Segui questo link per vedere altri tipi di pubblicazioni sul tema: Interpretable By Design Architectures.
Articoli di riviste sul tema "Interpretable By Design Architectures"
Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili
Vedi i top-50 articoli di riviste per l'attività di ricerca sul tema "Interpretable By Design Architectures".
Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.
Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.
Vedi gli articoli di riviste di molte aree scientifiche e compila una bibliografia corretta.
1
Zhang, Xinyu, Vincent C. S. Lee, Jia Rong, Feng Liu e Haoyu Kong. "Multi-channel convolutional neural network architectures for thyroid cancer detection". PLOS ONE 17, n. 1 (21 gennaio 2022): e0262128. http://dx.doi.org/10.1371/journal.pone.0262128.
Testo completoAbstract (sommario):
Early detection of malignant thyroid nodules leading to patient-specific treatments can reduce morbidity and mortality rates. Currently, thyroid specialists use medical images to diagnose then follow the treatment protocols, which have limitations due to unreliable human false-positive diagnostic rates. With the emergence of deep learning, advances in computer-aided diagnosis techniques have yielded promising earlier detection and prediction accuracy; however, clinicians’ adoption is far lacking. The present study adopts Xception neural network as the base structure and designs a practical framework, which comprises three adaptable multi-channel architectures that were positively evaluated using real-world data sets. The proposed architectures outperform existing statistical and machine learning techniques and reached a diagnostic accuracy rate of 0.989 with ultrasound images and 0.975 with computed tomography scans through the single input dual-channel architecture. Moreover, the patient-specific design was implemented for thyroid cancer detection and has obtained an accuracy of 0.95 for double inputs dual-channel architecture and 0.94 for four-channel architecture. Our evaluation suggests that ultrasound images and computed tomography (CT) scans yield comparable diagnostic results through computer-aided diagnosis applications. With ultrasound images obtained slightly higher results, CT, on the other hand, can achieve the patient-specific diagnostic design. Besides, with the proposed framework, clinicians can select the best fitting architecture when making decisions regarding a thyroid cancer diagnosis. The proposed framework also incorporates interpretable results as evidence, which potentially improves clinicians’ trust and hence their adoption of the computer-aided diagnosis techniques proposed with increased efficiency and accuracy.
2
Xie, Nan, e Yuexian Hou. "MMIM: An Interpretable Regularization Method for Neural Networks (Student Abstract)". Proceedings of the AAAI Conference on Artificial Intelligence 35, n. 18 (18 maggio 2021): 15933–34. http://dx.doi.org/10.1609/aaai.v35i18.17963.
Testo completoAbstract (sommario):
In deep learning models, most of network architectures are designed artificially and empirically. Although adding new structures such as convolution kernels in CNN is widely used, there are few methods to design new structures and mathematical tools to evaluate feature representation capabilities of new structures. Inspired by ensemble learning, we propose an interpretable regularization method named Minimize Mutual Information Method(MMIM), which minimize the generalization error by minimizing the mutual information of hidden neurons. The experimental results also verify the effectiveness of our proposed MMIM.
3
Di Gioacchino, Andrea, Jonah Procyk, Marco Molari, John S. Schreck, Yu Zhou, Yan Liu, Rémi Monasson, Simona Cocco e Petr Šulc. "Generative and interpretable machine learning for aptamer design and analysis of in vitro sequence selection". PLOS Computational Biology 18, n. 9 (29 settembre 2022): e1010561. http://dx.doi.org/10.1371/journal.pcbi.1010561.
Testo completoAbstract (sommario):
Selection protocols such as SELEX, where molecules are selected over multiple rounds for their ability to bind to a target of interest, are popular methods for obtaining binders for diagnostic and therapeutic purposes. We show that Restricted Boltzmann Machines (RBMs), an unsupervised two-layer neural network architecture, can successfully be trained on sequence ensembles from single rounds of SELEX experiments for thrombin aptamers. RBMs assign scores to sequences that can be directly related to their fitnesses estimated through experimental enrichment ratios. Hence, RBMs trained from sequence data at a given round can be used to predict the effects of selection at later rounds. Moreover, the parameters of the trained RBMs are interpretable and identify functional features contributing most to sequence fitness. To exploit the generative capabilities of RBMs, we introduce two different training protocols: one taking into account sequence counts, capable of identifying the few best binders, and another based on unique sequences only, generating more diverse binders. We then use RBMs model to generate novel aptamers with putative disruptive mutations or good binding properties, and validate the generated sequences with gel shift assay experiments. Finally, we compare the RBM’s performance with different supervised learning approaches that include random forests and several deep neural network architectures.
4
Feinauer, Christoph, Barthelemy Meynard-Piganeau e Carlo Lucibello. "Interpretable pairwise distillations for generative protein sequence models". PLOS Computational Biology 18, n. 6 (23 giugno 2022): e1010219. http://dx.doi.org/10.1371/journal.pcbi.1010219.
Testo completoAbstract (sommario):
Many different types of generative models for protein sequences have been proposed in literature. Their uses include the prediction of mutational effects, protein design and the prediction of structural properties. Neural network (NN) architectures have shown great performances, commonly attributed to the capacity to extract non-trivial higher-order interactions from the data. In this work, we analyze two different NN models and assess how close they are to simple pairwise distributions, which have been used in the past for similar problems. We present an approach for extracting pairwise models from more complex ones using an energy-based modeling framework. We show that for the tested models the extracted pairwise models can replicate the energies of the original models and are also close in performance in tasks like mutational effect prediction. In addition, we show that even simpler, factorized models often come close in performance to the original models.
5
Zhang, Zizhao, Han Zhang, Long Zhao, Ting Chen, Sercan Ö. Arik e Tomas Pfister. "Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding". Proceedings of the AAAI Conference on Artificial Intelligence 36, n. 3 (28 giugno 2022): 3417–25. http://dx.doi.org/10.1609/aaai.v36i3.20252.
Testo completoAbstract (sommario):
Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well. In this paper, we explore the idea of nesting basic local transformers on non-overlapping image blocks and aggregating them in a hierarchical way. We find that the block aggregation function plays a critical role in enabling cross-block non-local information communication. This observation leads us to design a simplified architecture that requires minor code changes upon the original vision transformer. The benefits of the proposed judiciously-selected design are threefold: (1) NesT converges faster and requires much less training data to achieve good generalization on both ImageNet and small datasets like CIFAR; (2) when extending our key ideas to image generation, NesT leads to a strong decoder that is 8 times faster than previous transformer-based generators; and (3) we show that decoupling the feature learning and abstraction processes via this nested hierarchy in our design enables constructing a novel method (named GradCAT) for visually interpreting the learned model. Source code is available https://github.com/google-research/nested-transformer.
6
Gao, Xinjian, Tingting Mu, John Yannis Goulermas, Jeyarajan Thiyagalingam e Meng Wang. "An Interpretable Deep Architecture for Similarity Learning Built Upon Hierarchical Concepts". IEEE Transactions on Image Processing 29 (2020): 3911–26. http://dx.doi.org/10.1109/tip.2020.2965275.
Testo completo
7
Liu, Hao, Youchao Sun, Xiaoyu Wang, Honglan Wu e Hao Wang. "NPFormer: Interpretable rotating machinery fault diagnosis architecture design under heavy noise operating scenarios". Mechanical Systems and Signal Processing 223 (gennaio 2025): 111878. http://dx.doi.org/10.1016/j.ymssp.2024.111878.
Testo completo
8
Sturm, Patrick Obin, e Anthony S. Wexler. "Conservation laws in a neural network architecture: enforcing the atom balance of a Julia-based photochemical model (v0.2.0)". Geoscientific Model Development 15, n. 8 (28 aprile 2022): 3417–31. http://dx.doi.org/10.5194/gmd-15-3417-2022.
Testo completoAbstract (sommario):
Abstract. Models of atmospheric phenomena provide insight into climate, air quality, and meteorology and provide a mechanism for understanding the effect of future emissions scenarios. To accurately represent atmospheric phenomena, these models consume vast quantities of computational resources. Machine learning (ML) techniques such as neural networks have the potential to emulate computationally intensive components of these models to reduce their computational burden. However, such ML surrogate models may lead to nonphysical predictions that are difficult to uncover. Here we present a neural network architecture that enforces conservation laws to numerical precision. Instead of simply predicting properties of interest, a physically interpretable hidden layer within the network predicts fluxes between properties which are subsequently related to the properties of interest. This approach is readily generalizable to physical processes where flux continuity is an essential governing equation. As an example application, we demonstrate our approach on a neural network surrogate model of photochemistry, trained to emulate a reference model that simulates formation and reaction of ozone. We design a physics-constrained neural network surrogate model of photochemistry using this approach and find that it conserves atoms as they flow between molecules while outperforming two other neural network architectures in terms of accuracy, physical consistency, and non-negativity of concentrations.
9
Jacob, Stefan, e Christian Koch. "Unveiling weak auditory evoked potentials using data-driven filtering". Journal of the Acoustical Society of America 154, n. 4_supplement (1 ottobre 2023): A141. http://dx.doi.org/10.1121/10.0023054.
