Automatic Approach Research Articles

A Novel Attention-Based Generalized Efficient Layer Aggregation Network for Landslide Detection from Satellite Data in the Higher Himalayas, Nepal

Landslide event detection poses a significant challenge in the remote sensing community, especially with the advancements in computer vision technology. As computational capabilities continue to grow, the traditional manual and partially automated methods of landslide recognition from remote sensing data are transitioning towards automatic approaches using deep learning algorithms. Moreover, attention models, encouraged by the human visual system, have emerged as crucial modules in diverse applications including natural hazard assessment. Therefore, we suggest a novel and intelligent generalized efficient layer aggregation network (GELAN) based on two prevalent attention modules, efficient channel attention (ECA) and convolutional block attention module (CBAM), to enrich landslide detection techniques from satellite images. CBAM and ECA are separately integrated into GELAN at different locations. The experiments are conducted using satellite images of the Nepal Himalayan region. Standard metrics such as precision, recall, F-score, and mAP (mean average precision) are considered for quantitative evaluation. GELANc+CBAM (F-score = 81.5%) demonstrates the best performance. This study underscores the suitability of the proposed approach in up-to-date inventory creation and accurate landslide mapping for disaster recovery and response efforts. Moreover, it contributes to developing early prediction models for landslide hazards.

Automated thermographic detection of blood vessels for DIEP flap reconstructive surgery.

Inadequate perfusion is the most common cause of partial flap loss in tissue transfer for post-mastectomy breast reconstruction. The current state-of-the-art uses computed tomography angiography (CTA) to locate the best perforators. Unfortunately, these techniques are expensive and time-consuming and not performed during surgery. Dynamic infrared thermography (DIRT) can offer a solution for these disadvantages. The research presented couples thermographic examination during DIEP flap breast reconstruction with automatic segmentation approach using a convolutional neural network. Traditional segmentation techniques and annotations by surgeons are used to create automatic labels for the training. The network used for image annotation is able to label in real-time on minimal hardware and the labels created can be used to locate and quantify perforator candidates for selection with a dice score accuracy of 0.8 after 2min and 0.9 after 4min. These results allow for a computational system that can be used in place during surgery to improve surgical success. The ability to track and measure perforators and their perfused area allows for less subjective results and helps the surgeon to select the most suitable perforator for DIEP flap breast reconstruction.

Compound 3D building modeling with structure-aware partition and primitive assembly from airborne laser scanning point clouds

ABSTRACT Urban digital twins and realistic three-dimensional (3D) scenes have further enhanced the ever-increasing demand for building models. Airborne Laser Scanning (ALS) point clouds are the predominant data source for 3D building reconstruction owing to their highly detailed spatial features. However, information on the reconstruction of compound buildings (i.e. buildings with diverse plane structures or various roof structures) is lacking. Existing methods often produce building models that suffer from topological inconsistencies and/or geometric errors. To address these issues, this study proposes an automatic building reconstruction approach based on ALS point cloud that offers both modeling flexibility and geometric consistency. Specifically, a structure-aware partitioning algorithm that partitions a complex building roof into several regular roof patches is incorporated. Subsequently, a primitive model library comprising representative primitives suitable for building reconstruction is created. Suitable primitive model selection and reconstruction optimization are employed to ensure the accuracy and compactness in the final model. To comprehensively evaluate the performance, two typical ALS point cloud datasets are tested. Experiments demonstrate the generated models can achieve a boundary consistency of 92% while ensuring Root Mean Square Error below 0.09 m. Comparative experiments with state-of-the-art methods further validate the effectiveness of the proposed approach in compound building reconstruction.

