Real Ones Research Articles

AUD-Net: A Unified Deep Detector for Multiple Hyperspectral Image Anomaly Detection via Relation and Few-Shot Learning.

This article addresses the problem of the building an out-of-the-box deep detector, motivated by the need to perform anomaly detection across multiple hyperspectral images (HSIs) without repeated training. To solve this challenging task, we propose a unified detector [anomaly detection network (AUD-Net)] inspired by few-shot learning. The crucial issues solved by AUD-Net include: how to improve the generalization of the model on various HSIs that contain different categories of land cover; and how to unify the different spectral sizes between HSIs. To achieve this, we first build a series of subtasks to classify the relations between the center and its surroundings in the dual window. Through relation learning, AUD-Net can be more easily generalized to unseen HSIs, as the relations of the pixel pairs are shared among different HSIs. Secondly, to handle different HSIs with various spectral sizes, we propose a pooling layer based on the vector of local aggregated descriptors, which maps the variable-sized features to the same space and acquires the fixed-sized relation embeddings. To determine whether the center of the dual window is an anomaly, we build a memory model by the transformer, which integrates the contextual relation embeddings in the dual window and estimates the relation embeddings of the center. By computing the feature difference between the estimated relation embeddings of the centers and the corresponding real ones, the centers with large differences will be detected as anomalies, as they are more difficult to be estimated by the corresponding surroundings. Extensive experiments on both the simulation dataset and 13 real HSIs demonstrate that this proposed AUD-Net has strong generalization for various HSIs and achieves significant advantages over the specific-trained detectors for each HSI.

Digital Image Authenticity Assessment Using Deep Learning

Its super important to find fake pictures online to make sure things are true so we came up with a smart idea using something called a convolutional neural network, CNN is like a really smart detective for pictures. It checks out lots of pictures, some real and some fake and learns how to tell them apart by looking at all the tiny details Before the detective work, we make all the pictures the same size, like putting them in the same-sized frame We also use a special tool called error level analysis (Ela). Ela helps us by showing parts of the pictures that might have been changed its like searching for clues in a detective movie We looked at a bunch of pictures, over 12,000 of them We made sure to have a mix of real ones like trees and people 7492 of them and some that were changed to trick people, 5123 of them this way, our detective could learn from lots of different situations our system is really good at finding fake pictures because it uses fancy math and clever techniques We tested it a lot to make sure it works in different situations, like when someone copies part of a picture or changes how it looks and guess what? Our tests showed that our system is great at finding fakes In the end, our idea helps make sure pictures online are real, which is super important in today’s world of digital pictures.

ОСОБЕННОСТИ ОЦЕНКИ ВЕРОЯТНОСТИ ОБНАРУЖЕНИЯ ПОЖАРА АВТОМАТИЧЕСКИМИ ПОЖАРНЫМИ ИЗВЕЩАТЕЛЯМИ

The purpose of this work is to draw the attention of fire automation specialists to the issue of the lack of a methodology for assessing the probability of timely detection of a fire by automatic fire detectors. At the same time, in regulatory documents on the calculation of fire risks at protection facilities, this parameter appears under the names «probability of effective operation» and «coefficient that takes into account the compliance of the fire alarm system with the requirements of regulatory documents on fire safety». At the same time, their values are fixed without a comprehensive analysis of statistical data on the operation of fire alarm systems on fires and without taking into account the impact of the service life of automatic fire detectors included in the system on the threshold of their operation. With this approach, the calculated values of fire risk values may differ significantly from the real ones. Therefore, the issue of the correct assessment of the probability of a timely fire by automatic fire detectors, and consequently, the fire alarm system formed by them, is relevant and requires a solution. The paper proposes to assess the probability of timely detection of fires by fire alarm systems based on a detailed analysis of statistical data on their work on fires, published annually in the statistical collections of Russian scientific research institute of fire protection of EMERCOM of Russia. In order to be able to conduct a detailed analysis, it is proposed to increase the volume of statistical data provided.