Testo completoAbstract (sommario):
Auditory evoked potentials (AEPs) are commonly used to objectively evaluate sound perception in humans. Close to the hearing threshold and for low frequencies, efficient filtering of AEP from other brain activities is of major concern due to weak potentials and the requirement of long averaging times. Filtered AEP data are well-interpretable and useful, especially in medical and psychological diagnostics. Here, we present two data-driven approaches for efficient AEP filtering. First, neural networks of different architectures trained for EEG denoising are used to extract weak late-response AEP for low-frequency and infrasonic stimuli. During the design of the networks, we leveraged knowledge of the specific characteristics of the expected AEP data. Second, a singular value decomposition (SVD) of EEG data is evaluated, attempting to create classifiers for the presence of weak late-response AEP modes. We anticipate that the evaluation of AEP with data-driven methods can support researchers and scientists, for example, with real-time evaluation and diagnosis of acoustic-induced discomfort.
10
Zhou, Shuhui. "An exploration of KANs and CKANs for more efficient deep learning architecture". Applied and Computational Engineering 83, n. 1 (27 settembre 2024): 20–25. http://dx.doi.org/10.54254/2755-2721/83/2024glg0060.
Testo completoAbstract (sommario):
Deep learning has revolutionized the field of machine learning with its ability to discern complex patterns from voluminous data. Despite the success of Multi-Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs), there is an ongoing quest for architectures that offer higher expressiveness with fewer parameters. This paper focuses on the Kolmogorov-Arnold Networks (KANs) and Convolutional Kolmogorov-Arnold Networks (CKANs), which integrate learnable spline functions for enhanced expressiveness and efficiency. This study designs a range of networks to compare KANs with MLPs and CKANs with classical CNNs on the CIFAR-10 dataset. Moreover, this study evaluates the models based on several metrics, including accuracy, precision, recall, F1 score, and parameter count. Based on the experimental results, networks with KANs and CKANs demonstrated improved accuracy with a reduced parameter footprint, indicating the potential of KAN-based models in capturing complex patterns. In conclusion, integrating KANs into CNNs and MLPs is a promising approach for developing more efficient and interpretable models, offering a path to advance deep learning architectures.
11
Koriakina, Nadezhda, Nataša Sladoje, Vladimir Bašić e Joakim Lindblad. "Deep multiple instance learning versus conventional deep single instance learning for interpretable oral cancer detection". PLOS ONE 19, n. 4 (30 aprile 2024): e0302169. http://dx.doi.org/10.1371/journal.pone.0302169.
Testo completoAbstract (sommario):
The current medical standard for setting an oral cancer (OC) diagnosis is histological examination of a tissue sample taken from the oral cavity. This process is time-consuming and more invasive than an alternative approach of acquiring a brush sample followed by cytological analysis. Using a microscope, skilled cytotechnologists are able to detect changes due to malignancy; however, introducing this approach into clinical routine is associated with challenges such as a lack of resources and experts. To design a trustworthy OC detection system that can assist cytotechnologists, we are interested in deep learning based methods that can reliably detect cancer, given only per-patient labels (thereby minimizing annotation bias), and also provide information regarding which cells are most relevant for the diagnosis (thereby enabling supervision and understanding). In this study, we perform a comparison of two approaches suitable for OC detection and interpretation: (i) conventional single instance learning (SIL) approach and (ii) a modern multiple instance learning (MIL) method. To facilitate systematic evaluation of the considered approaches, we, in addition to a real OC dataset with patient-level ground truth annotations, also introduce a synthetic dataset—PAP-QMNIST. This dataset shares several properties of OC data, such as image size and large and varied number of instances per bag, and may therefore act as a proxy model of a real OC dataset, while, in contrast to OC data, it offers reliable per-instance ground truth, as defined by design. PAP-QMNIST has the additional advantage of being visually interpretable for non-experts, which simplifies analysis of the behavior of methods. For both OC and PAP-QMNIST data, we evaluate performance of the methods utilizing three different neural network architectures. Our study indicates, somewhat surprisingly, that on both synthetic and real data, the performance of the SIL approach is better or equal to the performance of the MIL approach. Visual examination by cytotechnologist indicates that the methods manage to identify cells which deviate from normality, including malignant cells as well as those suspicious for dysplasia. We share the code as open source.
12
Diaz-Gomez, Liliana, Andres E. Gutierrez-Rodriguez, Alejandra Martinez-Maldonado, Jose Luna-Muñoz, Jose A. Cantoral-Ceballos e Miguel A. Ontiveros-Torres. "Interpretable Classification of Tauopathies with a Convolutional Neural Network Pipeline Using Transfer Learning and Validation against Post-Mortem Clinical Cases of Alzheimer’s Disease and Progressive Supranuclear Palsy". Current Issues in Molecular Biology 44, n. 12 (29 novembre 2022): 5963–85. http://dx.doi.org/10.3390/cimb44120406.
Testo completoAbstract (sommario):
Neurodegenerative diseases, tauopathies, constitute a serious global health problem. The etiology of these diseases is unclear and an increase in their incidence has been projected in the next 30 years. Therefore, the study of the molecular mechanisms that might stop these neurodegenerative processes is very relevant. Classification of neurodegenerative diseases using Machine and Deep Learning algorithms has been widely studied for medical imaging such as Magnetic Resonance Imaging. However, post-mortem immunofluorescence imaging studies of the brains of patients have not yet been used for this purpose. These studies may represent a valuable tool for monitoring aberrant chemical changes or pathological post-translational modifications of the Tau polypeptide. We propose a Convolutional Neural Network pipeline for the classification of Tau pathology of Alzheimer’s disease and Progressive Supranuclear Palsy by analyzing post-mortem immunofluorescence images with different Tau biomarkers performed with models generated with the architecture ResNet-IFT using Transfer Learning. These models’ outputs were interpreted with interpretability algorithms such as Guided Grad-CAM and Occlusion Analysis. To determine the best classifier, four different architectures were tested. We demonstrated that our design was able to classify diseases with an accuracy of 98.41% on average whilst providing an interpretation concerning the proper classification involving different structural patterns in the immunoreactivity of the Tau protein in NFTs present in the brains of patients with Progressive Supranuclear Palsy and Alzheimer’s disease.
13
Wang, Xingyu, Rui Ma, Jinyuan He, Taisi Zhang, Xiajing Wang e Jingfeng Xue. "INNT: Restricting Activation Distance to Enhance Consistency of Visual Interpretation in Neighborhood Noise Training". Electronics 12, n. 23 (23 novembre 2023): 4751. http://dx.doi.org/10.3390/electronics12234751.
Testo completoAbstract (sommario):
In this paper, we propose an end-to-end interpretable neighborhood noise training framework (INNT) to address the issue of inconsistent interpretations between clean and noisy samples in noise training. Noise training conventionally involves incorporating noisy samples into the training set, followed by generalization training. However, visual interpretations suggest that models may be learning the noise distribution rather than the desired robust target features. To mitigate this problem, we reformulate the noise training objective to minimize the visual interpretation consistency of images in the sample neighborhood. We design a noise activation distance constraint regularization term to enforce the similarity of high-level feature maps between clean and noisy samples. Additionally, we enhance the structure of noise training by iteratively resampling noise to more accurately depict the sample neighborhood. Furthermore, neighborhood noise is introduced to achieve more intuitive sample neighborhood sampling. Finally, we conducted qualitative and quantitative tests on different CNN architectures and public datasets. The results indicate that INNT leads to a more consistent decision rationale and balances the accuracy between noisy and clean samples.
14
Zhang, Ting-He, Md Musaddaqul Hasib, Yu-Chiao Chiu, Zhi-Feng Han, Yu-Fang Jin, Mario Flores, Yidong Chen e Yufei Huang. "Transformer for Gene Expression Modeling (T-GEM): An Interpretable Deep Learning Model for Gene Expression-Based Phenotype Predictions". Cancers 14, n. 19 (29 settembre 2022): 4763. http://dx.doi.org/10.3390/cancers14194763.
Testo completoAbstract (sommario):
Deep learning has been applied in precision oncology to address a variety of gene expression-based phenotype predictions. However, gene expression data’s unique characteristics challenge the computer vision-inspired design of popular Deep Learning (DL) models such as Convolutional Neural Network (CNN) and ask for the need to develop interpretable DL models tailored for transcriptomics study. To address the current challenges in developing an interpretable DL model for modeling gene expression data, we propose a novel interpretable deep learning architecture called T-GEM, or Transformer for Gene Expression Modeling. We provided the detailed T-GEM model for modeling gene–gene interactions and demonstrated its utility for gene expression-based predictions of cancer-related phenotypes, including cancer type prediction and immune cell type classification. We carefully analyzed the learning mechanism of T-GEM and showed that the first layer has broader attention while higher layers focus more on phenotype-related genes. We also showed that T-GEM’s self-attention could capture important biological functions associated with the predicted phenotypes. We further devised a method to extract the regulatory network that T-GEM learns by exploiting the attributions of self-attention weights for classifications and showed that the network hub genes were likely markers for the predicted phenotypes.
15
De Santi, Lisa Anita, Franco Italo Piparo, Filippo Bargagna, Maria Filomena Santarelli, Simona Celi e Vincenzo Positano. "Part-Prototype Models in Medical Imaging: Applications and Current Challenges". BioMedInformatics 4, n. 4 (28 ottobre 2024): 2149–72. http://dx.doi.org/10.3390/biomedinformatics4040115.