What you see is what you trace: a two-stage interview study on traceability practices and eye tracking potential

The benefits of traceability have widely been discussed in research. However, studies have also shown that traceability practices are still not prevalent in industrial settings due to the high manual effort and lack of tool support. In this paper, we explore the feasibility of using eye tracking to automatically detect trace links to reduce manual effort and thereby increase practical applicability. We conducted a two-stage interview study in industry. In Stage 1 we interviewed 20 practitioners to provide an overview of how traceability is established in practice and how an eye tracking approach would need to be applied in order to be useful. In Stage 2 we conducted interviews with 16 practitioners from one project context to elicit role-specific workflows and analyzed which activities are suitable to obtain useful traceability links based on gaze data. As there is no one-fits-all solution to traceability, and technical limitations of eye tracking still exist, we collected information on used artifact types, tools and requirements management practices to adjust an approach to actual traceability stakeholders’ needs. We report on perspectives from different roles in software projects and give an overview of traced artifacts, current traceability experiences, as well as benefits and doubts concerned with using eye tracking to obtain links automatically. We discuss the implications for the evaluation and implementation of an automatic tracing approach in practice and how eye tracking can support requirements engineering activities.

An experimentally validated approach to automated biological evidence generation in drug discovery using knowledge graphs

Explaining predictions for drug repositioning with biological knowledge graphs is a challenging problem. Graph completion methods using symbolic reasoning predict drug treatments and associated rules to generate evidence representing the therapeutic basis of the drug. Yet the vast amounts of generated paths that are biologically irrelevant or not mechanistically meaningful within the context of disease biology can limit utility. We use a reinforcement learning based knowledge graph completion model combined with an automatic filtering approach that produces the most relevant rules and biological paths explaining the predicted drug’s therapeutic connection to the disease. In this work we validate the approach against preclinical experimental data for Fragile X syndrome demonstrating strong correlation between automatically extracted paths and experimentally derived transcriptional changes of selected genes and pathways of drug predictions Sulindac and Ibudilast. Additionally, we show it reduces the number of generated paths in two case studies, 85% for Cystic fibrosis and 95% for Parkinson’s disease.

An Automatic Labeling Approach Towards Multi-class Sitting Posture Classification Based on Depth-Sensor Data

An Automatic Labeling Approach Towards Multi-class Sitting Posture Classification Based on Depth-Sensor Data

Automatic diagnosis of epileptic seizures using entropy-based features and multimodel deep learning approaches

Epilepsy is one of the most common brain diseases, characterised by repeated seizures that occur on a regular basis. During a seizure, a patient's muscles flex uncontrollably, causing a loss of mobility and balance, which can be harmful or even fatal. Developing an automatic approach for warning patients of oncoming seizures necessitates substantial research. Analyzing the electroencephalogram (EEG) output from the human brain's scalp region can help predict seizures. EEG data were analyzed to extract time domain features such as Hurst exponent (Hur), Tsallis entropy (TsEn), enhanced permutation entropy (impe), and amplitude-aware permutation entropy (AAPE). In order to automatically diagnose epileptic seizure in children from normal children, this study conducted two sessions. In the first session, the extracted features from the EEG dataset were classified using three machine learning (ML)-based models, including support vector machine (SVM), K nearest neighbor (KNN), or decision tree (DT), and in the second session, the dataset was classified using three deep learning (DL)-based recurrent neural network (RNN) classifiers in The EEG dataset was obtained from the Neurology Clinic of the Ibn Rushd Training Hospital. In this regard, extensive explanations and research from the time domain and entropy characteristics demonstrate that employing GRU, LSTM, and BiLSTM RNN deep learning classifiers on the All−time−entropy fusion feature improves the final classification results.

Comparison of baseline correction algorithms for in vivo 1H-MRS.