Rendimiento de remolacha azucarera bajo riego por goteo con ecuación de Penman y modelo AquaCrop

It is necessary to estimate sugar beet yield, because studies with this crop demonstrated than in Peruvian coastal zone, could be a profitable crop. The objective of the present experiment was to know if dry matter yield of sugar beet is related with Penman’s equation, or FAO’s AquaCrop model. Experiment was made in a sandy soil, non-salty, calcareous, very poor in organic matter, with drip irrigation in Peruvian northern coast. Four treatments: two, three, four and five plant rows per irrigation drip line, in a completely random design, with four replications were utilized. Calculated fresh matter weighs with AquaCrop were between 15.5 and 24.5 Mg.ha-1, very much lesser to real ones (between 67.5 and 103.9 Mg.ha-1) hence Aqua Crop model is not effective to estimate yield of sugar beet. It is possible to estimate yield of sugar beet, with Penman’s formula, which varied between 11.40 and 27.96 Mg.ha-1 dry weight, and the real one was between 13.4 and 21.5 Mg.ha-1, with a "Root Mean Square Error" (RMSE) of 3.73.

A High-Quality Sample Generation Method for Improving Steel Surface Defect Inspection.

Defect inspection is a critical task in ensuring the surface quality of steel plates. Deep neural networks have the potential to achieve excellent inspection accuracy if defect samples are sufficient. Nevertheless, it is very different to collect enough samples using cameras alone. To a certain extent, generative models can alleviate this problem but poor sample quality can greatly affect the final inspection performance. A sample generation method, which employs a generative adversarial network (GAN), is proposed to generate high-quality defect samples for training accurate inspection models. To improve generation quality, we propose a production-and-elimination, two-stage sample generation process by simulating the formation of defects on the surface of steel plates. The production stage learns to generate defects on defect-free background samples, and the elimination stage learns to erase defects on defective samples. By minimizing the differences between the samples at both stages, the proposed model can make generated background samples close to real ones while guiding the generated defect samples to be more realistic. Experimental results show that the proposed method has the ability to generate high-quality samples that can help train powerful inspection models and thereby improve inspection performance.

Generative data augmentation by conditional inpainting for multi-class object detection in infrared images

Multi-class object detection in infrared images is important in military and civilian use. Deep learning methods can obtain high accuracy but require a large-scale dataset. We propose a generative data augmentation framework DOCI-GAN, for infrared multi-class object detection with limited data. Contributions of this paper are four-folds. Firstly, DOCI-GAN is designed as a conditional image inpainting framework, yielding paired infrared multi-class object image and annotation. Secondly, a text-to-image converter is formulated to transform text-format object annotations to bounding box mask images, leading the augmentation to be mask-image-to-raw-image translation. Thirdly, a multiscale morphological erosion-based loss is created to alleviate the intensity inconsistency between inpainted local backgrounds and global background. Finally, for generating diverse images, artificial multi-class object annotations are integrated with real ones during augmentation. Experimental results demonstrated that DOCI-GAN augments dataset with high-quality infrared multi-class object images, consequently improving the accuracy of object detection baselines.

Surface-Enhanced Raman Spectroscopy (SERS) for Identifying Traces of Adenine in Organic-Bearing Extraterrestrial Dust Analogs Captured in the Tanpopo Aerogel after Hypervelocity Impacts.

Raman spectroscopy is a non-destructive analytical technique for characterizing organic and inorganic materials with spatial resolution in the micrometer range. This makes it a method of choice for space-mission sample characterization, whether on return or in situ. To enhance its sensitivity, we use signal amplification via interaction with plasmonic silver-based colloids, which corresponds to surface-enhanced Raman scattering (SERS). In this study, we focus on the analysis of biomolecules of prebiotic interest on extraterrestrial dust trapped in silica aerogel, jointly with the Japanese Tanpopo mission. The aim is twofold: to prepare samples as close as possible to the real ones, and to optimize analysis by SERS for this specific context. Serpentinite was chosen as the inorganic matrix and adenine as the target biomolecule. The dust was projected at high velocity into the trapping aerogel and then mechanically extracted. A quantitative study shows effective detection even for adenine doping from a 5·10-9mol/L solution. After the dust has been expelled from the aerogel using a solvent, SERS mapping enables unambiguous adenine detection over the entire dust surface. This study shows the potential of SERS as a key technique not only for return samples, but also for upcoming new explorations.

