To see the other types of publications on this topic, follow the link: Siamese Neural Models.
Journal articles on the topic 'Siamese Neural Models'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Siamese Neural Models.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Kurniasari, Dian, Mustofa Usman, Warsono Warsono, and Favorisen Rosyking Lumbanraja. "Comparative analysis of deep Siamese models for medical reports text similarity." International Journal of Electrical and Computer Engineering (IJECE) 14, no. 6 (December 1, 2024): 6969. http://dx.doi.org/10.11591/ijece.v14i6.pp6969-6980.
Full textAbstract:
Even though medical reports have been digitized, they are generally text data and have not been used optimally. Extracting information from these reports is challenging due to their high volume and unstructured nature. Analyzing the extraction of relevant and high-quality information can be achieved by measuring semantic textual similarity (STS). Consequently, the primary aim of this study is to develop and evaluate the performance of four models: Siamese Manhattan convolution neural network (CNN), Siamese Manhattan long short-term memory (LSTM), Siamese Manhattan hybrid CNN-LSTM, and Siamese Manhattan hybrid LSTM-CNN, in determining STS between sentence pairs in medical reports. Performance comparisons were conducted using Cosine Similarity and word mover's distance (WMD) methods. The results indicate that the Siamese Manhattan hybrid LSTM-CNN model outperforms the other models, with a similarity score of 1 for each sentence pair, signifying identical semantic meaning.
2
Ananthakrishnan, Balasundaram, Ayesha Shaik, Shivam Akhouri, Paras Garg, Vaibhav Gadag, and Muthu Subash Kavitha. "Automated Bone Marrow Cell Classification for Haematological Disease Diagnosis Using Siamese Neural Network." Diagnostics 13, no. 1 (December 29, 2022): 112. http://dx.doi.org/10.3390/diagnostics13010112.
Full textAbstract:
The critical structure and nature of different bone marrow cells which form a base in the diagnosis of haematological ailments requires a high-grade classification which is a very prolonged approach and accounts for human error if performed manually, even by field experts. Therefore, the aim of this research is to automate the process to study and accurately classify the structure of bone marrow cells which will help in the diagnosis of haematological ailments at a much faster and better rate. Various machine learning algorithms and models, such as CNN + SVM, CNN + XGB Boost and Siamese network, were trained and tested across a dataset of 170,000 expert-annotated cell images from 945 patients’ bone marrow smears with haematological disorders. The metrics used for evaluation of this research are accuracy of model, precision and recall of all the different classes of cells. Based on these performance metrics the CNN + SVM, CNN + XGB, resulted in 32%, 28% accuracy, respectively, and therefore these models were discarded. Siamese neural resulted in 91% accuracy and 84% validation accuracy. Moreover, the weighted average recall values of the Siamese neural network were 92% for training and 91% for validation. Hence, the final results are based on Siamese neural network model as it was outperforming all the other algorithms used in this research.
3
Xiao, Wanghui, and Yuting Ding. "A Two-Stage Siamese Network Model for Offline Handwritten Signature Verification." Symmetry 14, no. 6 (June 12, 2022): 1216. http://dx.doi.org/10.3390/sym14061216.
Full textAbstract:
Offline handwritten signature verification is one of the most prevalent and prominent biometric methods in many application fields. Siamese neural network, which can extract and compare the writers’ style features, proves to be efficient in verifying the offline signature. However, the traditional Siamese neural network fails to represent the writers’ writing style fully and suffers from low performance when the distribution of positive and negative handwritten signature samples is unbalanced. To address this issue, this study proposes a two-stage Siamese neural network model for accurate offline handwritten signature verification with two main ideas: (a) adopting a two-stage Siamese neural network to verify original and enhanced handwritten signatures simultaneously, and (b) utilizing the Focal Loss to deal with the extreme imbalance between positive and negative offline signatures. Experimental results on four challenging handwritten signature datasets with different languages demonstrate that compared with state-of-the-art models, our proposed model achieves better performance. Furthermore, this study tries to extend the proposed model to the Chinese signature dataset in the real environment, which is a significant attempt in the field of Chinese signature identification.
4
Cha, Byung-Rae, and Binod Vaidya. "Enhancing Human Activity Recognition with Siamese Networks: A Comparative Study of Contrastive and Triplet Learning Approaches." Electronics 13, no. 9 (May 1, 2024): 1739. http://dx.doi.org/10.3390/electronics13091739.
Full textAbstract:
This paper delves into the realm of human activity recognition (HAR) by leveraging the capabilities of Siamese neural networks (SNNs), focusing on the comparative effectiveness of contrastive and triplet learning approaches. Against the backdrop of HAR’s growing importance in healthcare, sports, and smart environments, the need for advanced models capable of accurately recognizing and classifying complex human activities has become paramount. Addressing this, we have introduced a Siamese network architecture integrated with convolutional neural networks (CNNs) for spatial feature extraction, bidirectional LSTM (Bi-LSTM) for temporal dependency capture, and attention mechanisms to prioritize salient features. Employing both contrastive and triplet loss functions, we meticulously analyze the impact of these learning approaches on the network’s ability to generate discriminative embeddings for HAR tasks. Through extensive experimentation, the study reveals that Siamese networks, particularly those utilizing triplet loss functions, demonstrate superior performance in activity recognition accuracy and F1 scores compared with baseline deep learning models. The inclusion of a stacking meta-classifier further amplifies classification efficacy, showcasing the robustness and adaptability of our proposed model. Conclusively, our findings underscore the potential of Siamese networks with advanced learning paradigms in enhancing HAR systems, paving the way for future research in model optimization and application expansion.
5
Aharchaou, Mehdi, Michael Matheney, Joe Molyneux, and Erik Neumann. "Edge-aware filtering with Siamese neural networks." Leading Edge 39, no. 10 (October 2020): 711–17. http://dx.doi.org/10.1190/tle39100711.1.
Full textAbstract:
Recent demands to reduce turnaround times and expedite investment decisions in seismic exploration have invited new ways to process and interpret seismic data. Among these ways is a more integrated collaboration between seismic processors and geologist interpreters aiming to build preliminary geologic models for early business impact. A key aspect has been quick and streamlined delivery of clean high-fidelity 3D seismic images via postmigration filtering capabilities. We present a machine learning-based example of such a capability built on recent advances in deep learning systems. In particular, we leverage the power of Siamese neural networks, a new class of neural networks that is powerful at learning discriminative features. Our novel adaptation, edge-aware filtering, employs a deep Siamese network that ranks similarity between seismic image patches. Once the network is trained, we capitalize on the learned features and self-similarity property of seismic images to achieve within-image stacking power endowed with edge awareness. The method generalizes well to new data sets due to the few-shot learning ability of Siamese networks. Furthermore, the learning-based framework can be extended to a variety of noise types in 3D seismic data. Using a convolutional architecture, we demonstrate on three field data sets that the learned representations lead to superior filtering performance compared to structure-oriented filtering. We examine both filtering quality and ease of application in our analysis. Then, we discuss the potential of edge-aware filtering as a data conditioning tool for rapid structural interpretation.
6
Gao, Peng, Xiao Liu, Hong-Chuan Sang, Yu Wang, and Fei Wang. "Efficient and Lightweight Visual Tracking with Differentiable Neural Architecture Search." Electronics 12, no. 17 (August 27, 2023): 3623. http://dx.doi.org/10.3390/electronics12173623.
Full textAbstract:
Over the last decade, Siamese network architectures have emerged as dominating tracking paradigms, which have led to significant progress. These architectures are made up of a backbone network and a head network. The backbone network comprises two identical feature extraction sub-branches, one for the target template and one for the search candidate. The head network takes both the template and candidate features as inputs and produces a local similarity score for the target object in each location of the search candidate. Despite promising results that have been attained in visual tracking, challenges persist in developing efficient and lightweight models due to the inherent complexity of the task. Specifically, manually designed tracking models that rely heavily on the knowledge and experience of relevant experts are lacking. In addition, the existing tracking approaches achieve excellent performance at the cost of large numbers of parameters and vast amounts of computations. A novel Siamese tracking approach called TrackNAS based on neural architecture search is proposed to reduce the complexity of the neural architecture applied in visual tracking. First, according to the principle of the Siamese network, backbone and head network search spaces are constructed, constituting the search space for the network architecture. Next, under the given resource constraints, the network architecture that meets the tracking performance requirements is obtained by optimizing a hybrid search strategy that combines distributed and joint approaches. Then, an evolutionary method is used to lighten the network architecture obtained from the search phase to facilitate deployment to devices with resource constraints (FLOPs). Finally, to verify the performance of TrackNAS, comparison and ablation experiments are conducted using several large-scale visual tracking benchmark datasets, such as OTB100, VOT2018, UAV123, LaSOT, and GOT-10k. The results indicate that the proposed TrackNAS achieves competitive performance in terms of accuracy and robustness, and the number of network parameters and computation volume are far smaller than those of other advanced Siamese trackers, meeting the requirements for lightweight deployment to resource-constrained devices.
