Traffic perception is essential for intelligent transportation systems (ITS) to improve road safety and facilitate traffic management. High-altitude video surveillance systems, known for their wide coverage, provide an effective solution for continuous traffic monitoring and are increasingly deployed worldwide. However, the application of high-altitude video surveillance faces significant challenges, such as the small size and high density of vehicles, and low ambient brightness at night or low-light conditions. In this study, we propose a novel lightweight model specifically for reliable traffic perception in low-light conditions, utilizing an encoder-decoder architecture. The proposed framework begins with an advanced image enhancement algorithm designed to amplify the semantic content of low-brightness nighttime images. Subsequently, we employ a lightweight, deep two-channel neural network to extract image features both pre-and post-enhancement. To effectively manage the noise introduced during image enhancement, we introduce a feature fusion module based on an attention mechanism, which adaptively merges the features extracted by the two-channel network. The final step involves a lightweight decoder that synergizes high-level semantic information with low-level features. Extensive evaluation on our nighttime dataset shows that the proposed method can reduce error by 40% compared to the methods without image enhancement and by 28% compared to those relying solely on enhancement, outperforming all baseline methods. Notably, the lightweight module embedded in our model empowers the framework to perform real-time traffic perception at night, providing an efficient solution for traffic monitoring.

In recent years, the Ethereum platform has witnessed a proliferation of smart contracts, accompanied by exponential growth in total value locked (TVL). High-TVL smart contracts often require complex numerical computations, particularly in mathematical financial models used by many decentralized applications (DApps). Improper calculations can introduce numerical defects, posing potential security risks. Existing research primarily focuses on traditional numerical defects like integer overflow, and there is currently a lack of systematic research and effective detection methods targeting new types of numerical defects. In this paper, we identify five new types of numerical defects through the analysis of 1,199 audit reports by utilizing the open card method. Each defect is defined and illustrated with a code example to highlight its features and potential consequences. We also propose NumScout, a symbolic execution-based tool designed to detect these five defects. Specifically, the tool combines information from source code and bytecode, analyzing key operations such as comparisons and transfers, to effectively locate defects and report them based on predefined detection patterns. Furthermore, NumScout uses a large language model (LLM) to prune functions which are unrelated to numerical operations. This step allows symbolic execution to quickly enter the target function and improve runtime speed by 28.4%. We run NumScout on 6,617 real-world contracts and evaluated its performance based on manually labeled results. We find that 1,774 contracts contained at least one of the five defects, and the tool achieved an overall precision of 89.7%.

The paper presents an approach to enhancing the dynamic response of a cascaded DC/DC converter system, where virtual impedance control schemes are used for stabilization. A cascaded DC/DC converter system may not be stable when the source and load converters are not designed appropriately. Such system can be stabilized by reshaping the input impedance of the load converter with the virtual impedance control method. However, the dynamic performance suffers due to the added virtual-impedance control loop. In this paper, the dynamic performance of the cascaded DC/DC converter system is enhanced with an additional auxiliary circuit that is connected to the output port of the load converter and functions to buffer fast load transients. The simulation result shows that the voltage transient deviation on the load converter is significantly reduced with the proposed method.

Traffic state estimation is one of the very basic and most important tasks in intelligent transportation systems. Data collected from multiple types of traffic sensors are valuable sources to estimate traffic state. However, those data are always incomplete for the cases such as sensors broken, data missing, etc. The incomplete data can also be used to accurately estimate traffic state by data prediction and data fusion. Firstly, the missing data are predicted based on the data correlations extracted on large amount of historical taxi GPS data. Then, data collected from multiple sensors are fused to get more accurate results. Finally, computing of data fusion is parallelized. The main research focus is placed on learning for extracting the inherent spatio-temporal correlations of traffic data and fusing multimedia traffic data. Accuracy and efficiency experiments are conducted and the experimental results demonstrate that our method can process incomplete data and achieve accurate and real-time traffic state estimation.

