The technological revolution that we have been witnessing recently has allowed components miniaturization and made electronic components accessible. Hyperspectral sensors benefited from these advances and could be mou...
详细信息
The technological revolution that we have been witnessing recently has allowed components miniaturization and made electronic components accessible. Hyperspectral sensors benefited from these advances and could be mounted on unmanned aerial vehicles, which was unthinkable until recently. This fact significantly increased the applications of hyperspectral data, namely in agriculture, especially in the detection of diseases at an early stage. The vineyard is one of the agricultural sectors that has the most to gain from the use of this type of data, both by the economic value and by the number of diseases the plants are exposed to. The Flavescense dorée is a disease that attacks vineyards and may conduct to a significant loss. Nowadays, the detection of this disease is based on the visual identification of symptoms performed by experts who cover the entire area. However, this work remains tedious and relies only on the human eye, which is a problem since sometimes healthy plants are torn out, while diseased ones are left. If the experts think they have found symptoms, they take samples to send to the laboratory for further analysis. If the test is positive, then the whole vine is uprooted, to limit the spread of the disease. In this context, the use of hyperspectral data will allow the development of new disease detection methods. However, it will be necessary to reduce the volume of data used to make them usable by conventional resources. Fortunately, the advent of machine learning techniques empowered the development of systems that allow better decisions to be made, and consequently save time and money. In this article, a machine learning approach, which is based on an autoencoder to automatically detect wine disease, is proposed.
It has been long debated how the so called cognitive map, the set of place cells, develops in rat hippocampus. The function of this organ is of high relevance, since the hippocampus is the key component of the medial ...
详细信息
It has been long debated how the so called cognitive map, the set of place cells, develops in rat hippocampus. The function of this organ is of high relevance, since the hippocampus is the key component of the medial temporal lobe memory system, responsible for forming episodic memory, declarative memory, the memory for facts and rules that serve cognition in humans. Here, a general mechanism is put forth: We introduce the novel concept of Cartesian factors. We show a non-linear projection of observations to a discretized representation of a Cartesian factor in the presence of a representation of a complementing one. The computational model is demonstrated for place cells that we produce from the egocentric observations and the head direction signals. Head direction signals make the observed factor and sparse allothetic signals make the complementing Cartesian one. We present numerical results, connect the model to the neural substrate, and elaborate on the differences between this model and other ones, including Slow Feature Analysis [17] .
records contain patient information such as laboratory values, doctor notes, or medications. However, clinical notes are underutilized because notes are complex, high dimensional, and sparse. However, these clinical r...
详细信息
records contain patient information such as laboratory values, doctor notes, or medications. However, clinical notes are underutilized because notes are complex, high dimensional, and sparse. However, these clinical records may play an essential role in modeling clinical decision support systems. The study aimed to develop an effective predictive learning model that can process these sparse data and extract useful information to benefit the clinical decision support system for the effective diagnosis. The proposed system conducts phase wise data modeling, and suitable text data treatment is carried out for data preparation. The study further utilized the Natural Language Processing (NLP) mechanism where word2vec with autoencoder is used as a clustering scheme for the topic modeling. Another significant contribution of the proposed work is that a novel approach of learning mechanism is devised by integrating Long Short Term Memory (LSTM) and Convolution Neural Network (CNN) to learn the inter-dependencies of the data sequences to predict diagnosis and patient testimony as output for the clinical decision. The development of the proposed system is carried out using the Python programming language. The study outcome based on the comparative analysis exhibits the effectiveness of the method.
A crucial component of industrial operations is the detection of production system failures, which aims to spot any problems before they get worse. By applying cutting -edge methods like deep learning and genetic algo...