Testo completoAbstract (sommario):
Recent developments in Artificial Intelligence have increasingly focused on explainability research. The potential of Explainable Artificial Intelligence (XAI) in producing trustworthy computer-aided diagnosis systems and its usage for knowledge discovery are gaining interest in the medical imaging (MI) community to support the diagnostic process and the discovery of image biomarkers. Most of the existing XAI applications in MI are focused on interpreting the predictions made using deep neural networks, typically including attribution techniques with saliency map approaches and other feature visualization methods. However, these are often criticized for providing incorrect and incomplete representations of the black-box models’ behaviour. This highlights the importance of proposing models intentionally designed to be self-explanatory. In particular, part-prototype (PP) models are interpretable-by-design computer vision (CV) models that base their decision process on learning and identifying representative prototypical parts from input images, and they are gaining increasing interest and results in MI applications. However, the medical field has unique characteristics that could benefit from more advanced implementations of these types of architectures. This narrative review summarizes existing PP networks, their application in MI analysis, and current challenges.
16
Jiang, Xuejie, Siti Norlizaiha Harun e Linyu Liu. "Explainable Artificial Intelligence for Ancient Architecture and Lacquer Art". Buildings 13, n. 5 (4 maggio 2023): 1213. http://dx.doi.org/10.3390/buildings13051213.
Testo completoAbstract (sommario):
This research investigates the use of explainable artificial intelligence (XAI) in ancient architecture and lacquer art. The aim is to create accurate and interpretable models to reveal these cultural artefacts’ underlying design principles and techniques. To achieve this, machine learning and data-driven techniques are employed, which provide new insights into their construction and preservation. The study emphasises the importance of transparent and trustworthy AI systems, which can enhance the reliability and credibility of the results. The developed model outperforms CNN-based emotion recognition and random forest models in all four evaluation metrics, achieving an impressive accuracy of 92%. This research demonstrates the potential of XAI to support the study and conservation of ancient architecture and lacquer art, opening up new avenues for interdisciplinary research and collaboration.
17
Criel, Bjorn, Steff Taelman, Wim Van Criekinge, Michiel Stock e Yves Briers. "PhaLP: A Database for the Study of Phage Lytic Proteins and Their Evolution". Viruses 13, n. 7 (26 giugno 2021): 1240. http://dx.doi.org/10.3390/v13071240.
Testo completoAbstract (sommario):
Phage lytic proteins are a clinically advanced class of novel enzyme-based antibiotics, so-called enzybiotics. A growing community of researchers develops phage lytic proteins with the perspective of their use as enzybiotics. A successful translation of enzybiotics to the market requires well-considered selections of phage lytic proteins in early research stages. Here, we introduce PhaLP, a database of phage lytic proteins, which serves as an open portal to facilitate the development of phage lytic proteins. PhaLP is a comprehensive, easily accessible and automatically updated database (currently 16,095 entries). Capitalizing on the rich content of PhaLP, we have mapped the high diversity of natural phage lytic proteins and conducted analyses at three levels to gain insight in their host-specific evolution. First, we provide an overview of the modular diversity. Secondly, datamining and interpretable machine learning approaches were adopted to reveal host-specific design rules for domain architectures in endolysins. Lastly, the evolution of phage lytic proteins on the protein sequence level was explored, revealing host-specific clusters. In sum, PhaLP can act as a starting point for the broad community of enzybiotic researchers, while the steadily improving evolutionary insights will serve as a natural inspiration for protein engineers.
18
Tian, Jinkai, e Wenjing Yang. "Mapping Data to Concepts: Enhancing Quantum Neural Network Transparency with Concept-Driven Quantum Neural Networks". Entropy 26, n. 11 (24 ottobre 2024): 902. http://dx.doi.org/10.3390/e26110902.
Testo completoAbstract (sommario):
We introduce the concept-driven quantum neural network (CD-QNN), an innovative architecture designed to enhance the interpretability of quantum neural networks (QNNs). CD-QNN merges the representational capabilities of QNNs with the transparency of self-explanatory models by mapping input data into a human-understandable concept space and making decisions based on these concepts. The algorithmic design of CD-QNN is comprehensively analyzed, detailing the roles of the concept generator, feature extractor, and feature integrator in improving and balancing model expressivity and interpretability. Experimental results demonstrate that CD-QNN maintains high predictive accuracy while offering clear and meaningful explanations of its decision-making process. This paradigm shift in QNN design underscores the growing importance of interpretability in quantum artificial intelligence, positioning CD-QNN and its derivative technologies as pivotal in advancing reliable and interpretable quantum intelligent systems for future research and applications.
19
Zhang, Zhiyuan, Zhan Wang e Inwhee Joe. "CAM-NAS: An Efficient and Interpretable Neural Architecture Search Model Based on Class Activation Mapping". Applied Sciences 13, n. 17 (27 agosto 2023): 9686. http://dx.doi.org/10.3390/app13179686.
Testo completoAbstract (sommario):
Artificial intelligence (AI) has made rapid progress in recent years, but as the complexity of AI models and the need to deploy them on multiple platforms gradually increases, the design of network model structures for specific platforms becomes more difficult. A neural network architecture search (NAS) serves as a solution to help experts discover new network structures that are suitable for different tasks and platforms. However, traditional NAS algorithms often consume time and many computational resources, especially when dealing with complex tasks and large-scale models, and the search process can become exceptionally time-consuming and difficult to interpret. In this paper, we propose a class activation graph-based neural structure search method (CAM-NAS) to address these problems. Compared with traditional NAS algorithms, CAM-NAS does not require full training of submodels, which greatly improves the search efficiency. Meanwhile, CAM-NAS uses the class activation graph technique, which makes the searched models have better interpretability. In our experiments, we tested CAM-NAS on an NVIDIA RTX 3090 graphics card and showed that it can evaluate a submodel in only 0.08 seconds, which is much faster than traditional NAS methods. In this study, we experimentally evaluated CAM-NAS using the CIFAR-10 and CIFAR-100 datasets as benchmarks. The experimental results show that CAM-NAS achieves very good results. This not only proves the efficiency of CAM-NAS, but also demonstrates its powerful performance in image classification tasks.
20
Xie, Falian, Haihong Song e Huina Zhang. "Research on Light Comfort of Waiting Hall of High-Speed Railway Station in Cold Region Based on Interpretable Machine Learning". Buildings 13, n. 4 (21 aprile 2023): 1105. http://dx.doi.org/10.3390/buildings13041105.
Testo completoAbstract (sommario):
Upon the need for sustainability and natural lighting performance simulation for high-speed railway station waiting halls in cold regions, a new prediction method was proposed for the quantitative analysis of their natural lighting performance in the early design stage. Taking the waiting hall of Harbin West Railway Station as the prototype, the authors explore the optimization design of green performance-oriented waiting halls in this paper. To maximize daylight and minimize visual discomfort, and with the help of Rhinoceros and Grasshopper and Ladybug, and Honeybee platform simulation programs, spatial elements such as building orientation, shape and windowing were simulated through optimizing target sDA, UDI and DGPexceed, respectively, based on natural lighting performance. Additionally, a dataset covering several light environment influencing factors was constructed by parametric simulations to develop a gradient boosted regression tree (GBRT) model. The results showed that the model was valid; that is, the coefficient of determination between the predicted value and the target one exceeds 0.980 without overfitting, indicating that the interpretability analysis based on the GBRT prediction model can be used to fully explore the contribution of related design parameters of the waiting hall to the indoor light environment indexes, and to facilitate more efficient lighting design in the early design stage without detailed analysis. In addition, the GBRT prediction model can be used to replace the traditional one as the effective basis for decision support. To conclude, the skylight ratio played a significant role in UDI, while the section aspect ratio (SAR) and plan aspect ratio (PAR) served as the key design parameters for sDA and DGPexceed, respectively. At the same time, the building orientation had the least degree of influence on the natural lighting of the waiting hall.
21
Wang, Sixuan, Cailong Ma, Wenhu Wang, Xianlong Hou, Xufeng Xiao, Zhenhao Zhang, Xuanchi Liu e JinJing Liao. "Prediction of Failure Modes and Minimum Characteristic Value of Transverse Reinforcement of RC Beams Based on Interpretable Machine Learning". Buildings 13, n. 2 (9 febbraio 2023): 469. http://dx.doi.org/10.3390/buildings13020469.
Testo completoAbstract (sommario):
Shear failure of reinforced concrete (RC) beams is a form of brittle failure and has always been a concern. This study adopted the interpretable machine-learning technique to predict failure modes and identify the boundary value between different failure modes to avoid diagonal splitting failure. An experimental database consisting of 295 RC beams with or without transverse reinforcements was established. Two features were constructed to reflect the design characteristics of RC beams, namely, the shear–span ratio and the characteristic value of transverse reinforcement. The characteristic value of transverse reinforcement has two forms: (i) λsv,ft=ρstpfsv/ft, from the China design code of GB 50010-2010; and (ii) λsv,fc′=ρstpfsv/fc′0.5, from the America design code of ACI 318-19 and Canada design code of CSA A23.3-14. Six machine-learning models were developed to predict failure modes, and gradient boosting decision tree and extreme gradient boosting are recommended after comparing the prediction performance. Then, shapley additive explanations (SHAP) indicates that the characteristic value of transverse reinforcement has the most significant effect on failure mode, follow by the shear–span ratio. The characteristic value of transverse reinforcement is selected as the form of boundary value. On this basis, an accumulated local effects (ALE) plot describes how this feature affects model prediction and gives the boundary value through numerical simulation, that is, the minimum characteristic value of transverse reinforcement. Compared with the three codes, the suggested value for λsv,fc′,min has higher reliability and security for avoiding diagonal splitting failure. Accordingly, the research approach in this case is feasible and effective, and can be recommended to solve similar tasks.