Syntax, vocabulary, phraseology: Aspects of correlation and interaction

This article raises the issues of using an integrative approach with respect to the study of language units, the problems of interaction of syntax, vocabulary and phraseology, and their interpenetration and contact within the framework of the semantic structure of the language as a functioning system. We also consider syntactic units that are in the zone of abstract meanings that ensure the integrity and vital activity of the language. The diachronic aspect of the coverage of the questions posed contributed to the identification of two processes – grammaticalization and lexicalization, which stimulate mutual transitions and borderline positions between principal and auxiliary parts, predicative and nominative parts, mono and polysemantic parts, as well as stable and instable parts in the sentence. The syntactic phraseomodels, analyzed in the article, are frequent in the sphere of hypotaxis when expressing adversarial-concessional, temporal and causal relations. It is especially important that the language has the integrativity of abstract vocabulary and relational semantics, designed to cement and structure speech activity. The syntactic phraseomodels under consideration complicate relational semantics with modal or expressive meanings. The modal component is usually realized through the vocabulary of anthropocentric content, covering the entire spectrum of human speech-psychomental activity, it is represented by separate semantic fields and lexical-semantic groups. Within the framework of expressive contexts, as essential elements are the lexical content of pretexts and the presence of emotive components in their composition. In these phrases, one can see a cause-and-effect relationship between two propositions, the real and potential ones in the subordinate part, although such models often move into the sphere of intensity semantics and the zone of emotiveness. The syntactic phraseomodels under consideration and those of them that have acquired a stable appearance are prone to parceling, budding from the base part and functioning more autonomously in the text. Thus, semantic-syntactic relations interact with abstract vocabulary and have a certain range of emotional-evaluative and modal meanings.

Review Paper on Deepfake Video Detection using Neural Networks

With the increasing computational power, the creation of indistinguishable human synthesized videos, known as deepfakes, has become remarkably easy. These realistic face-swapped deepfakes have raised concerns as they can be utilized for malicious purposes such as causing political unrest, fabricating terrorism events, spreading revenge porn, and blackmailing individuals. In this research, we present a novel deep learning-based method that effectively distinguishes AI-generated fake videos from real ones. Our approach focuses specifically on detecting replacement and reenactment deepfakes. We harness the power of Artificial Intelligence (AI) to combat the challenges posed by AI itself. The core of our system lies in a ResNext Convolutional Neural Network, which extracts frame-level features. These features are then used to train a Long Short-Term Memory (LSTM)-based Recurrent Neural Network (RNN) that classifies videos as either manipulated (deepfake) or authentic (real).To ensure real-time applicability and enhance the model's performance on real-world data, we evaluate our method using a large and balanced dataset

Jordanian banknote data recognition: A CNN-based approach with attention mechanism

Identifying counterfeit banknotes is crucial in financial transactions, as the process of identification cannot be handled by ATMs or vending machines. The recent developments in technology, particularly the smart systems that are integrated with cameras and artificial intelligence (AI) tools, allow for the distinction of currency and the detection of counterfeit. In this study, we are suggesting an approach for identifying counterfeit Jordanian banknotes and differentiating them from genuine ones. The suggested approach collaborates deep learning through a convolutional neural network (CNN) and another attention mechanism which contributes to focusing on features of importance while avoiding features of less importance. The proposed model has proven its ability to recognize counterfeits with high performance and accuracy while focusing on the important features extracted. The study made use of a data set from Kaggle that includes a collection of Jordanian banknotes in five different denominations. Image processing techniques were employed to produce artificial images by boosting the brightness of real ones. Eight trained models and the suggested model were compared. It demonstrated excellence with encouraging outcomes, achieving 96% accuracy, 96.6% precision, 96.4% recall, and 94.5% f1-score. Also, we tested our approach on two datasets Indian dataset and DS1, DS2, and DS3 datasets, we obtained 88% and 99.9% accuracy, respectively. The achievement of detecting counterfeit Jordanian banknotes is proof that a well-established AI model contributes to dealing with security vulnerabilities in many institutions.

Developing an Augmented Reality-Based Textbook on Heat and Transfer Materials to Improve Students Critical Thinking Skills

The Society 5.0 era necessitates that society address problems by harnessing information technology. Augmented Reality, one of the information technologies utilized in the education sector, presents virtual objects alongside real ones in a three-dimensional format, allowing for observation, interaction, and auditory engagement. Heat and transfer materials can be simulated and applied in the form of 3D objects and animations, facilitating direct student interaction and providing a captivating and distinctive learning experience. The objective of this research is to create an Augmented Reality-based textbook on heat and transfer material to enhance the critical thinking skills of junior high school students. This Research & Development used the ADDIE model including analyze, design, develop, implement and evaluate steps. Based on the results, augmented reality-based textbook is highly valid, practical, and effective in showcasing an improvement in the critical thinking skills of junior high school students, with the observed increase falling within the high category, specifically at 0.71

