Image Quality Research Articles

Instance Segmentation XXL-CT Challenge of a Historic Airplane

Instance segmentation of compound objects in XXL-CT imagery poses a unique challenge in non-destructive testing. This complexity arises from the lack of known reference segmentation labels, limited applicable segmentation tools, as well as partially degraded image quality. To asses recent advancements in the field of machine learning-based image segmentation, the ‘Instance Segmentation XXL-CT Challenge of a Historic Airplane’ was conducted. The challenge aimed to explore automatic or interactive instance segmentation methods for an efficient delineation of the different aircraft components, such as screws, rivets, metal sheets or pressure tubes. We report the organization and outcome of this challenge and describe the capabilities and limitations of the submitted segmentation methods.

Fundamental effects of array density and modulation frequency on image quality of diffuse optical tomography.

Diffuse optical tomography (DOT) provides three-dimensional image reconstruction of chromophore perturbations within a turbid volume. Two leading strategies to optimize DOT image quality include, (i) arrays of regular, interlacing, high-density (HD) grids of sources and detectors with closest spacing less than 15mm, or (ii) source modulated light of order ∼100MHz. However, the general principles for how these crucial design parameters of array density and modulation frequency may interact to provide an optimal system design have yet to be elucidated. Herein, we systematically evaluated how these design parameters effect image quality via multiple key metrics. Specifically, we simulated 32 system designs with realistic measurement noise and quantified localization error, spatial resolution, signal-to-noise, and localization depth of field for each of ∼85000 point spread functions in each model. We found that array density had a far stronger effect on image quality metrics than modulation frequency. Additionally, model fits for image quality metrics revealed that potential improvements diminish with regular arrays denser than 9mm closest spacing. Further, for a given array density, 300MHz source modulation provided the deepest reliable imaging compared to other frequencies. Our results indicate that both array density and modulation frequency affect the spatial sampling of tissue, which asymptotically saturates due to photon diffusivity within a turbid volume. In summary, our results provide comprehensive perspectives for optimizing future DOT system designs in applications from wearable functional brain imaging to breast tumor detection.

Low-Dose Cone-Beam Computed Tomography in Swedish Pediatric Patients With Alveolar Clefts Following Alveolar Bone Grafting-A Clinical Study.

The aim of this study was to investigate whether a low-dose cone-beam computed tomography (CBCT) protocol provides diagnostically acceptable image quality for assessing bone healing after alveolar bone grafting. The study cohort comprised 11 patients (aged 7-14 years) with orofacial clefts who had undergone alveolar bone grafting at Skåne University Hospital in Malmö, Sweden. During the postsurgical follow-up at 6 months, each patient was assessed twice: once with a standard-dose CBCT protocol and once with a low-dose CBCT protocol, which in total corresponds to one CBCT examination made with the exposure settings recommended by the manufacturer. Among others, the assessed parameters included subjective image quality, as well as bone graft height, thickness, and integration. No significant differences were found between the standard- and low-dose protocols for most parameters (p > 0.05). Exceptions included subjective image quality (one observer, p = 0.05) and confidence levels during the assessment (three observers, p = 0.01, 0.01, 0.02). The low-dose protocol yielded adequate image quality for postoperative CBCT healing assessment in patients who have undergone alveolar bone grafting. However, the confidence level of observers during the assessment with the low-dose protocol was reduced. This study is registered on ClinicalTrials.gov (NCT06395077). This study is registered on ClinicalTrials.gov (NCT06395077).