7
Melnychenko, Artem, and Kostyantyn Zdor. "EFFICIENCY OF SUPPLEMENTARY OUTPUTS IN SIAMESE NEURAL NETWORKS." Advanced Information Systems 7, no. 3 (September 20, 2023): 49–53. http://dx.doi.org/10.20998/2522-9052.2023.3.07.
Full textAbstract:
In the world of image analysis, effectively handling large image datasets is a complex challenge that requires using deep neural networks. Siamese neural networks, known for their twin-like structure, offer an effective solution to image comparison tasks, especially when data volume is limited. This research explores the possibility of enhancing these models by adding supplementary outputs that improve classification and help find specific data features. The article shows the results of two experiments using the Fashion MNIST and PlantVillage datasets, incorporating additional classification, regression, and combined output strategies with various weight loss configurations. The results from the experiments show that for simpler datasets, the introduction of supplementary outputs leads to a decrease in model accuracy. Conversely, for more complex datasets, optimal accuracy was achieved through the simultaneous integration of regression and classification supplementary outputs. It should be noted that the observed increase in accuracy is relatively marginal and does not guarantee a substantial impact on the overall accuracy of the model.
8
Contreras, Jhonatan, Sara Mostafapour, Jürgen Popp, and Thomas Bocklitz. "Siamese Networks for Clinically Relevant Bacteria Classification Based on Raman Spectroscopy." Molecules 29, no. 5 (February 28, 2024): 1061. http://dx.doi.org/10.3390/molecules29051061.
Full textAbstract:
Identifying bacterial strains is essential in microbiology for various practical applications, such as disease diagnosis and quality monitoring of food and water. Classical machine learning algorithms have been utilized to identify bacteria based on their Raman spectra. However, convolutional neural networks (CNNs) offer higher classification accuracy, but they require extensive training sets and retraining of previous untrained class targets can be costly and time-consuming. Siamese networks have emerged as a promising solution. They are composed of two CNNs with the same structure and a final network that acts as a distance metric, converting the classification problem into a similarity problem. Classical machine learning approaches, shallow and deep CNNs, and two Siamese network variants were tailored and tested on Raman spectral datasets of bacteria. The methods were evaluated based on mean sensitivity, training time, prediction time, and the number of parameters. In this comparison, Siamese-model2 achieved the highest mean sensitivity of 83.61 ± 4.73 and demonstrated remarkable performance in handling unbalanced and limited data scenarios, achieving a prediction accuracy of 73%. Therefore, the choice of model depends on the specific trade-off between accuracy, (prediction/training) time, and resources for the particular application. Classical machine learning models and shallow CNN models may be more suitable if time and computational resources are a concern. Siamese networks are a good choice for small datasets and CNN for extensive data.
9
Bilotserkovskyy, V. V., S. G. Udovenko, and L. E. Chala. "Method of neural network recognition of falsified images." Bionics of Intelligence 2, no. 95 (December 2, 2020): 32–42. http://dx.doi.org/10.30837/bi.2020.2(95).05.
Full textAbstract:
Methods for generating images falsified using Deepfake technologies and methods for detecting them are considered. A method for detecting falsified images is proposed, based on the joint use of an ensemble of convolutional neural models, the Attention mechanism and a Siamese network learning strategy. The ensembles of models were formed in different ways (using two, three or more components). The result was calculated as the average value of the AUC and LogLoss indices from all the models included in the ensemble. This approach improves the accuracy of convolutional neural network classifiers for detecting static and dynamic images created using Deepfake technologies.
10
Xie, Chunli, Xia Wang, Cheng Qian, and Mengqi Wang. "A Source Code Similarity Based on Siamese Neural Network." Applied Sciences 10, no. 21 (October 26, 2020): 7519. http://dx.doi.org/10.3390/app10217519.
Full textAbstract:
Finding similar code snippets is a fundamental task in the field of software engineering. Several approaches have been proposed for this task by using statistical language model which focuses on syntax and structure of codes rather than deep semantic information underlying codes. In this paper, a Siamese Neural Network is proposed that maps codes into continuous space vectors and try to capture their semantic meaning. Firstly, an unsupervised pre-trained method that models code snippets as a weighted series of word vectors. The weights of the series are fitted by the Term Frequency-Inverse Document Frequency (TF-IDF). Then, a Siamese Neural Network trained model is constructed to learn semantic vector representation of code snippets. Finally, the cosine similarity is provided to measure the similarity score between pairs of code snippets. Moreover, we have implemented our approach on a dataset of functionally similar code. The experimental results show that our method improves some performance over single word embedding method.
11
Song, Yabin, Jun Xiang, Jiawei Jiang, Enping Yan, Wei Wei, and Dengkui Mo. "A Cross-Domain Change Detection Network Based on Instance Normalization." Remote Sensing 15, no. 24 (December 18, 2023): 5785. http://dx.doi.org/10.3390/rs15245785.
Full textAbstract:
Change detection is a crucial task in remote sensing that finds broad application in land resource planning, forest resource monitoring, natural disaster monitoring, and evaluation. In this paper, we propose a change detection model for cross-domain recognition, which we call CrossCDNet. Our model significantly improves the modeling ability of the change detection on one dataset and demonstrates good generalization on another dataset without any additional operations. To achieve this, we employ a Siamese neural network for change detection and design an IBNM (Instance Normalization and Batch Normalization Module) that utilizes instance normalization and batch normalization in order to serve as the encoder backbone in the Siamese neural network. The IBNM extracts feature maps for each layer, and the Siamese neural network fuses the feature maps of the two branches using a unique operation. Finally, a simple MLP decoder is used for end-to-end change detection. We train our model on the LEVIR-CD dataset and achieve competitive performance on the test set. In cross-domain dataset testing, CrossCDNet outperforms all the other compared models. Specifically, our model achieves an F1-score of 91.69% on the LEVIR-CD dataset and an F1-score of 77.09% on the WHU-CD dataset, where the training set was LEVIR-CD.
12
Altalib, Mohammed Khaldoon, and Naomie Salim. "Hybrid-Enhanced Siamese Similarity Models in Ligand-Based Virtual Screen." Biomolecules 12, no. 11 (November 20, 2022): 1719. http://dx.doi.org/10.3390/biom12111719.
Full textAbstract:
Information technology has become an integral aspect of the drug development process. The virtual screening process (VS) is a computational technique for screening chemical compounds in a reasonable amount of time and cost. The similarity search is one of the primary tasks in VS that estimates a molecule’s similarity. It is predicated on the idea that molecules with similar structures may also have similar activities. Many techniques for comparing the biological similarity between a target compound and each compound in the database have been established. Although the approaches have a strong performance, particularly when dealing with molecules with homogenous active structural, they are not enough good when dealing with structurally heterogeneous compounds. The previous works examined many deep learning methods in the enhanced Siamese similarity model and demonstrated that the Enhanced Siamese Multi-Layer Perceptron similarity model (SMLP) and the Siamese Convolutional Neural Network-one dimension similarity model (SCNN1D) have good outcomes when dealing with structurally heterogeneous molecules. To further improve the retrieval effectiveness of the similarity model, we incorporate the best two models in one hybrid model. The reason is that each method gives good results in some classes, so combining them in one hybrid model may improve the retrieval recall. Many designs of the hybrid models will be tested in this study. Several experiments on real-world data sets were conducted, and the findings demonstrated that the new approaches outperformed the previous method.
13
Nantha, Oraphan, Benjaporn Sathanarugsawait, and Prasong Praneetpolgrang. "Cleft Lip and Palate Classification Through Vision Transformers and Siamese Neural Networks." Journal of Imaging 10, no. 11 (October 25, 2024): 271. http://dx.doi.org/10.3390/jimaging10110271.
Full textAbstract:
This study introduces a novel approach for the diagnosis of Cleft Lip and/or Palate (CL/P) by integrating Vision Transformers (ViTs) and Siamese Neural Networks. Our study is the first to employ this integration specifically for CL/P classification, leveraging the strengths of both models to handle complex, multimodal data and few-shot learning scenarios. Unlike previous studies that rely on single-modality data or traditional machine learning models, we uniquely fuse anatomical data from ultrasound images with functional data from speech spectrograms. This multimodal approach captures both structural and acoustic features critical for accurate CL/P classification. Employing Siamese Neural Networks enables effective learning from a small number of labeled examples, enhancing the model’s generalization capabilities in medical imaging contexts where data scarcity is a significant challenge. The models were tested on the UltraSuite CLEFT dataset, which includes ultrasound video sequences and synchronized speech data, across three cleft types: Bilateral, Unilateral, and Palate-only clefts. The two-stage model demonstrated superior performance in classification accuracy (82.76%), F1-score (80.00–86.00%), precision, and recall, particularly distinguishing Bilateral and Unilateral Cleft Lip and Palate with high efficacy. This research underscores the significant potential of advanced AI techniques in medical diagnostics, offering valuable insights into their application for improving clinical outcomes in patients with CL/P.
