Ensuring fire safety is essential to protect life and property, but modern infrastructure and complex settings require advanced fire detection methods. Traditional object detection systems, often reliant on manual feature extraction, may fall short, and while deep learning approaches are powerful, they can be computationally intensive, especially for real-time applications. This paper proposes a novel smoke and fire detection method based on the YOLOv8n model with several key architectural modifications. The standard Complete-IoU (CIoU) box loss function is replaced with the more robust Wise-IoU version 3 (WIoUv3), enhancing predictions through its attention mechanism and dynamic focusing. The model is streamlined by replacing the C2f module with a residual block, enabling targeted feature extraction, accelerating training and inference, and reducing overfitting. Integrating generalized efficient layer aggregation network (GELAN) blocks with C2f modules in the neck of the YOLOv8n model further enhances smoke and fire detection, optimizing gradient paths for efficient learning and high performance. Transfer learning is also applied to enhance robustness. Experiments confirmed the excellent performance of ESFD-YOLOv8n, outperforming the original YOLOv8n by 2%, 2.3%, and 2.7%, with a mean average precision (mAP@0.5) of 79.4%, precision of 80.1%, and recall of 72.7%. Despite its increased complexity, the model outperforms several state-of-the-art algorithms and meets the requirements for real-time fire and smoke detection.

Automatic and accurate detection of fruit in greenhouse is challenging due to complicated environment conditions. Leaves or branches occlusion, illumination variation, overlap and cluster between fruits make the fruit detection accuracy to decrease. To address this issue, an accurate and robust fruit-detection algorithm was proposed for tomato detection based on an improved YOLOv4-tiny model. First, an improved backbone network was used to enhance feature extraction and reduce overall computational complexity. To obtain the improved backbone network, the BottleneckCSP modules of the original YOLOv4-tiny backbone were replaced by a Bottleneck module and a reduced version of BottleneckCSP module. Then, a tiny version of CSP-Spatial Pyramid Pooling (CSP-SPP) was attached to the new backbone network to improve the receptive field. Finally, a Content Aware Reassembly of Features (CARAFE) module was used in the neck instead of the traditional up-sampling operator to obtain a better feature map with high resolution. These modifications improved the original YOLOv4-tiny and helped the new model to be more efficient and accurate. The experimental results showed that the precision, recall, F1 score, and the mean average precision (mAP) with Intersection over Union (IoU) of 0.5 to 0.95 were 96.3%, 95%, 95.6%, and 82.8% for the improved YOLOv4-tiny model, respectively. The detection time was 1.9 ms per image. The overall detection performance of the improved YOLOv4-tiny was better than that of state-of-the-art detection methods and met the requirements of tomato detection in real time.

This paper presents a novel localization method that leverages two sets of distributed microphone arrays using the Generalized Cross-Correlation Phase Transform (GCC-PHAT) technique to improve the performance of anti-drone systems. In contrast to conventional sound source localization techniques, the proposed approach enhances localization accuracy by precisely estimating the azimuth angle while considering the unique acoustic characteristics of drones. The effectiveness of the proposed method was validated through both simulations and field tests. Simulation results revealed that, in ideal channel conditions, the proposed method significantly reduced the mean and variance of localization errors compared to existing techniques, resulting in more accurate positioning. Furthermore, in noisy environments, the proposed approach consistently outperformed the comparison method across various Signal-to-Noise Ratio (SNR) levels, achieving up to 2.13 m of improvement at SNR levels above 0 dB. While the comparison method exhibited decreased localization accuracy along the y-axis and z-axis, the proposed method maintained stable performance across all axes by effectively distinguishing between azimuth and elevation angles. Field test results closely mirrored the simulation outcomes, further confirming the robustness and reliability of the proposed localization approach.

This paper proposes a two-dimensional resource allocation technique for vehicle-to-infrastructure (V2I) communications. Vehicular communications requires high data rates, low latency, and reliability simultaneously. The 3rd generation partnership project (3GPP) included various numerologies to support this, leading to diversification of transmit time interval (TTI). It enables the two-dimensional resource allocation that considers time and frequency simultaneously, which has yet to be studied much. To tackle this issue, we propose a reinforcement learning approach to solve the two-dimensional resource allocation problem for V2I communications. A reinforcement learning agent in a base station allocates a quality of service (QoS) guaranteed two-dimensional resource block to each vehicle to maximize the sum of achievable data quantity (ADQ). It exploits received power information and a resource occupancy status as input. It outputs vehicles’ allocation information that consists of a time-frequency position, bandwidth, and TTI, which is a solution to the two-dimensional resource allocation. The simulation results show that the proposed method outperforms the fixed allocation method. Because of the ability to pursue ADQ maximization and QoS guarantee, the proposed method performs better than an optimization-based benchmark method if each vehicle has a QoS constraint. Also, we can see that the resource the agent selects according to the QoS constraint varies and maximizes the ADQ.

In this letter, we propose two uplink channel estimation methods based on deep back projection networks (DBPN), one of the deep learning models for super-resolution, for reconfigurable intelligent surfaces (RIS) systems. The first method is to estimate the entire channel with partial channel samples using the DBPN. Due to the iterative up and down projection architecture of the DBPN, the channel can be accurately estimated with relatively small samples. However, the DBPN requires high computational complexity in the process of transferring information between layers. To solve this problem, we modify the model architecture. The second method is a channel estimation method using the simplified DBPN. Through simulations, it is confirmed that the proposed methods have superior channel estimation performance than benchmark schemes. Furthermore the proposed method with simplified DBPN has lower complexity than the method using the original DBPN without performance degradation. In this letter, we propose two uplink channel estimation methods based on deep back projection networks (DBPN) for reconfigurable intelligent surfaces (RIS) systems. The proposed method is to estimate the entire channel with partial channel samples using the DBPN. Due to the iterative up and down projection architecture of the DBPN, the channel can be accurately estimated with relatively small samples. However, the DBPN requires high complexity in transferring information between layers. To solve this problem, we also propose the channel estimation method with the simplified DBPN. Simulation results show the superior performances of the proposed methods than benchmark schemes.

This letter proposes a new partial transmit sequence (PTS) scheme to reduce envelope fluctuations in orthogonal frequency division multiple access (OFDMA) uplink systems. We found that the conventional PTS can be seriously degraded in the non-contiguous allocation of OFDMA uplink systems due to the linearity in the conventional phase rotations. To overcome this problem, we propose a new phase rotation using the complex conjugate, which can be implemented without multiplication like the conventional phase rotations. Simulation results show that the proposed PTS outperforms the conventional PTS in terms of cubic metric (CM) and bit error rate (BER).