Comprehensive Fake News Detection using Hybrid BERT and Rule-Based Analysis

A comparison of real-time acousto-optic processors for synthetic aperture radar (SAR) image formation has been performed. These processors take advantage of the high processing speed and large time bandwidth product of acousto-optic devices (AOD's) in combination with the multichannel correlation capability of charge coupled devices (CCD) to form the SAR image in real time. They offer significant size, weight and power consumption advantages compared to conventional optical or digital processors. The required two dimensional matched filtering operation is performed as a series of one dimensional operations. First, the matched filtering is performed in range using an AOD. Then the azimuth correlation is performed using a reference mask and a CCD operating as time delay and integrate correlator. The first operation is performed coherently on each radar pulse return while the second is an incoherent correlation performed over the several pulses required to form the synthetic aperture. Two features common to this type of architecture which might limit their applicability are the presence of unwanted signal-dependent bias terms and the inability to perform true complex processing. Architectures utilizing both spatial carriers and subtraction schemes for elimiminating the unwanted bias terms have been analyzed. Also, multichannel architectures for complex (quadrature) processing have been addressed. In addition to imaging performance, the impact of these approaches on system complexity, real-time processing speed and required component capabilities will also be discussed. Results from both our analysis and the experimental implementation of a selected group of these architectures will be presented.

ABSTRACTWe present a new 3D object tracking algorithm that supports multiple planar and nonplanar objects with real‐time processing speed and high accuracy. The main problem of object tracking algorithm is the limitation of the supporting type of target object, slow processing speed, and low tracking accuracy. Our algorithm provides high accuracy and real‐time performance while detecting not only planar objects but also nonplanar objects. The real‐time performance is accomplished by using Features from Accelerated Segment Test corner detection, region of interest, and parallel processing on a multicore processor. High accuracy is realized by using a scale‐invariant feature transform descriptor, random sample consensus, region of interest, and double robust filtering. Copyright © 2013 John Wiley & Sons, Ltd.

With the digitalization and intellectualization of substations, the amount of state data collected by intelligent components is becoming larger and larger. Traditional data mining technology cannot meet the requirements of real-time data processing and application speed. For a typical smart substation, a fault diagnosis method based on improved association rule mining algorithm is proposed for transformer near-zone fault analysis. Firstly, an improved association rule data mining algorithm based on rough set is designed to extract information from massive data and diagnose faults. Then genetic algorithm is applied to improve association rule data mining algorithm to speed up data processing. Finally, simulation analysis is carried out to demonstrate the effectiveness and rapidity of the proposed method. The results show that the intelligent substation fault diagnosis method based on improved association rule mining algorithm has fast and powerful reduction ability in data processing. It can extract useful data from intelligent substation components to accurately judge fault information, reduce data scale and improve fault processing speed.

The objective of foreground segmentation is to extract the desired foreground object from input videos. Over the years, there have been significant amount of efforts on this topic. Nevertheless, there still lacks a simple yet effective algorithm that can process live videos of objects with fuzzy boundaries (e.g., hair) captured by freely moving cameras. This paper presents an algorithm toward this goal. The key idea is to train and maintain two competing one-class support vector machines at each pixel location, which model local color distributions for both foreground and background, respectively. The usage of two competing local classifiers, as we have advocated, provides higher discriminative power while allowing better handling of ambiguities. By exploiting this proposed machine learning technique, and by addressing both foreground segmentation and boundary matting problems in an integrated manner, our algorithm is shown to be particularly competent at processing a wide range of videos with complex backgrounds from freely moving cameras. This is usually achieved with minimum user interactions. Furthermore, by introducing novel acceleration techniques and by exploiting the parallel structure of the algorithm, near real-time processing speed (14 frames/s without matting and 8 frames/s with matting on a midrange PC & GPU) is achieved for VGA-sized videos.

Changes in blood cell morphology are a primary indicator of serious diseases such as leukemia. In this study, an automated blood cell diagnostic approach is proposed by integrating the latest object detection algorithm, YOLOv11, with the statistical Neyman–Pearson hypothesis. The study utilizes an extended BCCD dataset consisting of 2,000 images (80% training, 10% testing, and 10% validation). The results demonstrate that the YOLOv11 model significantly outperforms the conventional Faster R-CNN algorithm in terms of higher accuracy (95.8% mAP) and real-time processing speed, thereby enhancing the efficiency of clinical diagnostics.

