Journal articles: 'Adaptive Sharpness Aware Minimization'

1

Dung Nguyen, Duc, and Jae Wook Jeon. "Enhancing accuracy and sharpness of motion field with adaptive scheme and occlusion-aware filter." IET Image Processing 7, no. 2 (March 1, 2013): 144–53. http://dx.doi.org/10.1049/iet-ipr.2012.0563.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Guo, Li, Weilong Chen, Yu Liao, Honghua Liao, and Jun Li. "An Edge-Preserved Image Denoising Algorithm Based on Local Adaptive Regularization." Journal of Sensors 2016 (2016): 1–6. http://dx.doi.org/10.1155/2016/2019569.

Full text

Abstract:

Image denoising methods are often based on the minimization of an appropriately defined energy function. Many gradient dependent energy functions, such as Potts model and total variation denoising, regard image as piecewise constant function. In these methods, some important information such as edge sharpness and location is well preserved, but some detailed image feature like texture is often compromised in the process of denoising. For this reason, an image denoising method based on local adaptive regularization is proposed in this paper, which can adaptively adjust denoising degree of noisy image by adding spatial variable fidelity term, so as to better preserve fine scale features of image. Experimental results show that the proposed denoising method can achieve state-of-the-art subjective visual effect, and the signal-noise-ratio (SNR) is also objectively improved by 0.3–0.6 dB.

APA, Harvard, Vancouver, ISO, and other styles

3

Raj, Anish, Fabian Tollens, Laura Hansen, Alena-Kathrin Golla, Lothar R. Schad, Dominik Nörenberg, and Frank G. Zöllner. "Deep Learning-Based Total Kidney Volume Segmentation in Autosomal Dominant Polycystic Kidney Disease Using Attention, Cosine Loss, and Sharpness Aware Minimization." Diagnostics 12, no. 5 (May 7, 2022): 1159. http://dx.doi.org/10.3390/diagnostics12051159.

Full text

Abstract:

Early detection of the autosomal dominant polycystic kidney disease (ADPKD) is crucial as it is one of the most common causes of end-stage renal disease (ESRD) and kidney failure. The total kidney volume (TKV) can be used as a biomarker to quantify disease progression. The TKV calculation requires accurate delineation of kidney volumes, which is usually performed manually by an expert physician. However, this is time-consuming and automated segmentation is warranted. Furthermore, the scarcity of large annotated datasets hinders the development of deep learning solutions. In this work, we address this problem by implementing three attention mechanisms into the U-Net to improve TKV estimation. Additionally, we implement a cosine loss function that works well on image classification tasks with small datasets. Lastly, we apply a technique called sharpness aware minimization (SAM) that helps improve the generalizability of networks. Our results show significant improvements (p-value < 0.05) over the reference kidney segmentation U-Net. We show that the attention mechanisms and/or the cosine loss with SAM can achieve a dice score (DSC) of 0.918, a mean symmetric surface distance (MSSD) of 1.20 mm with the mean TKV difference of −1.72%, and R2 of 0.96 while using only 100 MRI datasets for training and testing. Furthermore, we tested four ensembles and obtained improvements over the best individual network, achieving a DSC and MSSD of 0.922 and 1.09 mm, respectively.

APA, Harvard, Vancouver, ISO, and other styles

4

Vishal, Puri, and Ramesh Babu A. "Deployment of Context-Aware Sensor in Wireless Sensor Network Based on the Variants of Genetic Algorithm." International Journal of Artificial Life Research 8, no. 2 (July 2018): 1–24. http://dx.doi.org/10.4018/ijalr.2018070101.

Full text

Abstract:

Wireless sensor networks (WSNs) are generally a group of spatially scattered and devoted sensors to record and monitor the physical environmental condition, and the collected data is grouped at a central location. In fact, the environmental conditions such as sound, humidity, temperature, wind, pollution levels, etc., can be clearly determined by WSNs. The principal objective of WSNs is to organize the whole sensor nodes in their related positions, thereby developing an effective network. In WSNs, target COVerage (TCOV) and Network CONnectivity (NCON) are the main concern of the sensor deployment problem. Many research works aspire the evolvement of smart context awareness algorithm for sensor deployment issues in WSN. Here the TCOV and NCON process are deployed as the minimization problem. This article makes an analysis of different GA variations in attaining the objective. The GA variations are as follows: self-adaptive genetic algorithm (SAGA), deterministic-adaptive genetic algorithm (DAGA), Individual- Adaptive Genetic Algorithm (IAGA). Finally, the methods are compared to one another in terms of connectivity and coverage performance.