The Impact of a Local Well-Being Philosophy on Revisit Intentions to Bali Among Digital Nomads

The level of success in tourism is gauged by several metrics; however, the most widely used is the level of tourist arrivals. However, this research answered the call for greater investigation of the impacts of qualitative factors and intangible cultural–heritage assets on destination performance. The primary research purpose was to analyze the effect of implementing a local well-being philosophy (Tri Hita Karana) on tourist revisit intentions for Bali and the mediation of destination quality and destination image. A research model was developed to examine the relationships among local wisdom (TKH), destination quality, destination image, and revisit intentions. Data were collected via a survey of 520 digital nomadic tourists and analyzed using SmartPLS 4. The results indicated that the implementation of THK positively and significantly affected revisit intentions, destination image, and destination quality. Destination image and destination quality had positive and significant effects on revisit intentions, and destination image and destination quality also significantly mediated the effect of THK implementation on revisit intentions. The findings suggested that implementing local wisdom values such as THK in the management of a destination makes visitors feel more favorably about the quality and image of the destination and they have the intention to revisit.

Antecedents of tourist loyalty in China’s Kangyang tourism: The influence of destination image, service quality, tourist satisfaction, and affective commitment

Background: Kangyang tourism, a wellness tourism niche in China, integrates health preservation with tourism through natural and cultural resources. Despite a growing interest in Kangyang tourism, the factors driving tourist loyalty in this sector are underexplored. Methods: Using a sample of 413 tourists, this study employed Covariance-Based Structural Equation Modeling (CB-SEM) to examine the influence of destination image, service quality, tourist satisfaction, and affective commitment on tourist loyalty. Results: The findings reveal that destination image and service quality positively affect tourist satisfaction, affective commitment, and loyalty. Tourist satisfaction and affective commitment are identified as critical drivers of tourist loyalty. Notably, affective commitment plays a stronger role in fostering loyalty compared to satisfaction. Conclusion: These results highlight the importance of a positive destination image and high service quality in enhancing tourist loyalty through increased emotional and psychological attachment. The findings inform strategies for stakeholders to improve Kangyang tourism’s growth by focusing on emotionally engaging experiences and service excellence.

Polarization-insensitive optical coherence tomography using pseudo-depolarized reference light for mitigating birefringence-related image artifacts.

Optical coherence tomography (OCT) images are prone to image artifacts due to the birefringence of the sample or the optical system when a polarized light source is used for imaging. These artifacts can lead to degraded image quality and diagnostic information. We aim to mitigate these birefringence-related artifacts in OCT images by adding a depolarizer module in the reference arm of the interferometer. We investigated different configurations of liquid crystal patterned retarders as pseudo-depolarizers in the reference arm of OCT setups. We identified the most effective depolarization module layout for polarization artifact suppression for a spectral-domain OCT system based on a Michelson and a Mach-Zehnder interferometer. The performance of our approach was demonstrated in an achromatic quarter-wave plate allowing the selection of a variety of sample polarization states. A substantial improvement of the OCT signal magnitude was observed after placing the optimal depolarizer configuration, reducing the cross-polarization artifact from 5.7 to 1.8dB and from 8.0 to 1.0dB below the co-polarized signal for the fiber-based Michelson and Mach-Zehnder setup, respectively. An imaging experiment in the birefringent scleral tissue of a post-mortem alpine marmot eye and a mouse tail specimen further showcased a significant improvement in the detected signal intensity and an enhanced OCT image quality followed by a drastic elimination of the birefringence-related artifacts. Our study presents a simple yet cost-effective technique to mitigate birefringence-related artifacts in OCT imaging. This method can be readily implemented in existing OCT technology and improve the effectiveness of various OCT imaging applications in biomedicine.

Remote out-of-hours ultrasound live supervision in pediatrics - improvement of diagnostics and training.

