Speech emotion recognition plays a crucial role in analyzing psychological disorders, behavioral decision‐making, and human‐machine interaction applications. However, the majority of current methods for speech emotion recognition heavily rely on data‐driven approaches, and the scarcity of emotion speech datasets limits the progress in research and development of emotion analysis and recognition. To address this issue, this study introduces a new English speech dataset specifically designed for emotion analysis and recognition. This dataset consists of 5503 voices from over 60 English speakers in different emotional states. Furthermore, to enhance emotion analysis and recognition, fast Fourier transform (FFT), short‐time Fourier transform (STFT), mel‐frequency cepstral coefficients (MFCCs), and continuous wavelet transform (CWT) are employed for feature extraction from the speech data. Utilizing these algorithms, the spectrum images of the speeches are obtained, forming four datasets consisting of different speech feature images. Furthermore, to evaluate the dataset, 16 classification models and 19 detection algorithms are selected. The experimental results demonstrate that the majority of classification and detection models achieve exceptionally high recognition accuracy on this dataset, confirming its effectiveness and utility. The dataset proves to be valuable in advancing research and development in the field of emotion recognition.

Illegal construction not only seriously affects economic consumption and urban infrastructure (including monitoring equipment, 5G infrastructure, 6G devices, and other consumer electronics) but also hinders the development of smart cities. However, current illegal building detection methods have low detection accuracy and high calculation costs. Therefore, a method for detecting illegal building activities by identifying illegal building-related objects is proposed. A lightweight and highprecision detector and a dataset including 14,038 images of 29 categories of illegal building objects are proposed. The proposed detector is an enhanced version of YOLOv4. MobileNetV3 is utilized as the backbone to extract features, which greatly improves the detection accuracy. Further, depthwise separable convolution (DSC) is introduced to optimize the model structure and lower calculation costs and parameters. Furthermore, Mish was utilized to enhance the identification precision, generalization, and robustness of the detector. Experimental results revealed that the mean average precision (mAP) value of the detector is 88.79 with the dataset. Compared to other state-of-the-art (SOTA) detectors, this detector exhibited superior performance in identifying illegal construction objects, which can detect and prevent illegal building activities accurately and timely, enhancing the development of smart cities. Our project is released at https://github.com/QvQKing/YMMNet.git.

The advent of Contrastive Language-Image Pre-training (CLIP) models has revolutionized the integration of textual and visual representations, significantly enhancing the interpretation of static images. However, their application to video recognition poses unique challenges due to the inherent dynamism and multimodal nature of video content, which includes temporal changes and spatial details beyond the capabilities of traditional CLIP models. These challenges necessitate an advanced approach capable of comprehending the complex interplay between the spatial and temporal dimensions of video data. To this end, this study introduces an innovative approach, Retentive CLIP Adapter Tuning (RCAT), which synergizes the foundational strengths of CLIP with the dynamic processing prowess of a Retentive Network (RetNet). Specifically designed to refine CLIP’s applicability to video recognition, RCAT facilitates a nuanced understanding of video sequences by leveraging temporal analysis. At the core of RCAT is its specialized adapter tuning mechanism, which modifies the CLIP model to better align with the temporal intricacies and spatial details of video content, thereby enhancing the model’s predictive accuracy and interpretive depth. Our comprehensive evaluations on benchmark datasets, including UCF101, HMDB51, and MSR-VTT, underscore the effectiveness of RCAT. Our proposed approach achieves notable accuracy improvements of 1.4% on UCF101, 2.6% on HMDB51, and 1.1% on MSR-VTT compared to existing models, illustrating its superior performance and adaptability in the context of video recognition tasks.

Effective vehicle detection plays a crucial role in various applications in cities, including traffic management, urban planning, vehicle transport, and surveillance systems. However, existing vehicle detection methods suffer from low recognition accuracy, high computational costs, and excessive parameters. To address these challenges, this paper proposed a high-precision and lightweight detector along with a new dataset for construction-related vehicles. The dataset comprises 8425 images across 13 different categories of vehicles. The detector was based on a modified version of the You Only Look Once (YOLOv4) algorithm. DenseNet was utilized as the backbone to optimize feature transmission and reuse, thereby improving detection accuracy and reducing computational costs. Additionally, the detector employed depth-wise separable convolutions to optimize the model structure, specifically focusing on the lightweight neck and head components. Furthermore, H-swish was used to enhance non-linear feature extraction. The experimental results demonstrated that the proposed detector achieves a mean average precision (mAP) of 96.95% on the provided dataset, signifying a 4.03% improvement over the original YOLOv4. The computational cost and parameter count of the detector were 26.09GFLops and 16.08 MB, respectively. The proposed detector not only achieves lower computational costs but also provides higher detection when compared to YOLOv4 and other state-of-the-art detectors.

Erasure-coded systems require simultaneous updating of data chunks and parity chunks, thereby leading to high input/output (I/O) overhead. Following these updates, the most recent data and parity deltas are dispersed randomly in the log, which results in prolonged recovery time. This study introduces a novel approach named MPLR, which is specifically designed to expedite erasure-coded data updating and recovery. MPLR uses machine learning to categorize files into non-read-only and read-only classes, and then performs updates based on these classifications. For non-read-only files, MPLR applies in-place updates for data chunks and log-based updates for parity chunks, while setting aside disk space adjacent to the parity chunk to minimize disk seeks. For read-only files, MPLR likewise employs a mixture of in-place data updates and log-based parity updates, although without reserving space next to parity chunks. In regard to data recovery, MPLR enhances speed by accessing the parity delta stored in the allocated disk space. To further boost recovery acceleration, MPLR reads the parity delta in parallel and reduces the volume of parity delta leveraging the shareable aspects of the parity delta. Experimental results confirm the efficiency of MPLR in significantly improving update and recovery performances, compared to the state-of-the-art approaches.