Journal articles on the topic 'Ground truth prior'
To see the other types of publications on this topic, follow the link: Ground truth prior.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Ground truth prior.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Chen, Jierun, Song Wen, and S. H. Gary Chan. "Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 2 (May 18, 2021): 1018–26. http://dx.doi.org/10.1609/aaai.v35i2.16186.
Full textAbstract:
Image demosaicking and denoising are the two key fundamental steps in digital camera pipelines, aiming to reconstruct clean color images from noisy luminance readings. In this paper, we propose and study Wild-JDD, a novel learning framework for joint demosaicking and denoising in the wild. In contrast to previous works which generally assume the ground truth of training data is a perfect reflection of the reality, we consider here the more common imperfect case of ground truth uncertainty in the wild. We first illustrate its manifestation as various kinds of artifacts including zipper effect, color moire and residual noise. Then we formulate a two-stage data degradation process to capture such ground truth uncertainty, where a conjugate prior distribution is imposed upon a base distribution. After that, we derive an evidence lower bound (ELBO) loss to train a neural network that approximates the parameters of the conjugate prior distribution conditioned on the degraded input. Finally, to further enhance the performance for out-of-distribution input, we design a simple but effective fine-tuning strategy by taking the input as a weakly informative prior. Taking into account ground truth uncertainty, Wild-JDD enjoys good interpretability during optimization. Extensive experiments validate that it outperforms state-of-the-art schemes on joint demosaicking and denoising tasks on both synthetic and realistic raw datasets.
2
Prasanna, Shivika, Naveen Premnath, Suveen Angraal, Ramy Sedhom, Rohan Khera, Helen Parsons, Syed Hussaini, et al. "Sentiment analysis of tweets on prior authorization." Journal of Clinical Oncology 39, no. 28_suppl (October 1, 2021): 322. http://dx.doi.org/10.1200/jco.2020.39.28_suppl.322.
Full textAbstract:
322 Background: Natural language processing (NLP) algorithms can be leveraged to better understand prevailing themes in healthcare conversations. Sentiment analysis, an NLP technique to analyze and interpret sentiments from text, has been validated on Twitter in tracking natural disasters and disease outbreaks. To establish its role in healthcare discourse, we sought to explore the feasibility and accuracy of sentiment analysis on Twitter posts (‘’tweets’’) related to prior authorizations (PAs), a common occurrence in oncology built to curb payer-concerns about costs of cancer care, but which can obstruct timely and appropriate care and increase administrative burden and clinician frustration. Methods: We identified tweets related to PAs between 03/09/2021-04/29/2021 using pre-specified keywords [e.g., #priorauth etc.] and used Twarc, a command-line tool and Python library for archiving Twitter JavaScript Object Notation data. We performed sentiment analysis using two NLP models: (1) TextBlob (trained on movie reviews); and (2) VADER (trained on social media). These models provide results as polarity, a score between 0-1, and a sentiment as ‘’positive’’ (>0), ‘’neutral’’ (exactly 0), or ‘’negative’’ (<0). We (AG, NP) manually reviewed all tweets to give the ground truth (human interpretation of reality) including a notation for sarcasm since models are not trained to detect sarcasm. We calculated the precision (positive predictive value), recall (sensitivity), and the F1-Score (measure of accuracy, range 0-1, 0=failure, 1=perfect) for the models vs. the ground truth. Results: After preprocessing, 964 tweets (mean 137/ week) met our inclusion criteria for sentiment analysis. The two existing NLP models labeled 42.4%- 43.3% tweets as positive, as compared to the ground truth (5.6% tweets positive). F-1 scores of models across labels ranged from 0.18-0.54. We noted sarcasm in 2.8% of tweets. Detailed results in Table. Conclusions: We demonstrate the feasibility of performing sentiment analysis on a topic of high interest within clinical oncology and the deficiency of existing NLP models to capture sentiment within oncologic Twitter discourse. Ongoing iterations of this work further train these models through better identification of the tweeter (patient vs. health care worker) and other analytics from shared content.[Table: see text]
3
Witkowski, Jens, and David Parkes. "A Robust Bayesian Truth Serum for Small Populations." Proceedings of the AAAI Conference on Artificial Intelligence 26, no. 1 (September 20, 2021): 1492–98. http://dx.doi.org/10.1609/aaai.v26i1.8261.
Full textAbstract:
Peer prediction mechanisms allow the truthful elicitation of private signals (e.g., experiences, or opinions) in regard to a true world state when this ground truth is unobservable. The original peer prediction method is incentive compatible for any number of agents n >= 2, but relies on a common prior, shared by all agents and the mechanism. The Bayesian Truth Serum (BTS) relaxes this assumption. While BTS still assumes that agents share a common prior, this prior need not be known to the mechanism. However, BTS is only incentive compatible for a large enough number of agents, and the particular number of agents required is uncertain because it depends on this private prior. In this paper, we present a robust BTS for the elicitation of binary information which is incentive compatible for every n >= 3, taking advantage of a particularity of the quadratic scoring rule. The robust BTS is the first peer prediction mechanism to provide strict incentive compatibility for every n >= 3 without relying on knowledge of the common prior. Moreover, and in contrast to the original BTS, our mechanism is numerically robust and ex post individually rational.
4
KUMAR, P. V. HAREESH, P. MADHUSOODANAN, M. P. AJAI KUMAR, and A. RAGHUNADHA RAO. "Characteristics of Arabian Sea mini warm pool during May 2003." MAUSAM 56, no. 1 (January 19, 2022): 169–74. http://dx.doi.org/10.54302/mausam.v56i1.891.
Full textAbstract:
Oceanographic surveys were carried out onboard INS Sagardhwani as a part of ARMEX in the deep and coastal regions of the eastern Arabian Sea during May 2003 to study the mini warm pool characteristics. The observational period was characterized by typical pre-monsoon conditions, as indicated by weak winds and clear skies. TMI SST data showed very good agreement with the ground truth observations (root mean square departure of ~0.2oC). Both the satellite imagery and ground truth showed surface temperature (SST) in excess of 31° C in the eastern Arabian Sea. This mini warm pool attained its maximum dimension ~8 days prior to the onset of summer monsoon over Kerala and the dissipated stated prior to the onset date. This information can be used as an index for the prediction of summer monsoon onset. Alternate bands of cyclonic and anti-cyclonic circulation pattern were evident both in the ground truth and satellite imagery. In the regions of SST more than 31° C, surface salinity was found to be less than 34.75 PSU and its depth extent was limited to thin surface layer resulting highly stratified layer. The low saline water present in this region was due to the northward / northwestward advection of low saline waters of equatorial Indian Ocean origin and the re-circulation of Bay of Bengal water mass trapped in the central Arabian Sea during winter by the eddy type of circulation.
5
Tribble, Curt, Nick Teman, and Walter Merrill. "The Calm Before The Storm: The 4th Year of Medical School prior to a Surgery Residency." Heart Surgery Forum 24, no. 3 (May 24, 2021): E451—E455. http://dx.doi.org/10.1532/hsf.3919.
Full textAbstract:
Many medical students figure that their fourth year of medical school should be a time primarily focused on residency interviews and resting up for residency. While the interview part is necessary, the concept that one should be resting during that year is a myth. In fact, nothing could be further from the truth. Your top priority should be to prepare yourself to hit the ground running as a great surgical intern.
6
Tang, Tim Y., Daniele De Martini, Shangzhe Wu, and Paul Newman. "Self-supervised learning for using overhead imagery as maps in outdoor range sensor localization." International Journal of Robotics Research 40, no. 12-14 (September 28, 2021): 1488–509. http://dx.doi.org/10.1177/02783649211045736.
Full textAbstract:
Traditional approaches to outdoor vehicle localization assume a reliable, prior map is available, typically built using the same sensor suite as the on-board sensors used during localization. This work makes a different assumption. It assumes that an overhead image of the workspace is available and utilizes that as a map for use for range-based sensor localization by a vehicle. Here, range-based sensors are radars and lidars. Our motivation is simple, off-the-shelf, publicly available overhead imagery such as Google satellite images can be a ubiquitous, cheap, and powerful tool for vehicle localization when a usable prior sensor map is unavailable, inconvenient, or expensive. The challenge to be addressed is that overhead images are clearly not directly comparable to data from ground range sensors because of their starkly different modalities. We present a learned metric localization method that not only handles the modality difference, but is also cheap to train, learning in a self-supervised fashion without requiring metrically accurate ground truth. By evaluating across multiple real-world datasets, we demonstrate the robustness and versatility of our method for various sensor configurations in cross-modality localization, achieving localization errors on-par with a prior supervised approach while requiring no pixel-wise aligned ground truth for supervision at training. We pay particular attention to the use of millimeter-wave radar, which, owing to its complex interaction with the scene and its immunity to weather and lighting conditions, makes for a compelling and valuable use case.
7
Davani, Aida Mostafazadeh, Mark Díaz, and Vinodkumar Prabhakaran. "Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations." Transactions of the Association for Computational Linguistics 10 (2022): 92–110. http://dx.doi.org/10.1162/tacl_a_00449.