22
Li, Rui. "DBSCAN-based line density clustering algorithm for CAD architectural drawings". Applied and Computational Engineering 19, n. 1 (23 ottobre 2023): 109–15. http://dx.doi.org/10.54254/2755-2721/19/20231018.
Testo completoAbstract (sommario):
In the traditional architecture industry, architects often need to convert CAD drawings into BIM in order to express the final effect of the building more concretely and to understand whether the design of each profession is reasonable after the drawings are completed. The whole modeling process is boring and tedious, and due to human fatigue, the final result is prone to problems, which eventually leads to failure to meet expectations. In order to free architects from the tedious task of model transformation, companies have designed software for automatic model transformation using computers. The core of the software design is related to computational geometry. Line segment clustering is one of the elements of computational geometry and a frequent problem in programming. Appropriate clustering of line segments can often bring convenience to the problem. This paper combines the basic idea of the DBSCAN algorithm, improves the shortcomings of DBSCAN algorithm in dealing with line segment clustering, and proposes a density-based line clustering algorithm with shapely library as a tool. The algorithm is highly interpretable, and the method performs well and efficiently in the test of actual drawings, whether to group the line segments or to find the target line segments that meet the conditions, which provides convenience for the subsequent calculation.
23
Leung, Eman, Albert Lee, Yilin Liu, Chi-Tim Hung, Ning Fan, Sam C. C. Ching, Hilary Yee et al. "Impact of Environment on Pain among the Working Poor: Making Use of Random Forest-Based Stratification Tool to Study the Socioecology of Pain Interference". International Journal of Environmental Research and Public Health 21, n. 2 (5 febbraio 2024): 179. http://dx.doi.org/10.3390/ijerph21020179.
Testo completoAbstract (sommario):
Pain interferes with one’s work and social life and, at a personal level, daily activities, mood, and sleep quality. However, little research has been conducted on pain interference and its socioecological determinants among the working poor. Noting the clinical/policy decision needs and the technical challenges of isolating the intricately interrelated socioecological factors’ unique contributions to pain interference and quantifying the relative contributions of each factor in an interpretable manner to inform clinical and policy decision-making, we deployed a novel random forest algorithm to model and quantify the unique contribution of a diverse ensemble of environmental, sociodemographic, and clinical factors to pain interference. Our analyses revealed that features representing the internal built environment of the working poor, such as the size of the living space, air quality, access to light, architectural design conducive to social connection, and age of the building, were assigned greater statistical importance than other more commonly examined predisposing factors for pain interference, such as age, occupation, the severity and locations of pain, BMI, serum blood sugar, and blood pressure. The findings were discussed in the context of their benefit in informing community pain screening to target residential areas whose built environment contributed most to pain interference and informing the design of intervention programs to minimize pain interference among those who suffered from chronic pain and showed specific characteristics. The findings support the call for good architecture to provide the spirit and value of buildings in city development.
24
R, Jain. "Transparency in AI Decision Making: A Survey of Explainable AI Methods and Applications". Advances in Robotic Technology 2, n. 1 (19 gennaio 2024): 1–10. http://dx.doi.org/10.23880/art-16000110.
Testo completoAbstract (sommario):
Artificial Intelligence (AI) systems have become pervasive in numerous facets of modern life, wielding considerable influence in critical decision-making realms such as healthcare, finance, criminal justice, and beyond. Yet, the inherent opacity of many AI models presents significant hurdles concerning trust, accountability, and fairness. To address these challenges, Explainable AI (XAI) has emerged as a pivotal area of research, striving to augment the transparency and interpretability of AI systems. This survey paper serves as a comprehensive exploration of the state-of-the-art in XAI methods and their practical applications. We delve into a spectrum of techniques, spanning from model-agnostic approaches to interpretable machine learning models, meticulously scrutinizing their respective strengths, limitations, and real-world implications. The landscape of XAI is rich and varied, with diverse methodologies tailored to address different facets of interpretability. Model-agnostic approaches offer versatility by providing insights into model behavior across various AI architectures. In contrast, interpretable machine learning models prioritize transparency by design, offering inherent understandability at the expense of some predictive performance. Layer-wise Relevance Propagation (LRP) and attention mechanisms delve into the inner workings of neural networks, shedding light on feature importance and decision processes. Additionally, counterfactual explanations open avenues for exploring what-if scenarios, elucidating the causal relationships between input features and model outcomes. In tandem with methodological exploration, this survey scrutinizes the deployment and impact of XAI across multifarious domains. Successful case studies showcase the practical utility of transparent AI in healthcare diagnostics, financial risk assessment, criminal justice systems, and more. By elucidating these use cases, we illuminate the transformative potential of XAI in enhancing decision-making processes while fostering accountability and fairness. Nevertheless, the journey towards fully transparent AI systems is fraught with challenges and opportunities. As we traverse the current landscape of XAI, we identify pressing areas for further research and development. These include refining interpretability metrics, addressing the scalability of XAI techniques to complex models, and navigating the ethical dimensions of transparency in AI decision-making.Through this survey, we endeavor to cultivate a deeper understanding of transparency in AI decision-making, empowering stakeholders to navigate the intricate interplay between accuracy, interpretability, and ethical considerations. By fostering interdisciplinary dialogue and inspiring collaborative innovation, we aspire to catalyze future advancements in Explainable AI, ultimately paving the way towards more accountable and trustworthy AI systems.
25
Zhu, Guangxiang, Jianhao Wang, Zhizhou Ren, Zichuan Lin e Chongjie Zhang. "Object-Oriented Dynamics Learning through Multi-Level Abstraction". Proceedings of the AAAI Conference on Artificial Intelligence 34, n. 04 (3 aprile 2020): 6989–98. http://dx.doi.org/10.1609/aaai.v34i04.6183.
Testo completoAbstract (sommario):
Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-supervised learning framework, called Multi-level Abstraction Object-oriented Predictor (MAOP), which employs a three-level learning architecture that enables efficient object-based dynamics learning from raw visual observations. We also design a spatial-temporal relational reasoning mechanism for MAOP to support instance-level dynamics learning and handle partial observability. Our results show that MAOP significantly outperforms previous methods in terms of sample efficiency and generalization over novel environments for learning environment models. We also demonstrate that learned dynamics models enable efficient planning in unseen environments, comparable to true environment models. In addition, MAOP learns semantically and visually interpretable disentangled representations.
26
Nair, Rajit. "Unraveling the Decision-making Process Interpretable Deep Learning IDS for Transportation Network Security". Journal of Cybersecurity and Information Management 12, n. 2 (2023): 69–82. http://dx.doi.org/10.54216/jcim.120205.
Testo completoAbstract (sommario):
The growing ubiquity of IoT-enabled devices in recent years emphasizes the critical need to strengthen transportation network safety and dependability. Intrusion detection systems (IDS) are crucial in preventing attacks on transport networks that rely on the Internet of Things (IoT). However, understanding the rationale behind deep learning-based IDS models may be challenging because they do not explain their findings. We offer an interpretable deep learning system that may be used to improve transportation network safety using IoT. To develop naturally accessible explanations for IDS projections, we integrate deep learning models with the Shapley Additive Reasons (SHAP) approach. By adding weight to distinct elements of the input data needed to develop the model, we increase the readability of so-called black box processes. We use the ToN_IoT dataset, which provides statistics on the volume of network traffic created by IoT-enabled transport systems, to assess the success of our strategy. We use a tool called CICFlowMeter to create network flows and collect data. The regularity of the flows, as well as their correlation with specific assaults, has been documented, allowing us to train and evaluate the IDS model. The experiment findings show that our explainable deep learning system is extremely accurate at detecting and categorising intrusions in IoT-enabled transportation networks. By examining data using the SHAP approach, cybersecurity specialists may learn more about the IDS's decision-making process. This enables the development of robust solutions, which improves the overall security of the Internet of Things. Aside from simplifying IDS predictions, the proposed technique provides useful recommendations for strengthening the resilience of IoT-enabled transportation systems against cyberattacks. The usefulness of IDS in defending mission critical IoT infrastructure has been questioned by security experts in the Internet of Vehicles (IoV) industry. The IoV is the primary research object in this case. Deep learning algorithms' versatility in processing many forms of data has contributed to their growing prominence in the field of anomaly detection in intrusion detection systems. Although machine learning models may be highly useful, they frequently yield false positives, and the path they follow to their conclusions is not always obvious to humans. Cybersecurity experts who want to evaluate the performance of a system or design more secure solutions need to understand the thinking process behind an IDS's results. The SHAP approach is employed in our proposed framework to give greater insight into the decisions made by IDSs that depend on deep learning. As a result, IoT network security is strengthened, and more cyber-resilient systems are developed. We demonstrate the effectiveness of our technique by comparing it to other credible methods and utilising the ToN_IoT dataset. Our framework has the best success rate when compared to other frameworks, as evidenced by testing results showing an F1 score of 98.83 percent and an accuracy of 99.15 percent. These findings demonstrate that the architecture successfully resists a variety of destructive assaults on IoT networks. By integrating deep learning and methodologies with an emphasis on explainability, our approach significantly enhances network security in IoT use scenarios. The ability to assess and grasp IDS options provides the path for cybersecurity experts to design and construct more secure IoT systems.