Constrained spectral clustering (CSC) algorithms have shown great promise in significantly improving clustering accuracy by encoding side information into spectral clustering algorithms. However, existing CSC algorithms are inefficient in handling moderate and large datasets. In this paper, we aim to develop a scalable and efficient CSC algorithm by integrating sparse coding based graph construction into a framework called constrained normalized cuts. To this end, we formulate a scalable constrained normalized-cuts problem and solve it based on a closed-form mathematical analysis. We demonstrate that this problem can be reduced to a generalized eigenvalue problem that can be solved very efficiently. We also describe a principled k-way CSC algorithm for handling moderate and large datasets. Experimental results over benchmark datasets demonstrate that the proposed algorithm is greatly cost-effective, in the sense that (1) with less side information, it can obtain significant improvements in accuracy compared to the unsupervised baseline; (2) with less computational time, it can achieve high clustering accuracies close to those of the state-of-the-art.

Combination of renewable energy sources with utility grid and/or energy storage systems can deliver continuous power to the loads. Since many energy sources and loads use dc, it is envisioned that future smart homes may have dc distribution systems in order to interconnect various energy sources, storage, and loads with fewer converter stages and higher energy efficiency. In such applications, the system may have multiple sources and load voltage levels. The use of multiple-input multiple-output converters (MIMOCs) can simplify the conversion structure, reduce the design component, and lower the manufacturing cost. This paper introduces a nonisolated MIMOC, which can simultaneously draw power from different energy sources and provide multiple supply voltages. A specific switching scheme is proposed, and a multivariable control is presented to enable power budgeting between diverse sources and loads in addition to regulating all output voltages.

With increasing requirements on traffic efficiency, environmental quality, energy efficiency, and economic productivity, intelligent transportation systems (ITS) research, which is centered on traffic state evaluation, meets two grand challenges. One is to process heterogeneous transportation data collected from different types of traffic sensors and the other is to reduce the high computation intensity for processing massive transportation data. To overcome both challenges, this paper proposes an approach using parallelized fusion on multisensor transportation data. Parallelized fusion is an embodied case of CyberITS framework, which is developed for the synthesis of cyberinfrastructure and ITS. The fusion functionality is shaped by a rough evidential fusion model (REFM) based on rough set and Dempster–Shafer evidence theories. The REFM consists of four components, which are sensor data input, bootstrapping rough conversion, hierarchical evidential fusion, and traffic state output. Their computation intensity is centered on conversion and fusion components, which can be optimized by the algorithm- and data-centric parallelization, respectively. Computational experiments for accuracy and efficiency demonstrate that parallelized fusion achieves a distributed, high-performance, and collaborative CyberITS implementation to provide accurate and real-time traffic state evaluation.

One of the biggest challenges in speaker recognition is dealing with speaker-emotion variability. The basic problem is how to train the emotion GMMs of the speakers from their neutral speech and how to calculate the scores of the feature vectors against the emotion GMMs. In this paper, we present a new neutral-emotion GMM transformation algorithm to overcome this limitation. A transformation function based on polynomial function is learned to represent the relationship between the neutral and emotion GMM. It is adopted in testing to calculate the scores against the emotion GMM. The experiments carried on MASC show the performance is improved with an EER reduction of 39.5% from the baseline system.

Currently, most search engines are text-based and their structures are centralized. These kinds of engine are sufficient for searching text information in Internet. However, while searching audio resource, an efficient content-based audio search engine is required. In this paper, we demonstrate an audio search engine ASEKS based on keyword spotting technology in the peer-to-peer (P2P) network. The indexing sub-model spots information in local audio files and generates indices for later query; and the P2P networks distributes the query and gathers the results. ASEKS supports scalability and avoids the bottleneck of network load that usually exists in centralized architecture. The average accuracy of the keyword spotting sub-model is 88.4% in detection rate on the 5.267 false alarm per keyword per hour