14
Sun, Zhiyu, Yusen He, Andrey Gritsenko, Amaury Lendasse, and Stephen Baek. "Embedded spectral descriptors: learning the point-wise correspondence metric via Siamese neural networks." Journal of Computational Design and Engineering 7, no. 1 (February 1, 2020): 18–29. http://dx.doi.org/10.1093/jcde/qwaa003.
Full textAbstract:
Abstract A robust and informative local shape descriptor plays an important role in mesh registration. In this regard, spectral descriptors that are based on the spectrum of the Laplace–Beltrami operator have been a popular subject of research for the last decade due to their advantageous properties, such as isometry invariance. Despite such, however, spectral descriptors often fail to give a correct similarity measure for nonisometric cases where the metric distortion between the models is large. Hence, they are not reliable for correspondence matching problems when the models are not isometric. In this paper, it is proposed a method to improve the similarity metric of spectral descriptors for correspondence matching problems. We embed a spectral shape descriptor into a different metric space where the Euclidean distance between the elements directly indicates the geometric dissimilarity. We design and train a Siamese neural network to find such an embedding, where the embedded descriptors are promoted to rearrange based on the geometric similarity. We demonstrate our approach can significantly enhance the performance of the conventional spectral descriptors by the simple augmentation achieved via the Siamese neural network in comparison to other state-of-the-art methods.
15
Chang, Hong-Chan, Ren-Ge Liu, Chen-Cheng Li, and Cheng-Chien Kuo. "Fault Diagnosis of Induction Motors under Limited Data for across Loading by Residual VGG-Based Siamese Network." Applied Sciences 14, no. 19 (October 4, 2024): 8949. http://dx.doi.org/10.3390/app14198949.
Full textAbstract:
This study proposes an improved few-shot learning model of the Siamese network residual Visual Geometry Group (VGG). This model combined with time–frequency domain transformation techniques effectively enhances the performance of across-load fault diagnosis for induction motors with limited data conditions. The proposed residual VGG-based Siamese network consists of two primary components: the feature extraction network, which is the residual VGG, and the merged similarity layer. First, the residual VGG architecture utilizes residual learning to boost learning efficiency and mitigate the degradation problem typically associated with deep neural networks. The employment of smaller convolutional kernels substantially reduces the number of model parameters, expedites model convergence, and curtails overfitting. Second, the merged similarity layer incorporates multiple distance metrics for similarity measurement to enhance classification performance. For cross-domain fault diagnosis in induction motors, we developed experimental models representing four common types of faults. We measured the vibration signals from both healthy and faulty models under varying loads. We then applied the proposed model to evaluate and compare its effectiveness in cross-domain fault diagnosis against conventional AI models. Experimental results indicate that when the imbalance ratio reached 20:1, the average accuracy of the proposed residual VGG-based Siamese network for fault diagnosis across different loads was 98%, closely matching the accuracy of balanced and sufficient datasets, and significantly surpassing the diagnostic performance of other models.
16
Gao, Zhi-Yong, Heng-Xing Xie, Ji-Feng Li, and Shi-Li Liu. "Spatial-Structure Siamese Network for Plant Identification." International Journal of Pattern Recognition and Artificial Intelligence 32, no. 11 (July 24, 2018): 1850035. http://dx.doi.org/10.1142/s0218001418500350.
Full textAbstract:
Plant identification is now attracting considerable attention due to its important applications in agriculture automation and ecosystems. Recently, deep learning-based plant identification methods have drawn increasing interest and shown favorable performance. However, existing methods do not consider plant spatial structure and their similarities explicitly. In this paper, we propose a robust spatial-structure siamese network (3SN) for plant identification, which has the following advantages: (1) It models the spatial structure of a plant by recurrent neural networks exploiting their capability to capture long-range dependencies among sequential data, which enables it to capture even a slight difference between a specific plant and distractors. (2) The plant similarity modeling is achieved effectively by a siamese network with large numbers of image pairs. In this way, the plant classification task and siamese learning task are learned jointly in a unified framework, where both can enhance and complement each other. Extensive experimental results show that the proposed 3SN method outperforms the state-of-the-art methods consistently.
17
Chikoti, Bharath Chandra. "Text Similarity Using Siamese Networks and Transformers." International Journal for Research in Applied Science and Engineering Technology 10, no. 6 (June 30, 2022): 1856–63. http://dx.doi.org/10.22214/ijraset.2022.44283.
Full textAbstract:
Abstract-- In result-oriented conversational models like message renders and chatbots, finding the similarity between the input and output text result is a big task. In general, the conversational model developers lean to provide a minimal number of utterances per instance, and this makes the classification a difficult task. This problem becomes more difficult when the length of the processed text per action is short and length of the user input is long. Identical sentence pair detection reduces manual effort for users with high reputation. Siamese networks have been one of the best innovative architectures designed in the field of natural language processing. A Siamese network was initially designed for computer vision applications. Later the core concept of this algorithm was designed for NLP ,to identify similarity for two given sentences. Siamese networks are used in this algorithm. It's an artificial neural network also known as a twin neural network that works in tandem on two independent input vectors to calculate equivalent output vectors using the same weights. Also there are few commonly addressed drawbacks like word sense disambiguation and memory intolerance of initial inputs for sentences having more than 15-20 words. To tackle these issues, we propose a modified algorithm that integrates the transformer model implicitly with the core part of the siamese network. Transformer model helps to generate each output position based on the semantic analysis of overall sentence and can also deal with homonyms, by extracting its meaning based, which is syntactic based and semantic based on the overall sentence or paragraph or text.
18
Jeon, Minji, Donghyeon Park, Jinhyuk Lee, Hwisang Jeon, Miyoung Ko, Sunkyu Kim, Yonghwa Choi, Aik-Choon Tan, and Jaewoo Kang. "ReSimNet: drug response similarity prediction using Siamese neural networks." Bioinformatics 35, no. 24 (May 22, 2019): 5249–56. http://dx.doi.org/10.1093/bioinformatics/btz411.
Full textAbstract:
Abstract Motivation Traditional drug discovery approaches identify a target for a disease and find a compound that binds to the target. In this approach, structures of compounds are considered as the most important features because it is assumed that similar structures will bind to the same target. Therefore, structural analogs of the drugs that bind to the target are selected as drug candidates. However, even though compounds are not structural analogs, they may achieve the desired response. A new drug discovery method based on drug response, which can complement the structure-based methods, is needed. Results We implemented Siamese neural networks called ReSimNet that take as input two chemical compounds and predicts the CMap score of the two compounds, which we use to measure the transcriptional response similarity of the two compounds. ReSimNet learns the embedding vector of a chemical compound in a transcriptional response space. ReSimNet is trained to minimize the difference between the cosine similarity of the embedding vectors of the two compounds and the CMap score of the two compounds. ReSimNet can find pairs of compounds that are similar in response even though they may have dissimilar structures. In our quantitative evaluation, ReSimNet outperformed the baseline machine learning models. The ReSimNet ensemble model achieves a Pearson correlation of 0.518 and a precision@1% of 0.989. In addition, in the qualitative analysis, we tested ReSimNet on the ZINC15 database and showed that ReSimNet successfully identifies chemical compounds that are relevant to a prototype drug whose mechanism of action is known. Availability and implementation The source code and the pre-trained weights of ReSimNet are available at https://github.com/dmis-lab/ReSimNet. Supplementary information Supplementary data are available at Bioinformatics online.
19
Nicula, Bogdan, Mihai Dascalu, Natalie N. Newton, Ellen Orcutt, and Danielle S. McNamara. "Automated Paraphrase Quality Assessment Using Language Models and Transfer Learning." Computers 10, no. 12 (December 6, 2021): 166. http://dx.doi.org/10.3390/computers10120166.
Full textAbstract:
Learning to paraphrase supports both writing ability and reading comprehension, particularly for less skilled learners. As such, educational tools that integrate automated evaluations of paraphrases can be used to provide timely feedback to enhance learner paraphrasing skills more efficiently and effectively. Paraphrase identification is a popular NLP classification task that involves establishing whether two sentences share a similar meaning. Paraphrase quality assessment is a slightly more complex task, in which pairs of sentences are evaluated in-depth across multiple dimensions. In this study, we focus on four dimensions: lexical, syntactical, semantic, and overall quality. Our study introduces and evaluates various machine learning models using handcrafted features combined with Extra Trees, Siamese neural networks using BiLSTM RNNs, and pretrained BERT-based models, together with transfer learning from a larger general paraphrase corpus, to estimate the quality of paraphrases across the four dimensions. Two datasets are considered for the tasks involving paraphrase quality: ULPC (User Language Paraphrase Corpus) containing 1998 paraphrases and a smaller dataset with 115 paraphrases based on children’s inputs. The paraphrase identification dataset used for the transfer learning task is the MSRP dataset (Microsoft Research Paraphrase Corpus) containing 5801 paraphrases. On the ULPC dataset, our BERT model improves upon the previous baseline by at least 0.1 in F1-score across the four dimensions. When using fine-tuning from ULPC for the children dataset, both the BERT and Siamese neural network models improve upon their original scores by at least 0.11 F1-score. The results of these experiments suggest that transfer learning using generic paraphrase identification datasets can be successful, while at the same time obtaining comparable results in fewer epochs.