Ultrasound (US) is the preferred imaging modality in pediatrics for diagnostic and therapeutic issues. The absence of radiation and the constant on-site accessibility make it the ideal tool for children. However, despite remarkable technical advances in resolution and applicability, many sophisticated medical questions still require profound expertise on the part of the examiner, thus often hampering fast decisions particularly outside regular working hours. This single-center study, at a university children's hospital evaluated the use of US during emergency service. A four-week documentation period was followed by a subsequent eight-week supervision period with live supervision availability on demand guided by a remote US expert. The demand for expert support, diagnosis, grading of urgency, duration and success of examination, and satisfaction of both examiners were analyzed. 108 patients (mean age 9.7 years) were included. In 38% of cases, US was supervised on demand with a definite diagnosis in 92.6% of cases (25/27). Image quality and technical performance were graded sufficient in 100% of cases. Supervised compared to non-supervised US examinations were prolonged (14.4 min vs. 7.1 min, p<0.001), were more prevalent within the first 24 h in the hospital (70% vs. 56.8%, p=0.06), and were classified more frequently as emergency (22.2% vs. 2.3%; p=0.015). All participants classified the availability of US supervision as decisively helpful. Remote live supervised pediatric US was feasible and effective. It combined timely, high-quality diagnostics even in the case of challenging medical questions with simultaneous US training.

Image Dehazing Enhancement Strategy Based on Polarization Detection of Space Targets

In view of the fact that the technology of polarization detection performs better at identifying targets through clouds and fog, the recognition ability of the space target detection system under haze conditions will be improved by applying the technology. However, due to the low ambient brightness and limited target radiation information during space target detection, the polarization information of space target is seriously lost, and the advantages of polarization detection technology in identifying targets through clouds and fog cannot be effectively exerted under the condition of haze detection. In order to solve the above problem, a dehazing enhancement strategy specifically applied to polarization images of space targets is proposed. Firstly, a hybrid multi-channel interpolation method based on regional correlation analysis is proposed to improve the calculation accuracy of polarization information during preprocessing. Secondly, an image processing method based on full polarization information inversion is proposed to obtain the degree of polarization of the image after inversion and the intensity of the image after dehazing. Finally, the image fusion method based on discrete cosine transform is used to obtain the dehazing polarization fusion enhancement image. The effectiveness of the proposed image processing strategy is verified by carrying out simulated and real space target detection experiments. Compared with other methods, by using the proposed image processing strategy, the quality of the polarization images of space targets obtained under the haze condition is significantly improved. Our research results have important practical implications for promoting the wide application of polarization detection technology in the field of space target detection.

Giving the prostate the boost it needs: Spiral diffusion MRI using a high-performance whole-body gradient system for high b-values at short echo times.

To address key issues of low SNR and image distortions in prostate diffusion MRI (dMRI) by means of using strong gradients, single-shot spiral readouts and an expanded encoding model for image reconstruction. Diffusion-weighted spin echo imaging with EPI and spiral readouts is performed on a whole-body system equipped with strong gradients (up to 250 mT/m). An expanded encoding model including static off-resonance, coil sensitivities, and magnetic field dynamics is employed for image reconstruction. The acquisitions are performed on a phantom and in vivo (one healthy volunteer and one patient with prostate cancer). The resulting images are compared to conventional dMRI EPI with navigator-based image reconstruction and assessed in terms of their congruence, SNR, tissue contrast, and quantitative parameters. Using the expanded encoding model, high-quality images of the prostate gland are obtained across all b-values (up to 3 ms/μm2), clearly outperforming the results obtained with conventional image reconstruction. Compared to EPI, spiral imaging provides an SNR gain up to 45% within the gland and even higher in the lesion. In addition, prostate dMRI with single-shot spirals at submillimeter in-plane resolution (0.85 mm) is accomplished. The combination of strong gradients and an expanded encoding model enables imaging of the prostate with unprecedented image quality. Replacing the commonly used EPI with spirals provides the inherent benefit of shorter echo times and superior readout efficiency and results in higher SNR, which is in particular relevant for considered applications.

