CAPTCHA Research Articles

A Video-Based Augmented Reality System for Human-in-the-Loop Muscle Strength Assessment of Juvenile Dermatomyositis.

As the most common idiopathic inflammatory myopathy in children, juvenile dermatomyositis (JDM) is characterized by skin rashes and muscle weakness. The childhood myositis assessment scale (CMAS) is commonly used to measure the degree of muscle involvement for diagnosis or rehabilitation monitoring. On the one hand, human diagnosis is not scalable and may be subject to personal bias. On the other hand, automatic action quality assessment (AQA) algorithms cannot guarantee 100% accuracy, making them not suitable for biomedical applications. As a solution, we propose a video-based augmented reality system for human-in-the-loop muscle strength assessment of children with JDM. We first propose an AQA algorithm for muscle strength assessment of JDM using contrastive regression trained by a JDM dataset. Our core insight is to visualize the AQA results as a virtual character facilitated by a 3D animation dataset, so that users can compare the real-world patient and the virtual character to understand and verify the AQA results. To allow effective comparisons, we propose a video-based augmented reality system. Given a feed, we adapt computer vision algorithms for scene understanding, evaluate the optimal way of augmenting the virtual character into the scene, and highlight important parts for effective human verification. The experimental results confirm the effectiveness of our AQA algorithm, and the results of the user study demonstrate that humans can more accurately and quickly assess the muscle strength of children using our system.

Click and Session based Captcha as Graphical Password Authentication Process using AI Technology

Abstract: Graphical passwords, two-factor authentication, and other ways are just a few of the many options we have for authentication. Text based protection. Codes are susceptible to a variety of assaults, including dictionary attacks. As a result, as part of the authentication procedure, in addition to the usual alpha-numeric password, we also utilise pictures with captchas. It also fixes the problems with the pass points of graphical password systems. Automated Turing Test for Computers and Humans that Is Completely Public (CAPTCHA) Users who have successfully authenticated must pass a test in order to access their individual mail accounts. Accounts that put the secrecy, reliability, and privacy of data at risk are attacked by bots and other malicious software. This was stopped by the invention of CAPTCHA.

METHOD OF FACIAL SKIN REJUVENATION USING ELECTROSTIMULATION

Objectives: Purpose of the study evaluation of the cosmetic effect using patches by the company “Aganyan” for facial rejuvenation. Materials and Methods: The study was carried out in 106 participants with presence of perioral wrinkles of the skin. Participants applied four patches (2 copper and 2 zinc) on the face in the area of wrinkles crosswise according to the instructions. The patches were applied for eight hours every third day for three months. Perioral wrinkles were assessed by comparing photographs at the beginning and at the end of the study for each individual case. The efficacy was assessed according to the International Global Aesthetic Improvement Scale (GAIS). Visual confirmation of clinical improvement was also obtained by Life Viz 3D camera pictures. Results: After analyzing the photographs taken before and after using the patch and a personal conversation with each participant, the following data were obtained from participants: • a decrease in puffiness and dark circles under the eyes was noted: 6 out of 15 men, 34 out of 91 women; • smoothing of small mimic wrinkles was noted: 24 women out of 106 people; • lifting of the face oval was noted: 14 women out of 106 people. Evaluation of the effectiveness of the GAIS procedure on M03 and M05, 2/3 of patients had significant mprovement as assessed by physician and participants according to GAIS. Most of the patients also showed significant improvement at visit M12. After analyzing the photographs taken before and after the experiment, and a personal conversation with each patient of the cosmetology profile, the following results were obtained: in 38% of patients, puffiness and dark circles under the eyes decreased, in 23% of participants fine facial wrinkles were smoothed, in 12% of participants the oval of the face was tightened. Our results suggest that patches by the company “Aganyan” can serve as a novel therapy for controlled skin rejuvenation, effective wrinkles and folds. Conclusion: The results of the studies provide a basis for concluding that the method of skin. The patches by the company “Aganyan” have proven its effectiveness through electrical stimulation with low intensity current in patients in different age groups, the study revealed a large number of positive cosmetic effects.