20
Liang, Guoxi, Byung-Won On, Dongwon Jeong, Hyun-Chul Kim, and Gyu Choi. "Automated Essay Scoring: A Siamese Bidirectional LSTM Neural Network Architecture." Symmetry 10, no. 12 (December 1, 2018): 682. http://dx.doi.org/10.3390/sym10120682.
Full textAbstract:
Essay scoring is a critical task in education. Implementing automated essay scoring (AES) helps reduce manual workload and speed up learning feedback. Recently, neural network models have been applied to the task of AES and demonstrates tremendous potential. However, the existing work only considered the essay itself without considering the rating criteria behind the essay. One of the reasons is that the various kinds of rating criteria are very hard to represent. In this paper, we represent rating criteria by some sample essays that were provided by domain experts and defined a new input pair consisting of an essay and a sample essay. Corresponding to this new input pair, we proposed a symmetrical neural network AES model that can accept the input pair. The model termed Siamese Bidirectional Long Short-Term Memory Architecture (SBLSTMA) can capture not only the semantic features in the essay but also the rating criteria information behind the essays. We use the SBLSTMA model for the task of AES and take the Automated Student Assessment Prize (ASAP) dataset as evaluation. Experimental results show that our approach is better than the previous neural network methods.
21
Qi, Kunlun, Chao Yang, Chuli Hu, Yonglin Shen, Shengyu Shen, and Huayi Wu. "Rotation Invariance Regularization for Remote Sensing Image Scene Classification with Convolutional Neural Networks." Remote Sensing 13, no. 4 (February 5, 2021): 569. http://dx.doi.org/10.3390/rs13040569.
Full textAbstract:
Deep convolutional neural networks (DCNNs) have shown significant improvements in remote sensing image scene classification for powerful feature representations. However, because of the high variance and volume limitations of the available remote sensing datasets, DCNNs are prone to overfit the data used for their training. To address this problem, this paper proposes a novel scene classification framework based on a deep Siamese convolutional network with rotation invariance regularization. Specifically, we design a data augmentation strategy for the Siamese model to learn a rotation invariance DCNN model that is achieved by directly enforcing the labels of the training samples before and after rotating to be mapped close to each other. In addition to the cross-entropy cost function for the traditional CNN models, we impose a rotation invariance regularization constraint on the objective function of our proposed model. The experimental results obtained using three publicly-available scene classification datasets show that the proposed method can generally improve the classification performance by 2~3% and achieves satisfactory classification performance compared with some state-of-the-art methods.
22
Suyahman, Sunardi, Murinto, and Arfiani Nur Khusna. "Siamese Neural Networks with Chi-square Distance for Trademark Image Similarity Detection." Scientific Journal of Informatics 11, no. 2 (May 31, 2024): 429–38. https://doi.org/10.15294/sji.v11i2.4654.
Full textAbstract:
Purpose: The objective of this study is to address the limitations of existing trademark image similarity analysis methods by integrating a Chi-square distance metric within a Siamese neural network framework. Traditional approaches using Euclidean distance often fail to accurately capture the complex visual features of trademarks, leading to suboptimal performance in distinguishing similar trademarks. This research aims to improve the precision and robustness of trademark comparison by leveraging the Chi-square distance, which is more sensitive to image variations. Methods: The approach involves modifying a Siamese neural network traditionally employing Euclidean distance with the use the Chi-square distance metric instead. This alteration allows the network to better capture and analyze critical visual features such as color and texture. The modified network is trained and tested on a comprehensive dataset of trademark images, enabling the network to learn and distinguish between similar and dissimilar trademarks based on subtle visual cues. Result: The findings from this study show a significant increase in accuracy, with the modified network achieving an accuracy rate of 98%. This marks a notable improvement over baseline models that utilize Euclidean distance, demonstrating the effectiveness of the Chi-square distance metric in enhancing the model's ability to discriminate between trademarks. Novelty: The novelty of this research lies in its application of the Chi-square distance in a deep learning framework specifically for trademark image similarity detection, presenting a novel approach that yields higher precision in image-based comparisons.
23
Mehmood, Atif, Muazzam Maqsood, Muzaffar Bashir, and Yang Shuyuan. "A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease." Brain Sciences 10, no. 2 (February 5, 2020): 84. http://dx.doi.org/10.3390/brainsci10020084.
Full textAbstract:
Alzheimer’s disease (AD) may cause damage to the memory cells permanently, which results in the form of dementia. The diagnosis of Alzheimer’s disease at an early stage is a problematic task for researchers. For this, machine learning and deep convolutional neural network (CNN) based approaches are readily available to solve various problems related to brain image data analysis. In clinical research, magnetic resonance imaging (MRI) is used to diagnose AD. For accurate classification of dementia stages, we need highly discriminative features obtained from MRI images. Recently advanced deep CNN-based models successfully proved their accuracy. However, due to a smaller number of image samples available in the datasets, there exist problems of over-fitting hindering the performance of deep learning approaches. In this research, we developed a Siamese convolutional neural network (SCNN) model inspired by VGG-16 (also called Oxford Net) to classify dementia stages. In our approach, we extend the insufficient and imbalanced data by using augmentation approaches. Experiments are performed on a publicly available dataset open access series of imaging studies (OASIS), by using the proposed approach, an excellent test accuracy of 99.05% is achieved for the classification of dementia stages. We compared our model with the state-of-the-art models and discovered that the proposed model outperformed the state-of-the-art models in terms of performance, efficiency, and accuracy.
24
Chiș, Raluca-Diana. "Matching Apictorial Puzzle Pieces Using Deep Learning." Studia Universitatis Babeș-Bolyai Informatica 69, no. 1 (June 10, 2024): 5–20. http://dx.doi.org/10.24193/subbi.2024.1.01.
Full textAbstract:
Finding matches between puzzle pieces is a difficult problem relevant to applications that involve restoring broken objects. The main difficulty comes from the similarity of the puzzle pieces and the very small difference between a pair of pieces that almost match and one that does. The proposed solution is based on deep learning models and has two steps: firstly, the pieces are segmented from images with a U-Net model; then, matches are found with a Siamese Neural Network. To reach our goal, we created our own dataset, containing 462 images and just as many masks. With these masks, we built 3318 pairs of images, half of them representing pieces that fit together and half that do not. Our most relevant result is estimating correctly for 290 out of 332 pairs whether they match. Keywords: U-Net, Siamese architecture, Edge-matching, Puzzle Pieces.
25
Mao, Dianhui, and Zhihao Hao. "A Novel Sketch-Based Three-Dimensional Shape Retrieval Method Using Multi-View Convolutional Neural Network." Symmetry 11, no. 5 (May 23, 2019): 703. http://dx.doi.org/10.3390/sym11050703.
Full textAbstract:
Retrieving 3D models by adopting hand-drawn sketches to be the input has turned out to be a popular study topic. Most current methods are based on manually selected features and the best view produced for 3D model calculations. However, there are many problems with these methods such as distortion. For the purpose of dealing with such issues, this paper proposes a novel feature representation method to select the projection view and adapt the maxout network to the extended Siamese network architecture. In addition, the strategy is able to handle the over-fitting issue of convolutional neural networks (CNN) and mitigate the discrepancies between the 3D shape domain and the sketch. A pre-trained AlexNet was used to sketch the extract features. For 3D shapes, multiple 2D views were compiled into compact feature vectors using pre-trained multi-view CNNs. Then the Siamese convolutional neural networks were learnt for transforming the two domains’ original characteristics into nonlinear feature space, which mitigated the domain discrepancy and kept the discriminations. Two large data sets were used for experiments, and the experimental results show that the method is superior to the prior art methods in accuracy.
26
Stallmann, Dominik, and Barbara Hammer. "Unsupervised Cyclic Siamese Networks Automating Cell Imagery Analysis." Algorithms 16, no. 4 (April 12, 2023): 205. http://dx.doi.org/10.3390/a16040205.