Generating high-quality phase-only holograms of binary images using global loss and stochastic homogenization training strategy

Deep learning presents a highly effective for computer-generated holography (CGH). However, existing learning-based CGH algorithms may encounter significant obstacles in generating high-quality holograms for binary images. This study proposes a novel diffraction model-driven neural network, termed load sharing yielding holography (LSY-Holo), which leverages a dual-branch architecture and a global structural similarity index measure (Global_SSIM) loss function to generate phase-only holograms (POHs). LSY-Holo framework facilitates capturing global information, enhancing the network’s performance to address the ill-posed inverse problem. To further optimize the model for binary images, the research introduces a custom Binary dataset alongside a stochastic homogenization preprocessing method (SHPM), which mitigates the prevalent issue of excessive noise in reconstructed images. Additionally, this deep learning approach is integrated with an iterative algorithm, which employs holograms rapidly generated by LSY-Holo as the initial phase of the AdamW Holography (AH) algorithm. This strategy significantly accelerates the convergence of the iterative process. LSY-Holo is further extended to 3D scenes, enabling dynamic defocusing and focusing effects at varying depths. Results from numerical simulations and full-color optical reconstruction experiments demonstrate that the proposed method can enhance image quality and effectively reduce the artifacts in reconstructed images.

The Rise of Digital Reproduction Against Mechanical Reproduction: “Techno-Nostalgia” in Photography

As a result of advancements in contemporary digital technology, the production tools utilized in art, alongside new instruments that facilitate daily life, are becoming increasingly diverse and sophisticated. The innovations offered by technology provide a wide range of creative opportunities, particularly for artists. However, since the 1990s, there has been a notable tendency towards a retrospective return and mimicry in both daily life and art. This research primarily focuses on the paradox of returning to the past, despite all technological developments and digitalization, as explored through the medium of photography. In this study, the reasons for looking back and mimicking the past in defiance of contemporary realities and technologies are analyzed within the framework of the concept of “tech-nostalgia.” Concrete examples of “tech-nostalgia” in the realm of photography, such as the Lomography movement and Polaroid productions, have been examined in detail. Despite the high-resolution image quality achieved through current technology and the conveniences of the image production process, the reasons for the observed increase in analog photography have been addressed. The investigation delves into how this increase is shaped within the nature of art and photographic aesthetics, and this trend is attempted to be elucidated through psychological and sociological perspectives with relevant examples.

Remote Sensing Data Quality in the Era of AI

Abstract. The era of Artificial Intelligence ‘AI’ with all the benefits brought along, has raised new and additional challenges to the ongoing efforts of assessing, defining, formulating, and implementing the quality aspects of geospatial remote sensing data. Developed practices using artificial intelligence leveraged techniques such as image interpretation, classification, thematic mapping, and even image quality enhancement, necessitating by that the reassessment and redevelopment of some of the related emerging quality aspects. Moreover, technology also made the generation of false images and false data possible, this matter constrained and increased precaution and doubtfulness, altogether making some practices based on that data almost halt to further notice. This paper presents the collaborative research work to assess and clarify the quality aspects that arose with the advent and implementation of AI and associated technologies; the concerns and issues that can accompany the generation of false satellite and aerial images including the generated geospatial data out of which, how the new emerged quality aspects fit into the currently existing methods through the lifecycle of remote sensing data production and usage, and consequently how the quality dimensions are affected and should be further developed and improved to tackle the changes and innovations. Also, lame a bit on investigating how to accommodate the new challenges in standards, and practical procedures and raise the awareness to users, the level of dependency on improved and enhanced satellite images when it comes to data collection interpretation and classification, and finally define the research gaps, future expected challenges and thus enclose suggestions and recommendations in that respect.