详细信息
A crucial component of industrial operations is the detection of production system failures, which aims to spot any problems before they get worse. By applying cutting -edge methods like deep learning and genetic algorithms, failure detection accuracy may be improved, allowing for preemptive actions to reduce downtime and maximize system availability. These methods improve reactivity to possible errors and solve dynamic issues, which enhances the overall efficiency and reliability of production systems. This study offers a novel method for improving the availability and failure detection of production systems using deep learning techniques and genetic algorithms in a data -driven strategy. The goal of the project is to provide a complete framework for efficient failure detection that incorporates deep learning models, particularly Convolutional Neural Network (CNN) autoencoder. Furthermore, system configurations are optimized through the use of genetic algorithms, improving overall availability. The suggested model is able to identify complex patterns and connections in the data by being trained on a variety of datasets that contain information about equipment failure. The incorporation of genetic algorithm guarantees flexibility and resilience in system setups, hence augmenting total availability. The study presents a proactive and flexible approach to the dynamic issues encountered in industrial environments, providing a notable breakthrough in failure detection and availability improvement. The proposed model is implemented in Python software. It achieves an astounding 99.32% accuracy rate, which is 3.58% higher than that of current techniques like CNN-LSTM (Long Short -Term Memory), Bi-LSTM (Bi-directional Long Short -Term Memory), and CNN-RNN (Recurrent Neural Network). The data -driven approach's high accuracy highlights its efficacy in forecasting and avoiding problems, which minimizes downtime and maximizes production efficiency.
Unsupervised anomaly detection holds significant importance in large-scale industrial manufacturing. Recent methods have capitalized on the benefits of employing a classifier pretrained on natural images to extract re...
详细信息
Unsupervised anomaly detection holds significant importance in large-scale industrial manufacturing. Recent methods have capitalized on the benefits of employing a classifier pretrained on natural images to extract representative features from specific layers, which are subsequently processed using various techniques. Notably, memory bank-based methods, which have demonstrated exceptional accuracy, often incur a trade-off in terms of latency, posing a challenge in real-time industrial applications where prompt anomaly detection and response are crucial. Indeed, alternative approaches such as knowledge distillation and normalized flow have demonstrated promising performance in unsupervised anomaly detection while maintaining low latency. In this paper, we aim to revisit the concept of knowledge distillation in the context of unsupervised anomaly detection, emphasizing the significance of feature selection. By employing distinctive features and leveraging different models, we intend to highlight the importance of carefully selecting and utilizing relevant features specifically tailored for the task of anomaly detection. This article presents a novel approach for anomaly detection, which employs dual model knowledge distillation and incorporates various types of semantic information by leveraging high and low-level semantic information.
- Urban sculptures have long been a reflection of the cultural and historical identity of a city, serving as both artistic expressions and landmarks. The application of deep learning in the context of sculptures withi...
详细信息
- Urban sculptures have long been a reflection of the cultural and historical identity of a city, serving as both artistic expressions and landmarks. The application of deep learning in the context of sculptures within urban areas presents an intriguing intersection of art and technology. Deep learning algorithms, particularly those related to computer vision, have the capacity to analyze and understand the intricate details of sculptures. This paper presented a efficient 3D -AWE (3D -Weighted Architecture Estimation) in the analysis of urban sculptures. In an era where the preservation and interpretation of cultural heritage are of paramount importance, this study investigates the potential of advanced technology to enhance understanding of artistic and historical artifacts within urban environments. The proposed 3DAWE model uses the weighted estimation with computation of the pixels in the scupturs. Additionally, the proposed 3D -AWE model uses the min -max estimation model for the computation of the features in the images. With the estimated features the deep learning through weighted model for the analysis of the sculptures. The research focuses on the accurate classification of urban sculptures into specific styles and periods, such as Baroque, Renaissance, Modernist, Abstract, Ancient, and Contemporary. Utilizing precision, recall, F1 Scores, and overall accuracy, the study highlights the model's ability to minimize errors and provide reliable categorization. Furthermore, the application of 3D -AWE for feature extraction reveals quantifiable representations of sculpture attributes, offering valuable insights for sculpture categorization, similarity analysis, and the automated management of museum collections. The implications of these findings extend to art history, cultural heritage preservation, and urban planning, underscoring the significance of advanced technology in efforts to safeguard and interpret cultural legacy.
The article discusses the problem of detecting network attacks on a web server. The attention is focused on two common types of attacks: "denial of service" and "code injection". A review and an an...
详细信息
The article discusses the problem of detecting network attacks on a web server. The attention is focused on two common types of attacks: "denial of service" and "code injection". A review and an analysis of various attack detection techniques are conducted. A new lightweight approach to detect attacks as anomalies is proposed. It is based on recognition of the dynamic response of the web server during requests processing. An autoencoder is implemented for dynamic response anomaly recognition. A case study with the MyBB web server is described. Several flood attacks and SQL injection attack are modeled and successfully detected by the proposed method. The efficiency of the detection algorithm is evaluated, and the advantages and disadvantages of the proposed approach are analyzed.