The progressive pilgrim: Real and mythical Indian geography in contemporary retellings of the Rāmāyaṇa

AbstractSeveral English‐language adaptations of the Indian epic Rāmāyaṇa have been published since the beginning of the 21st century. The epic has been regarded and recreated as a metonym for the Indian nation. Contemporary versions have often referred to Indian geography and have tried to poetically or literally associate mythic spaces with real ones. In this paper, I use discourse analysis in order to study some of the most influential 21st‐century English‐language retellings of the Rāmāyaṇa. I conclude that these and other versions of the epic describe India as a regionally divided nation which can ultimately be united through national geography, its association with mythology and the contrast between the geography of India and that of foreign nations. In this sense, I regard these contemporary versions as a ‘literary pilgrimage’ through which Indian readers can get to know the geography of their nation and regard it as sacred.

CutFreq: Cut-and-Swap Frequency Components for Low-Level Vision Augmentation

Low-level vision plays a crucial role in a wide range of imaging quality and image recognition applications. However, the limited size, quality, and diversity of datasets often pose significant challenges for low-level tasks. Data augmentation is the most effective and practical way of sample expansion, but the commonly used augmentation methods in high-level tasks have limited improvement in the low-level due to the boundary effects or the non-realistic context information. In this paper, we propose the Cut-and-Swap Frequency Components (CutFreq) method for low-level vision, which aims to preserve high-level representations with directionality and improve image synthesis quality. Observing the significant frequency domain differences between reconstructed images and real ones, in CutFreq, we propose to transform the input and real images separately in the frequency domain, then define two stages for the model training process, and finally swap the specified frequency bands respectively and inversely transform to generate augmented samples. The experimental results show the superior performance of CutFreq on five low-level vision tasks. Moreover, we demonstrate the effectiveness of CutFreq in the low-data regime. Code is available at https://github.com/DreamerCCC/CutFreq.

Improving Cross-Modal Alignment with Synthetic Pairs for Text-Only Image Captioning

Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the CLIP's cross-modal association ability for image captioning, relying solely on textual information under unsupervised settings. However, not only does a modality gap exist between CLIP text and image features, but a discrepancy also arises between training and inference due to the unavailability of real-world images, which hinders the cross-modal alignment in text-only captioning. This paper proposes a novel method to address these issues by incorporating synthetic image-text pairs. A pre-trained text-to-image model is deployed to obtain images that correspond to textual data, and the pseudo features of generated images are optimized toward the real ones in the CLIP embedding space. Furthermore, textual information is gathered to represent image features, resulting in the image features with various semantics and the bridged modality gap. To unify training and inference, synthetic image features would serve as the training prefix for the language decoder, while real images are used for inference. Additionally, salient objects in images are detected as assistance to enhance the learning of modality alignment. Experimental results demonstrate that our method obtains the state-of-the-art performance on benchmark datasets.

Detection of Image Tampering Using Deep Learning, Error Levels and Noise Residuals

Images once were considered a reliable source of information. However, when photo-editing software started to get noticed it gave rise to illegal activities which is called image tampering. These days we can come across innumerable tampered images across the internet. Software such as Photoshop, GNU Image Manipulation Program, etc. are applied to form tampered images from real ones in just a few minutes. To discover hidden signs of tampering in an image deep learning models are an effective tool than any other methods. Models used in deep learning are capable of extracting intricate features from an image automatically. Here we proposed a combination of traditional handcrafted features along with a deep learning model to differentiate between authentic and tampered images. We have presented a dual-branch Convolutional Neural Network in conjunction with Error Level Analysis and noise residuals from Spatial Rich Model. For our experiment, we utilized the freely accessible CASIA dataset. After training the dual-branch network for 16 epochs, it generated an accuracy of 98.55%. We have also provided a comparative analysis with other previously proposed work in the field of image forgery detection. This hybrid approach proves that deep learning models along with some well-known traditional approaches can provide better results for detecting tampered images.

Donors’ Participation the Health System: A Double-Edged Sword

The presence of donors in health system, despite its positive results, can also have weaknesses that sometimes act as a double-edged sword in achieving health priorities. In some cases, the needs are considered by donors as unnecessarily the real ones in health system. On the other hand; sometimes, benevolent actions are involved in political intentions and pressures.
 In order to eliminate deficiencies, it is necessary to comply with standards, priorities, and real needs of health system in any field. What helps this alignment and action towards goals is using the capacity of scientific evidence. With the help of scientific evidence, the real needs of health sector can be identified and prioritized, and the capacity of donors can be used to meet those needs. Moreover, reforming and re-engineering the processes of benefactors' activities in the field of health, directing benefactors' aid, developing rules and standards, and creating transparency in costs for inter-sectoral coordination are solutions that will help to improve the conditions about this issue.