Osyp Kurylas’s Art Heritage: Battle Genre

The purpose of the article is to analyse the combat work by Osyp Kurylas in the ranks of the Ukrainian Sich Riflemen. The research methodology is based on the principles of historicism, impartiality, and reliability of the presented results, as well as on general scientific and special research methods, including analysis, synthesis, generalisation, descriptive, systematic, and biographical. According to the dominant in post-classical science paradigm of systematicity, they are integrated from different scientific directions, namely from art history, cultural studies, and history. Such an interdisciplinary methodology helped to reveal the main theme and value-meaning constants of the combat creativity by O. Kurylas in the ranks of the Ukrainian Sich Riflemen. The scientific novelty of the research consists in the cultural-historical and art-historical analysis of O. Kurylas's combat work, which significantly expands the understanding of his work and determines the relevance of his artistic heritage for modern art in the direction of increasing interest in combat fine art. Conclusions. Osyp Kurilas and his fellow artists made an invaluable contribution to the development of fine art, in particular, to battle painting and the portrait genre. The battle legacy of O. Kurylas (graphics, painting) is not just works of fine art, but also invaluable historical and documentary material. Due to the realism, the combat work by O. Kurilas, like other Sich artists, can be called a kind of documentary recording of the events of the Liberation Struggle period, which in terms of truthfulness, scrupulousness, and accuracy of the images can be put on the same level as modern photography. Their work is of great importance not only for preserving the memory of those who died for the will of Ukraine, but also serves as a visual confirmation of the courage, indomitability, and eternal desire of our people to build an independent Ukraine.
 Key words: Osyp Kurilas, battle genre, painting, fine art, Ukrainian Sich Riflemen.

COMMANDFENCE FOR SECURING SMART HOME SYSTEM

The smart home system has become increasingly popular due to its convenience and security benefits. The advantages of the smart home system in terms of convenience and security have made it more and more popular. It is, nevertheless, vulnerable to security lapses and cyberattacks.In this article, we suggest a method for protecting a smart home system using PIR sensor, Node MCU, Arduino Uno, LCD screen, buzzer, and Telegram software are all included. The suggested system is made to recognize and react to potential security concerns like infiltration, unauthorized access, and motion detection. The NodeMCU board receives a signal when the PIR sensor detects motion. The ESP32-CAM module and the Node MCU board then communicate in order to take photos, which are subsequently sent to the user's Telegram account for visual confirmation. Additionally, the system has an LCD display and a buzzer to offer Keywords- IOT (Internet of Things),Arduino,ESP8266,

Abstract 5326: Comparison of CAR-T cell-mediated cytotoxicity assays with suspension tumor cells using high-throughput plate-based image cytometry method

Abstract In the recent decade, chimeric antigen receptor (CAR)-T cell therapy has revolutionized strategies for cancer treatments due to its highly effective clinical efficacy and response for B cell malignancies. Currently, there are six CAR-T cell products available in the market including Kymriah, Yescarta, Tecartus, Breyanzi, Abecma, and Carvykt. The success of CAR-T cell therapy has stimulated the increase in the research and development of various CAR constructs to target different tumor types. Therefore, a robust and efficient in vitro potency assay is needed to quickly identify potential CAR gene design from a library of construct candidates. Traditionally, in vitro CAR-T cell-mediated cytotoxicity is assessed using release assays such as 51Cr (radioactivity), calcein (fluorescence), and LDH (enzymatic). However, release assays indirectly measure cell death via molecules released in supernatant and typically limited to only endpoint assays. In addition, handling and disposing of 51Cr hazardous materials is less preferred. Luciferase reporter assay, although highly sensitive, has similar drawbacks as the release assays. Finally, flow cytometry method can directly measure cell death and viability, but can be time-consuming and requires a large number of CAR-T cells when the effector-to-target (E:T) ratio is high. Furthermore, additional steps are required for adherent cells that require trypsinization. Image cytometry methodologies have been utilized for various CAR-T cell-mediated cytotoxicity assay using different fluorescent labeling methods, mainly due to their ease-of-use, ability to capture cell images for verification, and higher throughput performance. In this work, we employed the Celigo high-throughput plate-based Image Cytometer to evaluate and compare two CAR-T cell-mediated cytotoxicity assays using GFP-expressing or fluorescent dye-labeled myeloma and plasmacytoma cells. Performing time- and E:T ratio-dependent CAR-T cell-mediated cytotoxicity assays, the GFP-based method demonstrated higher sensitivity in detecting the level of cytotoxicity when compared to the CMFDA/DAPI viability method. We have established the criteria and considerations for the selection of cytotoxicity assays that are fit-for-purpose to ensure the results produced are meaningful for the specific testing conditions. Citation Format: Leo Li-Ying Chan, Yu-Jun Sun, Yi-Chun Chen, Wei-Kai Hua, Sariena Chiung-Yuan Wu. Comparison of CAR-T cell-mediated cytotoxicity assays with suspension tumor cells using high-throughput plate-based image cytometry method. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5326.