Quantifying structural status and locating structural anomalies are critical to tracking and safeguarding the safety of long-distance underground structures. Given the dynamic and distributed monitoring capabilities o...
详细信息
Quantifying structural status and locating structural anomalies are critical to tracking and safeguarding the safety of long-distance underground structures. Given the dynamic and distributed monitoring capabilities of an ultra-weak fiber Bragg grating (FBG) array, this paper proposes a method combining the stacked denoising autoencoder (SDAE) network and the improved dynamic time wrapping (DTW) algorithm to quantify the similarity of vibration responses. To obtain the dimensionality reduction features that were conducive to distance measurement, the silhouette coefficient was adopted to evaluate the training efficacy of the SDAE network under different hyperparameter settings. To measure the distance based on the improved DTW algorithm, the one nearest neighbor (1-NN) classifier was utilized to search the best constraint bandwidth. Moreover, the study proposed that the performance of different distance metrics used to quantify similarity can be evaluated through the 1-NN classifier. Based on two one-dimensional time-series datasets from the University of California, Riverside (UCR) archives, the detailed implementation process for similarity measure was illustrated. In terms of feature extraction and distance measure of UCR datasets, the proposed integrated approach of similarity measure showed improved performance over other existing algorithms. Finally, the field-vibration responses of the track bed in the subway detected by the ultra-weak FBG array were collected to determine the similarity characteristics of structural vibration among different monitoring zones. The quantitative results indicated that the proposed method can effectively quantify and distinguish the vibration similarity related to the physical location of structures.
In recent years, turbofan engine failures have frequently occurred, traditional breakdown maintenance has been difficult to meet the demand. Remaining useful life (RUL) prediction technology has become one of the effe...
详细信息
In recent years, turbofan engine failures have frequently occurred, traditional breakdown maintenance has been difficult to meet the demand. Remaining useful life (RUL) prediction technology has become one of the effective ways to solve the above-mentioned problems. To accurately obtain the RUL of the turbofan engine, an RUL prediction method based on Temporal Convolutional Networks (TCN) is proposed in this paper. The overall network can be divided as follows: Firstly, combining the advantages of LSTM and autoencoder to complete the feature extraction of sequence data. Secondly, TCN is used in the RUL prediction part. TCN does not disclose future sequence information and it has a larger and more flexible receptive field. TCN also features the residual structure to make full use of the original input information and to avoid the disappearance of gradients. The effectiveness of the proposed method is verified in CMAPSS datasets. Finally, compared with other excellent RUL prediction methods, the proposed method improves the prediction accuracy on complex datasets.
Early detection of atrial fibrillation (AF) is crucial for its effective management and prevention. Various methods for detecting AF using deep learning (DL) based on supervised learning with a large labeled dataset h...
详细信息
Early detection of atrial fibrillation (AF) is crucial for its effective management and prevention. Various methods for detecting AF using deep learning (DL) based on supervised learning with a large labeled dataset have a remarkable performance. However, supervised learning has several problems, as it is time-consuming for labeling and has a data dependency problem. Moreover, most of the DL methods do not provide any clinical evidence to physicians regarding the analysis of electrocardiography (ECG) for classification or detection of AF. To address these limitations, in this study, we proposed a novel AF diagnosis system using unsupervised learning for anomaly detection with three segments, PreQ, QRS, and PostS, based on the normal ECG. Two independent datasets, PTB-XL and China, were used in three experiments. We used a long short-term memory (LSTM)-based autoencoder to train the segments of the normal ECG. Based on the threshold of anomaly scores using mean squared error (MSE), it distinguished between normal and AF segments. In Experiment A, the best score was that of PreQ, which detected AF with an AUROC score of 0.96. In Experiment B and C for cross validation of each dataset, the best scores were also of PreQ, with AUROC scores of 0.9 and 0.95, respectively. To verify the significance of the anomaly score in distinguishing between AF and normal segments, we utilized an XG-Boosted model after generating anomaly scores in the three segments. The XG-Boosted model achieved an AUROC score of 0.98 and an F1 score of 0.94. AF detection using DL has been controversial among many physicians. However, our study differentiates itself from previous studies in that we can demonstrate evidence that distinguishes AF from normal segments based on the anomaly score.
暂无评论