Starting with the end-user requirements, it is argued that the most appropriate performance metric with which to evaluate video-based tracking methods, in the public transport domain, is to measure the information gained through their use. This is equivalent to the reduction in uncertainty about a passenger’s whereabouts, after tracking and appearance-based measurements have been taken into account. In this paper, we present a framework for the performance evaluation of such a system. Error propagation analysis is performed to investigate the impact of each system component on the final uncertainty, and allows an end-user requirement to be propagated through the system to determine the minimum performance requirement for each component. This proposed analysis framework is demonstrated on a simulated system.
Speech Emotion Recognition (SER) plays a crucial role in enhancing human-computer interaction. Cross-Linguistic SER (CLSER) has been a challenging research problem due to significant variability in linguistic and acoustic features of different languages. In this study, we propose a novel approach HuMP-CAT, which combines HuBERT, MFCC, and prosodic characteristics. These features are fused using a cross-attention transformer (CAT) mechanism during feature extraction. Transfer learning is applied to gain from a source emotional speech dataset to the target corpus for emotion recognition. We use IEMOCAP as the source dataset to train the source model and evaluate the proposed method on seven datasets in five languages (e.g., English, German, Spanish, Italian, and Chinese). We show that, by fine-tuning the source model with a small portion of speech from the target datasets, HuMP-CAT achieves an average accuracy of 78.75% across the seven datasets, with notable performance of 88.69% on EMODB (German language) and 79.48% on EMOVO (Italian language). Our extensive evaluation demonstrates that HuMP-CAT outperforms existing methods across multiple target languages.
Given the scarcity of spectral resources in traditional wireless networks, it has become popular to construct visible light communication (VLC) systems. They exhibit high energy efficiency, wide unlicensed communication bandwidth as well as innate security; hence, they may become part of future wireless systems. However, considering the limited coverage and dense deployment of light-emitting diode (LED) lamps, traditional network association strategies are not readily applicable to VLC networks. Hence, by exploiting the power of online learning algorithms, we focus our attention on sophisticated multi-LED access point selection strategies conceived for hybrid indoor LiFi-WiFi communication systems. We formulate a multi-armed bandit model for supporting the decisions on beneficially selecting LED access points. Moreover, the `exponential weights for exploration and exploitation' algorithm and the `exponentially weighted algorithm with linear programming' algorithm are invoked for updating the decision probability distribution, followed by determining the upper bound of the associated accumulation reward function. Significant throughput gains can be achieved by the proposed network association strategies.
In future mobile networks, it is difficult for static base stations (BSs) to support the rapidly increasing data services, especially for cell-edge users. Unmanned aerial vehicle (UAV) is a promising method that can assist BSs to offload the data traffic, due to its high mobility and flexibility. In this correspondence, we focus on the UAV trajectory at the edges of three adjacent cells to offload traffic for BSs. In the proposed scheme, the sum rate of UAV-served edge users is maximized subject to the rate requirements for all the users, by optimizing the UAV trajectory in each flying cycle. The optimization is a mixed-integer nonconvex problem, which is difficult to solve. Thus, it is transformed into two convex problems, and an iterative algorithm is proposed to solve it by optimizing the UAV trajectory and edge user scheduling alternately. Simulation results are presented to show the effectiveness of the proposed scheme.
Opportunistic scheduling schemes are investigated for uplink wiretap channels with multiple asymmetrically located legitimate users (LUs) and eavesdroppers. To exploit multiuser diversity, the cumulative distribution function-based scheduling method is leveraged to schedule the transmissions of the LUs. Under this scheduling framework, the closed-form expressions of the secrecy outage probability and ergodic secrecy rate are derived, illustrating the interplay among the system parameters, such as the channel statistics and the number of LUs and eavesdroppers. Through the secrecy outage analysis of the proposed scheduling schemes, we observe that the secrecy throughput is not always maximized with a larger channel access ratio (CAR), and consequently, we design a CAR adjustment scheme to maximize the secrecy throughput while satisfying the required secrecy level. We also prove that under our proposed scheduling schemes, the secrecy diversity order of each LU is equal to the reciprocal of the LU's CAR, implying that full diversity order is achieved, and the ergodic secrecy rate of each LU normalized by its CAR achieves the optimal double-logarithmic growth when the number of LUs increases to infinity.