Bidirectional dynamic frame prediction network for total-body [68Ga]Ga-PSMA-11 and [68Ga]Ga-FAPI-04 PET images

PurposeTotal-body dynamic positron emission tomography (PET) imaging with total-body coverage and ultrahigh sensitivity has played an important role in accurate tracer kinetic analyses in physiology, biochemistry, and pharmacology. However, dynamic PET scans typically entail prolonged durations (\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\:\\ge\\:$$\\end{document}60 minutes), potentially causing patient discomfort and resulting in artifacts in the final images. Therefore, we propose a dynamic frame prediction method for total-body PET imaging via deep learning technology to reduce the required scanning time.MethodsOn the basis of total-body dynamic PET data acquired from 13 subjects who received [68Ga]Ga-FAPI-04 (68Ga-FAPI) and 24 subjects who received [68Ga]Ga-PSMA-11 (68Ga-PSMA), we propose a bidirectional dynamic frame prediction network that uses the initial and final 10 min of PET imaging data (frames 1–6 and frames 25–30, respectively) as inputs. The peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were employed as evaluation metrics for an image quality assessment. Moreover, we calculated parametric images (68Ga-FAPI: \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\:{K}_{1}$$\\end{document}, 68Ga-PSMA: \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\:{K}_{i}$$\\end{document}) based on the supplemented sequence data to observe the quantitative accuracy of our approach. Regions of interest (ROIs) and statistical analyses were utilized to evaluate the performance of the model.ResultsBoth the visual and quantitative results illustrate the effectiveness of our approach. The generated dynamic PET images yielded PSNRs of 36.056 ± 0.709 dB for the 68Ga-PSMA group and 33.779 ± 0.760 dB for the 68Ga-FAPI group. Additionally, the SSIM reached 0.935 ± 0.006 for the 68Ga-FAPI group and 0.922 ± 0.009 for the 68Ga-PSMA group. By conducting a quantitative analysis on the parametric images, we obtained PSNRs of 36.155 ± 4.813 dB (68Ga-PSMA, \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\:{K}_{1}$$\\end{document}) and 43.150 ± 4.102 dB (68Ga-FAPI, \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\:{K}_{i}$$\\end{document}). The obtained SSIM values were 0.932 ± 0.041 (68Ga-PSMA) and 0.980 ± 0.011 (68Ga-FAPI). The ROI analysis conducted on our generated dynamic PET sequences also revealed that our method can accurately predict temporal voxel intensity changes, maintaining overall visual consistency with the ground truth.ConclusionIn this work, we propose a bidirectional dynamic frame prediction network for total-body 68Ga-PSMA and 68Ga-FAPI PET imaging with a reduced scan duration. Visual and quantitative analyses demonstrated that our approach performed well when it was used to predict one-hour dynamic PET images. https://github.com/OPMZZZ/BDF-NET.

Diagnostic performance of high and ultra-high-resolution photon counting CT for detection of coronary artery disease in patients evaluated for transcatheter aortic valve implantation.

We assessed the diagnostic performance of both ultra-high-resolution (UHR) and high-resolution (HR) modes of photon-counting detector (PCD)-CT within the confines of standard pre-TAVI CT scans, as well as the performance of UHR mode adjusted specifically for coronary imaging, using quantitative coronary angiography (QCA) as the reference. We included 60 patients undergoing pre-TAVI planning CT scans. Patients were divided into 3 groups: 20 scanned in HR mode, 20 in UHR mode, and 20 in adjusted UHR mode, on a dual-source PCD-CT. The adjusted UHR mode employed a lower tube voltage (90kV vs. 120kV) and a higher image quality level (65 vs. 34) to enhance coronary artery visualization. Patients underwent invasive coronary angiography as part of clinical routine. CCTA and QCA were reviewed to assess CAD presence defined as stenosis ≥ 50% in proximal and middle coronary segments. We included 60 patients (mean age 79 ± 7 years; 39(65%) men). Mean heart rate during scanning was 72 ± 13bpm. Median coronary calcium score was 973[379-2007]. QCA identified significant CAD in 24 patients (40%): 9 patients scanned with HR mode, 10 patients with the UHR mode, and 5 patients with the UHR adjusted mode. Per-patient area under the curves were 0.57 for HR, 0.80 for UHR, and 0.80 for adjusted UHR, with no significant differences between the scan modes, and per-vessel the area under the curves were 0.73 for HR, 0.69 for UHR, and 0.87 for adjusted UHR, with significant differences between UHR and adjusted UHR (p = 0.04). UHR and adjusted UHR modes of dual source PCD-CT show potential for improved sensitivity and negative predictive value for detecting CAD in patients undergoing pre-TAVI scans, however, no statistically significant difference from HR mode was observed.