Potential margin reduction in prostate cancer proton therapy with prompt gamma imaging for online treatment verification.

The potential of proton therapy is currently limited due to large safety margins. We estimated the potential reduction of clinical margins when using prompt gamma imaging (PGI) for online treatment verification of prostate cancer. For two adaptive scenarios a potential reduction relative to clinical practice was evaluated. The use of a trolley-mounted PGI system for online treatment verification to trigger an adaptation reduced the current range margins from 7mm to 3mm. In a case example, the dose reduction due to reduced range margins was substantially larger compared to reduced setup margins when using pre-treatment volumetric imaging.

An evaluation of isocentre shift magnitude and treatment site on image-guided radiation therapy online decision analysis times.

The ability to capture more anatomical detail in cone-beam computed tomography (CBCT) imaging compared to kilovoltage (kV) and megavoltage (MV) imaging, has seen a documented shift towards CBCT image verification and staff adopting more extensive image analysis processes. The timeframe associated with assessing online CBCT images, termed the online decision analysis time, if drawn out, can affect treatment efficiency and accuracy. This study aimed to determine the current CBCT online decision analysis time at Radiation Oncology Princess Alexandra Ipswich Road (ROPAIR) and investigate the influence of isocentre shift magnitude and treatment site considerations on this timeframe. This retrospective clinical audit collected treatment parameters from 202 CBCT images over 2 treatment days. The online decision analysis time was calculated by subtracting the image acquisition timestamp from the image verification shift application timestamp. The quantitative data were analysed using mean, standard deviation, and range in the following categories: all CBCTs, CBCTs grouped by isocentre shift magnitude and CBCTs grouped by treatment site. Content analysis was performed on staff comments made during image analysis. The average online decision analysis time was 2:37 ± 1:28 min. On average approximately, head and neck, spine and extremity treatment sites measured 1 min, pelvis, breast, and chest measured 2-3 min with abdomen measuring 4 min. Common categories reported in staff comments included anatomical changes, repositioning, and organs at risk size. The results provide baseline online decision analysis times. Further refinement is required to determine if the image match method, treatment site considerations, and rotational discrepancies influence this timeframe.

Robust Watermarking Techniques for the Authentication and Copyright Protection of Digital Images: A Survey

Digital image authentication and security are crucial concerns for the digital revolution since any image may be readily tampered with. Digital watermarking schemes were since been utilized to tackle a range of problems over time and involving the verification of digital images and copyright protection. In a real-world setting, watermarked contents are frequently subject to a succession of assaults which makes it necessary to strike a balance between resilience and imperceptibility in the face of attacks. There are numerous hazards to this, and numerous watermarking techniques have been created to counter them. Data with less perceptual distortion should be able to be included in a real watermarking technique in addition to restoring the original cover content. As a result, robustness, imperceptibility, and security are three crucial criteria for digital content'sauthentication and copyrightpreservation. This study therefore presents a careful review of some cutting-edge watermarking technologies used for copyright protection and authentication so as to identify their strengths and limitations. For clarity, this study shall explain some basic concepts of digital watermarking as well as the various forms of attacks on watermarks. The contributions from this work will be useful to researchers aim at developing efficient watermarking techniques