Adaptive support weight (ASW) strategies in local stereo matching have recently attracted many researchers due to their compelling results. In this paper, we present an evaluation study that focuses on weight computation methods that have been suggested in the most recent literature. We implemented 9 ASW stereo methods and tested them on all (35) ground truth test stereo image pairs of the Middlebury benchmark. Our evaluation considers both the accuracy of the matching process and the computational efficiency of its GPU implementation. According to our results, high-quality matching results at real-time processing speeds can be achieved by using the guided image filter weights.

Low-cost real-time aerial object detection and GPS location tracking pipeline

Multi-touch is a novel and vigorous Human Computer Interaction technique, which has being widely applied in both education and industry. This article describes the implementation of Mimosa — a standing multi-touch system that is primarily designed for exhibiting products or displaying virtual scenes in public space conditions. Mimosa is based on computer vision technique, and its whole implementation steps are discussed in detail in the paper. We firstly propose a hardware setup which is suitable for public space environments, and further analyze the software architecture bridging the gap between the hardware setup and application programs. Mimosa has a real-time processing speed and works fine in various environments. Therefore Mimosa is especially fit for the exhibition of interactive products and applications of Virtual Reality in public spaces.

Model-based systems engineering design ideas play an increasing significant role in the development and testing of new aircraft, the finite element method as an important means of model analysis can provide a theoretical basis for the design of airborne test systems. First, propose an optimized design scheme for model-based airborne test system, design a multi-source data fusion real-time processing system for UAV, make the real-time processing and analysis speed of the original data, link data and multi-band test data reach a subtle level; Then, according to the complex coupling heat transfer mechanism of the UAV, based on the structure characteristics, a method of calculating the thermal environment of the UAV in different regions was proposed, realize the rational design of temperature test structure layout. Finally, based on the theory of modal analysis and simulation experiment, the optimal selection of vibration auxiliary equipment is realized to solve the vibration data overrun problem caused by resonance. The test results show that the airborne test system has a reasonable layout and measurement design, which can effectively reduce about 32.5% of test flight resources, and can be applied to other flight tests.

As one of the most significant parts in the development of the next generation infrared detection system, the infrared signal processing system requires the ability of real-time processing and high speed data transmission. A newly developed real-time signal processing system for infrared detecting based on the heterogeneous multiprocessor system on chip (MPSoC) is proposed in this paper. The device follows the architecture of Xilinx Zynq platform, integrating a feature rich dual-core ARM and Xilinx FPGA in a single chip, built on the 28nm high-k metal gate process technology. According to our design, the FPGA fabric portion retains all the programmable flexibility to drive the infrared detector and acquire data from ADC, with registers parallel operations to implement hardware acceleration. Furthermore, the FPGA fabric is connected to the ARM centered processor unit through multiple high performance interfaces, confirming high bandwidth communication and high speed data transmission between the two portions. Finally, the dual core ARM takes charge of the infrared signal processing system in general. One of the CPUs controls separate hardware modules and maintains the GUI for user interaction. The other responds to the dedicated system commands and external interrupts to update system parameters simultaneously. The integration of ARM and FPGA provides levels of performance that two-chip solutions cannot match due to their limited I/O bandwidth, loose coupling and power budgets. Experiments show that the architecture of heterogeneous MPSoC enhances the efficiency of memory controller and increases the speed of data transmission, approaching the theoretical value of the interfaces bandwidth.

Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and InceptionNet, benefiting from their powerful feature representations but suffering from high computational costs. Conversely, some lightweight model based detectors can run at real time speed, while their performance is inferior to those equipped with powerful backbone network. In this paper, we propose an effective yet efficient one-stage detector. The proposed detector inherits the architecture of SSD and introduces two novel modules, Feature Enhancement Module (FEM) and Feature Fusion Module (FFM). The FEM could strengthen features by increasing the size of receptive field and introducing more context, while The FFM could enhance the shallow part of the detector by fusing two adjacent feature maps. To evaluate their effectiveness, experiments are conducted on two major benchmarks. Experimental results demonstrate that the proposed detector performs much better than the original SSD, without losing real-time processing speed.

