The cultivation of grapes encounters various challenges, such as the presence of pests and diseases, which have the potential to considerably diminish agricultural productivity. Plant diseases pose a significant imped...
详细信息
The cultivation of grapes encounters various challenges, such as the presence of pests and diseases, which have the potential to considerably diminish agricultural productivity. Plant diseases pose a significant impediment, resulting in diminished agricultural productivity and economic setbacks, thereby affecting the quality of crop yields. Hence, the precise and timely identification of plant diseases holds significant importance. This study employs a Convolutional neuralnetwork (CNN) with and without data augmentation, in addition to a DCNN classifier model based on VGG16, to classify grape leaf diseases. A publicly available dataset is utilized for the purpose of investigating diseases affecting grape leaves. The DCNN classifier Model successfully utilizes the strengths of the VGG16 model and modifies it by incorporating supplementary layers to enhance its performance and ability to generalize. Systematic evaluation of metrics, such as accuracy and F1-score, is performed. With training and test accuracy rates of 99.18 and 99.06%, respectively, the DCNN classifier model does a better job than the CNN models used in this investigation. The findings demonstrate that the DCNN classifier model, utilizing the VGG16 architecture and incorporating three supplementary CNN layers, exhibits superior performance. Also, the fact that the DCNN classifier model works well as a decision support system for farmers is shown by the fact that it can quickly and accurately identify grape diseases, making it easier to take steps to stop them. The results of this study provide support for the reliability of the DCNN classifier model and its potential utility in the field of agriculture.
With a global morbidity rate of 8.224 parts per thousand, congenital heart diseases (CHDs) are cardiovascular abnormalities progressing since fetal development. Many CHD patients remain undiagnosed, due to lack of car...
详细信息
With a global morbidity rate of 8.224 parts per thousand, congenital heart diseases (CHDs) are cardiovascular abnormalities progressing since fetal development. Many CHD patients remain undiagnosed, due to lack of cardiologists, echocardiograph devices and skilled operators, especially in remote regions of developing countries. Artificial intelligence assisted phonocardiogram (PCG) auscultation is promising for rapid and low-cost cardiac abnormality detection. However, a practical pediatric CHDs screening system was hindered by the lack of labeled PCG database recorded in real CHDs screening scenarios and the prerequisite of hand-sorting PCG fragments. A Largescale Congenital Heart diseases Screening Tool, named LaCHeST, is developed in this study to achieve userintervention-free online pediatric CHDs screening. In the LaCHeST, similarity among low-frequency PCG envelogram pieces is exploited to automatically extract PCG fragments and reject trajectories. For efficient feature extraction and segment-wise classification, a dual-path complementary neuralnetwork (DPC-Net) is established, with exemption from cardiac cycle segmentation, whose rationality was verified by occlusion maps. The algorithms in LaCHeST were developed based on our PCG database collected from 14,332 pediatric subjects, in a voluntary pediatric CHDs screening task in Shaoyang, Hunan, China, implemented by Hunan Children's Hospital. The LaCHeST achieved high agreement with expert interpretations (Kappa = 0.87), and outperformed the state-of-the-art methods with average Specificity = 99.6 %, Accuracy = 99.23 %, Recall = 87.43 %, and F1score = 88 % in segment-wise classification. Subject-wise classification performance was evaluated in a separate pediatric CHDs screening task involving 786 pediatric subjects, and achieved Specificity = 99.22 % and Recall = 100 %.
Background: Excellence in the growing technologies enables innovative techniques to ensure the privacy and security of individuals. Manual detection of anomalies through monitoring is time-consuming and inefficient mo...