Management of the Bone Deformity Caused by Congenital Cyst of the Periorbital Area: Analysis of the Surgical Technique and a Short-term Outcome

The congenital periorbital cysts like dermoids/epidermoids, in rare cases, can require not only its’ excision but also correction/camouflage of the caused bone deformity. This management can require virtual surgical planning, osteotomy, and placement of the custom-made patient implant. In this report, the ultrasonography (USG) was proved as a highly effective imaging for the presurgical verification of the mass’s structure and establishment of the clinical diagnosis. The multi-slice computed tomography (MSCT), even on a two-slice MSCT machine, provided high-quality three-dimensional reconstruction of the area of bone deformation caused by the cyst and allowed for accurate surgical planning. A 20-year-old male patient with a congenital periorbital epidermoid cyst that led to the deformation of the lateral orbital rim was treated using the soft tissue volume-increasing technique for the correction of bone deformation following cyst removal. Analysis of the terminological diversity related with dermoid/epidermoid cysts is presented. Early diagnostics and management of congenital periorbital cysts can decrease the visual, orbital, and esthetic complications, as well as the need to perform bone reconstructive surgeries or other corrective surgical procedures.

Digital Image Identification and Verification Using Maximum and Preliminary Score Approach with Watermarking for Security and Validation Enhancement

Digital face approaches possess currently received awesome attention because of their huge wide variety of digital audio, and visual programs. Digitized snapshots are progressively more communicated using an un-relaxed medium together with cyberspace. Consequently, defence, clinical, medical, and exceptional supervised photographs are essentially blanketed towards trying to employ it; such controls ought to damage such choices constructed totally based on those pictures. So, to shield the originality of digital audio/visual snapshots, several approaches proposed. Such techniques incorporate traditional encoding, breakable and nominal breakable watermarking with virtual impressions which are based upon the material of image content. Over the last few decades, various holistic approaches are proposed for improving image identification and verification. In this paper, a combination of both the feature level and score level of different techniques were used. Image is one of the identities of a person which reflects its emotions, feeling, age etc. which also helps to gather an information about a person without knowing their name, caste, and age and this could be not of much importance when it is used for domestic or framing applications. To secure the originality of digital audio/visual impressions many methods come into pictures and are proposed which include digital signatures, watermarking, cryptography, and fragile depend upon face contents. The objective of this research article is to identify & verify real-time video images using feature and score levels using watermarking that will help to judge the authenticity of any images at the initial stage by extracting the features which are evaluated by following an algorithm known as Viterbi and where input data is changed initially into an embedded treat or state then the matrix is evaluated of achieved transformation and on this basis preliminary score estimation will be generated after many iterations for each image that will help in validation. Finally, the tested image will be verified using several approaches to protect and provide security to the original image being verified. This approach may be useful for different surveillance applications for real-time image identification and verification. Also, measurement of accuracy was done by reconfiguring the HMM to identify the constant segmentation and feature removal of the image was settled by initializing parameters and teaching the image feature using the algorithm “Viterbi”.

Deep learning-based fast volumetric imaging using kV and MV projection images for lung cancer radiotherapy: A feasibility study.