Proton MRS is used clinically to collect localized, quantitative metabolic data from living tissues. However, the presence of baselines in the spectra complicates accurate MRS data quantification. The occurrence of baselines is not specific to short-echo-time MRS data. In short-echo-time MRS, the baseline consists typically of a dominating macromolecular (MM) part, and can, depending on B0 shimming, poor voxel placement, and/or localization sequences, also contain broad water and lipid resonance components, indicated by broad components (BCs). In long-echo-time MRS, the MM part is usually much smaller, but BCs may still be present. The sum of MM and BCs is denoted by the baseline. Many algorithms have been proposed over the years to tackle these artefacts. A first approach is to identify the baseline itself in a preprocessing step, and a second approach is to model the baseline in the quantification of the MRS data themselves. This paper gives an overview of baseline handling algorithms and also proposes a new algorithm for baseline correction. A subset of suitable baseline removal algorithms were tested on in vivo MRSI data (semi-LASER at TE= 40 ms) and compared with the new algorithm. The baselines in all datasets were removed using the different methods and subsequently fitted using spectrIm-QMRS with a TDFDFit fitting model that contained only a metabolite basis set and lacked a baseline model. The same spectra were also fitted using a spectrIm-QMRS model that explicitly models the metabolites and the baseline of the spectrum. The quantification results of the latter quantification were regarded as ground truth. The fit quality number (FQN) was used to assess baseline removal effectiveness, and correlations between metabolite peak areas and ground truth models were also examined. The results show a competitive performance of our new proposed algorithm, underscoring its automatic approach and efficiency. Nevertheless, none of the tested baseline correction methods achieved FQNs as good as the ground truth model. All separately applied baseline correction methods introduce a bias in the observed metabolite peak areas. We conclude that all baseline correction methods tested, when applied as a separate preprocessing step, yield poorer FQNs and biased quantification results. While they may enhance visual display, they are not advisable for use before spectral fitting.

Automatic Knowledge-driven Approach for Optimal Service Selection based on ELECTRE III and Quality-Aware Services

Automatic Knowledge-driven Approach for Optimal Service Selection based on ELECTRE III and Quality-Aware Services

Integration of background knowledge for automatic detection of inconsistencies in gene ontology annotation.

Biological background knowledge plays an important role in the manual quality assurance (QA) of biological database records. One such QA task is the detection of inconsistencies in literature-based Gene Ontology Annotation (GOA). This manual verification ensures the accuracy of the GO annotations based on a comprehensive review of the literature used as evidence, Gene Ontology (GO) terms, and annotated genes in GOA records. While automatic approaches for the detection of semantic inconsistencies in GOA have been developed, they operate within predetermined contexts, lacking the ability to leverage broader evidence, especially relevant domain-specific background knowledge. This paper investigates various types of background knowledge that could improve the detection of prevalent inconsistencies in GOA. In addition, the paper proposes several approaches to integrate background knowledge into the automatic GOA inconsistency detection process. We have extended a previously developed GOA inconsistency dataset with several kinds of GOA-related background knowledge, including GeneRIF statements, biological concepts mentioned within evidence texts, GO hierarchy and existing GO annotations of the specific gene. We have proposed several effective approaches to integrate background knowledge as part of the automatic GOA inconsistency detection process. The proposed approaches can improve automatic detection of self-consistency and several of the most prevalent types of inconsistencies. https://github.com/jiyuc/de-inconsistency.

A compensator design and stability margin monitor for digitally controlled DC-DC converters

ABSTRACT In this paper, an automatic direct digital design approach for compensators is presented to achieve a lookup table proportional – integral – derivative controller. Additionally, a correlation-based stability margin monitor with adaptive sliding window smoothing is proposed to increase the identifiable range for bandwidth detection. The proposed automatic compensator design approach meets the expected phase margin and crossover frequency and considers limit-cycle oscillation conditions throughout the design process. The digital controller with the direct digital design was implemented on a field programmable gate array to validate the approach and alternative design capabilities. Experimental results show that the direct digital design yields a higher crossover frequency than digital redesign. The best transient response performance can be obtained if a proper integral gain is designed. The digital controller with ASWS was fabricated using the TSMC 1P6M 0.18-μm standard CMOS process. Further experimental results show that the proposed ASWS provides a significantly more accurate identified frequency response by using narrow windows at low frequencies and expansive windows at high frequencies.