Full textAbstract:
Abstract Majority voting and averaging are common approaches used to resolve annotator disagreements and derive single ground truth labels from multiple annotations. However, annotators may systematically disagree with one another, often reflecting their individual biases and values, especially in the case of subjective tasks such as detecting affect, aggression, and hate speech. Annotator disagreements may capture important nuances in such tasks that are often ignored while aggregating annotations to a single ground truth. In order to address this, we investigate the efficacy of multi-annotator models. In particular, our multi-task based approach treats predicting each annotators’ judgements as separate subtasks, while sharing a common learned representation of the task. We show that this approach yields same or better performance than aggregating labels in the data prior to training across seven different binary classification tasks. Our approach also provides a way to estimate uncertainty in predictions, which we demonstrate better correlate with annotation disagreements than traditional methods. Being able to model uncertainty is especially useful in deployment scenarios where knowing when not to make a prediction is important.
8
Brooks, Douglas A., and Ayanna M. Howard. "Quantifying Upper-Arm Rehabilitation Metrics for Children through Interaction with a Humanoid Robot." Applied Bionics and Biomechanics 9, no. 2 (2012): 157–72. http://dx.doi.org/10.1155/2012/978498.
Full textAbstract:
The objective of this research effort is to integrate therapy instruction with child-robot play interaction in order to better assess upper-arm rehabilitation. Using computer vision techniques such as Motion History Imaging (MHI), edge detection, and Random Sample Consensus (RANSAC), movements can be quantified through robot observation. In addition, incorporating prior knowledge regarding exercise data, physical therapeutic metrics, and novel approaches, a mapping to therapist instructions can be created allowing robotic feedback and intelligent interaction. The results are compared with ground truth data retrieved via the Trimble 5606 Robotic Total Station and visual experts for the purpose of assessing the efficiency of this approach. We performed a series of upper-arm exercises with two male subjects, which were captured via a simple webcam. The specific exercises involved adduction and abduction and lateral and medial movements. The analysis shows that our algorithmic results compare closely to the results obtain from the ground truth data, with an average algorithmic error is less than 9% for the range of motion and less than 8% for the peak angular velocity of each subject.
9
Zagheni, Emilio, and Ingmar Weber. "Demographic research with non-representative internet data." International Journal of Manpower 36, no. 1 (April 7, 2015): 13–25. http://dx.doi.org/10.1108/ijm-12-2014-0261.
Full textAbstract:
Purpose – Internet data hold many promises for demographic research, but come with severe drawbacks due to several types of bias. The purpose of this paper is to review the literature that uses internet data for demographic studies and presents a general framework for addressing the problem of selection bias in non-representative samples. Design/methodology/approach – The authors propose two main approaches to reduce bias. When ground truth data are available, the authors suggest a method that relies on calibration of the online data against reliable official statistics. When no ground truth data are available, the authors propose a difference in differences approach to evaluate relative trends. Findings – The authors offer a generalization of existing techniques. Although there is not a definite answer to the question of whether statistical inference can be made from non-representative samples, the authors show that, when certain assumptions are met, the authors can extract signal from noisy and biased data. Research limitations/implications – The methods are sensitive to a number of assumptions. These include some regularities in the way the bias changes across different locations, different demographic groups and between time steps. The assumptions that we discuss might not always hold. In particular, the scenario where bias varies in an unpredictable manner and, at the same time, there is no “ground truth” available to continuously calibrate the model, remains challenging and beyond the scope of this paper. Originality/value – The paper combines a critical review of existing substantive and methodological literature with a generalization of prior techniques. It intends to provide a fresh perspective on the issue and to stimulate the methodological discussion among social scientists.
10
Diaz, Antonio L., Andrew E. Ortega, Henry Tingle, Andres Pulido, Orlando Cordero, Marisa Nelson, Nicholas E. Cocoves, et al. "The Bathy-Drone: An Autonomous Unmanned Drone-Tethered Sonar System." Drones 6, no. 8 (August 22, 2022): 220. http://dx.doi.org/10.3390/drones6080220.
Full textAbstract:
A unique drone-based system for underwater mapping (bathymetry) was developed at the University of Florida. The system, called the “Bathy-drone”, comprises a drone that drags, via a tether, a small vessel on the water surface in a raster pattern. The vessel is equipped with a recreational commercial off-the-shelf (COTS) sonar unit that has down-scan, side-scan, and chirp capabilities and logs GPS-referenced sonar data onboard or transmitted in real time with a telemetry link. Data can then be retrieved post mission and plotted in various ways. The system provides both isobaths and contours of bottom hardness. Extensive testing of the system was conducted on a 5 acre pond located at the University of Florida Plant Science and Education Unit in Citra, FL. Prior to performing scans of the pond, ground-truth data were acquired with an RTK GNSS unit on a pole to precisely measure the location of the bottom at over 300 locations. An assessment of the accuracy and resolution of the system was performed by comparison to the ground-truth data. The pond ground truth had an average depth of 2.30 m while the Bathy-drone measured an average 21.6 cm deeper than the ground truth, repeatable to within 2.6 cm. The results justify integration of RTK and IMU corrections. During testing, it was found that there are numerous advantages of the Bathy-drone system compared to conventional methods including ease of implementation and the ability to initiate surveys from the land by flying the system to the water or placing the platform in the water. The system is also inexpensive, lightweight, and low-volume, thus making transport convenient. The Bathy-drone can collect data at speeds of 0–24 km/h (0–15 mph) and, thus, can be used in waters with swift currents. Additionally, there are no propellers or control surfaces underwater; hence, the vessel does not tend to snag on floating vegetation and can be dragged over sandbars. An area of more than 10 acres was surveyed using the Bathy-drone in one battery charge and in less than 25 min.
11
Diaz, Antonio L., Andrew E. Ortega, Henry Tingle, Andres Pulido, Orlando Cordero, Marisa Nelson, Nicholas E. Cocoves, et al. "The Bathy-Drone: An Autonomous Uncrewed Drone-Tethered Sonar System." Drones 6, no. 10 (October 10, 2022): 294. http://dx.doi.org/10.3390/drones6100294.
Full textAbstract:
A unique drone-based system for underwater mapping (bathymetry) was developed at the University of Florida. The system, called the “Bathy-drone”, comprises a drone that drags, via a tether, a small vessel on the water surface in a raster pattern. The vessel is equipped with a recreational commercial off-the-shelf (COTS) sonar unit that has down-scan, side-scan, and chirp capabilities and logs GPS-referenced sonar data onboard or transmitted in real time with a telemetry link. Data can then be retrieved post mission and plotted in various ways. The system provides both isobaths and contours of bottom hardness. Extensive testing of the system was conducted on a 5 acre pond located at the University of Florida Plant Science and Education Unit in Citra, FL. Prior to performing scans of the pond, ground-truth data were acquired with an RTK GNSS unit on a pole to precisely measure the location of the bottom at over 300 locations. An assessment of the accuracy and resolution of the system was performed by comparison to the ground-truth data. The pond ground truth had an average depth of 2.30 m while the Bathy-drone measured an average 21.6 cm deeper than the ground truth, repeatable to within 2.6 cm. The results justify integration of RTK and IMU corrections. During testing, it was found that there are numerous advantages of the Bathy-drone system compared to conventional methods including ease of implementation and the ability to initiate surveys from the land by flying the system to the water or placing the platform in the water. The system is also inexpensive, lightweight, and low-volume, thus making transport convenient. The Bathy-drone can collect data at speeds of 0–24 km/h (0–15 mph) and, thus, can be used in waters with swift currents. Additionally, there are no propellers or control surfaces underwater; hence, the vessel does not tend to snag on floating vegetation and can be dragged over sandbars. An area of more than 10 acres was surveyed using the Bathy-drone in one battery charge and in less than 25 min.
12
Bobholz, Samuel, Allison Lowman, Jennifer Connelly, Elizabeth Cochran, Wade Mueller, Sean McGarry, Michael Brehler, Cassandra Gliszinski, Anna Wilczynski, and Peter LaViolette. "NIMG-23. COMPARISON OF A RADIO-PATHOMIC MODEL VERSUS A RADIOLOGY-ONLY TUMOR SEGMENTATION MODEL FOR THE DETECTION OF INFILTRATIVE TUMOR IN GLIOMA PATIENTS." Neuro-Oncology 22, Supplement_2 (November 2020): ii152. http://dx.doi.org/10.1093/neuonc/noaa215.636.
Full textAbstract:
Abstract This study used large format autopsy tissue samples to compare radio-pathomic maps of brain cancer to a current tumor segmentation algorithm. We hypothesized that an MRI-based machine learning model trained with actual histology rather than radiologist annotations cellularity would 1) improve delineation between tumor and treatment effect, and 2) detect abnormal pathology beyond the contrast-enhancing tumor region. Seventeen patients with pathologically confirmed glioma were included in this study. At autopsy, 43 tissue samples were collected from 17 subjects from whole brain slices sectioned to align with the last axial MRI prior to death. Cellularity was calculated using a color deconvolution on 40X digitized H&E stained slides from the tissue samples. In-house custom software was used to align tissue samples and cellularity information to the FLAIR image using manually defined control points. The DeepMedic algorithm was trained to segment tumors using the BraTs 2017 dataset, and then applied to our patients in order to create automated tumor probability maps. An MRI-based ensemble algorithm using a 5x5 voxel searchlight (input: T1, T1C, FLAIR, ADC) was used to predict cellularity at each voxel, using tissue samples from 14 subjects as ground truth. Both models were applied to 3 withheld test subjects in order to compare tumor probability and cellularity predictions to the pathological ground truth. The mutual information between tumor probability and actual cellularity was 1X10-15, relatively low compared to the rad-path predicted cellularity (=0.16), despite the tumor prediction model accurately highlighting regions of contrast enhancement. Additionally, the radio-pathomic ensemble model correctly identify regions of hypercellularity beyond the tumor segmentation model as well as regions of within the segmented tumor area. This study demonstrates the utility of training machine learning models with pathological ground truth rather than radiologist annotations for predicting localized tumor information, particularly in the post-treatment stage.