详细信息
ISBN:
(纸本)9789811925412;9789811925405
Background: Excellence in the growing technologies enables innovative techniques to ensure the privacy and security of individuals. Manual detection of anomalies through monitoring is time-consuming and inefficient most of the time;hence automatic identification of anomalous events is necessary to cope with modern technology. Purpose: To enhance the security in public places as well as in the dwelling areas, surveillance cameras are employed to detect anomalous events. Methods: As a contribution, this research focuses on developing an anomaly detection model based on the deep neural network classifier which effectively classifies the abnormal events in the surveillance videos and is effectively optimized using the grey wolf optimization algorithm. The extraction of the features utilizing the Histogram of Optical flow Orientation and Magnitude (HOFM) based feature descriptor furthermore improves the performance of the classifier. Results: The experimental results are obtained based on the frame level and pixel levels with an accuracy rate of 92.76 and 92.13%, Area under Curve (AUC) rate of 91.76 and 92%, and the equal error rate (EER) is 7.24 and 9.37% which is more efficient compared with existing state-of-art methods. Conclusion: The proposed method achieved enhanced accuracy and minimal error rate compared to the state of art techniques and hence it can be utilized for the detection of anomalies in the video.
Nation's social and economic improvement is highly based on the citizen's health profile. Road safety can be considered as one of the most crucial and vital aspects of every country. The trauma of road acciden...
详细信息
ISBN:
(纸本)9781728151564
Nation's social and economic improvement is highly based on the citizen's health profile. Road safety can be considered as one of the most crucial and vital aspects of every country. The trauma of road accidents is, it mainly affects developing countries like Sri Lanka, rather than the developed countries. In Sri Lanka, 2.8% of the deaths are occurred by road accidents which indicate the number of 3554 deaths in last year and over 180 US $ million annually have to spend on road accidents. Furthermore, to reduce the danger of road accidents and to improve road safety, an analysis of road accidents based on machine learning was proposed. The primary aim of this study is to develop a mechanism to predict the driver fault at the accident and identify the accident hot spot in the area, which can be effectively used for taking countermeasures to improve road safety in Sri Lanka. deepneuralnetworks (DNN) classifier, Decision tree, Linear classifier in deep learning have been used to accurately predict and uncover road accident patterns within the data set. Results revealed that the Decision Tree and the DNN classifier are more accurate and comparable than other machine learning techniques used and the first 25 km of the road is more accident-prone rather the other road segments in the road. The research will provide the information needed to guide the relevant decision-makers in adopting suitable measures to prevent and to reduce the accident rate.
This paper introduces a novel deepneuralnetwork tracker for robust object tracking. To this end, we employ a ranking loss which provides a fine-tuning of the target object position and returns more precise bounding ...
详细信息
ISBN:
(纸本)9781728150239
This paper introduces a novel deepneuralnetwork tracker for robust object tracking. To this end, we employ a ranking loss which provides a fine-tuning of the target object position and returns more precise bounding boxes framing the target object. This is achieved by systematically learning to give higher scores to the candidate regions better framing the target object than the regions that frame the object with less accuracy. As a result, the risk of tracking error accumulation and drifts are largely mitigated, and the object is tracked more successfully: When the proposed network is used with a simple yet effective model update rule, our proposed tracker achieves the state-of-the-art results on all tested challenging tracking datasets. Especially, our results on the OTB (Object Tracking Benchmark) datasets are very promising. The proposed tracker outperforms both deepneuralnetwork and correlation filter based trackers, MDNet and ECO, by about 2%, which is a significant improvement over the previous state-of-the-art.
Melanoma is the most serious type of skin cancer. We consider in this paper diagnosing melanoma based on skin lesion images obtained by common optical cameras. Given the lower quality of such images, we should cope wi...
详细信息
ISBN:
(纸本)9789897583544
Melanoma is the most serious type of skin cancer. We consider in this paper diagnosing melanoma based on skin lesion images obtained by common optical cameras. Given the lower quality of such images, we should cope with the imprecision of image data. This paper proposes a CAD system for decision making about the skin lesion severity. We first define the fuzzy modeling of the Bag-of-Words (BoW) of the lesion. Indeed, features are extracted from the skin lesion image related to four criteria inspired by the ABCD rule (Asymmetry, Border, Color, and Differential structures). Based on Fuzzy C-Means (FCM), membership degrees are determined for each BoW. Then, a deep neural network classifier is used for decision making. Based on a public database of 206 lesion images, experimental results demonstrate that the fuzzification of feature modeling presents good results in term of sensitivity (90.1%) and of accuracy (87.5%). A comparative study illustrates that our approach offers the best accuracy and sensitivity.
暂无评论