landing spot based on interventricular septum detection, which is more efficient since no extra effort in data preprocessing and model training is involved. The experimental results show that the coordinates of the generated landing spots with both of the two approaches are sufficiently close to the true contour and the proposed reinforcement-learning-based approach outperforms the existing U-net model and its improved version, even with a limited training set.

Summary The ant colony labor division model can be used to solve the dynamic and variable traffic signal timing problem because of its adaptive and self‐adjusting characteristics. Based on the basic model, this paper proposes a new extended ant colony labor division model for traffic signal timing. This model is combined with the vehicle characteristics to modify the calculation method of environmental stimulus values. Using the vehicle delay in the unit period, the original fixed response threshold is modified to the dynamic response threshold, and the state transition equation is reconstructed. Based on the mixed traffic flow model of two‐phase single‐point intersection cellular automata, through comparative experiments and discussion and analysis, it is found that the extended ant colony labor division model can effectively improve road traffic capacity according to road conditions and reasonable traffic signal timing.

The extensive deployment of smart meters in millions of households provides a huge amount of individual electricity consumption data for demand side analysis at a fine granularity. Different from traditional aggregated system-level data, smart meter data is more irregular and unpredictable. As a result, probabilistic load forecasting (PLF), which can provide a better understanding of the uncertainty and volatility in future demand, is critical to constructing energy-efficient and reliable smart grids. In this article, a recently developed technique called Bayesian deep learning is employed to solve this challenging problem. In particular, a novel multitask PLF framework based on Bayesian deep learning is proposed to quantify the shared uncertainties across distinct customer groups while accounting for their differences. Further, a clustering-based pooling method is designed to increase the data diversity and volume for the framework. This not only addresses the problem of overfitting but also improves the predictive performance. Numerical results are presented which demonstrate that the proposed framework provides superior probabilistic forecasting accuracy over conventional methods.

Nonintrusive load monitoring (NILM) is a technique that infers appliance-level energy consumption patterns and operation state changes based on feeder power signals. With the availability of fine-grained electric load profiles, there has been increasing interest in using this approach for demand-side energy management in smart grids. NILM is a multilabel classification problem due to the simultaneous operation of multiple appliances. Recently, deep learning based techniques have been shown to be a promising approach to solving this problem, but annotating the huge volume of load profile data with multiple active appliances for learning is very challenging and impractical. In this article, a new semisupervised multilabel deep learning based framework is proposed to address this problem with the goal of mitigating the reliance on large labeled datasets. Specifically, a temporal convolutional neural network is used to automatically extract high-level load signatures for individual appliances. These signatures can be efficiently used to improve the feature representation capability of the framework. Case studies conducted on two open-access NILM datasets demonstrate the effectiveness and superiority of the proposed approach.

In this paper, we consider an energy harvesting cognitive radio (CR) system operating in slotted mode, where the secondary user (SU) has no wired power supplies and is powered exclusively by energy harvested from ambient environment. The SU can only perform either energy harvesting, spectrum sensing or data transmission at a time due to hardware limitation such that a timeslot is segmented into three non-overlapping fractions. Considering a generalized multi-slot spectrum sensing paradigm and two types of fusion rules: data fusion and decision fusion, we focus on the “harvesting-sensing-throughput” tradeoff and joint optimization for save-ratio, sensing duration, sensing threshold as well as fusion rule to maximize the SU's expected achievable throughput while keeping primary users (PUs) sufficiently protected. For data-fusion spectrum sensing, we translate the original problem into a convex one and show that the optimal solutions for sample number, mini-slot number as well as sensing threshold are non-unique. For decision-fusion spectrum sensing, we propose a two-level algorithm to solve the original problem with in-depth analysis on the convexity of a simplified problem and experiments show that the proposed algorithm is more efficient than differential evolution algorithm. We find that despite the inherent difference between the two types of fusion rules, the optimal data-fusion and decision-fusion strategies both converge to single-slot spectrum sensing while the SU's maximal expected achievable throughput is attained. Simulation results show that the optimal single-slot spectrum sensing strategy outperforms three other multi-slot strategies as well as two existing strategies while the empirical probability of detection is limited under a predefined level.

The energy limitation of wireless sensor networks can be solved by harvesting energy from environmental sources such as solar and wind to power the sensor nodes. We propose an energy-harvest-aware routing scheme that incorporates harvest availability properties and energy storage capacity limits into the routing decisions. In contrast to most existing energy-harvesting routing algorithms that route each traffic flow independently from each other, we consider multiple traffic flows, or commodities, and formulate the multi-commodity routing problem as linear optimization problem. The proposed scheme balances two routing objectives of maximum total and maximum minimum residual energy to prolong the network lifetime. The simulation results show that both higher total and higher minimum residual energies are achieved.