Do Code Summarization Models Process Too Much Information? Function Signature May Be All That Is Needed

With the fast development of large software projects, automatic code summarization techniques, which summarize the main functionalities of a piece of code using natural languages as comments, play essential roles in helping developers understand and maintain large software projects. Many research efforts have been devoted to building automatic code summarization approaches. Typical code summarization approaches are based on deep learning models. They transform the task into a sequence-to-sequence task, which inputs source code and outputs summarizations in natural languages. All code summarization models impose different input size limits, such as 50 to 10,000, for the input source code. However, how the input size limit affects the performance of code summarization models still remains under-explored. In this article, we first conduct an empirical study to investigate the impacts of different input size limits on the quality of generated code comments. To our surprise, experiments on multiple models and datasets reveal that setting a low input size limit, such as 20, does not necessarily reduce the quality of generated comments. Based on this finding, we further propose to use function signatures instead of full source code to summarize the main functionalities first and then input the function signatures into code summarization models. Experiments and statistical results show that inputs with signatures are, on average, more than 2 percentage points better than inputs without signatures and thus demonstrate the effectiveness of involving function signatures in code summarization. We also invite programmers to do a questionnaire to evaluate the quality of code summaries generated by two inputs with different truncation levels. The results show that function signatures generate, on average, 9.2% more high-quality comments than full code.

Reduced threat avoidance but increased stress induced approach bias in women taking oral contraceptives

Recent research has increasingly acknowledged the impact of oral contraceptives on affective behavior and stress responses; however, the underlying mechanisms are still not well understood. Studies have previously shown that steroid hormones modulate automatic approach and avoidance behavior. Here, we thus investigated the effects of oral contraceptives on approach and avoidance behavior and whether these effects are modulated by stress. The study comprised 130 female participants, half of whom were using oral contraceptives, while the other half were not using any hormonal contraception (NC). The participants completed the Approach Avoidance Task (AAT), which measures automatic approach and avoidance behavior to socio-affective signals. The AAT was run once before and once after a stress manipulation using the Socially Evaluated Cold Pressor Test. OC users showed absent avoidance behavior to social threat signals and a stress-induced increase in approach behavior to positive social signals. The latter was found in particular in women taking androgenic acting OC, demonstrating that different OC preparations need to be taken into account in research on OC effects. However, OC and NC group did not differ in their cortisol stress response. Overall, the results suggest that OC usage impacts on approach and avoidance behavior to social signals, which might also contribute to the development of affective side effects.

Extraction of the three-dimensional architecture of deformation bands from ground-penetrating radar cubes using multiattribute analysis

Fault zones in porous siliciclastic rocks can be dominated by deformation bands (DBs), which are small-scale tabular structures that usually occur as cluster features. DBs can reduce permeability, contributing to the compartmentalization of oil reservoirs and aquifers. DBs cannot be imaged by seismic methods, but can be imaged by Ground-penetrating radar (GPR). Although DBs and host rocks share the same lithology, GPR imaging is possible because DBs can cause small vertical offsets and reduce the amplitude of the GPR signals. We present an automatic approach for extracting the three-dimensional (3D) architecture of DBs from GPR cubes using multiattribute analysis. We used a 200 MHz GPR cube surveyed on an outcrop of a sandstone formation highly impacted by DBs in the Rio do Peixe Basin, northeastern Brazil. The multiattribute analysis is based on edge evidence and sequential ant-tracking, a combination that can identify narrow zones of attenuated GPR signals. Furthermore, the 3D architecture of DBs was extracted as a geobody using an opacity balancing operator. The geological reliability and limitations of the geobody were demonstrated by comparing slices of the geobody with images of exposed DBs in similar positions, in addition to structural measurements obtained in field and in the geobody.