13
Bae, Jinseok, Hojun Jang, Cheol-Hui Min, Hyungun Choi, and Young Min Kim. "Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 1 (June 28, 2022): 86–94. http://dx.doi.org/10.1609/aaai.v36i1.19882.
Full textAbstract:
We present Neural Marionette, an unsupervised approach that discovers the skeletal structure from a dynamic sequence and learns to generate diverse motions that are consistent with the observed motion dynamics. Given a video stream of point cloud observation of an articulated body under arbitrary motion, our approach discovers the unknown low-dimensional skeletal relationship that can effectively represent the movement. Then the discovered structure is utilized to encode the motion priors of dynamic sequences in a latent structure, which can be decoded to the relative joint rotations to represent the full skeletal motion. Our approach works without any prior knowledge of the underlying motion or skeletal structure, and we demonstrate that the discovered structure is even comparable to the hand-labeled ground truth skeleton in representing a 4D sequence of motion. The skeletal structure embeds the general semantics of possible motion space that can generate motions for diverse scenarios. We verify that the learned motion prior is generalizable to the multi-modal sequence generation, interpolation of two poses, and motion retargeting to a different skeletal structure.
14
Su, Ya, and Mengyao Wang. "Age-Variation Face Recognition Based on Bayes Inference." International Journal of Pattern Recognition and Artificial Intelligence 31, no. 07 (April 10, 2017): 1756013. http://dx.doi.org/10.1142/s0218001417560134.
Full textAbstract:
Studies have discovered that face recognition will benefit from age information. However, since the age estimation is unstable in practice, it is still an open question how to improve face recognition with help of automatic age estimation techniques. This paper presents to improve the performance of face recognition by automatic age estimation. The main contribution is a new age-variational face recognition algorithm based on Bayesian framework (FRAB). By introducing the age estimation result as a prior, the recognition problem is divided into several age-specific sub-problems. As a result, the proposed algorithm leads to two algorithms according to how the age is given. The first one is FRAB-AE, which introduces age estimation result as the age prior. The second one is FRAB-GT, which considers that the ground truth of age information is given. Experimental results are conducted on FG-NET and Morph datasets to evaluate the performance of the proposed framework. It shows that the proposed algorithms is able to make use of age priors to improve the face recognition.
15
Chua, Sook-Ling, Lee Kien Foo, Hans W. Guesgen, and Stephen Marsland. "Incremental Learning of Human Activities in Smart Homes." Sensors 22, no. 21 (November 3, 2022): 8458. http://dx.doi.org/10.3390/s22218458.
Full textAbstract:
Sensor-based human activity recognition has been extensively studied. Systems learn from a set of training samples to classify actions into a pre-defined set of ground truth activities. However, human behaviours vary over time, and so a recognition system should ideally be able to continuously learn and adapt, while retaining the knowledge of previously learned activities, and without failing to highlight novel, and therefore potentially risky, behaviours. In this paper, we propose a method based on compression that can incrementally learn new behaviours, while retaining prior knowledge. Evaluation was conducted on three publicly available smart home datasets.
16
Le Moan, Steven, and Claude Cariou. "Minimax Bridgeness-Based Clustering for Hyperspectral Data." Remote Sensing 12, no. 7 (April 4, 2020): 1162. http://dx.doi.org/10.3390/rs12071162.
Full textAbstract:
Hyperspectral (HS) imaging has been used extensively in remote sensing applications like agriculture, forestry, geology and marine science. HS pixel classification is an important task to help identify different classes of materials within a scene, such as different types of crops on a farm. However, this task is significantly hindered by the fact that HS pixels typically form high-dimensional clusters of arbitrary sizes and shapes in the feature space spanned by all spectral channels. This is even more of a challenge when ground truth data is difficult to obtain and when there is no reliable prior information about these clusters (e.g., number, typical shape, intrinsic dimensionality). In this letter, we present a new graph-based clustering approach for hyperspectral data mining that does not require ground truth data nor parameter tuning. It is based on the minimax distance, a measure of similarity between vertices on a graph. Using the silhouette index, we demonstrate that the minimax distance is more suitable to identify clusters in raw hyperspectral data than two other graph-based similarity measures: mutual proximity and shared nearest neighbours. We then introduce the minimax bridgeness-based clustering approach, and we demonstrate that it can discover clusters of interest in hyperspectral data better than comparable approaches.
17
Hsieh, Cheng-Hsiung, Ze-Yu Chen, and Yi-Hung Chang. "Using Whale Optimization Algorithm and Haze Level Information in a Model-Based Image Dehazing Algorithm." Sensors 23, no. 2 (January 10, 2023): 815. http://dx.doi.org/10.3390/s23020815.
Full textAbstract:
Single image dehazing has been a challenge in the field of image restoration and computer vision. Many model-based and non-model-based dehazing methods have been reported. This study focuses on a model-based algorithm. A popular model-based method is dark channel prior (DCP) which has attracted a lot of attention because of its simplicity and effectiveness. In DCP-based methods, the model parameters should be appropriately estimated for better performance. Previously, we found that appropriate scaling factors of model parameters helped dehazing performance and proposed an improved DCP (IDCP) method that uses heuristic scaling factors for the model parameters (atmospheric light and initial transmittance). With the IDCP, this paper presents an approach to find optimal scaling factors using the whale optimization algorithm (WOA) and haze level information. The WOA uses ground truth images as a reference in a fitness function to search the optimal scaling factors in the IDCP. The IDCP with the WOA was termed IDCP/WOA. It was observed that the performance of IDCP/WOA was significantly affected by hazy ground truth images. Thus, according to the haze level information, a hazy image discriminator was developed to exclude hazy ground truth images from the dataset used in the IDCP/WOA. To avoid using ground truth images in the application stage, hazy image clustering was presented to group hazy images and their corresponding optimal scaling factors obtained by the IDCP/WOA. Then, the average scaling factors for each haze level were found. The resulting dehazing algorithm was called optimized IDCP (OIDCP). Three datasets commonly used in the image dehazing field, the RESIDE, O-HAZE, and KeDeMa datasets, were used to justify the proposed OIDCP. Then a comparison was made between the OIDCP and five recent haze removal methods. On the RESIDE dataset, the OIDCP achieved a PSNR of 26.23 dB, which was better than IDCP by 0.81 dB, DCP by 8.03 dB, RRO by 5.28, AOD by 5.6 dB, and GCAN by 1.27 dB. On the O-HAZE dataset, the OIDCP had a PSNR of 19.53 dB, which was better than IDCP by 0.06 dB, DCP by 4.39 dB, RRO by 0.97 dB, AOD by 1.41 dB, and GCAN by 0.34 dB. On the KeDeMa dataset, the OIDCP obtained the best overall performance and gave dehazed images with stable visual quality. This suggests that the results of this study may benefit model-based dehazing algorithms.
18
Lin, Cheng-Wu, Shanq-Jang Ruan, Wei-Chun Hsu, Ya-Wen Tu, and Shao-Li Han. "Optimizing the Sensor Placement for Foot Plantar Center of Pressure without Prior Knowledge Using Deep Reinforcement Learning." Sensors 20, no. 19 (September 29, 2020): 5588. http://dx.doi.org/10.3390/s20195588.
Full textAbstract:
We study the foot plantar sensor placement by a deep reinforcement learning algorithm without using any prior knowledge of the foot anatomical area. To apply a reinforcement learning algorithm, we propose a sensor placement environment and reward system that aims to optimize fitting the center of pressure (COP) trajectory during the self-selected speed running task. In this environment, the agent considers placing eight sensors within a 7 × 20 grid coordinate system, and then the final pattern becomes the result of sensor placement. Our results show that this method (1) can generate a sensor placement, which has a low mean square error in fitting ground truth COP trajectory, and (2) robustly discovers the optimal sensor placement in a large number of combinations, which is more than 116 quadrillion. This method is also feasible for solving different tasks, regardless of the self-selected speed running task.
19
Iantsen, Andrei, Marta Ferreira, Francois Lucia, Vincent Jaouen, Caroline Reinhold, Pietro Bonaffini, Joanne Alfieri, et al. "Convolutional neural networks for PET functional volume fully automatic segmentation: development and validation in a multi-center setting." European Journal of Nuclear Medicine and Molecular Imaging 48, no. 11 (March 27, 2021): 3444–56. http://dx.doi.org/10.1007/s00259-021-05244-z.
