Identification Technology Research Articles

1D-CNN-Transformer for Radar Emitter Identification and Implemented on FPGA

Deep learning has brought great development to radar emitter identification technology. In addition, specific emitter identification (SEI), as a branch of radar emitter identification, has also benefited from it. However, the complexity of most deep learning algorithms makes it difficult to adapt to the requirements of the low power consumption and high-performance processing of SEI on embedded devices, so this article proposes solutions from the aspects of software and hardware. From the software side, we design a Transformer variant network, lightweight convolutional Transformer (LW-CT) that supports parameter sharing. Then, we cascade convolutional neural networks (CNNs) and the LW-CT to construct a one-dimensional-CNN-Transformer(1D-CNN-Transformer) lightweight neural network model that can capture the long-range dependencies of radar emitter signals and extract signal spatial domain features meanwhile. In terms of hardware, we design a low-power neural network accelerator based on an FPGA to complete the real-time recognition of radar emitter signals. The accelerator not only designs high-efficiency computing engines for the network, but also devises a reconfigurable buffer called “Ping-pong CBUF” and two-level pipeline architecture for the convolution layer for alleviating the bottleneck caused by the off-chip storage access bandwidth. Experimental results show that the algorithm can achieve a high recognition performance of SEI with a low calculation overhead. In addition, the hardware acceleration platform not only perfectly meets the requirements of the radar emitter recognition system for low power consumption and high-performance processing, but also outperforms the accelerators in other papers in terms of the energy efficiency ratio of Transformer layer processing.

Advancements in Nutritional Composition of Milk and Species Identification

Abstract The milk product market is currently experiencing profound diversification, marked by an increasing presence of specialty milk and dairy products alongside traditional cow milk. These specialty varieties include yak, sheep, buffalo, and goat milk. Given their limited availability, these specialty milks often command higher prices than cow milk, rendering them susceptible to adulteration through substitution with the latter. Such fraudulent practices result in significant economic damage and pose risks to public health. Consequently, numerous identification methods have been devised to trace the origin of dairy products. While the prevailing methods predominantly focus on analyzing the nutrient composition of these products, this review aims to explore more cost-effective, sensitive, accurate, and efficient techniques. This endeavor begins with a comprehensive analysis of the common nutrients found in different dairy sources available in the market. Subsequently, this study elucidates various techniques employed for adulterating milk sources, with a specific emphasis on targeting these nutrients. Furthermore, a systematic comparative analysis was undertaken to evaluate the strengths and weaknesses of the diverse detection methods. This review provides a theoretical framework essential for the subsequent development of detection technologies for milk source identification.

Artificial intelligence applications in the diagnosis and treatment of bacterial infections.

The diagnosis and treatment of bacterial infections in the medical and public health field in the 21st century remain significantly challenging. Artificial Intelligence (AI) has emerged as a powerful new tool in diagnosing and treating bacterial infections. AI is rapidly revolutionizing epidemiological studies of infectious diseases, providing effective early warning, prevention, and control of outbreaks. Machine learning models provide a highly flexible way to simulate and predict the complex mechanisms of pathogen-host interactions, which is crucial for a comprehensive understanding of the nature of diseases. Machine learning-based pathogen identification technology and antimicrobial drug susceptibility testing break through the limitations of traditional methods, significantly shorten the time from sample collection to the determination of result, and greatly improve the speed and accuracy of laboratory testing. In addition, AI technology application in treating bacterial infections, particularly in the research and development of drugs and vaccines, and the application of innovative therapies such as bacteriophage, provides new strategies for improving therapy and curbing bacterial resistance. Although AI has a broad application prospect in diagnosing and treating bacterial infections, significant challenges remain in data quality and quantity, model interpretability, clinical integration, and patient privacy protection. To overcome these challenges and, realize widespread application in clinical practice, interdisciplinary cooperation, technology innovation, and policy support are essential components of the joint efforts required. In summary, with continuous advancements and in-depth application of AI technology, AI will enable doctors to more effectivelyaddress the challenge of bacterial infection, promoting the development of medical practice toward precision, efficiency, and personalization; optimizing the best nursing and treatment plans for patients; and providing strong support for public health safety.

Facial recognition for disease diagnosis using a deep learning convolutional neural network: a systematic review and meta-analysis.