Prov-DIFF: Play traces analysis through provenance differences

A game session comprises a series of user decisions, inputs, and the execution of a strategy to reach specific goals. Tracking generated data of a game session is important for game analytics for developers and players. Game session data can be used for reproducibility, analysis of game traces, understanding player behavior, and improving the outcome in future sessions by learning from mistakes. However, game telemetry can rapidly lead to large amounts of data that can overwhelm the analyst’s ability to analyze it, and it can be difficult to identify the reasons that might have caused a player to lose in that session. This paper proposes a provenance-based automatic debugging approach for game analytics. It identifies possible reasons and discrepancies that might have led a player to lose by contrasting their performance with other players. Our approach also proposes possible insights on how to improve the player’s performance to reach the goal. We integrated our solution into the existing provenance visualization tool Prov Viewer. We provided an experimental study to demonstrate that our approach can identify probable causes that led the player to lose and propose changes to make it work in the next execution.

HessFit: A Toolkit to Derive Automated Force Fields from Quantum Mechanical Information.

In this study, we introduce a novel approach to enhance the accuracy of molecular dynamics simulations by refining the force fields (FFs) through a combination of transferable parameters and molecule-specific characteristics derived from quantum mechanical (QM) calculations. Traditional FFs often prioritize generality over precision, leading to limitations in the accuracy of accurately capturing intra- and intermolecular interactions. To address this, we present an open-source toolkit, called HessFit, designed to integrate QM-derived bonded parameters and atomic charges into existing FFs. In combination with bond, angle, torsional, and nonbonded parameters derivation, HessFit can easily extract multiple barrier terms of dihedrals from QM Hessian and gradient or return all terms through a fitting procedure scheme of QM potential energy surface. We showcase the effectiveness of HessFit through comprehensive evaluations of vibrational properties across a diverse set of small molecules and demonstrate that experimental results support its ability in predicting thermodynamic properties of organic molecules compared to previous state-of-the-art approaches. We further explore its application to Zn2+ metalloprotein models, which are hard systems to treat with automatic approaches. Our results demonstrate that HessFit parameters compete with GAFF2 and OPLS parameters to describing small organic molecules, and its feasibility is also comparable to current FFs used to modeling nonstandard residues in Zn proteins for molecular dynamics simulations. The effectiveness of the HessFit protocol makes it a valuable tool for deriving or extending force field parameters for novel compounds in several molecular modeling applications.

An automatic radiomic-based approach for disease localization: A pilot study on COVID-19

Radiomics is an innovative field in Personalized Medicine to help medical specialists in diagnosis and prognosis. Mainly, the application of Radiomics to medical images requires the definition and delimitation of the Region Of Interest (ROI) on the medical image to extract radiomic features. The aim of this preliminary study is to define an approach that automatically detects the specific areas indicative of a particular disease and examines them to minimize diagnostic errors associated with false positives and false negatives. This approach aims to create a nxn grid on the DICOM image sequence and each cell in the matrix is associated with a region from which radiomic features can be extracted.The proposed procedure uses the Model Checking technique and produces as output the medical diagnosis of the patient, i.e., whether the patient under analysis is affected or not by a specific disease. Furthermore, the matrix-based method also localizes where appears the disease marks. To evaluate the performance of the proposed methodology, a case study on COVID-19 disease is used. Both results on disease identification and localization seem very promising. Furthermore, this proposed approach yields better results compared to methods based on the extraction of features using the whole image as a single ROI, as evidenced by improvements in Accuracy and especially Recall. Our approach supports the advancement of knowledge, interoperability and trust in the software tool, fostering collaboration among doctors, staff and Radiomics.