Crop Leaf Type Classification and Multi-Class Leaf Disease Identification with Tangent Hunter Prey Optimization-Based LeNet

The early detection and accurate rate of classification of plant leaf disease are more important for reliable and good agriculture, which prevents unwanted financial loss and resources. In this study, Tangent Hunter Prey Optimization-based LeNet (THPO-LeNet) is utilized for crop leaf classification and multi-class plant leaf disease identification. In this case, the input image that goes through the image pre-processing step is obtained from the plant village dataset. An adaptive Wiener filter is applied at the pre-processing stage to reduce needless mistakes and improve image quality. The pre-processed image is then sent to the leaf segmentation step, where a Mask Region-based Convolution Neural Network (Mask R-CNN) performs the segmentation. Consequently, image augmentation is performed using techniques such as scaling, rotation, translation, flipping, contrast, saturation, and hue. Afterwards, first-level classification plant leaf classification is processed by LeNet, which is optimized by Tangent Hunter Prey Optimization (THPO). The THPO is the incorporation of a Tangent Search Algorithm (TSA) and Hunter–Prey Optimizer (HPO). At last, the second-level classification of plant leaf disease is conducted by THPO-LeNet. Furthermore, the efficiency of THPO-LeNet is examined based on measures, like accuracy, Negative Predictive Value (NPV), True Positive Rate (TPR), True Negative Rate (TNR), Positive Predictive Value (PPV), loss value, and False Positive Rate (FPR), and the value attained is 95.68%, 92.50%, 91.48%, 92.25%, 92.54%, 8.321%, and 7.754%, respectively.

Pengaruh Kualitas Produk, Brand Image, dan Promosi Terhadap Keputusan Pembelian pada E-Commerce Shopee: Studi Empiris pada Konsumen E-Commerce Shopee Kabupaten Demak

Determining the impact of advertising, brand image, and product quality on Shopee e-commerce purchase decisions is the goal of this study. The Demak Regency's e-commerce clientele is the subject of this study; nevertheless, the precise population estimate is unknown. One hundred respondents were chosen for the sample using the target sampling technique. The hypothesis was tested using multiple linear regression analysis, and its validity was assessed using the F and t tests. The findings of the study indicate that: (1) brand image has no influence on purchasing decisions; (2) product quality has a positive and substantial effect on purchasing decisions; and (3) promotion has a positive and significant effect on purchasing decisions.

Product development of sweets chocolate cube using value engineering method

Cocoa is one of the plantation commodities that has an important role in economic activities as a foreign exchange earner. Indonesia is ranked first in Asia with the highest consumption of chocolate, which is 7.3 kg per capita. Chocolates are seen by consumers as a comfort food or stress relief. For consumers who buy chocolate for their own consumption, consuming chocolate in a small size causes consumers to act more impulsively to consume larger quantities. Consumption of chocolate in small sizes (one bite size) gives the impression that the product has a premium image and higher quality. The purpose of this study was to identify the characteristics of chocolate that influence the decisions of product purchasing and to develop one-bite-sized chocolate cubes using the value engineering method. The study used 433 respondents with the criteria of chocolate consumers aged 15-40 years. Based on the research, chocolate bars and molded chocolate are the types of chocolate most often consumed with a frequency of 2-3 times a month. Consumers have the highest complaints when consuming chocolate, namely melted chocolate which makes hands dirty due to its big size and is too hard to bite. Based on the consumer needs analysis, consumers want the development of milk chocolate cube candy with nuts filling. Four alternative cube milk chocolate concepts with a cocoa mass percentage of 50% were prepared using 2 variations in the number of cocoa beans and cocoa fat (40%:10% and 35%:15%) and 2 variations of nuts (almonds and cashews). Based on the hedonic test results, milk chocolate cubes with a formula of 10% cocoa butter and cashew nut filling had the highest product value of 0.013 compared to other formulas. Chocolate color and ease of eating are the attribute weights with the highest weights. It can be concluded that the milk chocolate cube formula is 40% cocoa beans; 10% cocoa butter, cashew nut filling is the selected formula with a production cost of IDR 985.00/g.

