订阅最新相关文献

针对液晶显示屏在复杂工业检测中面临的缺陷特征微弱、尺度跨度大与边缘设备资源受限的矛盾,提出 一种兼顾高精度与轻量化的检测算法FS-YOLO,构建用于工业场景的液晶屏缺陷数据集LCD-NET.FS-YOLO基于YOLOv8n模型,设计新的共享卷积特征金字塔(FPSC)模块,该模块通过不同膨胀率的卷积层来捕捉图像中不同尺度的上下文信息,同时利用共享机制抑制参数增长.此外,提出基于KernelWarehouse的C2f-KW模块,旨在提升模型的特征表达能力与计算效率.为实现精度与轻量化的平衡,设计检测头SAGHead,通过特征共享机制减少模型参数量,并通过组归一化策略实现精度与参数量的同步提升.对比实验与消融实验的结果表明:FS-YOLO在LCD-NET数据集上取得73.6％的mAP50(交并比阈值为0.5时的均值平均精度),且参数量与计算量分别减少13％与63％.该算法有效解决复杂工业环境下高精度检测模型难以在低算力设备落地的难题,具有显著的工程应用价值.

针对传统汽车防盗系统难以应对车主疏忽导致的安全隐患,设计了一种基于STC89C52 单片机的主动式汽车防盗系统,通过整合振动/红外传感器、GPS/GSM模块及限位开关,实现入侵检测与车窗状态监测.系统在识别异常振动或人员靠近时触发声光报警并推送定位信息至车主手机;若车窗未关则主动提醒处理.基于Proteus的硬件仿真验证了多模块协同运行的可靠性,实验证明其可有效降低因车主疏忽引发的盗窃风险,兼具低成本与高实用性,为智能防盗技术提供了创新性解决方案.

The development and implementation of an automated Smart Window system using Wi-Fi as an infrastructure, a microcontroller ESP32 as a central wireless component. The system aims at enhancing accessibility, energy efficiency and convenience of users, especially in residential facilities. The customer will be able to remotely control and monitor window behaviors through integration of sensors with thoughtfully designed smart phone application based on real-time environmental data. The mobile offered mobile app is compatible with laptops, tablets, and smart phones and is based on known messaging systems, such as Telegram. The project focuses on energy management as this touches on the automation of the operations of the windows to the circumstantial environmental conditions to reduce costs and to embrace environmental sustainability. Access control methods ensure the safety and privacy of the users and boost confidence on the reliability of the system. The test and evaluation outcomes demonstrate the effectiveness of the system in terms of its capability to maximize energy use and enhance the comfort of the user. In an attempt to add more functionality and ensure user-friendliness, further research might carry out improvements and interactions with other smart home devices. Taken altogether, Smart Window Automation system is the step forward of home automation technology, and this technology offers helpful solutions to the modern living spaces on the territory of the Internet of Things and intelligent devices.

Digital forensics has made significant advancements in addressing the challenges posed by cybercriminals, particularly with the increasing use of instant messaging (IM) platforms as digital evidence sources. As one of the most popular IM platforms globally, WhatsApp has proven to be a valuable tool for effective communication and file transfer, particularly through its web and desktop application features. This study explores forensic artifacts with a focus on identifying various forms of evidence, including text files, images, audio files, and videos. The investigation analyzes these artifacts on a Windows 11 operating system, where the victim accessed them through the WhatsApp Web client using the Microsoft Edge browser. The evidence being examined was sent to the victim's WhatsApp account on a mobile device. However, instead of opening the evidence on the phone, the victim used the WhatsApp Web client in the Microsoft Edge browser to view and interact with the attacker. A detailed experimental design was employed, incorporating virtual environments to analyze how data is synchronized between devices and the host machine. In this research, three forensic tools-FTK Imager, Autopsy, and OS Forensics-were utilized to locate, examine, and retrieve artifacts, including cache, IndexedDB, and log files. The findings reveal that while traces of media synchronization and certain activity logs were discovered, critical data such as text messages, deleted messages, and media files were often not automatically saved on the computer.

In this paper, the penetration tester will be going to hack into a phone which is using Android OS (operating system). This paper not only tests in the old version but also tries to hack into the latest version of Android which is Android 10. The tool used in this paper is a hacking tool name "AndroRAT". The first version of this hacking tool is used in the Windows OS and the author did it for his University Assignment, not used to hack another person's phone. In 2020, there is a new version of AndroRAT which use in the Kali Linux version. This paper, it will show how to use these two different versions of AndroRAT and how it works. Android 7, Android 9, and Android 10 will be the main versions of the android that will be used in this paper. Besides that, this paper has included the demonstration of hacking using these two versions of AndroRAT, the success and failure when trying to hack an Android phone.

Smartphones are the most extensive repositories of user profile data such as activities related to personal and professional lives, working habits, and navigation histories. This stems from their rising inflow and pervasiveness. While some data may be retrieved quickly and simply, other (deleted) data may require the employment of cutting-edge forensic investigative tools. Smartphone applications, built on complex architectures (APIs, servers, storage, and cloud, etc.), typically require the use of specialized tools to gather, segregate, assess, analyze, and report on data, making acquisition and analysis more complex and time-consuming. This paper highlights the challenges of smartphone forensics while testing a range of Operating Systems (OSs) including Android, iOS, and Windows for the extraction of forensic artifacts. The results of both logical and physical acquisitions are presented. Depending on the data, extractions may also include methods such as installing an OS on the current server via a file transfer.