The long acquisition time of CBCT discourages repeat verification imaging, therefore increasing treatment uncertainty. In this study, we present a fast volumetric imaging method for lung cancer radiation therapy using an orthogonal 2D kV/MV image pair. The proposed model is a combination of 2D and 3D networks. The proposed model consists of five major parts: (1) kV and MV feature extractors are used to extract deep features from the perpendicular kV and MV projections. (2) The feature-matching step is used to re-align the feature maps to their projection angle in a Cartesian coordinate system. By using a residual module, the feature map can focus more on the difference between the estimated and ground truth images. (3) In addition, the feature map is downsized to include more global semantic information for the 3D estimation, which is useful to reduce inhomogeneity. By using convolution-based reweighting, the model is able to further increase the uniformity of image. (4) To reduce the blurry noise of generated 3D volume, the Laplacian latent space loss calculated via the feature map that is extracted via specifically-learned Gaussian kernel is used to supervise the network. (5) Finally, the 3D volume is derived from the trained model. We conducted a proof-of-concept study using 50 patients with lung cancer. An orthogonal kV/MV pair was generated by ray tracing through CT of each phase in a 4D CT scan. Orthogonal kV/MV pairs from nine respiratory phases were used to train this patient-specific model while the kV/MV pair of the remaining phase was held for model testing. The results are based on simulation data and phantom results from a real Linac system. The mean absolute error (MAE) values achieved by our method were 57.5 HU and 77.4 HU within body and tumor region-of-interest (ROI), respectively. The mean achieved peak-signal-to-noise ratios (PSNR) were 27.6dB and 19.2dB within the body and tumor ROI, respectively. The achieved mean normalized cross correlation (NCC) values were 0.97 and 0.94 within the body and tumor ROI, respectively. A phantom study demonstrated that the proposed method can accurately re-position the phantom after shift. It is also shown that the proposed method using both kV and MV is superior to current method using kV or MV only in image quality. These results demonstrate the feasibility and accuracy of our proposed fast volumetric imaging method from an orthogonal kV/MV pair, which provides a potential solution for daily treatment setup and verification of patients receiving radiation therapy for lung cancer.

The spine and carina as a surrogate for target registration in cone-beam CT imaging verification in locally advanced lung cancer radiotherapy.

The aim of the study was to evaluate the accuracy of volumetric lung image guidance using the spine or carina as a surrogate to target for image registration, as the best approach is not established. Cone beam computed tomography images from the 1st, 10th, 15th, and 20th fraction in 40 lung cancer patients treated with radical radiotherapy were retrospectively registered to planning CT, using three approaches. The spine and carina alignment set-up deviations from a reference (tumour/lymph nodes) registration in the lateral (LAT), longitudinal (LONG) and vertical (VRT) directions were analysed and compared. Tumour location and nodal stage influence on registration accuracy were explored. The spine and carina mean set-up deviation from reference were largest in the LONG, with the best match in the VRT and LAT, respectively. Both strategies were more accurate in central tumours, with the carina being more precise in 50% LAT and 66% LONG mean deviations. For all measurements in all patients a carina vs. spine registration comparison showed improved carina accuracy in LAT and LONG. In comparative subgroup analysis the carina was superior compared to spine in LAT and LONG in centrally located tumours, N2 and N3. Both strategies were comparable for peripheral tumours and N0. Carina registration shows greater accuracy compared to spine in the LAT and LONG directions and is superior in central tumours, N2 and N3. The spine and carina surrogates are equally accurate for peripheral tumours and N0. We propose the carina as a surrogate to target for CBCT image registration in locally advanced lung cancer.

Mapping with Monocular Camera Sensor under Adversarial Illumination for Intelligent Vehicles.

High-precision maps are widely applied in intelligent-driving vehicles for localization and planning tasks. The vision sensor, especially monocular cameras, has become favoured in mapping approaches due to its high flexibility and low cost. However, monocular visual mapping suffers from great performance degradation in adversarial illumination environments such as on low-light roads or in underground spaces. To address this issue, in this paper, we first introduce an unsupervised learning approach to improve keypoint detection and description on monocular camera images. By emphasizing the consistency between feature points in the learning loss, visual features in dim environment can be better extracted. Second, to suppress the scale drift in monocular visual mapping, a robust loop-closure detection scheme is presented, which integrates both feature-point verification and multi-grained image similarity measurements. With experiments on public benchmarks, our keypoint detection approach is proven robust against varied illumination. With scenario tests including both underground and on-road driving, we demonstrate that our approach is able to reduce the scale drift in reconstructing the scene and achieve a mapping accuracy gain of up to 0.14 m in textureless or low-illumination environments.