Pengaruh Citra Merek. Kualitas Produk, dan Kepuasan Pelanggan Terhadap Loyalitas Pelanggan pada Produk Teh Pucuk Harum di Surabaya

This research aims to analyze the influence of brand image, product quality, and customer satisfaction on customer loyalty for Teh Pucuk Harum products in Surabaya City. This study employs a quantitative method approach. The population used in this study is consumers of Teh Pucuk Harum in Surabaya. The sample size in this study was determined using the Slovin formula, resulting in a required sample of 100 respondents. Data were collected through questionnaires and analyzed using multiple linear regression analysis. The results show that brand image, product quality, and customer satisfaction simultaneously have a significant effect on customer loyalty. However, partial analysis reveals that only customer satisfaction has a significant influence on customer loyalty. Brand image and product quality, although showing a positive influence, do not have a significant partial effect on customer loyalty.

Enhancing Visual Perception in Immersive VR and AR Environments: AI-Driven Color and Clarity Adjustments Under Dynamic Lighting Conditions

The visual fidelity of virtual reality (VR) and augmented reality (AR) environments is essential for user immersion and comfort. Dynamic lighting often leads to chromatic distortions and reduced clarity, causing discomfort and disrupting user experience. This paper introduces an AI-driven chromatic adjustment system based on a modified U-Net architecture, optimized for real-time applications in VR/AR. This system adapts to dynamic lighting conditions, addressing the shortcomings of traditional methods like histogram equalization and gamma correction, which struggle with rapid lighting changes and real-time user interactions. We compared our approach with state-of-the-art color constancy algorithms, including Barron’s Convolutional Color Constancy and STAR, demonstrating superior performance. Experimental results from 60 participants show significant improvements, with up to 41% better color accuracy and 39% enhanced clarity under dynamic lighting conditions. The study also included eye-tracking data, which confirmed increased user engagement with AI-enhanced images. Our system provides a practical solution for developers aiming to improve image quality, reduce visual discomfort, and enhance overall user satisfaction in immersive environments. Future work will focus on extending the model’s capability to handle more complex lighting scenarios.

An Autoencoder-Based Task-Oriented Semantic Communication System for M2M Communication

Semantic communication (SC) is a communication paradigm that has gained significant attention, as it offers a potential solution to move beyond Shannon’s formulation in bandwidth-limited communication channels by delivering the semantic meaning of the message rather than its exact form. In this paper, we propose an autoencoder-based SC system for transmitting images between two machines over error-prone channels to support emerging applications such as VIoT, XR, M2M, and M2H communications. The proposed autoencoder architecture, with a semantically modeled encoder and decoder, transmits image data as a reduced-dimension vector (latent vector) through an error-prone channel. The decoder then reconstructs the image to determine its M2M implications. The autoencoder is trained for different noise levels under various channel conditions, and both image quality and classification accuracy are used to evaluate the system’s efficacy. A CNN image classifier measures accuracy, as no image quality metric is available for SC yet. The simulation results show that all proposed autoencoders maintain high image quality and classification accuracy at high SNRs, while the autoencoder trained with zero noise underperforms other trained autoencoders at moderate SNRs. The results further indicate that all other proposed autoencoders trained under different noise levels are highly robust against channel impairments. We compare the proposed system against a comparable JPEG transmission system, and results reveal that the proposed system outperforms the JPEG system in compression efficiency by up to 50% and in received image quality with an image coding gain of up to 17 dB.