With the rapid advancement of deep learning network technology, the application of facial recognition technology in the medical field has received increasing attention. This study aims to systematically review the literature of the past decade on facial recognition technology based on deep learning networks in the diagnosis of rare dysmorphic diseases and facial paralysis, among other conditions, to determine the effectiveness and applicability of this technology in disease identification. This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines for literature search and retrieved relevant literature from multiple databases, including PubMed, on 31 December 2023. The search keywords included deep learning convolutional neural networks, facial recognition, and disease recognition. A total of 208 articles on facial recognition technology based on deep learning networks in disease diagnosis over the past 10years were screened, and 22 articles were selected for analysis. The meta-analysis was conducted using Stata 14.0 software. The study collected 22 articles with a total sample size of 57 539 cases, of which 43 301 were samples with various diseases. The meta-analysis results indicated that the accuracy of deep learning in facial recognition for disease diagnosis was 91.0% [95% CI (87.0%, 95.0%)]. The study results suggested that facial recognition technology based on deep learning networks has high accuracy in disease diagnosis, providing a reference for further development and application of this technology.

An Effective Tag Estimation Method Based upon Artificial Neural Networks and Signal Strength for Anticollision in Radio Frequency Identification Systems

Radio frequency identification (RFID) technology has been widely used in applications such as access control, inventory management, spatial positioning, and object identification. Accurate tag estimation is one of the major challenges in RFID reader systems particularly in areas where large tag populations are to be identified such as shopping carts, warehouse inventory monitoring, and small ruminant farms. This paper proposes a new tag estimation technique employing artificial neural networks (ANNs) and signal strength to read large tag populations. The technique estimates the number of tags through the signal strength of the backscatter channel for efficient implementation of dynamic framed slotted Aloha (DFSA) protocol by analyzing the RN16 and the received signal strength indicator (RSSI). The ANN model is trained using the signal strength of various tag populations and can identify the number of tags with minimal errors. The proposed technique does not require any modification in the tags and is implemented as a minimal software script to be added to the tag estimation module of the reader. The proposed signal strength-ANN model is able to estimate the accurate number of tags thereby improving the performance of the employed DFSA model.

Analyzing security vulnerabilities in face ID technology on mobile devices

Analyzing security vulnerabilities in face ID technology on mobile devices

Recent research progress of soil nematode ecology in China.

Soil nematodes are a crucial component of belowground ecosystems. Soil nematode ecology, the studies of community distribution, structural composition, ecological functions, and interaction mechanisms with environment, has always been a hot spot in soil biology research. We systematically elaborated soil nematodes' high diversity and various diet, their advantages as bioindicator and model organisms, and their roles in biological control, ecological functions and soil health. Then, we reviewed the research progress of soil nematode ecology in China, including molecular biology identification methods, responses to global changes, food web structure and function, aboveground and belowground diversity relationship, and large-scale diversity pattern. We put forward the development trend of soil nematology, focusing on the high-throughput sequencing technology in nematode identification and quantification, the necessity of establishing a universal analysis platform to promote soil nematode research, and the importance of strengthening large-scale soil nematode survey.

Three-dimensional quantitative characterization of defects in inconel 625 superalloy based on deep learning image identification

Three-dimensional (3D) quantitative characterization of defects in superalloys is an important way to promote the ability of material design and service life prediction. In this work, 3D spatial distribution of defects for Inconel 625 superalloy manufactured by laser additive manufacturing (LAM) is carried out deep learning (DL) image identification technology and 3D image reconstruction. Firstly, computer tomography (CT) technology was used to obtain continuous slice images of sample. The U-net DL algorithm was applied to intelligently identify material defects in the continuous slices. On this basis, quantitative identification and analysis of spatial defect positions and typical sizes is achieved by using 3D reconstruction software. Compared with traditional threshold segmentation (TS) techniques, the defect recognition rate has significantly improved from 61.90 ​% to 95.00 ​%. This work provides a promising characterization method for efficient characterizing alloy defects and damage especially during material performance evaluation.