27
Zhang, Feng, Chenxin Wang, Xingxing Zou, Yang Wei, Dongdong Chen, Qiudong Wang e Libin Wang. "Prediction of the Shear Resistance of Headed Studs Embedded in Precast Steel–Concrete Structures Based on an Interpretable Machine Learning Method". Buildings 13, n. 2 (11 febbraio 2023): 496. http://dx.doi.org/10.3390/buildings13020496.
Testo completoAbstract (sommario):
Headed shear studs are an essential interfacial connection for precast steel–concrete structures to ensure composite action; hence, the accurate prediction of the shear capacity of headed studs is of pivotal significance. This study first established a worldwide dataset with 428 push-out tests of headed shear studs embedded in concrete with varied strengths from 26 MPa to 200 MPa. Five advanced machine learning (ML) models and three widely used equations from design codes were comparatively employed to predict the shear resistance of the headed studs. Considering the inevitable data variation caused by material properties and load testing, the isolated forest algorithm was first used to detect the anomaly of data in the dataset. Then, the five ML models were established and trained, which exhibited higher prediction accuracy than three existing design codes that were widely used in the world. Compared with the equations from AASHTO (the one that has the best prediction accuracy among design specifications), the gradient boosting decision tree (GBDT) model showed an 80% lower root mean square error, 308% higher coefficient of determination, and 86% lower mean absolute percent error. Lastly, individual conditional expectation plots and partial dependence plots showed the relationship between the individual parameters and the predicted target based on the GBDT model. The results showed that the elastic modulus of concrete, the tensile strength of the studs, and the length–diameter ratio of the studs influenced most of the shear capacity of shear studs. Additionally, the effect of the length–diameter ratio has an upper limit which depends on the strength of the studs and concrete.
28
Zhang, Benyuan, Xin Jin, Wenyu Liang, Xiaoyu Chen, Zhenhong Li, George Panoutsos, Zepeng Liu e Zezhi Tang. "TabNet: Locally Interpretable Estimation and Prediction for Advanced Proton Exchange Membrane Fuel Cell Health Management". Electronics 13, n. 7 (3 aprile 2024): 1358. http://dx.doi.org/10.3390/electronics13071358.
Testo completoAbstract (sommario):
In the pursuit of advanced Predictive Health Management (PHM) for Proton Exchange Membrane Fuel Cells (PEMFCs), conventional data-driven models encounter considerable barriers due to data reconstruction resulting in poor data quality, and the complexity of models leading to insufficient interpretability. In addressing these challenges, this research introduces TabNet, a model aimed at augmenting predictive interpretability, and integrates it with an innovative data preprocessing technique to enhance the predictive performance of PEMFC health management. In traditional data processing approaches, reconstruction methods are employed on the original dataset, significantly reducing its size and consequently diminishing the accuracy of model predictions. To overcome this challenge, the Segmented Random Sampling Correction (SRSC) methodology proposed herein effectively eliminates noise from the original dataset whilst maintaining its effectiveness. Notably, as the majority of deep learning models operate as black boxes, it becomes challenging to identify the exact factors affecting the Remaining Useful Life (RUL) of PEMFCs, which is clearly disadvantageous for the health management of PEMFCs. Nonetheless, TabNet offers insights into the decision-making process for predicting the RUL of PEMFCs, for instance, identifying which experimental parameters significantly influence the prediction outcomes. Specifically, TabNet’s distinctive design employs sequential attention to choose features for reasoning at each decision-making step, not only enhancing the accuracy of RUL predictions in PEMFC but also offering interpretability of the results. Furthermore, this study utilized Gaussian augmentation techniques to boost the model’s generalization capability across varying operational conditions. Through pertinent case studies, the efficacy of this integrated framework, merging data processing with the TabNet architecture, was validated. This work not only evidences that the effective data processing and strategic deployment of TabNet can markedly elevate model performance but also, via a visual analysis of the parameters’ impact, provides crucial insights for the future health management of PEMFCs.
29
Gim, Mogan, Junseok Choe, Seungheun Baek, Jueon Park, Chaeeun Lee, Minjae Ju, Sumin Lee e Jaewoo Kang. "ArkDTA: attention regularization guided by non-covalent interactions for explainable drug–target binding affinity prediction". Bioinformatics 39, Supplement_1 (1 giugno 2023): i448—i457. http://dx.doi.org/10.1093/bioinformatics/btad207.
Testo completoAbstract (sommario):
Abstract Motivation Protein–ligand binding affinity prediction is a central task in drug design and development. Cross-modal attention mechanism has recently become a core component of many deep learning models due to its potential to improve model explainability. Non-covalent interactions (NCIs), one of the most critical domain knowledge in binding affinity prediction task, should be incorporated into protein–ligand attention mechanism for more explainable deep drug–target interaction models. We propose ArkDTA, a novel deep neural architecture for explainable binding affinity prediction guided by NCIs. Results Experimental results show that ArkDTA achieves predictive performance comparable to current state-of-the-art models while significantly improving model explainability. Qualitative investigation into our novel attention mechanism reveals that ArkDTA can identify potential regions for NCIs between candidate drug compounds and target proteins, as well as guiding internal operations of the model in a more interpretable and domain-aware manner. Availability ArkDTA is available at https://github.com/dmis-lab/ArkDTA Contact kangj@korea.ac.kr
30
Mahmoodian, Mojtaba, Farham Shahrivar, Sujeeva Setunge e Sam Mazaheri. "Development of Digital Twin for Intelligent Maintenance of Civil Infrastructure". Sustainability 14, n. 14 (15 luglio 2022): 8664. http://dx.doi.org/10.3390/su14148664.
Testo completoAbstract (sommario):
Over the life cycle of a civil infrastructure (a bridge as an example), 0.4–2% of the construction cost is spent annually on its maintenance. Utilising new technologies including the internet of things (IoT) and digital twin (DT) can significantly reduce the infrastructure maintenance costs. An infrastructure DT involves its digital replica and must include data on geometric, geospatial reference, performance, attributes (material, environment etc.) and management. Then, the acquired data need to be analysed and visualised to inform maintenance decision making. To develop this DT, the first step is the study of the infrastructure life cycle to design DT architecture. Using data semantics, this paper presents a novel DT architecture design for an intelligent infrastructure maintenance system. Semantic modelling is used as a powerful tool to structure and organize data. This approach provides an industry context through capturing knowledge about infrastructures in the structure of semantic model graph. Using new technologies, DT approach derives and presents meaningful data on infrastructure real-time performance and maintenance requirements, and in a more expressible and interpretable manner. The data semantic model will guide when and what data to collect for feeding into the infrastructure DT. The proposed DT concept was applied on one of the conveyors of Dalrymple Bay Coal Terminal in Queensland Australia to monitor the structural performance in real-time, which enables predictive maintenance to avoid breakdowns and disruptions in operation and consequential financial impacts.
31
Chen, Yung-Yao, Yu-Hsiu Lin, Chia-Ching Kung, Ming-Han Chung e I.-Hsuan Yen. "Design and Implementation of Cloud Analytics-Assisted Smart Power Meters Considering Advanced Artificial Intelligence as Edge Analytics in Demand-Side Management for Smart Homes". Sensors 19, n. 9 (2 maggio 2019): 2047. http://dx.doi.org/10.3390/s19092047.
Testo completoAbstract (sommario):
In a smart home linked to a smart grid (SG), demand-side management (DSM) has the potential to reduce electricity costs and carbon/chlorofluorocarbon emissions, which are associated with electricity used in today’s modern society. To meet continuously increasing electrical energy demands requested from downstream sectors in an SG, energy management systems (EMS), developed with paradigms of artificial intelligence (AI) across Internet of things (IoT) and conducted in fields of interest, monitor, manage, and analyze industrial, commercial, and residential electrical appliances efficiently in response to demand response (DR) signals as DSM. Usually, a DSM service provided by utilities for consumers in an SG is based on cloud-centered data science analytics. However, such cloud-centered data science analytics service involved for DSM is mostly far away from on-site IoT end devices, such as DR switches/power meters/smart meters, which is usually unacceptable for latency-sensitive user-centric IoT applications in DSM. This implies that, for instance, IoT end devices deployed on-site for latency-sensitive user-centric IoT applications in DSM should be aware of immediately analytical, interpretable, and real-time actionable data insights processed on and identified by IoT end devices at IoT sources. Therefore, this work designs and implements a smart edge analytics-empowered power meter prototype considering advanced AI in DSM for smart homes. The prototype in this work works in a cloud analytics-assisted electrical EMS architecture, which is designed and implemented as edge analytics in the architecture described and developed toward a next-generation smart sensing infrastructure for smart homes. Two different types of AI deployed on-site on the prototype are conducted for DSM and compared in this work. The experimentation reported in this work shows the architecture described with the prototype in this work is feasible and workable.
32
Baillargeon, Jean-Thomas, Luc Lamontagne e Etienne Marceau. "Mining Actuarial Risk Predictors in Accident Descriptions Using Recurrent Neural Networks". Risks 9, n. 1 (29 dicembre 2020): 7. http://dx.doi.org/10.3390/risks9010007.