APA, Harvard, Vancouver, ISO, and other styles

5

Bruschi, Roberto, Alessandro Carrega, and Franco Davoli. "A Game for Energy-Aware Allocation of Virtualized Network Functions." Journal of Electrical and Computer Engineering 2016 (2016): 1–10. http://dx.doi.org/10.1155/2016/4067186.

Full text

Abstract:

Network Functions Virtualization (NFV) is a network architecture concept where network functionality is virtualized and separated into multiple building blocks that may connect or be chained together to implement the required services. The main advantages consist of an increase in network flexibility and scalability. Indeed, each part of the service chain can be allocated and reallocated at runtime depending on demand. In this paper, we present and evaluate an energy-aware Game-Theory-based solution for resource allocation of Virtualized Network Functions (VNFs) within NFV environments. We consider each VNF as a player of the problem that competes for the physical network node capacity pool, seeking the minimization of individual cost functions. The physical network nodes dynamically adjust their processing capacity according to the incoming workload, by means of an Adaptive Rate (AR) strategy that aims at minimizing the product of energy consumption and processing delay. On the basis of the result of the nodes’ AR strategy, the VNFs’ resource sharing costs assume a polynomial form in the workflows, which admits a unique Nash Equilibrium (NE). We examine the effect of different (unconstrained and constrained) forms of the nodes’ optimization problem on the equilibrium and compare the power consumption and delay achieved with energy-aware and non-energy-aware strategy profiles.

APA, Harvard, Vancouver, ISO, and other styles

6

AbdulAlim, Md Abdul, Yu Cheng Wu, and Wei Wang. "A Fuzzy Based Clustering Protocol for Energy-Efficient Wireless Sensor Networks." Advanced Materials Research 760-762 (September 2013): 685–90. http://dx.doi.org/10.4028/www.scientific.net/amr.760-762.685.

Full text

Abstract:

Minimization of energy consumption is one of the most important research areas in Wireless Sensor Networks. Nowadays, the paradigms of computational intelligence (CI) are widely used in WSN, such as localization, clustering, energy aware routing, task scheduling, security, etc. Though many fuzzy based clustering techniques have been proposed earlier, many of them could not increase the total network life time in terms of LND (Last Node Dies) with comparing to LEACH. In this paper, a fuzzy logic based energy-aware dynamic clustering technique is proposed, which increases the network lifetime in terms of LND. Here, two inputs are given in the fuzzy inference system and a node is selected as a cluster head according to the fuzzy cost (output). The main advantage of this protocol is that the optimum number of cluster is formed in every round, which is almost impossible in LEACH (low-energy adaptive clustering hierarchy). Moreover, this protocol has less computational load and complexity. The simulation result demonstrates that this approach performs better than LEACH in terms of energy saving as well as network lifetime.

APA, Harvard, Vancouver, ISO, and other styles

7

Garg, Anchal, and Gurjinder Kaur. "Zone Head Selection Algorithm Based on Fuzzy Logic for Wireless Sensor Networks." Journal of University of Shanghai for Science and Technology 23, no. 10 (October 1, 2021): 29–37. http://dx.doi.org/10.51201/jusst/21/09706.

Full text

Abstract:

Clustering extends energy resources, improves scalability and preserves communication bandwidth of the network. Clustering is either categorized as static and dynamic or as equal and unequal. Hot-spots issue needs a high overhead and is prone to connectivity problems in the wireless sensor network and this can be only possible because of unequal clustering. In this paper a zone divisional method based on fuzzy logic has been proposed. This method uses a fuzzy logic to form clusters and allot nodes to them for the reduction of energy consumption, and extends the age of the sensor network. The simulation and results section shows that the outperformance of the proposed algorithm, where the (EAUCF) energy-aware unequal clustering fuzzy, (LEACH) lowenergy adaptive clustering hierarchy, (EAMMH) energy-aware multi-hop multi-path hierarchical, and (TTDFP) two-tier distributed fuzzy logic-based protocol for efficient data aggregation in multi-hop wireless sensor networks algorithms. The proposed algorithm has better results in terms of energy consumption minimization, load balancing, and prolongation of the network lifetime.

APA, Harvard, Vancouver, ISO, and other styles

8

Garg, Anchal, and Gurjinder Kaur. "Fuzzy Logic Based Zone Head Selection Algorithm for Wireless Sensor Networks." Journal of University of Shanghai for Science and Technology 23, no. 07 (July 24, 2021): 1210–15. http://dx.doi.org/10.51201/jusst/21/07294.