In this paper, we consider a cognitive radio (CR) system operating in slotted mode, where the secondary user (SU) has no wired power supplies and is powered exclusively through extracting energy from ambient environment. Due to hardware limitation, the SU can only perform either of energy harvesting, spectrum sensing or data transmission at the same time and we assume that a timeslot is partitioned into three non-overlapping fractions. Considering a generalized multi-slot spectrum sensing paradigm with data fusion rule, we focus on the "saving-sensing-throughput" tradeoff and joint optimization for save-ratio, sensing duration as well as sensing threshold to maximize the SU's expected achievable throughput while keeping primary users (PUs) sufficiently protected. By translating the original optimization problem into a convex one, we show that the optimal solutions for sample number, mini-slot number as well as sensing threshold are non-unique and single-slot spectrum sensing is more practically preferable. We also investigate the impact of system parameters to the optimal sensing strategy.

As a promising technology to address the issue of spectrum scarcity, cognitive radio (CR) has been receiving an increasing attention in recent years and existing works suggested that mobile service band could potentially present reuse opportunities for unlicensed access. In this sense, understanding mobile service's temporal and spatial dynamics can be of great help on spectrum management for mobile service band. In this paper, we perform in-depth theoretical analysis on the probability distribution of wireless signal strength received from mobile stations and propose a polylogarithm-like statistical model that characterizes mobile service usage's spatio-temporal dynamics (e.g., temporal and spatial density). To validate the proposed model, we perform empirical studies on the spectrum measurement data collected in an open area and fit the overall signal strength's probability density function (PDF) and cumulative distribution function (CDF) with the proposed model. The results indicate a significant fitting and testify the applicability of the proposed model to estimate the temporal and spatial density of mobile services in open areas.

Traditional battery-powered sensor networks suffer from the inevitable lifetime limit due to the finite capacity of batteries. Energy harvesting WSN systems can provide a sustainable solution, however, the energy harvest properties need to be incorporated into the network design. In this paper, we consider the incorporation of energy-harvesting hardware, such as Photovoltaic (PV) panels, into the sensor nodes to augment the initial energy supply and to prolong or potentially achieve unlimited lifetime. In addition to accounting for node residual battery levels and forecast energy harvest, we propose a route selection scheme that takes into account the predicted wastage due to overcharge of finite battery, which has not been previously considered. We show in the simulation results that higher total residual energy can be achieved by considering energy harvest wastage into the routing decisions.

With the rapid development of small cell, the interference problem in small cell enhancement network is urgent to be solved. This paper focuses on the interference coordination for co-channel deployed macrocell and small cell cluster where interferences exist in both cross-tier and intra- tier. Considering different priorities of macrocell and small cell, a semi-distributed strategy is proposed to optimize network performance. Frequency resource allocation scheme is investigated to get a target of interference limitation and throughput optimization for the network. Non-cooperative game Cournot model is employed for power adjustment in small cell cluster to increase cell-edge throughput by considering power limitation and the influence of macrocell. Simulation results show that the proposed strategy improves system performance in cell-edge throughput and coverage. Moreover, the strategy can also be applied to the scenario that macrocell and small cell have different priorities successfully.

In recent years, the excessive energy consumption in wireless communication systems has been increasingly critical, and environmental and financial considerations have motivated a trend in wireless communication technologies to resort to renewable energy sources. Energy harvesting is considered as a promising solution to alleviate such issues and has received extensive attentions. In this paper, we consider a cognitive radio system with one primary user (PU) and one secondary user (SU) and both of their transmitters operate in time-slotted mode. The SU, which harvests energy exclusively from ambient radio signal, follows a save-then-transmit protocol. In such a scenario, we investigate the SU's optimal cooperation strategy, namely, the optimal decision (to cooperate with the PU or not) and the optimal action (to spend how much time on energy harvesting and to allocate how much power for cooperative relay). We separately investigate the optimal action in non-cooperation and cooperation modes to maximize the SU's achievable throughout and derive the optimal closed-form solutions. Based on the analytical results of the optimal solutions, we propose the optimal cooperation protocol (OCP) to make the optimal decision, which simply involves a two-level test. Simulation results show that the proposed OCP outperforms the other two protocols (non-cooperation protocol and stochastic cooperation protocol) and the optimal underlay (OU) transmission mode.

In recent years, with the rapid growth in wireless communication applications, issues in energy consumption has been increasingly critical, especially in cognitive radio (CR) systems with the exclusive functionality of spectrum sensing. In this paper, we consider a self-powered cognitive radio system, in which the SU has no fixed power supplies (e.g. batteries) and is powered by an energy harvester which extracts energy from the ambient radio signal. It is assumed that the SU operates in a harvesting (also termed “saving”)-sensing-transmitting fashion, which partitions a timeslot into three non-overlapping fractions. Taking the tradeoff between the three operations into account, we focus on optimization for spectrum sensing strategy to maximize the SU's expected achievable throughput. We formulate the expected achievable throughput optimization as a mixe-dinteger non-linear programming (MINLP) problem and derive the optimal spectrum sensing strategy via a modified differential evolution (DE) algorithm. We also present in-depth numerical analysis on the optimal spectrum sensing strategy and the experimental results demonstrate the optimal sensing strategy outperforms the stochastic one in terms of statistical expectation.