Spatial and temporal analysis of scooter-induced traffic patterns and their environmental implications

Scooters are a popular means of transportation in urban areas. However, studies examining their spatial and temporal features are lacking. This study examined traffic patterns in New Taipei City from September 2021 to June 2023 using real-time surveillance camera images and the YOLOv4 algorithm. The focus of the study was to investigate the role of scooters in urban transportation and their effect on air quality. The findings revealed that sedans and scooters accounted for approximately 90% of the total vehicles, and their usage exhibited significant spatial and temporal variations across the city. Sedans were more prevalent in rural areas, whereas scooters were predominant in urban and suburban regions. An examination of diurnal patterns revealed that peak traffic occurred during early morning and evening rush hours, with distinct usage patterns between weekdays and weekends. Through hierarchical clustering, the city's stations were categorized into three types based on the dominant vehicle usage: sedan-dominant, sedan-prevailing, and scooter-dominant. The analysis also established a correlation between the number of vehicles and air pollution, highlighting the significant role of sedans and scooters as primary sources of emissions, particularly in areas where scooters were dominant. This suggests that the current emission inventories may underestimate the impact of scooters and buses on air quality while overestimating the trucks' contribution. Consequently, this study emphasizes the significance of scooters in determining urban air quality and advocates for improved monitoring and image identification technologies to accurately assess the numbers and speeds of scooters. These measures are essential for improving the accuracy of emissions inventories and forecasts, which are crucial for effective urban air quality management.

Development of DNA Insertion-specific Markers Based on the Intergenic Region of Oplegnathus punctatus Cdkn1/srsf3 for Sex Identification.

Spotted knifejaw (Oplegnathus punctatus) is a marine economic fish with high food and ecological value, and its growth process has obvious male and female sexual dimorphism, with males growing significantly faster than females. However, the current sex identification technology is not yet mature, which will limit the growth rate of O. punctatus aquaculture and the efficiency of separate sex breeding, so the development of efficient sex molecular markers is imperative. This study identified a 926bp DNA insertion fragment in the cdkn1/srsf3 intergenic region of O. punctatus males through whole-genome scanning, comparative genomics, and structural variant analysis. A pair of primers was designed based on the insertion information of the Y chromosome intergenic region in male individuals. Agarose gel electrophoresis revealed the amplification of two DNA fragments, 1118bp and 192bp, in male O. punctatus individuals. The 926bp fragment was identified as the insertion in the intergenic region of cdkn1/srsf3 in males, while only a single 192bp DNA fragment was amplified in females. The biological sex of the individuals identified in this manner was consistent with their known phenotypic sex.In this study, we developed a method to detect DNA insertion variants in the intergenic region of O. punctatus. Additionally, we introduced a new DNA marker for the rapid identification of the sex of O. punctatus, which enhances detection efficiency. The text has important reference significance and application value in sex identification, all-male breeding, and lineage selection. It provides new insights into the regulation of variation in the intergenic region of cdkn1/srsf3 genes and the study of RNA shearing.

Exploration of the application of artificial intelligence in modern agricultural production Take orchard management as an example

In the context of increasing global agricultural challenges, the application of artificial intelligence technology in the agricultural field is increasingly a trend, especially in the production of agricultural products, intelligent identification technology has shown the potential to significantly improve production efficiency and optimize yield and quality. By the mid-21st century, demand for food production is expected to reach 50 percent, and there will be enormous pressure to achieve this goal with traditional agricultural technologies, which could be achieved through the application of artificial intelligence. The application of artificial intelligence technology in modern agricultural production will be analyzed in detail in this paper, the guidance of future research fields will be proposed, and the existing challenges and technical problems will be identified and discussed in order to promote the deepening and wide application of intelligent agriculture. This paper specifically discusses examples of applications in orchard management, pest detection, and automated harvesting and summarizes the effectiveness and obstacles of these techniques.

Calculation of Lateral Logging Response and Environmental Impact Factor Analysis for Small Borehole Array

This paper refines an optimized array lateral logging tool designed for small boreholes, leveraging existing technologies. The tool features four investigation depth curves, and resistivity response curves are derived through finite element model simulations considering variables such as borehole size, mud characteristics, invasion zone features, resistive annuli, formation rock properties, and formation resistivity anisotropy. The findings included the following: (1) Increasing the wellbore diameter uniformly decreased resistivity across all four investigation depths, positively correlating with borehole size. When mud resistivity (Rm) exceeded formation resistivity (Rt), resistivity curves became distorted. (2) For high- and low-invasion models, the ratio of the deepest to the shallowest investigation depth curves ranged from 1 to 8 and 0.6 to 0.9, respectively, with maximum separation at an invasion depth of 0.5–0.8 m. (3) Under invasion conditions with annuli, an invasion zone depth and annulus width around 0.4 m yield well separated the resistivity curves for all depths. Low- and high-resistivity annuli of 2 m and 0.7 m, respectively, can cause curve intersections. (4) When the formation thickness exceeded 0.2 m, the tool accurately reflected formation resistivity variations and demonstrated effective layer identification in multi-layer conditions. (5) In anisotropic formations, resistivity was negatively correlated with the anisotropy coefficient (λ) as it changed from 2 to 4. The instrument can be fully utilized in the exploration of thin interlayers in oil and gas, significantly enhancing the accuracy of resource identification and extraction technologies.