Full text

Abstract:

Hot-spots are a problem that comes in the cluster-based routing protocol that employs multi-hop communication due to this problem the energy among the sensor nodes is not balanced. The hot-spots issue requires high overhead and is prone to connectivity issues in the sensor network this can be only possible because of unequal clustering. In this method, we have to act on all the nodes of the sensor network for communication. This process consumes high system energy if the numbers of nodes are very high. To offer guaranteed connectivity, decrease high usage and complexity, a fuzzy logic-based zone divisional method has been proposed in this paper. Use fuzzy logic to create clusters and assign nodes to them to decrease the consumption of energy and the age of the network prolongation. The simulation and results section shows the outperformance of the proposed protocol, where the (LEACH) low-energy adaptive clustering hierarchy, (EAUCF) energy-aware unequal clustering fuzzy,(EAMMH) energy-aware multi-hop multi-path hierarchical, and (TTDFP) two-tier distributed fuzzy logic-based protocol for efficient data aggregation in multi-hop wireless sensor networks algorithms. The proposed algorithm has better results in terms of energy consumption minimization, and prolongation of the network lifetime.

APA, Harvard, Vancouver, ISO, and other styles

9

Wu, Xintong, Shanlin Sun, Yun Li, Zhicheng Tan, Wentao Huang, and Xing Yao. "A Power Control Algorithm Based on Outage Probability Awareness in Vehicular Ad Hoc Networks." Advances in Multimedia 2018 (August 1, 2018): 1–8. http://dx.doi.org/10.1155/2018/8729645.

Full text

Abstract:

This paper addresses the problem of adaptive power control based on outage probability minimization in Vehicular Ad Hoc Networks (VANETs), called a Power Control Algorithm Based on Outage Probability Awareness (PC-OPA). Unlike most of the existing works, our power control method aims at minimizing the outage probability and then is subject to the density of nodes in certain area. To fulfill power control, cumulative interference is assumed to be available at the transmitter of each terminal. The transmitters sent data by maximum power and then get the cumulative interference-aware outage probability. Furthermore, we build the interference model by stochastic geometric theory and then derive the expression between outage probability and cumulative interference. According to the expression, we adjust the transmitter power and optimize the outage probability. Simulation results are provided to demonstrate the effectiveness of the proposed power control strategies. It is shown that the PC-OPA can achieve a significant performance gain in terms of the outage probability and throughputs. Comparing MPC (Maximum Power Control algorithm) and WFPC (Water-Filled Power Control algorithm), the proposed PC-OPA decreased by 23% in terms of the outage probability and increased by 25% in terms of throughputs.

APA, Harvard, Vancouver, ISO, and other styles

10

Mueen, Ahmed, Mohammad Awedh, and Bassam Zafar. "Multi-obstacle aware smart navigation system for visually impaired people in fog connected IoT-cloud environment." Health Informatics Journal 28, no. 3 (July 2022): 146045822211126. http://dx.doi.org/10.1177/14604582221112609.

Full text

Abstract:

Design of smart navigation for visually impaired/blind people is a hindering task. Existing researchers analyzed it in either indoor or outdoor environment and also it’s failed to focus on optimum route selection, latency minimization and multi-obstacle presence. In order to overcome these challenges and to provide precise assistance to visually impaired people, this paper proposes smart navigation system for visually impaired people based on both image and sensor outputs of the smart wearable. The proposed approach involves the upcoming processes: (i) the input query of the visually impaired people (users) is improved by the query processor in order to achieve accurate assistance. (ii) The safest route from source to destination is provided by implementing Environment aware Bald Eagle Search Optimization algorithm in which multiple routes are identified and classified into three different classes from which the safest route is suggested to the users. (iii) The concept of fog computing is leveraged and the optimal fog node is selected in order to minimize the latency. The fog node selection is executed by using Nearest Grey Absolute Decision Making Algorithm based on multiple parameters. (iv) The retrieval of relevant information is performed by means of computing Euclidean distance between the reference and database information. (v) The multi-obstacle detection is carried out by YOLOv3 Tiny in which both the static and dynamic obstacles are classified into small, medium and large obstacles. (vi) The decision upon navigation is provided by implementing Adaptive Asynchronous Advantage Actor-Critic (A3C) algorithm based on fusion of both image and sensor outputs. (vii) Management of heterogeneous is carried out by predicting and pruning the fault data in the sensor output by minimum distance based extended kalman filter for better accuracy and clustering the similar information by implementing Spatial-Temporal Optics Clustering Algorithm to reduce complexity. The proposed model is implemented in NS 3.26 and the results proved that it outperforms other existing works in terms of obstacle detection and task completion time.