A feasibility study of enhanced prompt gamma imaging for range verification in proton therapy using deep learning

Background and objective. Range uncertainty is a major concern affecting the delivery precision in proton therapy. The Compton camera (CC)-based prompt-gamma (PG) imaging is a promising technique to provide 3D in vivo range verification. However, the conventional back-projected PG images suffer from severe distortions due to the limited view of the CC, significantly limiting its clinical utility. Deep learning has demonstrated effectiveness in enhancing medical images from limited-view measurements. But different from other medical images with abundant anatomical structures, the PGs emitted along the path of a proton pencil beam take up an extremely low portion of the 3D image space, presenting both the attention and the imbalance challenge for deep learning. To solve these issues, we proposed a two-tier deep learning-based method with a novel weighted axis-projection loss to generate precise 3D PG images to achieve accurate proton range verification. Materials and methods: the proposed method consists of two models: first, a localization model is trained to define a region-of-interest (ROI) in the distorted back-projected PG image that contains the proton pencil beam; second, an enhancement model is trained to restore the true PG emissions with additional attention on the ROI. In this study, we simulated 54 proton pencil beams (energy range: 75–125 MeV, dose level: 1 × 109 protons/beam and 3 × 108 protons/beam) delivered at clinical dose rates (20 kMU min−1 and 180 kMU min−1) in a tissue-equivalent phantom using Monte-Carlo (MC). PG detection with a CC was simulated using the MC-Plus-Detector-Effects model. Images were reconstructed using the kernel-weighted-back-projection algorithm, and were then enhanced by the proposed method. Results. The method effectively restored the 3D shape of the PG images with the proton pencil beam range clearly visible in all testing cases. Range errors were within 2 pixels (4 mm) in all directions in most cases at a higher dose level. The proposed method is fully automatic, and the enhancement takes only ∼0.26 s. Significance. Overall, this preliminary study demonstrated the feasibility of the proposed method to generate accurate 3D PG images using a deep learning framework, providing a powerful tool for high-precision in vivo range verification of proton therapy.

Strategies for the Minimisation of Misinformation Spread Through the Local Media Environment

ABSTRACT Coping with misinformation in a media environment is one of the challenges that undermine the role of the media. The pandemic of Covid-19 influenced the media organisations in their working processes significantly and a decrease in accuracy was one of the findings of our study. This paper examines the impact of the pandemic in local media to journalists’ practices and the role of the media. We aimed to research the effects of the pandemic in the local environment on journalistic procedures and the media's role after this period. In answering the research questions, we used the method of a structured questionnaire for journalists and semi-structured in-depth interviews for local News Editors. We aimed to research the media production practices on various levels of professionals included in local news. We detected those production practices that could endanger the credibility of the local media. The findings provided insights into how Slovenian local journalists and editors define, understand, and practice fact-checking. The results led to an understanding that the perception of the media role in offering information was higher during the pandemic period and that human verification is key in ensuring the credibility of content in local newsrooms.

4DCT is long overdue for improvement.

4DCT is long overdue for improvement.

Considering the role of medical radiation technologists to mitigate the care delivery problems associated with nasogastric tube verification and improve patient care

IntroductionMisplaced nasogastric (NG) tubes can have deleterious consequences for patients, including death. Medical radiation technologists (MRTs) may be well-positioned to improve the NG tube verification process. The objective of this study was to identify the care delivery problems (CDPs) associated with verifying NG tube placement and to consider where MRTs may mitigate current challenges. MethodsThis study involved three sources of data; a data audit of NG tube chest x-rays (CXRs), a review of related incident reports, and a staff survey, all conducted in the general radiography departments at two large, affiliated teaching hospitals in Toronto, Ontario. ResultsOver a 36-month period, 9,655 NG tube examinations were performed. Just over half of all exams (55.5%) required a single image for verification, while 10.1% required four or more images. The median time an MRT spent for an NG tube examination was 13.5 minutes, with 45.4% of exams completed in 10 minutes or less, while 4.5% required over 30 minutes. 118 incident reports and 57 survey submissions suggested five key CDPs; delayed verification, lack of verification, incorrect verification, increased radiation exposure, and inefficient workflow. ConclusionsCDPs associated with verifying NG tube placement can lead to poor patient care and inefficient workflows. The results of this study suggest that there may be value in future exploration of additional responsibility for MRTs as a potential solution for improving the NG tube process and thus patient care.