Intelligent warehousing performance management based on Internet of Things and automation technology in the context of green manufacturing

At present, there is a significant imbalance in the development level of warehousing in China, and most enterprises still use traditional material identification technology, resulting in many unnecessary manual operations in the management process, thereby reducing efficiency and causing waste. Therefore, in the context of green manufacturing, we propose an intelligent warehousing performance management solution based on Internet of Things technology and automation technology. By conducting research on the development and research status of the Internet of Things and intelligent warehousing at home and abroad, this paper delves into the various requirements of intelligent warehousing systems and formulates a targeted architecture for this system. Through experiments, it has been proven that the intelligent warehouse performance evaluation model improved by dual technology can effectively improve warehouse management level, reduce enterprise costs, and enhance enterprise efficiency. After in-depth analysis, it is concluded that this method has considerable adequacy and practicality in evaluating the performance management of intelligent warehousing. Therefore, in the context of green manufacturing, the intelligent warehouse performance management system built by adding IoT technology and automation technology has achieved automation and intelligence in performance management evaluation and warehouse entry and exit management, and has extremely high practical value.

Prediction of tight sandstone reservoirs by multiwave joint prestack inversion technology: A case study of the Qiulin area in the Sichuan Basin

The Shaximiao (SXM) Formation of the Middle Triassic in the central Sichuan Basin is a river-lake sedimentary system with an average burial depth of 2800 m. The channel sand bodies of the SXM Formation in the Qiulin area are developed with large lateral variation and high- and medium-porosity sand. This leads to great differences in the seismic response and difficulty in predicting the sand bodies and reservoirs using P-wave data. We carry out well-log analysis for different types of sand bodies. The no. 8 sand body of high porosity can be effectively identified using P-wave impedance (PI). Whereas for the no. 7 sand body of relatively lower porosity (mainly due to the higher shale content in the no. 7 sand compared with the no. 8 sand), sandstone and mudstone can be distinguished using S-wave impedance (SI), and reservoirs can be recognized by the P- to S-wave velocity ratio ([Formula: see text]/[Formula: see text]). Based on the PP wave and the P-to-S converted wave (PS wave) (after matching) angle-stacked data, a prestack inversion of multicomponent data is performed. Multiwave joint inversion results (SI and [Formula: see text]/[Formula: see text]) have better accuracy and stronger stability than the PP-wave inversion in practical application. In addition, the PI of the joint inversion more clearly describes the distribution and boundaries of the channel sand and better matches the prediction and drilling data in sand 8. The SI of the joint inversion can identify subtle sand bodies (weak PI contrast) that are difficult to be detected by PP-wave inversion. The distribution of the reservoir predicted by the [Formula: see text]/[Formula: see text] of the joint inversion is clearer (the no. 7 sand body) and better than that by the PP-wave inversion. This study demonstrates the advantage of the multiwave joint inversion technology in tight sand identification.

Enhanced Indoor Positioning Using RSSI and Time-Distributed Auto Encoder-Gated Recurrent Unit Model.

This study presents a novel approach to indoor positioning leveraging radio frequency identification (RFID) technology based on received signal strength indication (RSSI). The proposed methodology integrates Gaussian Kalman filtering for effective signal preprocessing and a time-distributed auto encoder-gated recurrent unit (TAE-GRU) model for precise location prediction. Addressing the prevalent challenges of low accuracy and extended localization times in current systems, the proposed method significantly enhances the preprocessing of RSSI data and effectively captures the temporal relationships inherent in the data. Experimental validation demonstrates that the proposed approach achieves a 75.9% improvement in localization accuracy over simple neural network methods and markedly enhances the speed of localization, thereby proving its practical applicability in real-world indoor localization scenarios.

Untangling the role of the microbiome across the stages of HIV disease.