When the classical gray stretching algorithm is applied in digital low light level devices, it cannot meet the requirements of illumination environment change in large dynamic range, and the image processed under very low illumination or very high illumination is prone to the loss of target details, an adaptive gray stretching algorithm suitable for digital low light level devices is designed. The algorithm adds the variable of the brightness value of the original image information collected by the digital low light level device to the gray stretching transformation matrix, deduces the current environmental illuminance value according to the transformation of the brightness value, timely adjusts the relevant parameters in the gray stretching calculation matrix according to the environmental illuminance value, and obtains the gray stretching transformation matrix suitable for different image features under different illuminance environments, In order to meet the requirement that digital low light level devices should be suitable for the change of illumination environment in a large dynamic range. This paper also compares the adaptive algorithm with the classical algorithm, and gives the test results. At the end of the paper, the operation efficiency of the algorithm is tested to verify that the algorithm can meet the requirements of real-time image processing speed of digital low light level devices.

A lightweight feature activation guided multi-receptive field attention network for light compensation

In real-time image and video processing boards, power, speed, and area are the most often used measures for determining the performance of motion imagery applications. Due to technological advancement, power consumption has gained major attention in real-time image processing ability compared to speed. The increase in on-chip temperature due to larger power consumption has resulted in reduced operating life of chip and battery-driven devices. In this work, a new logic family has been introduced i.e., dual-mode logic (DML), which provides flexibility between the optimization of energy and delay (E-D optimization). This gate can be switched between two modes of operation that is a static mode (CMOS-like mode), which provides low power consumption and dynamic mode, which provides high speed. Recently, power leakage has become a dominant problem due to continuous data transfer among a large number of connected devices. Thus, to reduce power leakage, a self-controllable voltage level (SVL) power reduction technique is used along with DML logic. In the SVL technique, a maximum dc voltage is provided to the active load circuit on-demand or decrease the dc supplied to the load circuit in the standby mode. Integrating DML with the SVL technique reduces power consumption as well as leakage power. A 4-bit RCA, 8-bit RCA, and 16-bit RCA are used for verifying the proposed method and comparison of performance parameters is done with a conventional circuit. Complete circuit implementation and simulation are carried out in TANNER EDA version 13 tools with operating voltage of 1 V. The proposed system is further applied to real-time image, and we obtain the finest resolution level with minimum power consumption.

This study focuses on the application of neural networks for anomaly detection in microservice architectures. The increasing complexity of modern microservice systems makes traditional anomaly detection methods less effective, as they struggle to adapt to dynamic environments and large volumes of data. Neural networks offer a promising solution due to their ability to model complex patterns and detect subtle deviations that may indicate system failures or security threats. The aim of this work is to compare the effectiveness of different neural network-based approaches to anomaly detection, evaluate their strengths and weaknesses, and determine the most suitable method for practical implementation. To achieve this, several key tasks were outlined: an in-depth review of contemporary anomaly detection techniques applied to microservices; an analysis of neural network-based models, with a particular focus on autoencoders and recurrent neural networks (RNNs); a comparative assessment of these methods in terms of accuracy, computational efficiency, and robustness to noise; an exploration of hybrid models that combine different techniques to improve detection performance; and the formulation of recommendations for selecting the optimal approach based on specific application scenarios. This research examines the use of deep neural networks for detecting behavioral anomalies in microservice environments. Various architectures are tested and compared to identify trade-offs between detection accuracy, processing speed, and resistance to false positives. The findings indicate that deep neural networks, particularly autoencoders and recurrent models, achieve high precision in identifying anomalies, but their efficiency varies depending on the architecture and the nature of the dataset. The study highlights that while autoencoders effectively capture deviations in data distribution, recurrent networks excel in detecting temporal anomalies in sequential microservice interactions. The conclusions confirm that neural networks provide a powerful tool for anomaly detection in microservice monitoring, significantly outperforming conventional statistical approaches. However, challenges remain, including the need for adaptive models capable of learning in real time and optimizing computational resources. Further research should focus on hybrid approaches that integrate multiple neural architectures to enhance detection accuracy and scalability. The development of self-learning and auto-tuning models could also improve adaptability to evolving microservice behaviors, ensuring robust and efficient anomaly detection in complex distributed systems.