Full textAbstract:
Abstract Purpose In this work, we addressed fully automatic determination of tumor functional uptake from positron emission tomography (PET) images without relying on other image modalities or additional prior constraints, in the context of multicenter images with heterogeneous characteristics. Methods In cervical cancer, an additional challenge is the location of the tumor uptake near or even stuck to the bladder. PET datasets of 232 patients from five institutions were exploited. To avoid unreliable manual delineations, the ground truth was generated with a semi-automated approach: a volume containing the tumor and excluding the bladder was first manually determined, then a well-validated, semi-automated approach relying on the Fuzzy locally Adaptive Bayesian (FLAB) algorithm was applied to generate the ground truth. Our model built on the U-Net architecture incorporates residual blocks with concurrent spatial squeeze and excitation modules, as well as learnable non-linear downsampling and upsampling blocks. Experiments relied on cross-validation (four institutions for training and validation, and the fifth for testing). Results The model achieved good Dice similarity coefficient (DSC) with little variability across institutions (0.80 ± 0.03), with higher recall (0.90 ± 0.05) than precision (0.75 ± 0.05) and improved results over the standard U-Net (DSC 0.77 ± 0.05, recall 0.87 ± 0.02, precision 0.74 ± 0.08). Both vastly outperformed a fixed threshold at 40% of SUVmax (DSC 0.33 ± 0.15, recall 0.52 ± 0.17, precision 0.30 ± 0.16). In all cases, the model could determine the tumor uptake without including the bladder. Neither shape priors nor anatomical information was required to achieve efficient training. Conclusion The proposed method could facilitate the deployment of a fully automated radiomics pipeline in such a challenging multicenter context.
20
Li, Nanxin, Bochao Cheng, and Junran Zhang. "A Cascade Model with Prior Knowledge for Bone Age Assessment." Applied Sciences 12, no. 15 (July 22, 2022): 7371. http://dx.doi.org/10.3390/app12157371.
Full textAbstract:
Bone age is commonly used to reflect growth and development trends in children, predict adult heights, and diagnose endocrine disorders. Nevertheless, the existing automated bone age assessment (BAA) models do not consider the nonlinearity and continuity of hand bone development simultaneously. In addition, most existing BAA models are based on datasets from European and American children and may not be applicable to the developmental characteristics of Chinese children. Thus, this work proposes a cascade model that fuses prior knowledge. Specifically, a novel bone age representation is defined, which incorporates nonlinear and continuous features of skeletal development and is implemented by a cascade model. Moreover, corresponding regions of interest (RoIs) based on RUS-CHN were extracted by YOLO v5 as prior knowledge inputs to the model. In addition, based on MobileNet v2, an improved feature extractor was proposed by introducing the Convolutional Block Attention Module and increasing the receptive field to improve the accuracy of the evaluation. The experimental results show that the mean absolute error (MAE) is 4.44 months and significant correlations with the reference bone age is (r = 0.994, p < 0.01); accuracy is 94.04% for ground truth within ±1 year. Overall, the model design adequately considers hand bone development features and has high accuracy and consistency, and it also has some applicability on public datasets, showing potential for practical and clinical applications.
21
Kim, Do-Un, Woo-Cheol Lee, Han-Lim Choi, Joontae Park, Jihoon An, and Wonjun Lee. "Ground Moving Target Tracking Filter Considering Terrain and Kinematics." Sensors 21, no. 20 (October 18, 2021): 6902. http://dx.doi.org/10.3390/s21206902.
Full textAbstract:
This paper addresses ground target tracking (GTT) for airborne radar. Digital terrain elevation data (DTED) are widely used for GTT as prior information under the premise that ground targets are constrained on terrain. Existing works fuse DTED to a tracking filter in a way that adopts only the assumption that the position of the target is constrained on the terrain. However, by kinematics, it is natural that the velocity of the moving ground target is constrained as well. Furthermore, DTED provides neither continuous nor accurate measurement of terrain elevation. To overcome such limitations, we propose a novel soft terrain constraint and a constraint-aided particle filter. To resolve the difficulties in applying the DTED to the GTT, first, we reconstruct the ground-truth terrain elevation using a Gaussian process and treat DTED as a noisy observation of it. Then, terrain constraint is formulated as joint soft constraints of position and velocity. Finally, we derive a Soft Terrain Constrained Particle Filter (STC-PF) that propagates particles while approximately satisfying the terrain constraint in the prediction step. In the numerical simulations, STC-PF outperforms the Smoothly Constrained Kalman Filter (SCKF) in terms of tracking performance because SCKF can only incorporate hard constraints.
22
Norberg, Johannes, Ilkka I. Virtanen, Lassi Roininen, Juha Vierinen, Mikko Orispää, Kirsti Kauristie, and Markku S. Lehtinen. "Bayesian statistical ionospheric tomography improved by incorporating ionosonde measurements." Atmospheric Measurement Techniques 9, no. 4 (April 28, 2016): 1859–69. http://dx.doi.org/10.5194/amt-9-1859-2016.
Full textAbstract:
Abstract. We validate two-dimensional ionospheric tomography reconstructions against EISCAT incoherent scatter radar measurements. Our tomography method is based on Bayesian statistical inversion with prior distribution given by its mean and covariance. We employ ionosonde measurements for the choice of the prior mean and covariance parameters and use the Gaussian Markov random fields as a sparse matrix approximation for the numerical computations. This results in a computationally efficient tomographic inversion algorithm with clear probabilistic interpretation. We demonstrate how this method works with simultaneous beacon satellite and ionosonde measurements obtained in northern Scandinavia. The performance is compared with results obtained with a zero-mean prior and with the prior mean taken from the International Reference Ionosphere 2007 model. In validating the results, we use EISCAT ultra-high-frequency incoherent scatter radar measurements as the ground truth for the ionization profile shape. We find that in comparison to the alternative prior information sources, ionosonde measurements improve the reconstruction by adding accurate information about the absolute value and the altitude distribution of electron density. With an ionosonde at continuous disposal, the presented method enhances stand-alone near-real-time ionospheric tomography for the given conditions significantly.
23
Norberg, J., I. I. Virtanen, L. Roininen, J. Vierinen, M. Orispää, K. Kauristie, and M. S. Lehtinen. "Ionosonde measurements in Bayesian statistical ionospheric tomography with incoherent scatter radar validation." Atmospheric Measurement Techniques Discussions 8, no. 9 (September 21, 2015): 9823–51. http://dx.doi.org/10.5194/amtd-8-9823-2015.
Full textAbstract:
Abstract. We validate two-dimensional ionospheric tomography reconstructions against EISCAT incoherent scatter radar measurements. Our tomography method is based on Bayesian statistical inversion with prior distribution given by its mean and covariance. We employ ionosonde measurements for the choice of the prior mean and covariance parameters, and use the Gaussian Markov random fields as a sparse matrix approximation for the numerical computations. This results in a computationally efficient and statistically clear inversion algorithm for tomography. We demonstrate how this method works with simultaneous beacon satellite and ionosonde measurements obtained in northern Scandinavia. The performance is compared with results obtained with a zero mean prior and with the prior mean taken from the International Reference Ionosphere 2007 model. In validating the results, we use EISCAT UHF incoherent scatter radar measurements as the ground truth for the ionization profile shape. We find that ionosonde measurements improve the reconstruction by adding accurate information about the absolute value and the height distribution of electron density, and outperforms the alternative prior information sources. With an ionosonde at continuous disposal, the presented method enhances stand-alone near real-time ionospheric tomography for the given conditions significantly.
24
Ghassami, AmirEmad, Saber Salehkaleybar, Negar Kiyavash, and Kun Zhang. "Counting and Sampling from Markov Equivalent DAGs Using Clique Trees." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 3664–71. http://dx.doi.org/10.1609/aaai.v33i01.33013664.
Full textAbstract:
A directed acyclic graph (DAG) is the most common graphical model for representing causal relationships among a set of variables. When restricted to using only observational data, the structure of the ground truth DAG is identifiable only up to Markov equivalence, based on conditional independence relations among the variables. Therefore, the number of DAGs equivalent to the ground truth DAG is an indicator of the causal complexity of the underlying structure–roughly speaking, it shows how many interventions or how much additional information is further needed to recover the underlying DAG. In this paper, we propose a new technique for counting the number of DAGs in a Markov equivalence class. Our approach is based on the clique tree representation of chordal graphs. We show that in the case of bounded degree graphs, the proposed algorithm is polynomial time. We further demonstrate that this technique can be utilized for uniform sampling from a Markov equivalence class, which provides a stochastic way to enumerate DAGs in the equivalence class and may be needed for finding the best DAG or for causal inference given the equivalence class as input. We also extend our counting and sampling method to the case where prior knowledge about the underlying DAG is available, and present applications of this extension in causal experiment design and estimating the causal effect of joint interventions.
25
Wu, Xinyi, Zhenyao Wu, Lili Ju, and Song Wang. "Binaural Audio-Visual Localization." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 4 (May 18, 2021): 2961–68. http://dx.doi.org/10.1609/aaai.v35i4.16403.