APA, Harvard, Vancouver, ISO, and other styles

11

Luo, Fan-Ming, Shengyi Jiang, Yang Yu, ZongZhang Zhang, and Yi-Feng Zhang. "Adapt to Environment Sudden Changes by Learning a Context Sensitive Policy." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (June 28, 2022): 7637–46. http://dx.doi.org/10.1609/aaai.v36i7.20730.

Full text

Abstract:

Dealing with real-world reinforcement learning (RL) tasks, we shall be aware that the environment may have sudden changes. We expect that a robust policy is able to handle such changes and adapt to the new environment rapidly. Context-based meta reinforcement learning aims at learning environment adaptable policies. These methods adopt a context encoder to perceive the environment on-the-fly, following which a contextual policy makes environment adaptive decisions according to the context. However, previous methods show lagged and unstable context extraction, which are hard to handle sudden changes well. This paper proposes an environment sensitive contextual policy learning (ESCP) approach, in order to improve both the sensitivity and the robustness of context encoding. ESCP is composed of three key components: variance minimization that forces a rapid and stable encoding of the environment context, relational matrix determinant maximization that avoids trivial solutions, and a history-truncated recurrent neural network model that avoids old memory interference. We use a grid-world task and 5 locomotion controlling tasks with changing parameters to empirically assess our algorithm. Experiment results show that in environments with both in-distribution and out-of-distribution parameter changes, ESCP can not only better recover the environment encoding, but also adapt more rapidly to the post-change environment (10x faster in the grid-world) while the return performance is kept or improved, compared with state-of-the-art meta RL methods.

APA, Harvard, Vancouver, ISO, and other styles

12

Liu, Ren, Fengmiao Bian, and Xiaoqun Zhang. "Binary Quantized Network Training With Sharpness-Aware Minimization." Journal of Scientific Computing 94, no. 1 (December 11, 2022). http://dx.doi.org/10.1007/s10915-022-02064-7.

Full text

APA, Harvard, Vancouver, ISO, and other styles

13

Abedini, Fereshteh, and Sasan Gooran. "Structure-Aware Color Halftoning with Adaptive Sharpness Control." Journal of Imaging Science and Technology, November 1, 2022, 060405–1. http://dx.doi.org/10.2352/j.imagingsci.technol.2022.66.6.060405.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Xu, Zhengguo, Hengtuo Pan, Wei Ye, Zhuangwei Xu, and Hongkai Wang. "Detection Method of Wheat Rust Based on Transfer Learning and Sharpness‐Aware Minimization." Plant Pathology, October 24, 2022. http://dx.doi.org/10.1111/ppa.13661.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Sukegawa, Shintaro, Futa Tanaka, Keisuke Nakano, Takeshi Hara, Kazumasa Yoshii, Katsusuke Yamashita, Sawako Ono, et al. "Effective deep learning for oral exfoliative cytology classification." Scientific Reports 12, no. 1 (August 2, 2022). http://dx.doi.org/10.1038/s41598-022-17602-4.

Full text

Abstract:

AbstractThe use of sharpness aware minimization (SAM) as an optimizer that achieves high performance for convolutional neural networks (CNNs) is attracting attention in various fields of deep learning. We used deep learning to perform classification diagnosis in oral exfoliative cytology and to analyze performance, using SAM as an optimization algorithm to improve classification accuracy. The whole image of the oral exfoliation cytology slide was cut into tiles and labeled by an oral pathologist. CNN was VGG16, and stochastic gradient descent (SGD) and SAM were used as optimizers. Each was analyzed with and without a learning rate scheduler in 300 epochs. The performance metrics used were accuracy, precision, recall, specificity, F1 score, AUC, and statistical and effect size. All optimizers performed better with the rate scheduler. In particular, the SAM effect size had high accuracy (11.2) and AUC (11.0). SAM had the best performance of all models with a learning rate scheduler. (AUC = 0.9328) SAM tended to suppress overfitting compared to SGD. In oral exfoliation cytology classification, CNNs using SAM rate scheduler showed the highest classification performance. These results suggest that SAM can play an important role in primary screening of the oral cytological diagnostic environment.

APA, Harvard, Vancouver, ISO, and other styles

16

Sukegawa, Shintaro, Futa Tanaka, Takeshi Hara, Kazumasa Yoshii, Katsusuke Yamashita, Keisuke Nakano, Kiyofumi Takabatake, Hotaka Kawai, Hitoshi Nagatsuka, and Yoshihiko Furuki. "Deep learning model for analyzing the relationship between mandibular third molar and inferior alveolar nerve in panoramic radiography." Scientific Reports 12, no. 1 (October 8, 2022). http://dx.doi.org/10.1038/s41598-022-21408-9.