Open-top Bessel beam two-photon light sheet microscopy for three-dimensional pathology

Nondestructive pathology based on three-dimensional (3D) optical microscopy holds promise as a complement to traditional destructive hematoxylin and eosin (H&E) stained slide-based pathology by providing cellular information in high throughput manner. However, conventional techniques provided superficial information only due to shallow imaging depths. Herein, we developed open-top two-photon light sheet microscopy (OT-TP-LSM) for intraoperative 3D pathology. An extended depth of field two-photon excitation light sheet was generated by scanning a nondiffractive Bessel beam, and selective planar imaging was conducted with cameras at 400 frames/s max during the lateral translation of tissue specimens. Intrinsic second harmonic generation was collected for additional extracellular matrix (ECM) visualization. OT-TP-LSM was tested in various human cancer specimens including skin, pancreas, and prostate. High imaging depths were achieved owing to long excitation wavelengths and long wavelength fluorophores. 3D visualization of both cells and ECM enhanced the ability of cancer detection. Furthermore, an unsupervised deep learning network was employed for the style transfer of OT-TP-LSM images to virtual H&E images. The virtual H&E images exhibited comparable histological characteristics to real ones. OT-TP-LSM may have the potential for histopathological examination in surgical and biopsy applications by rapidly providing 3D information.

Open-top Bessel beam two-photon light sheet microscopy for three-dimensional pathology.

Nondestructive pathology based on three-dimensional (3D) optical microscopy holds promise as a complement to traditional destructive hematoxylin and eosin (H&E) stained slide-based pathology by providing cellular information in high throughput manner. However, conventional techniques provided superficial information only due to shallow imaging depths. Herein, we developed open-top two-photon light sheet microscopy (OT-TP-LSM) for intraoperative 3D pathology. An extended depth of field two-photon excitation light sheet was generated by scanning a nondiffractive Bessel beam, and selective planar imaging was conducted with cameras at 400 frames/s max during the lateral translation of tissue specimens. Intrinsic second harmonic generation was collected for additional extracellular matrix (ECM) visualization. OT-TP-LSM was tested in various human cancer specimens including skin, pancreas, and prostate. High imaging depths were achieved owing to long excitation wavelengths and long wavelength fluorophores. 3D visualization of both cells and ECM enhanced the ability of cancer detection. Furthermore, an unsupervised deep learning network was employed for the style transfer of OT-TP-LSM images to virtual H&E images. The virtual H&E images exhibited comparable histological characteristics to real ones. OT-TP-LSM may have the potential for histopathological examination in surgical and biopsy applications by rapidly providing 3D information.

TRANSMISSION BELTS PERFORMANCE IN NORMAL AND HEAVY-DUTY CONDITIONS

The main purpose of this article was to study the behavior of vehicle transmission belts in conditions similar to real ones, which can appear during their use. Transmission belts can be classified into several categories, but depending on their function, can be belts that work in dry conditions or immersed in oil. In this study, were analyzed both types of transmission belts. The samples were subject to different physical-mechanical tests: determination of hardness, density, thickness, abrasion, flex resistance, tensile strength and percentage extension and also to various conditions like, high and low temperature, immersion in liquids (oil, toluene, diesel). All the tests were performed before and after exposure, according to actual standards in ICPI accredited laboratory. Microscopy studies were done before and after the exposure to various factors, in order to appreciate the damage degree. Also, chemical specific analyses were made for determining the transmission belts composition. The findings from this study provide important insights into the behavior of transmission belts under different operating conditions.

RF Energy Harvesting

This article presents research on the usefulness of three different electric circuit simulation environments for exploring energy harvesting from electromagnetic waves using energy harvesters. The software that is compared includes KiCad EDA, LT Spice and MATLAB Simscape Electrical.Too prepare a common background for the results comparison, crucial equations that combine RF transmission with energy are presented. Commercially available harvesters are also presented. An overview of the state-of-the-art research on this topic is summarised. In order to verify software using conditions that are similar to real ones, the power available at the 868 MHZ ISM band, which is close to the LTE bands used for telecommunications, is calculated. The results obtained using different software are close to being identical for all tested simulation environments.