In this paper, we consider a CR system operating in slotted mode, in which the SU has no fixed power supplies and extract energy only via wireless energy harvesting from ambient radio signal. It is assumed that the SU operates in a saving-sensing-transmitting (SST) fashion, which partitions a timeslot into non-overlapping fractions for the three operations. Considering the tradeoff between durations of saving, sensing and transmitting, we focus on the optimal structure for the three operations that maximizes the achievable throughput. By formulating the achievable throughput optimization as a mixed-integer non-linear programming (MINLP) problem, we derive the optimal SST structure via a modified differential evolution (DE) algorithm and perform in-depth numerical analysis. The simulation results demonstrate the performance gain of the optimal structure over non-optimal ones as well as affects of energy harvesting rate.

Energy harvesting is considered as a promising solution to efficiently prolong the lifetime of energy-constrained wireless networks. In particular, wireless energy harvesting, which scavenges energy from ambient radio signals, has recently received an increasing attention. In this paper, we consider a self-powered wireless system with one transmitter and one receiver, in which the transmitter has no fixed power supplies and extract energy only via wireless energy harvesting from ambient radio signals. It is assumed that the transmitter follows a save-then-transmit protocol, which specifies that a fraction (referred to as save-ratio) of time is devoted exclusively to energy harvesting while the remaining fraction is used for data transmission. We focus on the optimal save-ratio selection and achievable throughput maximization in two cases with regard to energy harvesting rate: the deterministic case, in which energy harvesting rate is known in advance, and the stochastic case, in which energy harvesting rate is unknown and only its statistical properties (e.g. probability distribution) are available. The optimal save-ratio for the two cases is theoretically derived as a function of energy harvesting rate (or its statistical properties). The experimental results characterize how the optimal save-ratio and the maximal achievable throughput vary with energy harvesting rate and validate the optimality of save-ratio selection.

Nowadays, cyber-physical system (CPS) relies on wireless networks for devices control and information backhaul. But the mass deployment CPS devices make operators' spectrum scarce situations even more worse. Hence, cellular network operators anticipate the Dynamic Spectrum Access (DSA) technology to solve the spectrum shortage problem in the context of cognitive radio (CR). Femtocells, acting as gateways in CPS, integrate CPS devices into cellular networks in a seamless manner. The concept of cognitive femtocell can solve the spectrum congestion problem even within a massive network on the CPS scale. However, in practical systems, cellular white space spectrum should be quantitatively measured to guide cognitive femtocell access algorithms design. We are the first to conduct a comprehensive measurement study for the purpose of measurement, discovery and model features of GSM white space spectrum. We evaluate availabilities of extra 21.4 MHz capacity in GSM white space spectrum as a reason of artificial GSM network spectrum planning. In our study, we find out that perfect results can hardly be obtained because of inherent measurement trade-offs, even when extremely high sweep speed of 16 GHz/s is applied at the receiver. Based on statistical analysis of real-scene traces, we propose an Efficient Duty Cycle (EDC) model to accurately characterize the white space in GSM network by considering miss-detection probabilities. Cross-validating evaluation results show that the EDC model can well decrease interference probabilities at high time-granularity measurement periodicity scenarios. Our results confirm the feasibility of cognitive femtocells access in an intra-operator scenario and can be applied to future wireless networks.

In an Radio Frequency Identification (RFID) system, Dynamic Frame Length Aloha (DFSA) has been widely used in anti-collision protocol due to its high efficiency. A fast and accurate estimate of tag population is critical to the performance of DFSA. In this paper, we propose a closed-form tag estimator which reduces greatly the computational complexity while maintains high accuracy. Also we propose a two-step estimate method which can further improve the estimate performance. Simulations show that the error of proposed tag estimator is less than 4%. Furthermore, the proposed tag estimator has significant advantage in lower complexity over existing estimate methods.

Dynamic spectrum access has been a subject of extensive study in recent years. The increasing volume of literatures calls for a deeper understanding of the characteristics of current spectrum utilization. In this paper, we present a detailed spectrum measurement study, with data collected in the 20 MHz to 3 GHz spectrum band and at four locations concurrently in Guangdong province of China. We examine the statistics of the collected data, including channel vacancy statistics, channel utilization within each individual wireless service, and the spectral and spatial correlation of these measures. Main findings include that the channel vacancy durations follow an exponential-like distribution, but are not independently distributed over time, and that significant spectral and spatial correlations are found between channels of the same service. We then exploit such spectrum correlation to develop a 2D frequent pattern mining algorithm that can predict channel availability based on past observations with considerable accuracy.

Dynamic spectrum access has been a subject of extensive research activity in recent years. The increasing volume of literature calls for a deeper understanding of the characteristics of current spectrum utilization. In this paper we present a detailed spectrum measurement study, with data collected in the 20MHz to 3GHz spectrum band and at four locations concurrently in South China. We examine the first and second order statistics of the collected data, including channel occupancy/vacancy statistics, channel utilization within each individual wireless service, and the temporal, spectral, and spatial correlation of these measures. Main findings include that the channel vacancy durations follow an exponential-like distribution, but are not independently distributed over time, and that significant spectral and spatial correlations are found between channels of the same service. We then exploit such spectrum correlation to develop a 2-dimensional frequent pattern mining algorithm that can accurately predict channel availability based on past observations.