Enhancing visual autonomous navigation in row-based crops with effective synthetic data generation

Abstract Introduction Service robotics is recently enhancing precision agriculture enabling many automated processes based on efficient autonomous navigation solutions. However, data generation and in-field validation campaigns hinder the progress of large-scale autonomous platforms. Simulated environments and deep visual perception are spreading as successful tools to speed up the development of robust navigation with low-cost RGB-D cameras. Materials and methods In this context, the contribution of this work resides in a complete framework to fully exploit synthetic data for a robust visual control of mobile robots. A wide realistic multi-crops dataset is accurately generated to train deep semantic segmentation networks and enabling robust performance in challenging real-world conditions. An automatic parametric approach enables an easy customization of virtual field geometry and features for a fast reliable evaluation of navigation algorithms. Results and conclusion The high quality of the generated synthetic dataset is demonstrated by an extensive experimentation with real crops images and benchmarking the resulting robot navigation both in virtual and real fields with relevant metrics.

Automatic prediction of non-iodine-avid status in lung metastases for radioactive I131 treatment in differentiated thyroid cancer patients.

The growing incidence of differentiated thyroid cancer (DTC) have been linked to insulin resistance and metabolic syndrome. The imperative need for developing effective diagnostic imaging tools to predict the non-iodine-avid status of lung metastasis (LMs) in differentiated thyroid cancer (DTC) patients is underscored to prevent unnecessary radioactive iodine treatment (RAI). Primary cohort consisted 1962 pretreated LMs of 496 consecutive DTC patients with pretreated initially diagnosed LMs who underwent chest CT and subsequent post-treatment radioiodine SPECT. After automatic lesion segmentation by SE V-Net, SE Net deep learning was trained to predict non-iodine-avid status of LMs. External validation cohort contained 123 pretreated LMs of 24 consecutive patients from other two hospitals. Stepwise validation was further performed according to the nodule's largest diameter. The SE-Net deep learning network yielded area under the receiver operating characteristic curve (AUC) values of 0.879 (95% confidence interval: 0.852-0.906) and 0.713 (95% confidence interval: 0.613-0.813) for internal and external validation. With the LM diameter decreasing from ≥10mm to ≤4mm, the AUCs remained relatively stable, for smallest nodules (≤4mm), the model yielded an AUC of 0.783. Decision curve analysis showed that most patients benefited using deep learning to decide radioactive I131 treatment. This study presents a noninvasive, less radioactive and fully automatic approach that can facilitate suitable DTC patient selection for RAI therapy of LMs. Further prospective multicenter studies with larger study cohorts and related metabolic factors should address the possibility of comprehensive clinical transformation.

Health of Things Melanoma Detection System—detection and segmentation of melanoma in dermoscopic images applied to edge computing using deep learning and fine-tuning models

According to the World Health Organization (WHO), melanoma is a type of cancer that affects people globally in different parts of the human body, leading to deaths of thousands of people every year worldwide. Intelligent diagnostic tools through automatic detection in medical images are extremely effective in aiding medical diagnosis. Computer-aided diagnosis (CAD) systems are of utmost importance for image-based pre-diagnosis, and the use of artificial intelligence–based tools for monitoring, detection, and segmentation of the pathological region are increasingly used in integrated smart solutions within smart city systems through cloud data processing with the use of edge computing. This study proposes a new approach capable of integrating into computational monitoring and medical diagnostic assistance systems called Health of Things Melanoma Detection System (HTMDS). The method presents a deep learning–based approach using the YOLOv8 network for melanoma detection in dermatoscopic images. The study proposes a workflow through communication between the mobile device, which extracts captured images from the dermatoscopic device and uploads them to the cloud API, and a new approach using deep learning and different fine-tuning models for melanoma detection and segmentation of the region of interest, along with the cloud communication structure and comparison with methods found in the state of the art, addressing local processing. The new approach achieved satisfactory results with over 98% accuracy for detection and over 99% accuracy for skin cancer segmentation, surpassing various state-of-the-art works in different methods, such as manual, semi-automatic, and automatic approaches. The new approach demonstrates effective results in the performance of different intelligent automatic models with real-time processing, which can be used in affiliated institutions or offices in smart cities for population use and medical diagnosis purposes.