Full textAbstract:
Localizing sound sources in a visual scene has many important applications and quite a few traditional or learning-based methods have been proposed for this task. Humans have the ability to roughly localize sound sources within or beyond the range of the vision using their binaural system. However most existing methods use monaural audio, instead of binaural audio, as a modality to help the localization. In addition, prior works usually localize sound sources in the form of object-level bounding boxes in images or videos and evaluate the localization accuracy by examining the overlap between the ground-truth and predicted bounding boxes. This is too rough since a real sound source is often only a part of an object. In this paper, we propose a deep learning method for pixel-level sound source localization by leveraging both binaural recordings and the corresponding videos. Specifically, we design a novel Binaural Audio-Visual Network (BAVNet), which concurrently extracts and integrates features from binaural recordings and videos. We also propose a point-annotation strategy to construct pixel-level ground truth for network training and performance evaluation. Experimental results on Fair-Play and YT-Music datasets demonstrate the effectiveness of the proposed method and show that binaural audio can greatly improve the performance of localizing the sound sources, especially when the quality of the visual information is limited.
26
Cheng, Wei, Ziyan Luo, and Qiyue Yin. "Adaptive Prior-Dependent Correction Enhanced Reinforcement Learning for Natural Language Generation." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 14 (May 18, 2021): 12701–9. http://dx.doi.org/10.1609/aaai.v35i14.17504.
Full textAbstract:
Natural language generation (NLG) is an important task with various applications like neural machine translation (NMT) and image captioning. Since deep-learning-based methods have issues of exposure bias and loss inconsistency, reinforcement learning (RL) is widely adopted in NLG tasks recently. But most RL-based methods ignore the deviation ignorance issue, which means the model fails to understand the extent of token-level deviation well. It leads to semantic incorrectness and hampers the agent to perform well. To address the issue, we propose a technique called adaptive prior-dependent correction (APDC) to enhance RL. It leverages the distribution generated by computing the distances between the ground truth and all other words to correct the agent's stochastic policy. Additionally, some techniques on RL are explored to coordinate RL with APDC, which requires a reward estimation at every time step. We find that the RL-based NLG tasks are a special case in RL, where the state transition is deterministic and the afterstate value equals the Q-value at every time step. To utilize such prior knowledge, we estimate the advantage function with the difference of the Q-values which can be estimated by Monte Carlo rollouts. Experiments show that, on three tasks of NLG (NMT, image captioning, abstractive text summarization), our method consistently outperforms the state-of-the-art RL-based approaches on different frequently-used metrics.
27
Lowman, Allison, Samuel Bobholz, Michael Brehler, Savannah Duenweg, Fitzgerald Kyereme, Elizabeth Cochran, Dylan Coss, et al. "NIMG-18. A GROUND TRUTH COMPARISON OF PATHOLOGICALLY CONFIRMED GLIOBLASTOMA MARGINS TO CONTRAST ENHANCEMENT AT AUTOPSY." Neuro-Oncology 24, Supplement_7 (November 1, 2022): vii165. http://dx.doi.org/10.1093/neuonc/noac209.636.
Full textAbstract:
Abstract PURPOSE Glioblastoma is one of the most common and deadly adult brain tumors. Current standard treatment is surgical resection followed by radiation and concomitant chemotherapy (chemoRT). Glioblastoma progression is monitored using MRI, primarily relying on post-contrast T1-weighted imaging (T1C). Unfortunately, tumor invasion is known to extend beyond traditional contrast enhancement. T1-subtraction (T1S) maps have been introduced as a better tumor volume estimate. In this study we compare T1S map derived tumor annotations to a radiologist for identifying histologically confirmed tumor in patients with differing treatment histories at autopsy. METHODS Ten patients with autopsy confirmed glioblastoma and MRI within 1 month of death were recruited for this study. Seven patients received chemoRT combined (chemoRT+) and three patients received no treatment beyond surgery (chemoRT-). Patient’s brains were sliced axially in the same orientation as their final MRI using a patient-specific slicing jig. Large tissue samples were taken, processed, embedded in paraffin, stained for hematoxylin and eosin, and digitized at 40x resolution. Digital images were annotated for infiltrative tumor, pseudopalisading necrosis, and necrosis without palisading cells. T1S and radiologist annotations were created for each patient using their final MRI (mean 18 days prior to death). The annotated histology images were aligned and resampled into MRI space using custom software and the overlap of pathologically confirmed tumor and MRI derived annotations was compared. RESULTS T1S maps alone were significantly better at identifying areas of histologically confirmed tumor in chemoRT+ patients compared to chemoRT- patients (p=0.043). T1S derived annotations overlapped with 52% of histologically confirmed tumor in the chemoRT- patients and 78% in the chemoRT+. The radiologist drawn tumor masks were more accurate in chemoRT+ patients, identifying 61% confirmed tumor (trending, p=0.097, chemoRT+=61%). CONCLUSION These results demonstrate the difficulty of identifying pathologically confirmed tumor outside contrast enhancement in glioblastoma patients, even in the untreated state.
28
Michaelsen, Eckart, and Stéphane Vujasinovic. "Estimating Efforts and Success of Symmetry-Seeing Machines by Use of Synthetic Data." Symmetry 11, no. 2 (February 14, 2019): 227. http://dx.doi.org/10.3390/sym11020227.
Full textAbstract:
Representative input data are a necessary requirement for the assessment of machine-vision systems. For symmetry-seeing machines in particular, such imagery should provide symmetries as well as asymmetric clutter. Moreover, there must be reliable ground truth with the data. It should be possible to estimate the recognition performance and the computational efforts by providing different grades of difficulty and complexity. Recent competitions used real imagery labeled by human subjects with appropriate ground truth. The paper at hand proposes to use synthetic data instead. Such data contain symmetry, clutter, and nothing else. This is preferable because interference with other perceptive capabilities, such as object recognition, or prior knowledge, can be avoided. The data are given sparsely, i.e., as sets of primitive objects. However, images can be generated from them, so that the same data can also be fed into machines requiring dense input, such as multilayered perceptrons. Sparse representations are preferred, because the author’s own system requires such data, and in this way, any influence of the primitive extraction method is excluded. The presented format allows hierarchies of symmetries. This is important because hierarchy constitutes a natural and dominant part in symmetry-seeing. The paper reports some experiments using the author’s Gestalt algebra system as symmetry-seeing machine. Additionally included is a comparative test run with the state-of-the-art symmetry-seeing deep learning convolutional perceptron of the PSU. The computational efforts and recognition performance are assessed.
29
Fu, Kui, and Jia Li. "A Randomized Framework for Estimating Image Saliency Through Sparse Signal Reconstruction." International Journal of Multimedia Data Engineering and Management 9, no. 2 (April 2018): 1–20. http://dx.doi.org/10.4018/ijmdem.2018040101.
Full textAbstract:
This article proposes a randomized framework that estimates image saliency through sparse signal reconstruction. The authors simulate the measuring process of ground-truth saliency and assume that an image is free-viewed by several subjects. In the free-viewing process, each subject attends to a limited number of regions randomly selected, and a mental map of the image is reconstructed by using the subject-specific prior knowledge. By assuming that a region is difficult to be reconstructed will become conspicuous, the authors represent the prior knowledge of a subject by a dictionary of sparse bases pre-trained on random images and estimate the conspicuity score of a region according to the activation costs of sparse bases as well as the sparse reconstruction error. Finally, the saliency map of an image is generated by summing up all conspicuity maps obtained. Experimental results show proposed approach achieves impressive performance in comparisons with 16 state-of-the-art approaches.
30
Kim, Bong-Kyu, Nam Hoon Goo, Jong Hyuk Lee, and Jun Hyun Han. "Reconstruction and Size Prediction of Prior Austenite Grain Boundary (PAGB) using Artificial Neural Networks." Korean Journal of Metals and Materials 58, no. 12 (December 5, 2020): 822–29. http://dx.doi.org/10.3365/kjmm.2020.58.12.822.
Full textAbstract:
To automatically reconstruct the prior austenite grains from as-quenched martensitic structure, we applied a deep learning algorithm to recognize the prior austenite grains boundaries hidden in the martensitic matrix. The FC-DenseNet architecture based on FCN (fully convolutional networks) was used to train the martensite and ground truth label of the prior austenite grain boundaries. The original martensite structures and prior austenite grain boundaries were prepared using different chemical etching solutions. The initial PAGS detection rate was as low as 37.1%, which is not suitable for quantifying the basic properties of the microstructure such as grain size or grain boundary area. By changing the weight factor of the neural net loss function and increasing the size of the data set, the detection rate was improved up to 56.1%. However, even when the detection rate reached 50% or more, the quality of the reconstructed PAGS was not comparable to the analytically calculated results based on EBSD measurements and crystallographic orientation relationships. The prior austenite grain size data sets were obtained from martensite samples via the FCDenseNet method, and had a linear correlation with the mechanical properties measured in the same samples. In order to improve the accuracy of the detection rate using neural networks, it is necessary to increase the number of neural networks and data sets.
31
Semassel, Imed Eddine, and Sadok Ben Yahia. "Effective Optimization of Billboard Ads Based on CDR Data Leverage." Journal of Telecommunications and the Digital Economy 10, no. 2 (June 10, 2022): 76–95. http://dx.doi.org/10.18080/jtde.v10n2.527.