Testo completoAbstract (sommario):
One crucial task of actuaries is to structure data so that observed events are explained by their inherent risk factors. They are proficient at generalizing important elements to obtain useful forecasts. Although this expertise is beneficial when paired with conventional statistical models, it becomes limited when faced with massive unstructured datasets. Moreover, it does not take profit from the representation capabilities of recent machine learning algorithms. In this paper, we present an approach to automatically extract textual features from a large corpus that departs from the traditional actuarial approach. We design a neural architecture that can be trained to predict a phenomenon using words represented as dense embeddings. We then extract features identified as important by the model to assess the relationship between the words and the phenomenon. The technique is illustrated through a case study that estimates the number of cars involved in an accident using the accident’s description as input to a Poisson regression model. We show that our technique yields models that are more performing and interpretable than some usual actuarial data mining baseline.
33
Purohit, Kuldeep, e A. N. Rajagopalan. "Region-Adaptive Dense Network for Efficient Motion Deblurring". Proceedings of the AAAI Conference on Artificial Intelligence 34, n. 07 (3 aprile 2020): 11882–89. http://dx.doi.org/10.1609/aaai.v34i07.6862.
Testo completoAbstract (sommario):
In this paper, we address the problem of dynamic scene deblurring in the presence of motion blur. Restoration of images affected by severe blur necessitates a network design with a large receptive field, which existing networks attempt to achieve through simple increment in the number of generic convolution layers, kernel-size, or the scales at which the image is processed. However, these techniques ignore the non-uniform nature of blur, and they come at the expense of an increase in model size and inference time. We present a new architecture composed of region adaptive dense deformable modules that implicitly discover the spatially varying shifts responsible for non-uniform blur in the input image and learn to modulate the filters. This capability is complemented by a self-attentive module which captures non-local spatial relationships among the intermediate features and enhances the spatially varying processing capability. We incorporate these modules into a densely connected encoder-decoder design which utilizes pre-trained Densenet filters to further improve the performance. Our network facilitates interpretable modeling of the spatially-varying deblurring process while dispensing with multi-scale processing and large filters entirely. Extensive comparisons with prior art on benchmark dynamic scene deblurring datasets clearly demonstrate the superiority of the proposed networks via significant improvements in accuracy and speed, enabling almost real-time deblurring.
34
Silva, Erica N., Akshat Singhal, Sungjoon Park, Jason Kreisberg e Trey Ideker. "Abstract 636: Prediction of therapeutic response via data-driven maps of tumor cell architecture". Cancer Research 82, n. 12_Supplement (15 giugno 2022): 636. http://dx.doi.org/10.1158/1538-7445.am2022-636.
Testo completoAbstract (sommario):
Abstract Machine learning is revolutionizing the analysis of biological and biomedical data. One continued challenge is to build models that are not only predictive but also provide mechanistic explanations. Directly incorporating explainability into the model’s design has emerged as a possible solution. Recently, we reported several “visible” machine learning systems - DCell and DrugCell - which predict cellular growth based on genetic perturbations. In these visible models, the structure of the underlying neural network mirrors known aspects of cell biology. Here we designed a cancer-specific model of therapeutic response. First, we selected NeST (Nested Systems in Tumors; Zheng et al., Science 2021), a data-driven hierarchy of tumor cell systems under selection in cancer, as the structure for our visible neural network. Second, we restricted input features to genes currently assayed on clinical cancer gene panels. We considered training schemes that assess the model’s ability to generalize to novel genotypes. Most importantly, we assessed performance on patient data from the AACR Project GENIE clinical trial where we discriminated between patients who are likely to respond to selected drug treatments. Finally, we examined model explanations within the visible NeST architecture to highlight cellular mechanisms of response to drug therapy. Overall, we found that by considering a tumor cell architecture optimized for clinical application, we can design an interpretable deep learning model that both accurately stratifies patient responses and explains the drug mechanism in cancer cells. Citation Format: Erica N. Silva, Akshat Singhal, Sungjoon Park, Jason Kreisberg, Trey Ideker. Prediction of therapeutic response via data-driven maps of tumor cell architecture [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 636.
35
Zhang, Jingyan, e Xiaoyu Zheng. "Exploring the implementation and applications of 7-segment clocks on FPGA". Theoretical and Natural Science 26, n. 1 (20 dicembre 2023): 37–43. http://dx.doi.org/10.54254/2753-8818/26/20241009.
Testo completoAbstract (sommario):
The core objective of this undertaking revolves around digital circuits and Field-programmable gate arrays (FPGAs), focusing on the design and implementation of a digital clock capable of showcasing real-time hours, minutes, and seconds. To ensure accurate time tracking, the project ingeniously employs a MOD 60 counter, dedicated specifically for counting both minutes and seconds, while a separate MOD 24 counter is harnessed to track hours. These counters serve as the backbone of the clocks accurate time-keeping capability. To translate this raw digital data into an easily interpretable format for users, the project incorporates a seven-segment display, ensuring that the time can be read intuitively at a glance. The entire architecture and logic of the digital clock is artfully crafted using Verilog HDL, a versatile programming language revered for its aptness in hardware description and simulation. To bring the clock to life and rigorously test its functionality, the Quartus platform is utilized. This renowned platform not only facilitates the efficient translation of the Verilog HDL code into tangible digital circuitry but also offers a robust environment for simulation, ensuring the clock operates flawlessly in real-world scenarios.
36
Polcin, Douglas. "How should we study residential recovery homes?" Therapeutic Communities: The International Journal of Therapeutic Communities 36, n. 3 (14 settembre 2015): 163–72. http://dx.doi.org/10.1108/tc-07-2014-0027.
Testo completoAbstract (sommario):
Purpose – Persons with serious alcohol and drug problems who are attempting to maintain abstinence often lack an alcohol- and drug-free living environment that supports sustained recovery. Residential recovery homes, called “sober living houses” in California, are alcohol- and drug-free living environments that offer long-term support for persons with addictive disorders. They do not offer formal treatment services but usually encourage or mandate attendance at self-help recovery groups such as Alcoholics Anonymous. The paper aims to discuss these issues. Design/methodology/approach – The approach involved analysis of the strengths and weaknesses of different research designs for studying residential recovery homes. Alternatives to randomized designs that are able to capture “real world” data that are readily generalized are described and understudied topics are identified. Findings – A significant limitation of traditional randomized designs is they eliminate mutual selection processes between prospective residents and recovery home residents and staff. Naturalistic research designs have the advantage of including mutual selection processes and there are methods available for limiting self-selection bias. Qualitative methods should be used to identify factors that residents experience as helpful that can then be studied further. Innovative studies are needed to investigate how outcomes are affected by architectural characteristics of the houses and resident interactions with the surrounding community. Practical implications – Use of the recommended strategies could lead to findings that are more informative, intuitively appealing, and interpretable. Social implications – Recovery homes and similar programs will be more responsive to consumers. Originality/value – This paper represents one of the first to review various options for studying recovery homes and to provide suggestions for new studies.
37
Cui, Min, Yang Liu, Yanbo Wang e Pan Wang. "Identifying the Acoustic Source via MFF-ResNet with Low Sample Complexity". Electronics 11, n. 21 (1 novembre 2022): 3578. http://dx.doi.org/10.3390/electronics11213578.
Testo completoAbstract (sommario):
Acoustic signal classification plays a central role in acoustic source identification. In practical applications, however, varieties of training data are typically inadequate, which leads to a low sample complexity. Applying classical deep learning methods to identify acoustic signals involves a large number of parameters in the classification model, which calls for great sample complexity. Therefore, low sample complexity modeling is one of the most important issues related to the performance of the acoustic signal classification. In this study, the authors propose a novel data fusion model named MFF-ResNet, in which manual design features and deep representation of log-Mel spectrogram features are fused with bi-level attention. The proposed approach involves an amount of prior human knowledge as implicit regularization, thus leading to an interpretable and low sample complexity model of the acoustic signal classification. The experimental results suggested that MFF-ResNet is capable of accurate acoustic signal classification with fewer training samples.
38
Kesici, Neslişah, e Nilgün Çolpan Erkan. "THE EFFECT OF PUBLIC FACADE CHARACTERISTICS ON CHANGING PEDESTRIAN BEHAVIORS". JOURNAL OF ARCHITECTURE AND URBANISM 47, n. 1 (15 maggio 2023): 68–76. http://dx.doi.org/10.3846/jau.2023.17688.
Testo completoAbstract (sommario):
The facades that define the public open space shape the pedestrian behavior by affecting the visual perception of the pedestrians. In the literature on facade and human interaction, there are pioneering studies in the perspective of environmental perception, but there is a lack and method limitation on the effect of the facade on pedestrian behavior. For this reason, the research aims to evaluate pedestrian behaviors in two areas that are variable in terms of facades, together with video analysis and heat maps. Areas of similar typology in Istanbul’s Kadıköy district are compared because of the temporary exterior decoration of the historical candy store in case 1 during the New Year’s Eve. According to the research findings, there is a significant difference between the quantity of pedestrians exhibiting stagnant and flowing behaviors and the distribution of these pedestrians in the space. In addition, the subcategories of fluid and static behavior in evening and day conditions also reveal interpretable results regarding the front. The results of the research reveal that the facade features of the public space significantly affect the pedestrian behavior, and therefore this issue should also gain importance in the future of public space design.