Tidally perturbed gravity-mode pulsations in a sample of close eclipsing binaries

Context. Thanks to the high-precision photometry from space missions such as Kepler and TESS, tidal perturbations and tilting of pulsations have been detected in more than a dozen binary systems. However, only two of these were gravity-mode (g-mode) pulsators. Aims. We aim to detect tidally perturbed g modes in additional binary systems and characterise them observationally. Methods. We performed a custom data reduction of the available Kepler and TESS photometry of a well-studied, published sample of 35 binary systems with γ Doradus (γ Dor) pulsators. For each target, we modelled the binary signal using a sum of 100 sine waves with frequencies at orbital harmonics and measured significant pulsation frequencies in an iterative pre-whitening analysis of the residual light curve. Pulsations are labelled as tidally perturbed g modes if they are part of both period-spacing patterns and multiplets spaced by integer multiples of the orbital frequency. After visual inspection and confirmation, the properties of these targets and g modes were characterised. Results. We detect tidally perturbed g-mode pulsations for five short-period binaries that are circularised and (almost) synchronously rotating: KIC 3228863, KIC 3341457, KIC 4947528, KIC 9108579, and KIC 12785282. Tidally perturbed g modes that occur within the same star and have the same mode identification (k, m), are found to have near-identical relative amplitude and phase modulations, which are within their respective 1 − σ uncertainties and also identical for the Kepler and TESS photometric passbands. By contrast, pulsations with different mode identifications (k, m) are found to exhibit different modulations. Moreover, the observed amplitude and phase modulations are correlated, indicating that the binary tides primarily distort the g-mode amplitudes on the stellar surface. The phase modulations are then primarily a geometric effect of the integration of the stellar flux over the visible stellar surface. All selected binaries also exhibit signal that resembles rotational modulation in the Fourier domain. In the case of KIC 3228863, this is caused by the presence of the known tertiary component, and for the other systems we hypothesise that it is caused by temperature variations on the stellar surface. Alternatively, the signal can be made up of overstable convective modes in the stellar core or may belong to the non-pulsating companion. Conclusions. While g-mode pulsation periods are known to be a direct probe of the deep interior stellar structure, the binary tides that cause the pulsation modulations are dominant in the outer stellar layers. Hence, in the future, tidally perturbed g modes may allow us to carry out core-to-surface asteroseismic modelling of tidally distorted stars.

Automatic Bounding Box Annotation with Small Training Datasets for Industrial Manufacturing.

In the past few years, object detection has attracted a lot of attention in the context of human-robot collaboration and Industry 5.0 due to enormous quality improvements in deep learning technologies. In many applications, object detection models have to be able to quickly adapt to a changing environment, i.e., to learn new objects. A crucial but challenging prerequisite for this is the automatic generation of new training data which currently still limits the broad application of object detection methods in industrial manufacturing. In this work, we discuss how to adapt state-of-the-art object detection methods for the task of automatic bounding box annotation in a use case where the background is homogeneous and the object's label is provided by a human. We compare an adapted version of Faster R-CNN and the Scaled-YOLOv4-p5 architecture and show that both can be trained to distinguish unknown objects from a complex but homogeneous background using only a small amount of training data. In contrast to most other state-of-the-art methods for bounding box labeling, our proposed method neither requires human verification, a predefined set of classes, nor a very large manually annotated dataset. Our method outperforms the state-of-the-art, transformer-based object discovery method LOST on our simple fruits dataset by large margins.