Full textAbstract:
Call Detail Records (CDRs) provide metadata about phone calls and text message usage. Many studies have shown these CDR data to provide gainful information on people's mobility patterns and relationships with fine-grained aspects, both temporal and spatial elements. This information allows tracking population levels in each country region, individual movements, seasonal locations, population changes, and migration. This paper introduces a method for analyzing and exploiting CDR data to recommend billboard ads. We usher by clustering the locations based on the recorded activities' pattern regarding users' mobility. The key idea is to rate sites by performing a thorough cluster analysis over the achieved data, having no prior ground-truth information, to assess and optimize the ads' placements and timing for more efficiency at the billboards.
32
Feng, Luyu, Yaru Xue, Chong Chen, Mengjun Guo, and Hewei Shen. "De-aliased high-resolution Radon transform based on the sparse prior information from the convolutional neural network." Journal of Geophysics and Engineering 19, no. 4 (July 9, 2022): 663–80. http://dx.doi.org/10.1093/jge/gxac041.
Full textAbstract:
Abstract The resolution of Radon transform is crucial in seismic data interpolation. The high-frequency components usually suffer from serious aliasing problems while the sampling is insufficient. Constraining high-frequency components with unaliased low-frequency components is an effective method for improving the resolution of seismic data. However, it is difficult to obtain high-resolution low-frequency Radon coefficients by traditional analytical methods due to the strong correlation of basis functions. For this problem, a sparse inversion method using the neural network is proposed. First, the convolution model is deduced between the conjugated Radon solution and its ground truth. Then, a convolutional neural network (CNN), with the conjugate Radon solution as input, is designed to realize the deconvolution from the conjugate solution to the sparse and high-resolution Radon solution. Finally, the obtained sparse solution is regarded as prior knowledge of the iteratively reweighted least-squares algorithm. The proposed strategy has a distinct advantage in improving the resolution of low-frequency components, which helps overcome the aliasing. Interpolation experiments on synthetic and field data demonstrate the de-aliased performance of this CNN-based method.
33
Kabasakal Badamchi, Devrim. "Academic freedom: How to conceptualize and justify it?" Philosophy & Social Criticism 48, no. 4 (May 2022): 619–30. http://dx.doi.org/10.1177/01914537211072888.
Full textAbstract:
This article deals with the question of how academic freedom can be conceptualized and justified. First, I analyze two conceptions of academic freedom: institutional autonomy and intellectual and professional autonomy. I claim that institutional autonomy is a limited way to conceptualize academic freedom because there is no guarantee that institutions always favor freedom of intellectuals. In line with this, I argue that academic freedom as intellectual and professional autonomy should be the prior, if not the only, conception of academic freedom. Second, I examine critically different justifications of academic freedom that provide us with reasons to attach high protection to academic freedom as a particular right. I contend that the justification of the university as a realm of discovery of truth and independent knowledge production has to be complemented with the justifications of the university as a realm of democratic free debate and the autonomy of academics to speak freely. This is because, the discovery of truth argument alone does not require us to accept any moral principle other than skepticism about our own beliefs, which is not a strong ground for free speech on its own. Third, I argue that equal autonomy provides a good reason for academic freedom by emphasizing the rights of academics to speak in line with what they believe is true and only in this way can they contribute to the democratic debate in academia. This line of reasoning endorses the value of the search for truth and knowledge too since it is only possible for academics to perform the profession of search for truth when they are able to speak, write and research freely.
34
Hou, Yingxu, Xiaodong Huang, and Lin Zhao. "Point-to-Surface Upscaling Algorithms for Snow Depth Ground Observations." Remote Sensing 14, no. 19 (September 28, 2022): 4840. http://dx.doi.org/10.3390/rs14194840.
Full textAbstract:
To validate the accuracy of snow depth products retrieved from passive microwave remote sensing data with a high confidence level, the verification method based on points of ground observation is subject to great uncertainty, due to the scale effect. Thus, it is necessary to use a point-to-surface scale transformation method to obtain the relative ground truth at the remote sensing pixel scale. In this study, by using the snow depth ground observations at different observation scales, the upscaling methods are conducted based on simple average (SA), geostatistical, Bayes maximum entropy (BME), and random forest (RF) algorithms. In addition, the cross-validation of the leave-one-out method is employed to validate the upscaling results. The results show that the SA algorithm is seriously inadequate for estimating snow depth variation in space, and is only suitable for regions with relatively flat terrain and small variation of snow depth. The BME algorithm can introduce prior knowledge and perform kernel smoothing on observed data, and the upscaling result is superior to geostatistical and RF algorithms, especially when the observed data is insufficient, and outliers appear. The results of the study are expected to provide a reference for developing a point-to-surface upscaling method based on snow depth ground observations, and to further solve the uncertainties caused by scale effects in snow depth and other land surface parameter inversion and validation, by using remote sensing data.
35
Schüle, T., C. Schnörr, J. Hornegger, and S. Weber. "A Linear Programming Approach to Limited Angle 3D Reconstruction from DSA Projections." Methods of Information in Medicine 43, no. 04 (2004): 320–26. http://dx.doi.org/10.1055/s-0038-1633875.
Full textAbstract:
Summary Objectives: We investigate the feasibility of binary-valued 3D tomographic reconstruction using only a small number of projections acquired over a limited range of angles. Methods: Regularization of this strongly ill-posed problem is achieved by (i) confining the reconstruction to binary vessel/non-vessel decisions, and (ii) by minimizing a global functional involving a smoothness prior. Results: Our approach successfully reconstructs volumetric vessel structures from three projections taken within 90°. The percentage of reconstructed voxels differing from ground truth is below 1%. Conclusion: We demonstrate that for particular applications – like Digital Subtraction Angiography – 3D reconstructions are possible where conventional methods must fail, due to a severely limited imaging geometry. This could play an important role for dose reduction and 3D reconstruction using non-conventional technical setups.
36
Duenweg, Savannah R., Xi Fang, Samuel A. Bobholz, Allison K. Lowman, Michael Brehler, Fitzgerald Kyereme, Kenneth A. Iczkowski, Kenneth M. Jacobsohn, Anjishnu Banerjee, and Peter S. LaViolette. "Diffusion Restriction Comparison between Gleason 4 Fused Glands and Cribriform Glands within Patient Using Whole-Mount Prostate Pathology as Ground Truth." Tomography 8, no. 2 (March 2, 2022): 635–43. http://dx.doi.org/10.3390/tomography8020053.
Full textAbstract:
The presence and extent of cribriform patterned Gleason 4 (G4) glands are associated with poor prognosis following radical prostatectomy. This study used whole-mount prostate histology and multiparametric magnetic resonance imaging (MP-MRI) to evaluate diffusion differences in G4 gland morphology. Fourty-eight patients underwent MP-MRI prior to prostatectomy, of whom 22 patients had regions of both G4 cribriform glands and G4 fused glands (G4CG and G4FG, respectively). After surgery, the prostate was sliced using custom, patient-specific 3D-printed slicing jigs modeled according to the T2-weighted MR image, processed, and embedded in paraffin. Whole-mount hematoxylin and eosin-stained slides were annotated by our urologic pathologist and digitally contoured to differentiate the lumen, epithelium, and stroma. Digitized slides were co-registered to the T2-weighted MRI scan. Linear mixed models were fitted to the MP-MRI data to consider the different hierarchical structures at the patient and slide level. We found that Gleason 4 cribriform glands were more diffusion-restricted than fused glands.
37
Lu, Shaolin, Shibo Li, Yu Wang, Lihai Zhang, Ying Hu, and Bing Li. "Prior information-based high-resolution tomography image reconstruction from a single digitally reconstructed radiograph." Physics in Medicine & Biology 67, no. 8 (April 1, 2022): 085004. http://dx.doi.org/10.1088/1361-6560/ac508d.
Full textAbstract:
Abstract Tomography images are essential for clinical diagnosis and trauma surgery, allowing doctors to understand the internal information of patients in more detail. Since the large amount of x-ray radiation from the continuous imaging during the process of computed tomography scanning can cause serious harm to the human body, reconstructing tomographic images from sparse views becomes a potential solution to this problem. Here we present a deep-learning framework for tomography image reconstruction, namely TIReconNet, which defines image reconstruction as a data-driven supervised learning task that allows a mapping between the 2D projection view and the 3D volume to emerge from corpus. The proposed framework consists of four parts: feature extraction module, shape mapping module, volume generation module and super resolution module. The proposed framework combines 2D and 3D operations, which can generate high-resolution tomographic images with a relatively small amount of computing resources and maintain spatial information. The proposed method is verified on chest digitally reconstructed radiographs, and the reconstructed tomography images have achieved PSNR value of 18.621 ± 1.228 dB and SSIM value of 0.872 ± 0.041 when compared against the ground truth. In conclusion, an innovative convolutional neural network architecture is proposed and validated in this study, which proves that there is the potential to generate a 3D high-resolution tomographic image from a single 2D image using deep learning. This method may actively promote the application of reconstruction technology for radiation reduction, and further exploration of intraoperative guidance in trauma and orthopedics.
38
Wang, Jun, Qian He, Ping Zhou, and Qinghua Gong. "Test of the RUSLE and Key Influencing Factors Using GIS and Probability Methods: A Case Study in Nanling National Nature Reserve, South China." Advances in Civil Engineering 2019 (November 11, 2019): 1–15. http://dx.doi.org/10.1155/2019/7129639.
