An effective traffic management system is crucial to smart city growth. Consequently, the significance of IoT devices is increasing. Numerous IoT devices, including cameras, are commonly positioned along major roads in a smart city. These IoT devices, embedded with computing and transmitting capabilities, collect data from cameras and then relay it to the central traffic controller (CTC) responsible for managing traffic flow. In our study, we introduce a novel framework termed semantic communication (SemCom), which integrates a Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) network. The SemCom model employs a semantic encoder within each IoT device to extract pertinent information from raw images. This encoded data is transmitted to the CTC as symbols by the transmitter of the IoT device. Subsequently, the CTC’s semantic decoder utilizes this sequence of symbols to predict vehicle counts on respective roads and devise traffic management strategies accordingly. To enhance the quality of experience (QoE), we formulate an optimization problem considering vehicle user safety, IoT device transmission power, prediction accuracy, and semantic entropy. Through numerical analysis, we demonstrate that the SemCom model significantly reduces overhead by 54.42% compared to conventional source encoder/decoder models. Moreover, simulation results showcase the superiority of our proposed model in terms of mean absolute error (MAE) and QoE metrics over existing state-of-the-art approaches. Since vehicle count prediction is pivotal in traffic management, our SemCom framework offers a promising avenue for efficient and accurate vehicle count prediction, contributing to more effective traffic management in smart cities.

Vehicle count prediction is an important aspect of smart city traffic management. Most major roads are monitored by cameras with computing and transmitting capabilities. These cameras provide data to the central traffic controller (CTC), which is in charge of traffic control management. In this paper, we propose a joint CNN-LSTM-based semantic communication (SemCom) model in which the semantic encoder of a camera extracts the relevant semantics from raw images. The encoded semantics are then sent to the CTC by the transmitter in the form of symbols. The semantic decoder of the CTC predicts the vehicle count on each road based on the sequence of received symbols and develops a traffic management strategy accordingly. Using numerical results, we show that the proposed SemCom model reduces overhead by 54.42% when compared to source encoder/decoder methods. Also, we demonstrate through simulations that the proposed model outperforms state-of-the-art models in terms of mean absolute error (MAE) and mean-squared error (MSE).

Abstract The differential privacy (DP) literature often centers on meeting privacy constraints by introducing noise to the query, typically using a pre-specified parametric distribution model with one or two degrees of freedom. However, this emphasis tends to neglect the crucial considerations of response accuracy and utility, especially in the context of categorical or discrete numerical database queries, where the parameters defining the noise distribution are finite and could be chosen optimally. This paper addresses this gap by introducing a novel framework for designing an optimal noise probability mass function (PMF) tailored to discrete and finite query sets. Our approach considers the modulo summation of random noise as the DP mechanism, aiming to present a tractable solution that not only satisfies privacy constraints but also minimizes query distortion. Unlike existing approaches focused solely on meeting privacy constraints, our framework seeks to optimize the noise distribution under an arbitrary $$(\epsilon , \delta )$$ ( ϵ , δ ) constraint, thereby enhancing the accuracy and utility of the response. We demonstrate that the optimal PMF can be obtained through solving a mixed-integer linear program. Additionally, closed-form solutions for the optimal PMF are provided, minimizing the probability of error for two specific cases. Numerical experiments highlight the superior performance of our proposed optimal mechanisms compared to state-of-the-art methods. This paper contributes to the DP literature by presenting a clear and systematic approach to designing noise mechanisms that not only satisfy privacy requirements but also optimize query distortion. The framework introduced here opens avenues for improved privacy-preserving database queries, offering significant enhancements in response accuracy and utility.

The recent emergence of 6G raises the challenge of increasing the transmission data rate even further in order to break the barrier set by the Shannon limit. Traditional communication methods fall short of the 6G goals, paving the way for Semantic Communication (SemCom) systems. These systems find applications in wide range of fields such as economics, metaverse, autonomous transportation systems, healthcare, smart factories, etc. In SemCom systems, only the relevant information from the data, known as semantic data, is extracted to eliminate unwanted overheads in the raw data and then transmitted after encoding. In this paper, we first use the shared knowledge base to extract the keywords from the dataset. Then, we design an auto-encoder and auto-decoder that only transmit these keywords and, respectively, recover the data using the received keywords and the shared knowledge. We show analytically that the overall semantic distortion function has an upper bound, which is shown in the literature to converge. We numerically compute the accuracy of the reconstructed sentences at the receiver. Using simulations, we show that the proposed methods outperform a state-of-the-art method in terms of the average number of words per sentence.

Machine-to-Machine (M2M) networks are an emerging technology with applications in various fields including smart grids, healthcare, vehicular telematics, smart cities etc. Heterogeneous M2M networks contain different types of nodes, e.g., nodes that send emergency, periodic and normal type data. An important problem is to rapidly estimate the number of active nodes of each node type in every time frame in such a network. In this paper, we design an estimation scheme for estimating the active node cardinalities of each node type in a heterogeneous M2M network with three types of nodes. Our scheme consists of two phases- in phase 1, coarse estimates are computed and these estimates are used to compute the final estimates to the required accuracy level in phase 2. We analytically derive a condition that can be used to decide as to which of two possible approaches is to be used in phase 2. Using simulations, we show that our proposed scheme requires significantly fewer time slots to execute compared to separately executing a well-known estimation protocol designed for a homogeneous network in prior work thrice to estimate the cardinalities of the three node types, even though both these schemes obtain estimates with the same accuracy.

Machine-to-Machine (M2M) networks are an emerging technology with applications in numerous areas including smart grids, smart cities, vehicular telematics, healthcare, security and public safety. In this paper, we design a medium access control (MAC) protocol that supports multi-channel operation for a heterogeneous M2M network, with three types of M2M devices (e.g., those that send emergency, periodic and normal type data), operating as a secondary network using Cognitive Radio technology. Also, we design an estimation protocol for rapidly obtaining separate estimates of the number of active nodes of each traffic type, and use these estimates to find the optimal contention probabilities to be used in the Cognitive MAC protocol. We compute a closed form expression for the expected number of time slots required by our estimation protocol to execute as well as a simple upper bound on it, which shows that the expected number of time slots required by our protocol to obtain the above estimates is small. Also, we mathematically analyze the performance of the Cognitive MAC protocol and obtain expressions for the expected number of successful contentions and the expected amount of energy consumed per frame. Finally we evaluate the performance, in terms of average throughput and average delay, of our MAC protocol using simulations.

The design of an efficient Medium Access Control (MAC) protocol for multichannel ad hoc Cognitive Radio Networks is an important problem and has been the topic of extensive recent research. In this paper, we present the design and performance evaluation of a protocol, Group MAC (GMAC), which is customized for a situation that commonly arises in ad hoc networks: the network consists of multiple groups of nodes such that a large fraction of the traffic of each node needs to be sent to other nodes of its own group. Some examples are: (a) units (e.g., platoons) in a military ad hoc network, (b) divisions in an emergency or disaster relief network, (c) departments in a corporate or university network. Our protocol requires each secondary node to have only one narrowband transceiver, does not rely on a control channel and incorporates a novel technique for dynamically balancing the traffic load of secondary nodes across the set of free channels. We analyze the stability region of the protocol using a queuing theoretic framework. Our extensive simulations show that a large fraction of the bandwidth unoccupied by primary users is utilized by the GMAC protocol for data transmissions.