39
Chan, Albert P. C., Yang Yang, Francis K. W. Wong, Daniel W. M. Chan e Edmond W. M. Lam. "Wearing comfort of two construction work uniforms". Construction Innovation 15, n. 4 (5 ottobre 2015): 473–92. http://dx.doi.org/10.1108/ci-06-2015-0037.
Testo completoAbstract (sommario):
Purpose – The aim of this study is to investigate wearing comfort of summer work uniforms judged by construction workers. Design/methodology/approach – A total of 189 male construction workers participated in a series of wear trials and questionnaire surveys in the summer of 2014. They were asked to randomly wear two types of work uniforms (i.e. uniforms A and B) in the two-day field survey and the subjective attributes of these uniforms were assessed. Three analytical techniques, namely, multiple regression, artificial neural network and fuzzy logic were used to predict wearing comfort affected by the six subjective sensations. Findings – The results revealed that fuzzy logic was a robust and practical tool for predicting wearing comfort in terms of better prediction performance and more interpretable results than the other models. Pressure attributes were further found to exert a greater effect than thermal–wet attributes on wearing comfort. Overall, the use of uniform B exhibited profound benefits on wearing comfort because it kept workers cooler, drier and more comfortable with less work performance interference than wearing uniform A. Originality/value – The findings provide a fresh insight into construction workers’ needs for work clothes, which further facilitates the improvement in the clothing tailor-made design and the enhancement of the well-being of workers.
40
Bai, Yidong, e Toshiharu Sugawara. "Enhancing Multi-Agent Cooperation Through Action-Probability-Based Communication". Journal of Robotics and Mechatronics 36, n. 3 (20 giugno 2024): 658–68. http://dx.doi.org/10.20965/jrm.2024.p0658.
Testo completoAbstract (sommario):
Although communication plays a pivotal role in achieving coordinated activities in multi-agent systems, conventional approaches often involve complicated high-dimensional messages generated by deep networks. These messages are typically indecipherable to humans, are relatively costly to transmit, and require intricate encoding and decoding networks. This can pose a design limitation for the agents such as autonomous (mobile) robots. This lack of interpretability can lead to systemic issues with security and reliability. In this study, inspired by common human communication about likely actions in collaborative endeavors, we propose a novel approach in which each agent’s action probabilities are transmitted to other agents as messages, drawing inspiration from the common human practice of sharing likely actions in collaborative endeavors. Our proposed framework is referred to as communication based on action probabilities (CAP), and focuses on generating straightforward, low-dimensional, interpretable messages to support multiple agents in coordinating their activities to achieve specified cooperative goals. CAP streamlines our comprehension of the agents’ learned coordinated and cooperative behaviors and eliminates the need to use additional network models to generate messages. CAP’s network architecture is simpler than that of state-of-the-art methods, and our experimental results show that it nonetheless performed comparably, converged faster, and exhibited a lower volume of communication with better interpretability.
41
Torres Silva, Ever Augusto, Sebastian Uribe, Jack Smith, Ivan Felipe Luna Gomez e Jose Fernando Florez-Arango. "XML Data and Knowledge-Encoding Structure for a Web-Based and Mobile Antenatal Clinical Decision Support System: Development Study". JMIR Formative Research 4, n. 10 (16 ottobre 2020): e17512. http://dx.doi.org/10.2196/17512.
Testo completoAbstract (sommario):
Background Displeasure with the functionality of clinical decision support systems (CDSSs) is considered the primary challenge in CDSS development. A major difficulty in CDSS design is matching the functionality to the desired and actual clinical workflow. Computer-interpretable guidelines (CIGs) are used to formalize medical knowledge in clinical practice guidelines (CPGs) in a computable language. However, existing CIG frameworks require a specific interpreter for each CIG language, hindering the ease of implementation and interoperability. Objective This paper aims to describe a different approach to the representation of clinical knowledge and data. We intended to change the clinician’s perception of a CDSS with sufficient expressivity of the representation while maintaining a small communication and software footprint for both a web application and a mobile app. This approach was originally intended to create a readable and minimal syntax for a web CDSS and future mobile app for antenatal care guidelines with improved human-computer interaction and enhanced usability by aligning the system behavior with clinical workflow. Methods We designed and implemented an architecture design for our CDSS, which uses the model-view-controller (MVC) architecture and a knowledge engine in the MVC architecture based on XML. The knowledge engine design also integrated the requirement of matching clinical care workflow that was desired in the CDSS. For this component of the design task, we used a work ontology analysis of the CPGs for antenatal care in our particular target clinical settings. Results In comparison to other common CIGs used for CDSSs, our XML approach can be used to take advantage of the flexible format of XML to facilitate the electronic sharing of structured data. More importantly, we can take advantage of its flexibility to standardize CIG structure design in a low-level specification language that is ubiquitous, universal, computationally efficient, integrable with web technologies, and human readable. Conclusions Our knowledge representation framework incorporates fundamental elements of other CIGs used in CDSSs in medicine and proved adequate to encode a number of antenatal health care CPGs and their associated clinical workflows. The framework appears general enough to be used with other CPGs in medicine. XML proved to be a language expressive enough to describe planning problems in a computable form and restrictive and expressive enough to implement in a clinical system. It can also be effective for mobile apps, where intermittent communication requires a small footprint and an autonomous app. This approach can be used to incorporate overlapping capabilities of more specialized CIGs in medicine.
42
Garcon, Antoine, Julian Vexler, Dmitry Budker e Stefan Kramer. "Deep neural networks to recover unknown physical parameters from oscillating time series". PLOS ONE 17, n. 5 (13 maggio 2022): e0268439. http://dx.doi.org/10.1371/journal.pone.0268439.
Testo completoAbstract (sommario):
Deep neural networks are widely used in pattern-recognition tasks for which a human-comprehensible, quantitative description of the data-generating process, cannot be obtained. While doing so, neural networks often produce an abstract (entangled and non-interpretable) representation of the data-generating process. This may be one of the reasons why neural networks are not yet used extensively in physics-experiment signal processing: physicists generally require their analyses to yield quantitative information about the system they study. In this article we use a deep neural network to disentangle components of oscillating time series. To this aim, we design and train the neural network on synthetic oscillating time series to perform two tasks: a regression of the signal latent parameters and signal denoising by an Autoencoder-like architecture. We show that the regression and denoising performance is similar to those of least-square curve fittings with true latent-parameters initial guesses, in spite of the neural network needing no initial guesses at all. We then explore various applications in which we believe our architecture could prove useful for time-series processing, when prior knowledge is incomplete. As an example, we employ the neural network as a preprocessing tool to inform the least-square fits when initial guesses are unknown. Moreover, we show that the regression can be performed on some latent parameters, while ignoring the existence of others. Because the Autoencoder needs no prior information about the physical model, the remaining unknown latent parameters can still be captured, thus making use of partial prior knowledge, while leaving space for data exploration and discoveries.
43
Scherrer, Simon, Markus Legner, Adrian Perrig e Stefan Schmid. "An Axiomatic Perspective on the Performance Effects of End-Host Path Selection". ACM SIGMETRICS Performance Evaluation Review 49, n. 3 (22 marzo 2022): 16–17. http://dx.doi.org/10.1145/3529113.3529118.
Testo completoAbstract (sommario):
In various contexts of networking research, end-host path selection has recently regained momentum as a design principle. While such path selection has the potential to increase performance and security of networks, there is a prominent concern that it could also lead to network instability (i.e., flow-volume oscillation) if paths are selected in a greedy, load-adaptive fashion. However, the extent and the impact vectors of instability caused by path selection are rarely concretized or quantified, which is essential to discuss the merits and drawbacks of end-host path selection. In this work, we investigate the effect of end-host path selection on various metrics of networks both qualitatively and quantitatively. To achieve general and fundamental insights, we leverage the recently introduced axiomatic perspective on congestion control and adapt it to accommodate joint algorithms for path selection and congestion control, i.e., multi-path congestion-control protocols. Using this approach, we identify equilibria of the multi-path congestioncontrol dynamics and analytically characterize these equilibria with respect to important metrics of interest in networks (the "axioms") such as efficiency, fairness, and loss avoidance. We analyze how these axiomatic ratings for a general network change compared to a scenario without path selection, thereby obtaining an interpretable and quantititative formalization of the performance impact of end-host path-selection. Finally, we show that there is a fundamental trade-off in multi-path congestion-control protocol design between efficiency, stability, and loss avoidance on one side and fairness and responsiveness on the other side.
44
Abdel-Jaber, Fayez, e Kim N. Dirks. "A Review of Cooling and Heating Loads Predictions of Residential Buildings Using Data-Driven Techniques". Buildings 14, n. 3 (11 marzo 2024): 752. http://dx.doi.org/10.3390/buildings14030752.
Testo completoAbstract (sommario):
Energy efficiency is currently a hot topic in engineering due to the monetary and environmental benefits it brings. One aspect of energy efficiency in particular, the prediction of thermal loads (specifically heating and cooling), plays a significant role in reducing the costs associated with energy use and in minimising the risks associated with climate change. Recently, data-driven approaches, such as artificial intelligence (AI) and machine learning (ML) techniques, have provided cost-effective and high-quality solutions for solving energy efficiency problems. This research investigates various ML methods for predicting energy efficiency in buildings, with a particular emphasis on heating and cooling loads. The review includes many ML techniques, including ensemble learning, support vector machines (SVM), artificial neural networks (ANN), statistical models, and probabilistic models. Existing studies are analysed and compared in terms of new criteria, including the datasets used, the associated platforms, and, more importantly, the interpretability of the models generated. The results show that, despite the problem under investigation being studied using a range of ML techniques, few have focused on developing interpretable classifiers that can be exploited by stakeholders to support the design of energy-efficient residential buildings for climate impact minimisation. Further research in this area is required.