Full textAbstract:
The main purposes of the study were to test the performance of the Revised Universal Soil Loss Equation (RUSLE) and to understand the key factors responsible for generating soil erosion in the Nanling National Nature Reserve (NNNR), South China, where soil erosion has become a very serious ecological and environmental problem. By combining the RUSLE and geographic information system (GIS) data, we first produced a map of soil erosion risk at 30 m-resolution pixel level with predicted factors. We then used consecutive Landsat 8 satellite images to obtain the spatial distribution of four types of soil erosion and carried out ground truth checking of the RUSLE. On this basis, we innovatively developed a probability model to explore the relationship between four types of soil erosion and the key influencing factors, identify high erosion area, and analyze the reason for the differences derived from the RUSLE. The results showed that the overall accuracy of image interpretation was acceptable, which could be used to represent the currently actual spatial distribution of soil erosion. Ground truth checking indicated some differences between the spatial distribution and class of soil erosion derived from the RUSLE and the actual situation. The performance of the RUSLE was unsatisfactory, producing differences and even some errors when used to estimate the ecological risks posed by soil erosion within the NNNR. We finally produced a probability table revealing the degree of influence of each factor on different types of soil erosion and quantitatively elucidated the reason for generating these differences. We suggested that soil erosion type and the key influencing factors should be identified prior to soil erosion risk assessment in a region.
39
Peng, Andi, Besmira Nushi, Emre Kiciman, Kori Inkpen, and Ece Kamar. "Investigations of Performance and Bias in Human-AI Teamwork in Hiring." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (June 28, 2022): 12089–97. http://dx.doi.org/10.1609/aaai.v36i11.21468.
Full textAbstract:
In AI-assisted decision-making, effective hybrid (human-AI) teamwork is not solely dependent on AI performance alone, but also on its impact on human decision-making. While prior work studies the effects of model accuracy on humans, we endeavour here to investigate the complex dynamics of how both a model's predictive performance and bias may transfer to humans in a recommendation-aided decision task. We consider the domain of ML-assisted hiring, where humans---operating in a constrained selection setting---can choose whether they wish to utilize a trained model's inferences to help select candidates from written biographies. We conduct a large-scale user study leveraging a re-created dataset of real bios from prior work, where humans predict the ground truth occupation of given candidates with and without the help of three different NLP classifiers (random, bag-of-words, and deep neural network). Our results demonstrate that while high-performance models significantly improve human performance in a hybrid setting, some models mitigate hybrid bias while others accentuate it. We examine these findings through the lens of decision conformity and observe that our model architecture choices have an impact on human-AI conformity and bias, motivating the explicit need to assess these complex dynamics prior to deployment.
40
Bulsink, Rianne, Mithun Kuniyil Ajith Singh, Marvin Xavierselvan, Srivalleesha Mallidi, Wiendelt Steenbergen, and Kalloor Joseph Francis. "Oxygen Saturation Imaging Using LED-Based Photoacoustic System." Sensors 21, no. 1 (January 4, 2021): 283. http://dx.doi.org/10.3390/s21010283.
Full textAbstract:
Oxygen saturation imaging has potential in several preclinical and clinical applications. Dual-wavelength LED array-based photoacoustic oxygen saturation imaging can be an affordable solution in this case. For the translation of this technology, there is a need to improve its accuracy and validate it against ground truth methods. We propose a fluence compensated oxygen saturation imaging method, utilizing structural information from the ultrasound image, and prior knowledge of the optical properties of the tissue with a Monte-Carlo based light propagation model for the dual-wavelength LED array configuration. We then validate the proposed method with oximeter measurements in tissue-mimicking phantoms. Further, we demonstrate in vivo imaging on small animal and a human subject. We conclude that the proposed oxygen saturation imaging can be used to image tissue at a depth of 6–8 mm in both preclinical and clinical applications.
41
Yan, Hui, and Jianrong Dai. "Reconstructing a 3D Medical Image from a Few 2D Projections Using a B-Spline-Based Deformable Transformation." Mathematics 11, no. 1 (December 25, 2022): 69. http://dx.doi.org/10.3390/math11010069.
Full textAbstract:
(1) Background: There was a need for 3D image reconstruction from a series of 2D projections in medical applications. However, additional exposure to X-ray projections may harm human health. To alleviate it, minimizing the projection numbers is a solution to reduce X-ray exposure, but this would cause significant image noise and artifacts. (2) Purpose: In this study, a method was proposed for the reconstruction of a 3D image from a minimal set of 2D X-ray projections using a B-spline-based deformable transformation. (3) Methods: The inputs of this method were a 3D image which was acquired in previous treatment and used as a prior image and a minimal set of 2D projections which were acquired during the current treatment. The goal was to reconstruct a new 3D image in current treatment from the two inputs. The new 3D image was deformed from the prior image via the displacement matrixes that were interpolated by the B-spline coefficients. The B-spline coefficients were solved with the objective function, which was defined as the mean square error between the reconstructed and the ground-truth projections. In the optimization process the gradient of the objective function was calculated, and the B-spline coefficients were then updated. For the acceleration purpose, the computation of the 2D and 3D image reconstructions and B-spline interpolation were implemented on a graphics processing unit (GPU). (4) Results: When the scan angles were more than 60°, the image quality was significantly improved, and the reconstructed image was comparable to that of the ground-truth image. As the scan angles were less than 30°, the image quality was significantly degraded. The influence of the scan orientation on the image quality was minor. With the application of GPU acceleration, the reconstruction efficiency was improved by hundred times compared to that of the conventional CPU. (5) Conclusions: The proposed method was able to generate a high-quality 3D image using a few 2D projections, which amount to ~ 20% of the total projections required for a standard image. The introduction of the B-spline-interpolated displacement matrix was effective in the suppressing noise in the reconstructed image. This method could significantly reduce the imaging time and the radiation exposure of patients under treatment.
42
Radeva, Maria, Dorothee Predel, Sven Winzler, Ulf Teichgräber, Alexander Pfeil, Ansgar Malich, and Ismini Papageorgiou. "Reliability of a Risk-Factor Questionnaire for Osteoporosis: A Primary Care Survey Study with Dual Energy X-ray Absorptiometry Ground Truth." International Journal of Environmental Research and Public Health 18, no. 3 (January 28, 2021): 1136. http://dx.doi.org/10.3390/ijerph18031136.
Full textAbstract:
(1) Purpose: Predisposing factors to osteoporosis (OP) as well as dual-source x-ray densitometry (DXA) steer therapeutic decisions by determining the FRAX index. This study examines the reliability of a standard risk factor questionnaire in OP-screening. (2) Methods: n = 553 eligible questionnaires encompassed 24 OP-predisposing factors. Reliability was assessed using DXA as a gold standard. Multiple logistic regression and Spearman’s correlations, as well as the confounding influence of age and body mass index, were analyzed in SPSS (IBM Corporation, Armonk, NY, USA). (3) Results: Our study revealed low patient self-awareness regarding OP and its risk factors. One out of every four patients reported a positive history for osteoporosis not confirmed by DXA. The extraordinarily high incidence of rheumatoid arthritis and thyroid disorders likely reflect confusion with other diseases or health anxiety. FRAX-determining risk factors such as malnutrition, liver insufficiency, prior fracture without trauma, and glucocorticoid therapy did not correlate with increased OP incidence, altogether demonstrating how inaccurate survey information could influence therapeutic decisions on osteoporosis. (4) Conclusions: Contradictive results and a low level of patient self-awareness suggest a high degree of uncertainty and low reliability of the current OP risk factor survey.
43
Czerkawski, Mikolaj, Priti Upadhyay, Christopher Davison, Astrid Werkmeister, Javier Cardona, Robert Atkinson, Craig Michie, Ivan Andonovic, Malcolm Macdonald, and Christos Tachtatzis. "Deep Internal Learning for Inpainting of Cloud-Affected Regions in Satellite Imagery." Remote Sensing 14, no. 6 (March 10, 2022): 1342. http://dx.doi.org/10.3390/rs14061342.
Full textAbstract:
Cloud cover remains a significant limitation to a broad range of applications relying on optical remote sensing imagery, including crop identification/yield prediction, climate monitoring, and land cover classification. A common approach to cloud removal treats the problem as an inpainting task and imputes optical data in the cloud-affected regions employing either mosaicing historical data or making use of sensing modalities not impacted by cloud obstructions, such as SAR. Recently, deep learning approaches have been explored in these applications; however, the majority of reported solutions rely on external learning practices, i.e., models trained on fixed datasets. Although these models perform well within the context of a particular dataset, a significant risk of spatial and temporal overfitting exists when applied in different locations or at different times. Here, cloud removal was implemented within an internal learning regime through an inpainting technique based on the deep image prior. The approach was evaluated on both a synthetic dataset with an exact ground truth, as well as real samples. The ability to inpaint the cloud-affected regions for varying weather conditions across a whole year with no prior training was demonstrated, and the performance of the approach was characterised.