Full textAbstract:
Novel neural network models that can handle complex tasks with fewer examples than before are being developed for a wide range of applications. In some fields, even the creation of a few labels is a laborious task and impractical, especially for data that require more than a few seconds to generate each label. In the biotechnological domain, cell cultivation experiments are usually done by varying the circumstances of the experiments, seldom in such a way that hand-labeled data of one experiment cannot be used in others. In this field, exact cell counts are required for analysis, and even by modern standards, semi-supervised models typically need hundreds of labels to achieve acceptable accuracy on this task, while classical image processing yields unsatisfactory results. We research whether an unsupervised learning scheme is able to accomplish this task without manual labeling of the given data. We present a VAE-based Siamese architecture that is expanded in a cyclic fashion to allow the use of labeled synthetic data. In particular, we focus on generating pseudo-natural images from synthetic images for which the target variable is known to mimic the existence of labeled natural data. We show that this learning scheme provides reliable estimates for multiple microscopy technologies and for unseen data sets without manual labeling. We provide the source code as well as the data we use. The code package is open source and free to use (MIT licensed).
27
Tian, Yubo, and Fei Meng. "WLAN monopole antenna design by Siamese convolutional neural network and KNN exploiting Gaussian process." MATEC Web of Conferences 395 (2024): 01012. http://dx.doi.org/10.1051/matecconf/202439501012.
Full textAbstract:
In the process of antenna design, surrogate models can generally be used, but modeling requires a large number of samples. Although full wave electromagnetic simulation software can handle this task, obtaining a large number of samples is time-consuming, however too small number of sample may lead to lower accuracy of the trained surrogate model. Inspired by semi-supervised learning methods, this paper uses Siamese convolutional neural networks (SCNN) and K-nearest neighbor (KNN) algorithms to generate highly reliable virtual samples and expand the training sample set, further improving the accuracy and robustness of the surrogate model by exploiting Gaussian process (GP) models. The proposed method is named SCNN-KNN-GP, which is used for the design of WLAN dual band monopole antennas. Moreover, the relationships between the performance of the proposed model and the increased number of virtual samples and the coefficient of the KNN are studied, resulting in a more excellent surrogate model structure.
28
Wu, Xiaofeng, Xinyue Han, Zongyu Zhang, Han Wu, Xu Yang, and Hai Huang. "A Hybrid Excitation Model Based Lightweight Siamese Network for Underwater Vehicle Object Tracking Missions." Journal of Marine Science and Engineering 11, no. 6 (May 26, 2023): 1127. http://dx.doi.org/10.3390/jmse11061127.
Full textAbstract:
Performing object tracking tasks and efficiently perceiving the underwater environment in real time for underwater vehicles is a challenging task due to the complex nature of the underwater environment. A hybrid excitation model based lightweight Siamese network is proposed to solve the mismatch between underwater objects with limited characteristics and complex deep learning models. The lightweight neural network is applied to the residual network in the Siamese network to reduce the computational complexity and cost of the model while constructing a deeper network. In addition, to deal with the changeable complex underwater environment and consider the timing of video tracking, the global excitation model (HE module) is introduced. The model adopts the excitation methods of space, channel, and motion to improve the accuracy of the algorithm. Based on the designed underwater vehicle, the underwater target tracking and target grabbing experiments are carried out, and the experimental results show that the proposed tracking algorithm has a high tracking success rate.
29
Thanh Le, Luan. "Uncovering Import Document Fraud: Leveraging the Deep Learning Approach." Global Trade and Customs Journal 20, Issue 1 (January 1, 2025): 3–10. http://dx.doi.org/10.54648/gtcj2025002.
Full textAbstract:
The scrutiny, identification, and verification of handwritten signatures on Certificates of Origin (C/O) is a critical task for customs authorities in preventing trade fraud. This task remains a significant challenge due to limitations in manpower and the need for manual verification amidst a vast volume of documents. Deep learning (DL) algorithms offer a valuable solution to address this issue. This paper deploys a Siamese Neural Network (SNN) model to assist customs officials in identifying and verifying handwritten signatures on C/O. The results demonstrate the superior performance of the SNN model over conventional Convolutional Neural Network (CNN) models and Machine Learning (ML) models, with accuracy, precision, recall, F1-score, and AUC values of 0.943, 0.912, 0.899, 0.905, and 0.919, respectively. The paper also provides in-depth analyses of omission cases and suggests applications of the model to support the work of customs officials.
30
Osman, Abubakr. "ARIF: Autonomous Recognition in the Field Enhancing National Security with Computer Vision-Based Facial Recognition." International Journal of Automation and Digital Transformation 3, no. 1 (January 16, 2024): 19–43. http://dx.doi.org/10.54878/z68s0z54.
Full textAbstract:
Through a novel research approach that employs a mix of Convolutional Neural architectures & Siamese Neural Nets, we propose a viable mechanism that focuses on leveraging these groundbreaking advancements, through the utilization of deep learning algorithms we were able to effectively & accurately identify and authenticate individuals based on unique facial features derived from machine learnt embeddings. In The ARIF Project we implement the proposed architecture models through utilization of developer friendly modules like the python facial recognition library, the OpenCV framework & Jupiter Notebooks, performing the necessary product development, market research and product analysis throughout the development process, finally deliver a refined & minimalistic solution that not only fills market gaps but also serves as a solid foundation for rapid adoption & deployment.
31
Pavlenko, Serhii, and Petro Kuliabko. "Deduplication of error reports in software malfunction: Algorithms for comparing call stacks." Вісник Черкаського державного технологічного університету 28, no. 4 (November 16, 2023): 59–69. http://dx.doi.org/10.62660/2306-4412.4.2023.59-69.
Full textAbstract:
In the software industry, the standard recognises automatic fault monitoring systems as mandatory for implementation. Considering the constant development of technologies and the high complexity of programmes, the importance of optimising processes for detecting and eliminating errors becomes a relevant task due to the need for reliability and stability of software. The purpose of this study is to conduct a detailed analysis of existing deduplication algorithms for reports from automatic systems collecting information about software failures. Among the algorithms considered were: the longest common subsequence method, Levenshtein distance, deep learning methods, Siamese neural networks, and hidden Markov models. The results obtained indicate a great potential for optimising processes of error detection and elimination in software. The developed comprehensive approach to the analysis and detection of duplicates in call stacks in failure reports allows for effectively addressing issues. The deep learning methods and hidden Markov models have demonstrated their effectiveness and feasibility for real-world applications. Effective methods for comparing key parameters of reports are identified, which contributes to the identification and grouping of recurring errors. The use of call stack comparison algorithms has proven critical for accurately identifying similar error cases in products with large audiences and high parallelism conditions. Siamese neural networks and the Scream Tracker 3 Module algorithm are used to determine the similarity of call stacks, including the application of recurrent neural networks (long short-term memory, bidirectional long short-term memory). Optimisation of report processing and clustering particularly enhances the speed and efficiency of responding to new failure cases, allowing developers to improve system stability and focus on high-priority issues. The study is useful for software developers, software development companies, system administrators, research groups, algorithm and tool development companies, cybersecurity professionals, and educational institutions
32
Suyahman, Sunardi, and Murinto. "Comparative Analysis of CNN Architectures in Siamese Networks with Test-Time Augmentation for Trademark Image Similarity Detection." Scientific Journal of Informatics 11, no. 4 (December 23, 2024): 949–58. https://doi.org/10.15294/sji.v11i4.13811.
Full textAbstract:
Purpose: This study aims to enhance the detection of trademark image similarity by conducting a comparative analysis of various Convolutional Neural Network (CNN) architectures within Siamese networks, integrated with test-time augmentation techniques. Existing methods often face challenges in accurately capturing subtle visual similarities between trademarks due to limitations in feature extraction and generalization capabilities. The research seeks to identify the most effective CNN architecture for this task and to assess the impact of test-time augmentation on model performance. Methods: The study implements Siamese networks utilizing three distinct CNN architectures: VGG16, VGG19, and ResNet50. Each network is trained on a dataset of trademark images to learn deep feature representations that can discriminate between similar and dissimilar trademarks. During the evaluation phase, test-time augmentation (TTA) is applied to enhance model robustness by averaging predictions over multiple augmented versions of the input images. TTA includes transformations such as random rotations (up to 40%), width and height shifts (up to 20%), random shear transformations, zooming (up to 20%), horizontal and vertical flips, and random brightness adjustments. Result: Experimental findings reveal that the Siamese network based on VGG19 achieves the highest accuracy at 98.82%, outperforming the VGG16-based network with an accuracy of 97.07% and the ResNet50-based network with 50.00% accuracy. The application of TTA has improved performance across all models, with the VGG19 model receiving the highest improvement. The extremely low accuracy of ResNet50 can be attributed to its misinterpretation of original trademark images as close-forged ones, probably due to overfitting or lack of an efficient ability in generalizing very fine visual features. Novelty: The study conducted a comparative analysis of CNN architectures, namely VGG16, VGG19, and ResNet50 in Siamese networks for trademark image similarity detection.
33
Zhang, Lili, Xiuhui Wang, Qifu Bao, Bo Jia, Xuesheng Li, and Yaru Wang. "Infrared Fault Classification Based on the Siamese Network." Applied Sciences 13, no. 20 (October 19, 2023): 11457. http://dx.doi.org/10.3390/app132011457.