45
Xiao, Jingyu, Qingsong Zou, Qing Li, Dan Zhao, Kang Li, Zixuan Weng, Ruoyu Li e Yong Jiang. "I Know Your Intent". Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7, n. 3 (27 settembre 2023): 1–28. http://dx.doi.org/10.1145/3610906.
Testo completoAbstract (sommario):
With the booming of smart home market, intelligent Internet of Things (IoT) devices have been increasingly involved in home life. To improve the user experience of smart homes, some prior works have explored how to use machine learning for predicting interactions between users and devices. However, the existing solutions have inferior User Device Interaction (UDI) prediction accuracy, as they ignore three key factors: routine, intent and multi-level periodicity of human behaviors. In this paper, we present SmartUDI, a novel accurate UDI prediction approach for smart homes. First, we propose a Message-Passing-based Routine Extraction (MPRE) algorithm to mine routine behaviors, then the contrastive loss is applied to narrow representations among behaviors from the same routines and alienate representations among behaviors from different routines. Second, we propose an Intent-aware Capsule Graph Attention Network (ICGAT) to encode multiple intents of users while considering complex transitions between different behaviors. Third, we design a Cluster-based Historical Attention Mechanism (CHAM) to capture the multi-level periodicity by aggregating the current sequence and the semantically nearest historical sequence representations through the attention mechanism. SmartUDI can be seamlessly deployed on cloud infrastructures of IoT device vendors and edge nodes, enabling the delivery of personalized device service recommendations to users. Comprehensive experiments on four real-world datasets show that SmartUDI consistently outperforms the state-of-the-art baselines with more accurate and highly interpretable results.
46
Elahe, Md Fazla, Md Alamgir Kabir, S. M. Hasan Mahmud e Riasat Azim. "Factors Impacting Short-Term Load Forecasting of Charging Station to Electric Vehicle". Electronics 12, n. 1 (23 dicembre 2022): 55. http://dx.doi.org/10.3390/electronics12010055.
Testo completoAbstract (sommario):
The rapid growth of electric vehicles (EVs) is likely to endanger the current power system. Forecasting the demand for charging stations is one of the critical issues while mitigating challenges caused by the increased penetration of EVs. Uncovering load-affecting features of the charging station can be beneficial for improving forecasting accuracy. Existing studies mostly forecast electricity demand of charging stations based on load profiling. It is difficult for public EV charging stations to obtain features for load profiling. This paper examines the power demand of two workplace charging stations to address the above-mentioned issue. Eight different types of load-affecting features are discussed in this study without compromising user privacy. We found that the workplace EV charging station exhibits opposite characteristics to the public EV charging station for some factors. Later, the features are used to design the forecasting model. The average accuracy improvement with these features is 42.73% in terms of RMSE. Moreover, the experiments found that summer days are more predictable than winter days. Finally, a state-of-the-art interpretable machine learning technique has been used to identify top contributing features. As the study is conducted on a publicly available dataset and analyzes the root cause of demand change, it can be used as baseline for future research.
47
Manicka, Santosh, e Michael Levin. "Minimal Developmental Computation: A Causal Network Approach to Understand Morphogenetic Pattern Formation". Entropy 24, n. 1 (10 gennaio 2022): 107. http://dx.doi.org/10.3390/e24010107.
Testo completoAbstract (sommario):
What information-processing strategies and general principles are sufficient to enable self-organized morphogenesis in embryogenesis and regeneration? We designed and analyzed a minimal model of self-scaling axial patterning consisting of a cellular network that develops activity patterns within implicitly set bounds. The properties of the cells are determined by internal ‘genetic’ networks with an architecture shared across all cells. We used machine-learning to identify models that enable this virtual mini-embryo to pattern a typical axial gradient while simultaneously sensing the set boundaries within which to develop it from homogeneous conditions—a setting that captures the essence of early embryogenesis. Interestingly, the model revealed several features (such as planar polarity and regenerative re-scaling capacity) for which it was not directly selected, showing how these common biological design principles can emerge as a consequence of simple patterning modes. A novel “causal network” analysis of the best model furthermore revealed that the originally symmetric model dynamically integrates into intercellular causal networks characterized by broken-symmetry, long-range influence and modularity, offering an interpretable macroscale-circuit-based explanation for phenotypic patterning. This work shows how computation could occur in biological development and how machine learning approaches can generate hypotheses and deepen our understanding of how featureless tissues might develop sophisticated patterns—an essential step towards predictive control of morphogenesis in regenerative medicine or synthetic bioengineering contexts. The tools developed here also have the potential to benefit machine learning via new forms of backpropagation and by leveraging the novel distributed self-representation mechanisms to improve robustness and generalization.
48
Kumar Singh, Siddhanta, e Ajay Kumar Singh. "Vehicular impact analysis of driving for accidents using on board diagnostic II". Bulletin of Electrical Engineering and Informatics 11, n. 5 (1 ottobre 2022): 2696–704. http://dx.doi.org/10.11591/eei.v11i5.3864.
Testo completoAbstract (sommario):
A large number of people meet with an accident everyday around the world. One of the leading causes of death is traffic accidents. The reasons behind India's rising number of road accidents contribute to bad driving behavior, poor road design and infrastructure, lack of enforcement of traffic laws. The post accidental investigation report is very important to know the actual reason of collision for the concerned parties and the insurance company and the police. The proposed work effectively extracts interpretable features describing complex driving patterns. It will provide analytical report of the accidents to various parties involved in process. This work analyzes the type and cause of accident. The experiment has been simulated using on board diagnostic II (OBD II) and smart phone accelerometer for post accidental analysis of collision. As the electronic control unit (ECU) does not provide accelerometer sensor, so the smart phone accelerometer has been utilized in conjunction with another parameter of OBD II device. The gravitational force (G-force) values observed from accelerometer sensor along the different axes and speed, acceleration, fuel consumption rate, and are retrieved from OBD II device. The result shows that the parameters recorded are very helpful in finding the actual accidental status of the vehicle.
49
Moujabbir, Mohammed, Khalid Bahani, Mohammed Ramdani e Hamza Ali-Ou-Salah. "Wind power forecasting model based on linguistic fuzzy rules". Bulletin of Electrical Engineering and Informatics 12, n. 4 (1 agosto 2023): 2372–80. http://dx.doi.org/10.11591/beei.v12i4.4733.
Testo completoAbstract (sommario):
The design and operationalization of a wind energy system is mainly based on wind speed and wind direction, theses parameters depend on several geographic, temporal, and climatic factors. Fluctuating factors such as climate cause irregularities in wind energy production. Therefore, wind power forecasting is necessary before using wind power systems. Furthermore, in order to make informed decisions, it is necessary to explain the system's predictions to stakeholders. The explainable artificial intelligence (XAI) provides an interactive interface for intelligent systems to interact with machines, validate their results, and trust their behavior. In this paper, we provide an interpretable system for predicting wind energy using weather data. This system is based on a two-step method for fuzzy rules learning clustering (FRLC). The first step uses subtractive clustering and a linguistic approximation to extract linguistic rules. The second step uses linguistic hedges to refine linguistic rules. FRLC is compared to with artificial neural network (ANN), random forest (RF), k-nearest neighbors (K-NN), and support vector regression (SVR) models. The experimental results show that the accuracy of FRLC is acceptable regarding the comparison models and outperform them in terms of the interpretability. In parallel with prediction, FRLC model provides a set of linguistic fuzzy rules that explain the obtained results to the stakeholders.
50
Moujabbir, Mohammed, Khalid Bahani, Mohammed Ramdani e Hamza Ali-Ou-Salah. "Wind power forecasting model based on linguistic fuzzy rules". Bulletin of Electrical Engineering and Informatics 12, n. 4 (1 agosto 2023): 2372–80. http://dx.doi.org/10.11591/eei.v12i4.4733.
Testo completoAbstract (sommario):
The design and operationalization of a wind energy system is mainly based on wind speed and wind direction, theses parameters depend on several geographic, temporal, and climatic factors. Fluctuating factors such as climate cause irregularities in wind energy production. Therefore, wind power forecasting is necessary before using wind power systems. Furthermore, in order to make informed decisions, it is necessary to explain the system's predictions to stakeholders. The explainable artificial intelligence (XAI) provides an interactive interface for intelligent systems to interact with machines, validate their results, and trust their behavior. In this paper, we provide an interpretable system for predicting wind energy using weather data. This system is based on a two-step method for fuzzy rules learning clustering (FRLC). The first step uses subtractive clustering and a linguistic approximation to extract linguistic rules. The second step uses linguistic hedges to refine linguistic rules. FRLC is compared to with artificial neural network (ANN), random forest (RF), k-nearest neighbors (K-NN), and support vector regression (SVR) models. The experimental results show that the accuracy of FRLC is acceptable regarding the comparison models and outperform them in terms of the interpretability. In parallel with prediction, FRLC model provides a set of linguistic fuzzy rules that explain the obtained results to the stakeholders.