Fog computing, complementary to cloud computing, has recently emerged as a promising solution that extends the computing infrastructure from the cloud center to the network edge. By offloading computational applications to the network edge, fog computing could support delay-sensitive applications and reliable access to nearby users. However, with the growing number of demands from various applications, fog computing may be overwhelmed and it may result in significant performance degradation. Thus, to process applications efficiently, we propose an integrated fog and cloud computing (FCC) approach, where users can offload a series of applications to nearby fog nodes (FNs) or cloud center cooperatively. Nevertheless, due to the constrained computing, storage, and radio resources, how to perform resource allocation to achieve an optimal and stable performance is an important problem. To address this issue, we focus on multiple resource allocation problem in a general system, which consists of multi-user, multi-FN, and a cloud center. In addition, to reduce offloading transmission latency and release the constraint of limited radio resource, non-orthogonal multiple access, which enables multiple users to transmit data to the same FN for offloading tasks on the same spectrum resource, is introduced into the proposed FCC approach. To this end, we formulate joint offloading decision, user scheduling, and resource allocation problem as an optimization problem that aims at minimizing the total system cost of energy as well as the delay of users. Furthermore, we decouple the original problem and transform it into a convex problem. Finally, we develop alternating direction method of multipliers based algorithms to solve the optimization problem in a distributed and efficient way. Simulation results show that the proposed approach achieves better performance compared with existing schemes.
In this paper, we propose to adapt the early regulation of unresponsive flows (ERUF) to third generation wireless networks employing link layer retransmissions. Wireless channel degradations may result in backlog of downlink packets at the link layer queue, causing real-time packets with hard delivery deadlines to expire and be dropped at the receiver. We propose to regulate these congested flows by dropping expiring packets at the ingress edge node of the general packet radio service (GPRS)/universal mobile telecommunication services (UMTS) core network to release shared network resources for other flows. Based on an analysis of the characteristics of the radio link control (RLC) layer of the GPRS/UMTS network, we develop a new set of mechanisms based on active queue management to achieve this goal. We present simulation results to show that this new wireless early regulation of unresponsive flows (WERUF) scheme can significantly improve the overall end-to-end quality-of-service of all traffic flows.
In this paper, we propose TCP Vegas with online network coding (TCP VON), which incorporates online network coding into TCP. It is shown that the use of online network coding in transport layer can improve the throughput and reliability of the end-to-end communication. Compared to generation based network coding, in online network coding, packets can be decoded consecutively instead of generation by generation. Thus, online network coding incurs a low decoding delay. In TCP VON, the sender transmits redundant coded packets when it detects packet losses from acknowledgement. Otherwise, it transmits innovative coded packets. We establish a Markov chain to analytically model the average decoding delay of TCP VON. We also conduct ns-2 simulations to validate the proposed analytical model. Finally, we compare the delay and throughput performance of TCP VON and automatic repeat request (ARQ) network coding based TCP (TCP ARQNC). Simulation results show that TCP VON outperforms TCP ARQNC in terms of the average decoding delay and network throughput.
This letter proposes non-orthogonal multiple access (NOMA) based coordinated direct and relay transmission (CDRT) and hybrid multiple access (HMA) protocols for a general CDRT system, where a base station directly serves cell-center users (CCUs), while it communicates with cell-edge users (CEUs) via a relay. The ergodic sum capacity (ESC), capacity scaling and the number of successive interference cancellation (SIC) operations are derived correspondingly. If the number of CCUs is less than that of CEUs and the interference level of imperfect SIC is small, the proposed NOMA-based CDRT can achieve much better ESC than HMA. Otherwise, the proposed HMA achieves a better performance-complexity tradeoff. Numerical results verify the effectiveness and superiority of the proposed protocols.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)