Full textAbstract:
The rapid development of solar energy technology has led to significant progress in recent years, but the daily maintenance of solar panels faces significant challenges. The diagnosis of solar panel failures by infrared detection devices can improve the efficiency of maintenance personnel. Currently, due to the scarcity of infrared solar panel failure samples and the problem of unclear image effective features, traditional deep neural network models can easily encounter overfitting and poor generalization performance under small sample conditions. To address these problems, this paper proposes a solar panel failure diagnosis method based on an improved Siamese network. Firstly, two types of solar panel samples of the same category are constructed. Secondly, the images of the samples are input into the feature model combining convolution, adaptive coordinate attention (ACA), and the feature fusion module (FFM) to extract features, learning the similarities between different types of solar panel samples. Finally, the trained model is used to determine the similarity of the input solar image, obtaining the failure diagnosis results. In this case, adaptive coordinate attention can effectively obtain interested effective feature information, and the feature fusion module can integrate the different effective information obtained, further enriching the feature information. The ACA-FFM Siamese network method can alleviate the problem of insufficient sample quantity and effectively improve the classification accuracy, achieving a classification accuracy rate of 83.9% on an open-accessed infrared failure dataset with high similarity.
34
Surjuse, Manthan. "Deforestation Detection Using Deep Learning Manthan Surjuse." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 05 (May 31, 2024): 1–5. http://dx.doi.org/10.55041/ijsrem35190.
Full textAbstract:
This is a major environmental problem that affects many countries around the world” (World, 2020). In this paper, we have explored several methods of automatic method for deforestation detection such as Early Fusion Convolutional network (EFCN), Siamese Convolutional Network (S-CNN) and Support Vector Machine (SVM). As shown in all experimental results, EFCN can obviously outperform S-CNN and SVM. This work is aimed at presenting a novel curated dataset and also an approach based on deep learning, more specifically Convolutional Neural Networks (CNN) combined with cutting edge data processing techniques to solve the forestation problem. These tools, combined with more advanced deep learning models and higher resolution satellite imagery, have greatly expanded our ability to do this. Finally, this paper explains a tool for daily the detection of rainforests deforestation in satellite images from MODIS/TERRA sensor using Artificial Neural Networks and U-net architectures. “What Comes to Mind When Considering Deforestation. Image, satellite images, deep learning, and CNN (Convolutional Neural Network).”
35
Du, Guocai, Peiyong Zhou, Ruxianguli Abudurexiti, Mahpirat, Alimjan Aysa, and Kurban Ubul. "High-Performance Siamese Network for Real-Time Tracking." Sensors 22, no. 22 (November 18, 2022): 8953. http://dx.doi.org/10.3390/s22228953.
Full textAbstract:
Target tracking algorithms based on deep learning have achieved good results in public datasets. Among them, the network tracking algorithm based on Siamese tracking has a high accuracy and fast speed, which has attracted significant attention. However, the Siamese tracker uses the AlexNet network as its backbone and the network layers are relatively shallow, so it does not make full use of the ability of the deep neural network. If only the backbones of target tracking are replaced, there will be no obvious improvement, such as in the cases of ResNet and Inception. Therefore, this paper designs a wider and deeper network structure. At a wider level, a mechanism that can adaptively adjust the receptive field (RF) size is designed. Firstly, multiple branches are divided by the split operator, and each branch has a different size of kernel corresponding to a different size of RF; then, the fuse operator is used to fuse the information of each branch to obtain the selection weights; and finally, according to the selection, the aggregation feature map is weighted. At a deeper level, a new kind of residual models is designed. The channel is simplified by pruning in order to improve the tracking speed. According to the above, a wider and deeper Siamese network was proposed in this paper. The experimental results show that the structure proposed in this paper achieves a good tracking effect and real-time performance on six kinds of datasets. The proposed tracker achieves an SUC and Prec of LaSOT of 0.569 and 0.571, respectively.
36
Tang, Jiawei, Shengquan Yang, Shujuan Huang, and Bozhi Xiao. "Remote Sensing Building Damage Assessment Based on Machine Learning." International Journal of Advanced Network, Monitoring and Controls 9, no. 3 (September 1, 2024): 1–12. http://dx.doi.org/10.2478/ijanmc-2024-0021.
Full textAbstract:
Abstract After the occurrence of various types of disasters, including natural disasters and man-made damage, aid workers need accurate and timely data, such as the damage status of buildings, in order to take effective measures for rescue. So as to solve this problem, this paper researches and designs a building damage classification system based on machine learning. The damage assessment system consists of two network models (building extraction network and damage classification network). This article analyzes and designs the structure of each network model, and discusses the principles related to computer vision in machine learning. Buildings in satellite images are segmented through Siamese Convolutional Neural Network, the BottleNeck Module and Feature Pyramid Network are used in the damage classification assessment network to detect damage to buildings in sub-temporal remote sensing images. Subsequently, the model was trained and tested on different disaster events on the xBD dataset. The results show that the building damage detection system based on Siamese-CNN achieves good detection accuracy, and the system has the advantages of simple operation, good timeliness and low resource consumption, and can well meet the needs of disaster assessment.
37
de Gélis, I., S. Lefèvre, and T. Corpetti. "3D URBAN CHANGE DETECTION WITH POINT CLOUD SIAMESE NETWORKS." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B3-2021 (June 29, 2021): 879–86. http://dx.doi.org/10.5194/isprs-archives-xliii-b3-2021-879-2021.
Full textAbstract:
Abstract. As the majority of the earth population is living in urban environments, cities are continuously evolving and efficient monitoring tools are needed to retrieve and classify their evolution. In this context, analysing changes between two dates is a crucial point. In urban environments, most changes occur along the vertical axis (with new construction or demolition of buildings) and the use of 3D data is therefore mandatory. Among them, LiDAR constitutes a valuable source of information. However, With the difficulty of processing sparse and unordered 3D point clouds, most of existing methods start by rasterizing point clouds (for example to Digital Surface Models) before using more conventional image processing tools. This implies a significant loss of information. Among existing studies dealing directly with point clouds, and to the best of our knowledge, no deep neural network-based method has been explored yet. Thus, in order to fill this gap and to test the ability of deep methods to deal with change detection and characterization of 3D point clouds, we propose a Siamese network with Kernel Point Convolution inspired by Siamese architectures that have already shown their performances on change detection in 2D images and on KPConv network which achieves high-quality results for semantic segmentation of raw 3D point clouds. We show quantitatively and qualitatively that our method outperforms by more than 25% (in terms of average Intersection over Union for classes of change) existing machine learning methods based on hand-crafted features.
38
Palsapure, Pranita Niraj, Rajeswari Rajeswari, and Sandeep Kumar Kempegowda. "Enhancing speaker verification accuracy with deep ensemble learning and inclusion of multifaceted demographic factors." International Journal of Electrical and Computer Engineering (IJECE) 13, no. 6 (December 1, 2023): 6972. http://dx.doi.org/10.11591/ijece.v13i6.pp6972-6983.
Full textAbstract:
<span lang="EN-US">Effective speaker identification is essential for achieving robust speaker recognition in real-world applications such as mobile devices, security, and entertainment while ensuring high accuracy. However, deep learning models trained on large datasets with diverse demographic and environmental factors may lead to increased misclassification and longer processing times. This study proposes incorporating ethnicity and gender information as critical parameters in a deep learning model to enhance accuracy. Two convolutional neural network (CNN) models classify gender and ethnicity, followed by a Siamese deep learning model trained with critical parameters and additional features for speaker verification. The proposed model was tested using the VoxCeleb 2 database, which includes over one million utterances from 6,112 celebrities. In an evaluation after 500 epochs, equal error rate (EER) and minimum decision cost function (minDCF) showed notable results, scoring 1.68 and 0.10, respectively. The proposed model outperforms existing deep learning models, demonstrating improved performance in terms of reduced misclassification errors and faster processing times.</span>
39
Yue, Zhen, Zhenqi Han, Xiulong Yang, and Lizhuang Liu. "DCSPose: A Dual-Channel Siamese Framework for Unseen Textureless Object Pose Estimation." Applied Sciences 14, no. 2 (January 15, 2024): 730. http://dx.doi.org/10.3390/app14020730.
Full textAbstract:
The demand for object pose estimation is steadily increasing, and deep learning has propelled the advancement of this field. However, the majority of research endeavors face challenges in their applicability to industrial production. This is primarily due to the high cost of annotating 3D data, which places higher demands on the generalization capabilities of neural network models. Additionally, existing methods struggle to handle the abundance of textureless objects commonly found in industrial settings. Finally, there is a strong demand for real-time processing capabilities in industrial production processes. Therefore, in this study, we introduced a dual-channel Siamese framework to address these challenges in industrial applications. The architecture employs a Siamese structure for template matching, enabling it to learn the matching capability between the templates constructed from high-fidelity simulated data and real-world scenes. This capacity satisfies the requirements for generalization to unseen objects. Building upon this, we utilized two feature extraction channels to separately process RGB and depth information, addressing the limited feature issue associated with textureless objects. Through our experiments, we demonstrated that this architecture effectively estimates the three-dimensional pose of objects, achieving a 6.0% to 10.9% improvement compared to the state-of-the-art methods, while exhibiting robust generalization and real-time processing capabilities.