44
Amyar, Amine, Romain Modzelewski, Pierre Vera, Vincent Morard, and Su Ruan. "Weakly Supervised Tumor Detection in PET Using Class Response for Treatment Outcome Prediction." Journal of Imaging 8, no. 5 (May 9, 2022): 130. http://dx.doi.org/10.3390/jimaging8050130.
Full textAbstract:
It is proven that radiomic characteristics extracted from the tumor region are predictive. The first step in radiomic analysis is the segmentation of the lesion. However, this task is time consuming and requires a highly trained physician. This process could be automated using computer-aided detection (CAD) tools. Current state-of-the-art methods are trained in a supervised learning setting, which requires a lot of data that are usually not available in the medical imaging field. The challenge is to train one model to segment different types of tumors with only a weak segmentation ground truth. In this work, we propose a prediction framework including a 3D tumor segmentation in positron emission tomography (PET) images, based on a weakly supervised deep learning method, and an outcome prediction based on a 3D-CNN classifier applied to the segmented tumor regions. The key step is to locate the tumor in 3D. We propose to (1) calculate two maximum intensity projection (MIP) images from 3D PET images in two directions, (2) classify the MIP images into different types of cancers, (3) generate the class activation maps through a multitask learning approach with a weak prior knowledge, and (4) segment the 3D tumor region from the two 2D activation maps with a proposed new loss function for the multitask. The proposed approach achieves state-of-the-art prediction results with a small data set and with a weak segmentation ground truth. Our model was tested and validated for treatment response and survival in lung and esophageal cancers on 195 patients, with an area under the receiver operating characteristic curve (AUC) of 67% and 59%, respectively, and a dice coefficient of 73% and 0.77% for tumor segmentation.
45
Rantala, Leevi, and Mika Mäntylä. "Predicting technical debt from commit contents: reproduction and extension with automated feature selection." Software Quality Journal 28, no. 4 (July 4, 2020): 1551–79. http://dx.doi.org/10.1007/s11219-020-09520-3.
Full textAbstract:
AbstractSelf-admitted technical debt refers to sub-optimal development solutions that are expressed in written code comments or commits. We reproduce and improve on a prior work by Yan et al. (2018) on detecting commits that introduce self-admitted technical debt. We use multiple natural language processing methods: Bag-of-Words, topic modeling, and word embedding vectors. We study 5 open-source projects. Our NLP approach uses logistic Lasso regression from Glmnet to automatically select best predictor words. A manually labeled dataset from prior work that identified self-admitted technical debt from code level commits serves as ground truth. Our approach achieves + 0.15 better area under the ROC curve performance than a prior work, when comparing only commit message features, and + 0.03 better result overall when replacing manually selected features with automatically selected words. In both cases, the improvement was statistically significant (p < 0.0001). Our work has four main contributions, which are comparing different NLP techniques for SATD detection, improved results over previous work, showing how to generate generalizable predictor words when using multiple repositories, and producing a list of words correlating with SATD. As a concrete result, we release a list of the predictor words that correlate positively with SATD, as well as our used datasets and scripts to enable replication studies and to aid in the creation of future classifiers.
46
Zhang, Chenyang, Rongchun Zhang, Sheng Jin, and Xuefeng Yi. "PFD-SLAM: A New RGB-D SLAM for Dynamic Indoor Environments Based on Non-Prior Semantic Segmentation." Remote Sensing 14, no. 10 (May 19, 2022): 2445. http://dx.doi.org/10.3390/rs14102445.
Full textAbstract:
Now, most existing dynamic RGB-D SLAM methods are based on deep learning or mathematical models. Abundant training sample data is necessary for deep learning, and the selection diversity of semantic samples and camera motion modes are closely related to the robust detection of moving targets. Furthermore, the mathematical models are implemented at the feature-level of segmentation, which is likely to cause sub or over-segmentation of dynamic features. To address this problem, different from most feature-level dynamic segmentation based on mathematical models, a non-prior semantic dynamic segmentation based on a particle filter is proposed in this paper, which aims to attain the motion object segmentation. Firstly, GMS and optical flow are used to calculate an inter-frame difference image, which is considered an observation measurement of posterior estimation. Then, a motion equation of a particle filter is established using Gaussian distribution. Finally, our proposed segmentation method is integrated into the front end of visual SLAM and establishes a new dynamic SLAM, PFD-SLAM. Extensive experiments on the public TUM datasets and real dynamic scenes are conducted to verify location accuracy and practical performances of PFD-SLAM. Furthermore, we also compare experimental results with several state-of-the-art dynamic SLAM methods in terms of two evaluation indexes, RPE and ATE. Still, we provide visual comparisons between the camera estimation trajectories and ground truth. The comprehensive verification and testing experiments demonstrate that our PFD-SLAM can achieve better dynamic segmentation results and robust performances.
47
Yu, Emilie, Rahul Arora, J. Andreas Bærentzen, Karan Singh, and Adrien Bousseau. "Piecewise-smooth surface fitting onto unstructured 3D sketches." ACM Transactions on Graphics 41, no. 4 (July 2022): 1–16. http://dx.doi.org/10.1145/3528223.3530100.
Full textAbstract:
We propose a method to transform unstructured 3D sketches into piecewise smooth surfaces that preserve sketched geometric features. Immersive 3D drawing and sketch-based 3D modeling applications increasingly produce imperfect and unstructured collections of 3D strokes as design output. These 3D sketches are readily perceived as piecewise smooth surfaces by viewers, but are poorly handled by existing 3D surface techniques tailored to well-connected curve networks or sparse point sets. Our algorithm is aligned with human tendency to imagine the strokes as a small set of simple smooth surfaces joined along stroke boundaries. Starting with an initial proxy surface, we iteratively segment the surface into smooth patches joined sharply along some strokes, and optimize these patches to fit surrounding strokes. Our evaluation is fourfold: we demonstrate the impact of various algorithmic parameters, we evaluate our method on synthetic sketches with known ground truth surfaces, we compare to prior art, and we show compelling results on more than 50 designs from a diverse set of 3D sketch sources.
48
Kulkarni, Viraj, Manish Gawali, and Amit Kharat. "Key Technology Considerations in Developing and Deploying Machine Learning Models in Clinical Radiology Practice." JMIR Medical Informatics 9, no. 9 (September 9, 2021): e28776. http://dx.doi.org/10.2196/28776.
Full textAbstract:
The use of machine learning to develop intelligent software tools for the interpretation of radiology images has gained widespread attention in recent years. The development, deployment, and eventual adoption of these models in clinical practice, however, remains fraught with challenges. In this paper, we propose a list of key considerations that machine learning researchers must recognize and address to make their models accurate, robust, and usable in practice. We discuss insufficient training data, decentralized data sets, high cost of annotations, ambiguous ground truth, imbalance in class representation, asymmetric misclassification costs, relevant performance metrics, generalization of models to unseen data sets, model decay, adversarial attacks, explainability, fairness and bias, and clinical validation. We describe each consideration and identify the techniques used to address it. Although these techniques have been discussed in prior research, by freshly examining them in the context of medical imaging and compiling them in the form of a laundry list, we hope to make them more accessible to researchers, software developers, radiologists, and other stakeholders.
49
Lee, Yoonho, Wonjae Kim, Wonpyo Park, and Seungjin Choi. "Discrete Infomax Codes for Supervised Representation Learning." Entropy 24, no. 4 (April 2, 2022): 501. http://dx.doi.org/10.3390/e24040501.
Full textAbstract:
For high-dimensional data such as images, learning an encoder that can output a compact yet informative representation is a key task on its own, in addition to facilitating subsequent processing of data. We present a model that produces discrete infomax codes (DIMCO); we train a probabilistic encoder that yields k-way d-dimensional codes associated with input data. Our model maximizes the mutual information between codes and ground-truth class labels, with a regularization which encourages entries of a codeword to be statistically independent. In this context, we show that the infomax principle also justifies existing loss functions, such as cross-entropy as its special cases. Our analysis also shows that using shorter codes reduces overfitting in the context of few-shot classification, and our various experiments show this implicit task-level regularization effect of DIMCO. Furthermore, we show that the codes learned by DIMCO are efficient in terms of both memory and retrieval time compared to prior methods.
50
Lilli, L., E. Giarnieri, and S. Scardapane. "A Calibrated Multiexit Neural Network for Detecting Urothelial Cancer Cells." Computational and Mathematical Methods in Medicine 2021 (June 13, 2021): 1–11. http://dx.doi.org/10.1155/2021/5569458.
Full textAbstract:
Deep convolutional networks have become a powerful tool for medical imaging diagnostic. In pathology, most efforts have been focused in the subfield of histology, while cytopathology (which studies diagnostic tools at the cellular level) remains underexplored. In this paper, we propose a novel deep learning model for cancer detection from urinary cytopathology screening images. We leverage recent ideas from the field of multioutput neural networks to provide a model that can efficiently train even on small-scale datasets, such as those typically found in real-world scenarios. Additionally, we argue that calibration (i.e., providing confidence levels that are aligned with the ground truth probability of an event) has been a major shortcoming of prior works, and we experiment a number of techniques to provide a well-calibrated model. We evaluate the proposed algorithm on a novel dataset, and we show that the combination of focal loss, multiple outputs, and temperature scaling provides a model that is significantly more accurate and calibrated than a baseline deep convolutional network.