As the number of android applications available in the market are increasing rapidly, various types of security attacks using the android apps have also increased at the same pace. The ransomware attack is one of these kinds of security attacks in which the attackers lock the user's phone, encrypts user's data or blocks the user's access to their own data and threatens the user to pay a ransom to gain the access back. Android devices are more prone to these ransomware attacks when compared to Windows and IOS devices. In this work, a novel hybrid ransomware detection method is proposed that analyses image data, text, and application code to extract plain or encrypted threat text. Threatening text is a potential tool and could be one of the most effective features for ransomware detection. Our approach to ransomware detection combines static and dynamic analysis, along with multiple machine learning models acting as classifiers. Notably, our experiments show promising results with an accuracy rate reaching up to 91% and a low rate of false negatives.

Due to the high transparency and precision of mobile phone glass covers, there are still challenges in the production process, such as a large range of dimensional variations in defects, difficulty in capturing small defect features, and high computational requirements for high-precision image acquisition. These challenges make it difficult to meet the accuracy and speed requirements of surface quality inspection for production and quality control. Therefore, this paper proposes a novel method (ViT-Faster-RCNN) combining Vision Transformer (ViT) and Faster-RCNN to detect defects in glass covers, achieving rapid global detection of high-resolution image acquisition. By introducing the encoding and decoding structures of the Transformer framework into the backbone network, the model's ability to extract context information and global information is effectively enhanced, building upon its capability to accurately capture key local features. The model is able to ensure precise localization of defects of different sizes under complex background interference. Furthermore, the performance of the encoder is optimized by introducing residual structures and window attention mechanisms, which alleviates the gradient disappearance problem caused by network depth. This enhances the model's convergence speed and reduces computational complexity. The Simple Feature Pyramid Network (SFPN) is used to simplify the multi-scale feature fusion structure, further enhancing detection efficiency and accuracy. Experimental results demonstrate that the proposed method can accurately and automatically detect small defects on the glass cover plates, achieving an accuracy rate reaching 97.9%.

The introduction of the towed transient electromagnetic instrument (tTEM) has changed near-surface geophysical exploration. This system has swiftly emerged as a preferred method among geophysicists, particularly for investigations requiring intermediate depths (0 - 200 m) with high vertical and horizontal resolution. Over the past 5 years, the tTEM system has been accessible to both researchers and practitioners in the geophysical field. Our ongoing enhancements to the system focus on improving signal quality, achieving greater depths of investigation, and ensuring high-precision data acquisition. These advancements are made possible by the integration of advanced electronic components, such as high-speed Field-Programmable Gate Arrays (FPGAs) for precise timing, modern Application Programming Interfaces (APIs) for reliable data transmission, and GPS-based synchronization. Also, the entire software platform is new, and the instrument is now controlled from a cell phone or a tablet. We have upgraded the current tTEM system to the more versatile SuperTEM platform. This upgrade includes a receiver system equipped with a dual-channel analog signal, sampled by an 18-bit Analog-to-Digital Converter (ADC) at a clock speed of 4 Mhz. The data is subsequently integrated into up to 1024 gate windows. This extensive range of gated TEM signals facilitates more efficient and reliable signal processing techniques, such as Tapered Gating, to suppress Very Low Frequency (VLF) noise. As a result, the signal-to-noise ratio is nearly doubled, leading to deeper investigative capabilities. Also, the receiver coil is redesigned to a much smaller formfactor while the bandwidth and noise suppression capabilities have been increased. The new transmitter system features a constant current design, maintaining consistent pulse transmission by regulating the input voltage to the H-bridge. This approach ensures the desired current in the transmitter loop, accommodating variations in loop resistance due to size and number of turns. Consequently, the tTEM system can be reconfigured for smaller loops (e.g., 2x2 m~2, 3x3 m~2, 4x4 m~2) based on specific application requirements. The transmitter unit includes an automatic power distribution setup, allowing for multiple voltage inputs (12-36V). The choice of voltage input is determined by the coil size; for example, transmitting 30 amps in a 4x4 m~2 coil with four turns necessitates an input exceeding 20V, thus a 24V input supply is required to achieve the target current. This paper will detail the technological advancements in the tTEM system, demonstrating its enhanced capabilities and potential applications in near-surface geophysical exploration.

There is a growing interest in the field of brain-computer interface (BCI) that uses electroencephalography (EEG) to connect the brain to external devices. BCI aims to provide people with special needs the ability to make autonomous decisions in so-called "smart homes" defined as a regular home place equipped with smart phone related technologies. Smart homes enable the inhabitants to control household devices like turning on/off the lights, the fans, air conditioning, and T.V. or opening and closing doors and windows as well as monitoring smart phones. Knowing that a significant progress has been made on regular users for smart homes, it is highlighted that less attention is focused on those with special needs, with mobility issues or quadriplegia; novel inventions have been developed to address such mobility issues. The recent advancement of this new technology opens a plethora of possibilities for patients to use their brain waves to control artificial prosthetic arms and legs. The present paper is an overview of state-of-the-art studies that incorporate BCI in medical applications such as operating a robotic arm, smart home, and smart phones. These studies enhanced our understanding of the different uses of BCI. However, the majority of the studies had a small number of participants which limits the generalization of their findings. Second, the application of BCI in the majority of studies is still a prototype. This paper recommends increasing the number of participants in future studies and apply BCI technologies on real life situations.