40
Zhou, Yongduo, Cheng Wang, Hebing Zhang, Hongtao Wang, Xiaohuan Xi, Zhou Yang, and Meng Du. "TCPSNet: Transformer and Cross-Pseudo-Siamese Learning Network for Classification of Multi-Source Remote Sensing Images." Remote Sensing 16, no. 17 (August 23, 2024): 3120. http://dx.doi.org/10.3390/rs16173120.
Full textAbstract:
The integration of multi-source remote sensing data, bolstered by advancements in deep learning, has emerged as a pivotal strategy for enhancing land use and land cover (LULC) classification accuracy. However, current methods often fail to consider the numerous prior knowledge of remote sensing images and the characteristics of heterogeneous remote sensing data, resulting in data loss between different modalities and the loss of a significant amount of useful information, thus affecting classification accuracy. To tackle these challenges, this paper proposes a LULC classification method based on remote sensing data that combines a Transformer and cross-pseudo-siamese learning deep neural network (TCPSNet). It first conducts shallow feature extraction in a dynamic multi-scale manner, fully leveraging the prior information of remote sensing data. Then, it further models deep features through the multimodal cross-attention module (MCAM) and cross-pseudo-siamese learning module (CPSLM). Finally, it achieves comprehensive fusion of local and global features through feature-level fusion and decision-level fusion combinations. Extensive experiments on datasets such as Trento, Houston 2013, Augsburg, MUUFL and Berlin demonstrate the superior performance of the proposed TCPSNet. The overall accuracy (OA) of the network on the Trento, Houston 2013 and Augsburg datasets is of 99.76%, 99.92%, 97.41%, 87.97% and 97.96%, respectively.
41
Messa, Gian Marco, Francesco Napolitano, Sarah H. Elsea, Diego di Bernardo, and Xin Gao. "A Siamese neural network model for the prioritization of metabolic disorders by integrating real and simulated data." Bioinformatics 36, Supplement_2 (December 2020): i787—i794. http://dx.doi.org/10.1093/bioinformatics/btaa841.
Full textAbstract:
Abstract Motivation Untargeted metabolomic approaches hold a great promise as a diagnostic tool for inborn errors of metabolisms (IEMs) in the near future. However, the complexity of the involved data makes its application difficult and time consuming. Computational approaches, such as metabolic network simulations and machine learning, could significantly help to exploit metabolomic data to aid the diagnostic process. While the former suffers from limited predictive accuracy, the latter is normally able to generalize only to IEMs for which sufficient data are available. Here, we propose a hybrid approach that exploits the best of both worlds by building a mapping between simulated and real metabolic data through a novel method based on Siamese neural networks (SNN). Results The proposed SNN model is able to perform disease prioritization for the metabolic profiles of IEM patients even for diseases that it was not trained to identify. To the best of our knowledge, this has not been attempted before. The developed model is able to significantly outperform a baseline model that relies on metabolic simulations only. The prioritization performances demonstrate the feasibility of the method, suggesting that the integration of metabolic models and data could significantly aid the IEM diagnosis process in the near future. Availability and implementation Metabolic datasets used in this study are publicly available from the cited sources. The original data produced in this study, including the trained models and the simulated metabolic profiles, are also publicly available (Messa et al., 2020).
42
Xu, Wei, and Veerawat Sirivesmas. "Study on Network Virtual Printing Sculpture Design using Artificial Intelligence." International Journal of Communication Networks and Information Security (IJCNIS) 15, no. 1 (May 30, 2023): 132–45. http://dx.doi.org/10.17762/ijcnis.v15i1.5694.
Full textAbstract:
Sculptures are visionaries of a country’s culture from time immemorial. Chinese sculptures hold an aesthetic value in the global market, catalysed by opening the country's gates. On the other hand, this paved the way for many duplicates and replicates of the original sculptures, defaming the entire artwork. This work proposes a defrauding model that deploys a Siamese-based Convolutional Neural Network (S-CNN) that effectively detects the mimicked sculpture images. Nevertheless, adversarial attacks are gaining momentum, compromising the deep learning models to make predictions for faked or forged images. The work uses a Simplified Graph Convolutional Network (SGCN) to misclassify the adversarial images generated by the Fast Gradient Sign Method (FGSM) to combat this attack. The model's training is done with adversarial images of the Imagenet dataset. By transfer learning, the model is rested for its efficacy in identifying the adversarial examples of the Chinese God images dataset. The results showed that the proposed model could detect the generated adversarial examples with a reasonable misclassification rate.
43
Sun, Xinjie, Tao Qin, Lingyun Tong, Haoliang Zhang, and Weihan Xu. "Intelligent fault detection strategy for knowledge entities in fault semantic networks of distribution network based on siamese networks." PLOS ONE 19, no. 5 (May 16, 2024): e0303084. http://dx.doi.org/10.1371/journal.pone.0303084.
Full textAbstract:
The advent of smart grid technologies has brought about a paradigm shift in the management and operation of distribution networks, allowing for intricate system information to be encapsulated within semantic network models. These models, while robust, are not immune to faults within their knowledge entities, which can arise from a myriad of issues, potentially leading to verification failures and operational disruptions. Addressing this critical vulnerability, our research delves into the development of a novel fault detection methodology specifically tailored for the knowledge entity variables of semantic networks in distribution networks. In our approach, we first construct a state space equation that models the behavior of knowledge entity variables in the presence of faults. This foundational framework enables us to apply an unknown input observer strategy to effectively detect anomalies within the system. To bolster the fault identification process, we introduce the innovative use of a siamese network, a neural network architecture which is proficient in differentiating between similar datasets. Through simulation scenarios, we demonstrate the efficacy of our proposed fault detection method.
44
Toofanee, Mohammud Shaad Ally, Mohamed Hamroun, Sabeena Dowlut, Karim Tamine, Vincent Petit, Anh Kiet Duong, and Damien Sauveron. "Federated Learning: Centralized and P2P for a Siamese Deep Learning Model for Diabetes Foot Ulcer Classification." Applied Sciences 13, no. 23 (November 28, 2023): 12776. http://dx.doi.org/10.3390/app132312776.
Full textAbstract:
It is a known fact that AI models need massive amounts of data for training. In the medical field, the data are not necessarily available at a single site but are distributed over several sites. In the field of medical data sharing, particularly among healthcare institutions, the need to maintain the confidentiality of sensitive information often restricts the comprehensive utilization of real-world data in machine learning. To address this challenge, our study experiments with an innovative approach using federated learning to enable collaborative model training without compromising data confidentiality and privacy. We present an adaptation of the federated averaging algorithm, a predominant centralized learning algorithm, to a peer-to-peer federated learning environment. This adaptation led to the development of two extended algorithms: Federated Averaging Peer-to-Peer and Federated Stochastic Gradient Descent Peer-to-Peer. These algorithms were applied to train deep neural network models for the detection and monitoring of diabetic foot ulcers, a critical health condition among diabetic patients. This study compares the performance of Federated Averaging Peer-to-Peer and Federated Stochastic Gradient Descent Peer-to-Peer with their centralized counterparts in terms of model convergence and communication costs. Additionally, we explore enhancements to these algorithms using targeted heuristics based on client identities and f1-scores for each class. The results indicate that models utilizing peer-to-peer federated averaging achieve a level of convergence that is comparable to that of models trained via conventional centralized federated learning approaches. This represents a notable progression in the field of ensuring the confidentiality and privacy of medical data for training machine learning models.
45
Wang, Yu, Zhutian Yang, Wei Yang, and Jiamin Yang. "A Novel Target Tracking Scheme Based on Attention Mechanism in Complex Scenes." Electronics 11, no. 19 (September 29, 2022): 3125. http://dx.doi.org/10.3390/electronics11193125.
Full textAbstract:
In recent years, target tracking algorithms based on deep learning have realized significant progress, especially the Siamese neural network structure, which has a simple structure and excellent scalability. Although these methods provide excellent generalization capabilities, they fail to perform the task of learning target information discrimination smoothly due to being affected by distractors such as background clutter, occlusion, and target size. To solve this problem, in this paper we propose a newly improved Siamese network target tracking algorithm based on an attention mechanism. We introduce a channel attention module and a spatial attention module into the original network to improve the problem of insufficient semantic extraction ability of the convolutional layer of the tracking algorithm in complex environments. A channel attention mechanism enhances the feature extraction ability by using the network to learn the importance of each channel and establish the relationship between channels, while a spatial attention mechanism strengthens the feature extraction ability by establishing the importance of spatial position in locating the target or carrying out a certain degree of deformation. In this paper, the above two models are combined to improve the robustness of trackers without sacrificing tracking speed. We conduct a comprehensive experiment on the Object Tracking Benchmark dataset. The experimental results show that our algorithm outperforms other real-time trackers in both accuracy and robustness in most complex environments.