The primate microbiome consists of bacteria, eukaryotes, and viruses that dynamically shape and respond to host health and disease. Understanding how the symbiotic relationship between the host and microbiome responds to HIV has implications for therapeutic design. Advances in microbiome identification technologies have expanded our ability to identify constituents of the microbiome and to infer their functional capacity. The dual use of these technologies and animal models has allowed interrogation into the role of the microbiome in lentiviral acquisition, vaccine efficacy, and the response to antiretrovirals. Lessons learned from such studies are now being harnessed to design microbiome-based interventions. Previous studies considering the role of the microbiome in people living with HIV largely described viral acquisition as an intrusion on the host:microbiome interface. Re-framing this view to consider HIV as a novel, albeit unwelcome, component of the microbiome may better inform the research and development of pre and postexposure prophylaxes.

Penetration state recognition for tungsten inert gas welding via an alternating cusp-shaped magnetic field-assisted molten pool-oscillation

To ensure optimal penetration in direct current (DC) argon tungsten arc welding, a method was proposed to recognize the molten pool penetration during molten pool oscillation under alternating cusp-shaped magnetic field (ACSMF). An arc discharge model is established to analyze the oscillation mechanism of the molten pool under ACSMF. The periodic variation of arc shape induces the periodic oscillation to establish a mapping relationship with the fluctuation of arc voltage waveform. At the excitation current of 3 A and frequency of 10 Hz, the arc voltage waveform undergoes abrupt changes at 1.26 V and 1.37 V, corresponding to the critical and the full penetration states, respectively. The errors in identifying moving penetration are 0.8 % and 0.7 %, with a full penetration weld, demonstrating a penetration rate of 100 %, indicating effective penetration recognition. Arc sensing technology for tungsten inert gas (TIG) welding under ACSMF is poised for gradual application in single-side welding and double-side forming of medium and thick plates. It is anticipated to evolve towards real-time identification technology for molten pool penetration monitoring.

Use of Chipless Radio Frequency Identification Technology for Smart Food Packaging: An Economic Analysis for an Australian Seafood Industry

Effective monitoring of perishable food products has become increasingly important for ensuring quality, enabling smart packaging to be a key consideration for food companies. Among the promising technologies available for transforming packaging into intelligent packaging, chipless radio frequency identification (RFID) sensors stand out. Despite the high initial implementation costs associated with chipless RFID technology, the potential benefits could outweigh the costs if electrical challenges can be overcome. We examine various economic methods to analyze the economic benefits of chipless RFID technology, evaluating the benefits of using this technology for the quality monitoring of seafood products of an Australian seafood producer, Tassal. The analysis considers three primary business drivers, viz. quality monitoring, operational efficiency, and tracking and tracing, using net present value and return on investment as the key indicators to assess the feasibility of implementing the technology. Based on sensitivity analysis, we suggest chipless RFID technology is currently best suited for large firms facing significant quality monitoring and operational efficiency challenges. However, as the cost of chipless RFID sensors decreases with further development, this technology may become a more viable option for small businesses in the future.

Determination of Parameters of Radio Frequency Identification Transponder Antennas Dedicated to IoTT Systems Located on Non-Planar Objects

Integration of Radio Frequency Identification (RFID) technology with conductive textiles has greatly expanded the possibilities for creating smart devices that fit perfectly into the concept of the Internet of Things. The use of e-textiles for antenna manufacturing has enabled the development of a textronic RFID tag. Integration of such tags into products with often non-flat surfaces may result in exposure to changes in antenna geometry caused by bending. As a result, the antenna parameters may change, resulting in disruption of the entire tag operation. The authors, through simulation and experimental studies, analyzed the effects of bending the antennas of RFID tags operating in the HF (High Frequency) band.

Research on the application and prospect of RFID technology

As Radio Frequency Identification (RFID) has the advantages of fast scanning speed, small size, large data storage, high security, and other technologies, it is widely used in various fields to upgrade working efficiency. Meanwhile, as one of the research topics of the Internet of Things (IoT), Radio Frequency Identification also provides the possibility for the development and application scope of IoT. Based on the application principle of Radio Frequency Identification technology, this paper discusses the application of Radio Frequency Identification in the two fields of intelligent libraries and intelligent logistics through literature review and theoretical analysis. Through the analysis of the current situation of RFID application in the library management and logistics industry, this paper discusses the advantages and shortcomings of radio frequency identification technology, and according to the existing problems the future direction of development of the corresponding improvement proposals to promote the further improvement of the application of radio frequency identification technology.