46
Kholodna, N., and V. Vysotska. "REWRITING IDENTIFICATION TECHNOLOGY FOR TEXT CONTENT BASED ON MACHINE LEARNING METHODS." Radio Electronics, Computer Science, Control, no. 4 (December 13, 2022): 126. http://dx.doi.org/10.15588/1607-3274-2022-4-11.
Full textAbstract:
Context. Paraphrased textual content or rewriting is one of the difficult problems of detecting academic plagiarism. Most plagiarism detection systems are designed to detect common words, sequences of linguistic units, and minor changes, but are unable to detect significant semantic and structural changes. Therefore, most cases of plagiarism using paraphrasing remain unnoticed.
Objective of the study is to develop a technology for detecting paraphrasing in text based on a classification model and machine learning methods through the use of Siamese neural network based on recurrent and Transformer type – RoBERTa to analyze the level of similarity of sentences of text content.
Method. For this study, the following semantic similarity metrics or indicators were chosen as features: Jacquard coefficient for shared N-grams, cosine distance between vector representations of sentences, Word Mover’s Distance, distances according to WordNet dictionaries, prediction of two ML models: Siamese neural network based on recurrent and Transformer type - RoBERTa.
Results. An intelligent system for detecting paraphrasing in text based on a classification model and machine learning methods has been developed. The developed system uses the principle of model stacking and feature engineering. Additional features indicate the semantic affiliation of the sentences or the normalized number of common N-grams. An additional fine-tuned RoBERTa neural network (with additional fully connected layers) is less sensitive to pairs of sentences that are not paraphrases of each other. This specificity of the model may contribute to incorrect accusations of plagiarism or incorrect association of user-generated content. Additional features increase both the overall classification accuracy and the model’s sensitivity to pairs of sentences that are not paraphrases of each other.
Conclusions. The created model shows excellent classification results on PAWS test data: precision – 93%, recall – 92%, F1score – 92%, accuracy – 92%. The results of the study showed that Transformer-type NNs can be successfully applied to detect paraphrasing in a pair of texts with fairly high accuracy without the need for additional feature generation.
47
Li, Chenpu, Qianjian Xing, and Zhenguo Ma. "HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter." Sensors 20, no. 7 (April 10, 2020): 2137. http://dx.doi.org/10.3390/s20072137.
Full textAbstract:
In the field of visual tracking, trackers based on a convolutional neural network (CNN) have had significant achievements. The fully-convolutional Siamese (SiamFC) tracker is a typical representation of these CNN trackers and has attracted much attention. It models visual tracking as a similarity-learning problem. However, experiments showed that SiamFC was not so robust in some complex environments. This may be because the tracker lacked enough prior information about the target. Inspired by the key idea of a Staple tracker and Kalman filter, we constructed two more models to help compensate for SiamFC’s disadvantages. One model contained the target’s prior color information, and the other the target’s prior trajectory information. With these two models, we design a novel and robust tracking framework on the basis of SiamFC. We call it Histogram–Kalman SiamFC (HKSiamFC). We also evaluated HKSiamFC tracker’s performance on dataset of the online object tracking benchmark (OTB) and Temple Color (TC128), and it showed quite competitive performance when compared with the baseline tracker and several other state-of-the-art trackers.
48
Farabbi, Andrea, and Luca Mainardi. "Domain-Specific Processing Stage for Estimating Single-Trail Evoked Potential Improves CNN Performance in Detecting Error Potential." Sensors 23, no. 22 (November 8, 2023): 9049. http://dx.doi.org/10.3390/s23229049.
Full textAbstract:
We present a novel architecture designed to enhance the detection of Error Potential (ErrP) signals during ErrP stimulation tasks. In the context of predicting ErrP presence, conventional Convolutional Neural Networks (CNNs) typically accept a raw EEG signal as input, encompassing both the information associated with the evoked potential and the background activity, which can potentially diminish predictive accuracy. Our approach involves advanced Single-Trial (ST) ErrP enhancement techniques for processing raw EEG signals in the initial stage, followed by CNNs for discerning between ErrP and NonErrP segments in the second stage. We tested different combinations of methods and CNNs. As far as ST ErrP estimation is concerned, we examined various methods encompassing subspace regularization techniques, Continuous Wavelet Transform, and ARX models. For the classification stage, we evaluated the performance of EEGNet, CNN, and a Siamese Neural Network. A comparative analysis against the method of directly applying CNNs to raw EEG signals revealed the advantages of our architecture. Leveraging subspace regularization yielded the best improvement in classification metrics, at up to 14% in balanced accuracy and 13.4% in F1-score.
49
Rouček, Tomáš, Arash Sadeghi Amjadi, Zdeněk Rozsypálek, George Broughton, Jan Blaha, Keerthy Kusumam, and Tomáš Krajník. "Self-Supervised Robust Feature Matching Pipeline for Teach and Repeat Navigation." Sensors 22, no. 8 (April 7, 2022): 2836. http://dx.doi.org/10.3390/s22082836.
Full textAbstract:
The performance of deep neural networks and the low costs of computational hardware has made computer vision a popular choice in many robotic systems. An attractive feature of deep-learned methods is their ability to cope with appearance changes caused by day–night cycles and seasonal variations. However, deep learning of neural networks typically relies on large numbers of hand-annotated images, which requires significant effort for data collection and annotation. We present a method that allows autonomous, self-supervised training of a neural network in visual teach-and-repeat (VT&R) tasks, where a mobile robot has to traverse a previously taught path repeatedly. Our method is based on a fusion of two image registration schemes: one based on a Siamese neural network and another on point-feature matching. As the robot traverses the taught paths, it uses the results of feature-based matching to train the neural network, which, in turn, provides coarse registration estimates to the feature matcher. We show that as the neural network gets trained, the accuracy and robustness of the navigation increases, making the robot capable of dealing with significant changes in the environment. This method can significantly reduce the data annotation efforts when designing new robotic systems or introducing robots into new environments. Moreover, the method provides annotated datasets that can be deployed in other navigation systems. To promote the reproducibility of the research presented herein, we provide our datasets, codes and trained models online.
50
Luo, Peilei, Huichun Ye, Wenjiang Huang, Jingjuan Liao, Quanjun Jiao, Anting Guo, and Binxiang Qian. "Enabling Deep-Neural-Network-Integrated Optical and SAR Data to Estimate the Maize Leaf Area Index and Biomass with Limited In Situ Data." Remote Sensing 14, no. 21 (November 7, 2022): 5624. http://dx.doi.org/10.3390/rs14215624.
Full textAbstract:
Accurate estimation of the maize leaf area index (LAI) and biomass is of great importance in guiding field management and early yield estimation. Physical models and traditional machine learning methods are commonly used for LAI and biomass estimation. However, these models and methods mostly rely on handcrafted features and theoretical formulas under idealized assumptions, which limits their accuracy. Deep neural networks have demonstrated great superiority in automatic feature extraction and complicated nonlinear approximation, but their application to LAI and biomass estimation has been hindered by the shortage of in situ data. Therefore, bridging the gap of data shortage and making it possible to leverage deep neural networks to estimate maize LAI and biomass is of great significance. Optical data cannot provide information in the lower canopy due to the limited penetrability, but synthetic aperture radar (SAR) data can do this, so the integration of optical and SAR data is necessary. In this paper, 158 samples from the jointing, trumpet, flowering, and filling stages of maize were collected for investigation. First, we propose an improved version of the mixup training method, which is termed mixup+, to augment the sample amount. We then constructed a novel gated Siamese deep neural network (GSDNN) based on a gating mechanism and a Siamese architecture to integrate optical and SAR data for the estimation of the LAI and biomass. We compared the accuracy of the GSDNN with those of other machine learning methods, i.e., multiple linear regression (MLR), support vector regression (SVR), random forest regression (RFR), and a multilayer perceptron (MLP). The experimental results show that without the use of mixup+, the GSDNN achieved a similar accuracy to that of the simple neural network MLP in terms of R2 and RMSE, and this was slightly lower than those of MLR, SVR, and RFR. However, with the help of mixup+, the GSDNN achieved state-of-the-art performance (R2 = 0.71, 0.78, and 0.86 and RMSE = 0.58, 871.83, and 150.76 g/m2, for LAI, Biomass_wet, and Biomass_dry, respectively), exceeding the accuracies of MLR, SVR, RFR, and MLP. In addition, through the integration of optical and SAR data, the GSDNN achieved better accuracy in LAI and biomass estimation than when optical or SAR data alone were used. We found that the most appropriate amount of synthetic data from mixup+ was five times the amount of original data. Overall, this study demonstrates that the GSDNN + mixup+ has great potential for the integration of optical and SAR data with the aim of improving the estimation accuracy of the maize LAI and biomass with limited in situ data.