Full text

Abstract:

AbstractIn this study, the accuracy of the positional relationship of the contact between the inferior alveolar canal and mandibular third molar was evaluated using deep learning. In contact analysis, we investigated the diagnostic performance of the presence or absence of contact between the mandibular third molar and inferior alveolar canal. We also evaluated the diagnostic performance of bone continuity diagnosed based on computed tomography as a continuity analysis. A dataset of 1279 images of mandibular third molars from digital radiographs taken at the Department of Oral and Maxillofacial Surgery at a general hospital (2014–2021) was used for the validation. The deep learning models were ResNet50 and ResNet50v2, with stochastic gradient descent and sharpness-aware minimization (SAM) as optimizers. The performance metrics were accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristic curve (AUC). The results indicated that ResNet50v2 using SAM performed excellently in the contact and continuity analyses. The accuracy and AUC were 0.860 and 0.890 for the contact analyses and 0.766 and 0.843 for the continuity analyses. In the contact analysis, SAM and the deep learning model performed effectively. However, in the continuity analysis, none of the deep learning models demonstrated significant classification performance.

APA, Harvard, Vancouver, ISO, and other styles

17

"Energy Aware Relay GAF algorithm for WSN using Improved Conservative schemes." International Journal of Engineering and Advanced Technology 8, no. 6 (August 30, 2019): 1175–78. http://dx.doi.org/10.35940/ijeat.f8359.088619.

Full text

Abstract:

Wireless sensor systems (WSN) is the system of Sensor Nodes (SNs) in which every hub have detecting, correspondence and calculation office. The fundamental impediment of WSN is that SNs have restricted vitality. So the fundamental focal point of research in WSN is to improve the Network Lifetime by falling vitality utilization. A few areas mindful directing convention has been proposed. Geographic Adaptive Fidelity (GAF) is one of the most famous vitality mindful steering conventions. It moderates vitality by recognizing equality between sensors from a steering point of view and after that killing superfluous sensors, while keeping up the availability of the system. Anyway conventional GAF can't achieve the ideal vitality use. It requires progressively number of jumps to transmit information from source to sink.so that it prompts higher bundle delay. The underlying issue of essential GAF is information can be sent in just flat and vertical. The issues which are being worked in this undertaking are minimization of jump check, parcel deferral and separation secured by the bundle postponement steering utilizing vitality mindful Relay GAF calculation Both the conventions are actualized in MATLAB. Investigation and reproduction results show critical enhancements of the projected work contrasting with customary GAF in the part of absolute jump check, arrange lifetime vitality utilization, all out separation secured by the information bundle before achieving the sink, and parcel delay

APA, Harvard, Vancouver, ISO, and other styles

18

Song, Yeong-Hun, Jun-Young Yi, Young Noh, Hyemin Jang, Sang Won Seo, Duk L. Na, and Joon-Kyung Seong. "On the reliability of deep learning-based classification for Alzheimer’s disease: Multi-cohorts, multi-vendors, multi-protocols, and head-to-head validation." Frontiers in Neuroscience 16 (September 7, 2022). http://dx.doi.org/10.3389/fnins.2022.851871.

Full text

Abstract:

Structural changes in the brain due to Alzheimer’s disease dementia (ADD) can be observed through brain T1-weighted magnetic resonance imaging (MRI) images. Many ADD diagnostic studies using brain MRI images have been conducted with machine-learning and deep-learning models. Although reliability is a key in clinical application and applicability of low-resolution MRI (LRMRI) is a key to broad clinical application, both are not sufficiently studied in the deep-learning area. In this study, we developed a 2-dimensional convolutional neural network-based classification model by adopting several methods, such as using instance normalization layer, Mixup, and sharpness aware minimization. To train the model, MRI images from 2,765 cognitively normal individuals and 1,192 patients with ADD from the Samsung medical center cohort were exploited. To assess the reliability of our classification model, we designed external validation in multiple scenarios: (1) multi-cohort validation using four additional cohort datasets including more than 30 different centers in multiple countries, (2) multi-vendor validation using three different MRI vendor subgroups, (3) LRMRI image validation, and finally, (4) head-to-head validation using ten pairs of MRI images from ten individual subjects scanned in two different centers. For multi-cohort validation, we used the MRI images from 739 subjects from the Alzheimer’s Disease Neuroimaging Initiative cohort, 125 subjects from the Dementia Platform of Korea cohort, 234 subjects from the Premier cohort, and 139 subjects from the Gachon University Gil Medical Center. We further assessed classification performance across different vendors and protocols for each dataset. We achieved a mean AUC and classification accuracy of 0.9868 and 0.9482 in 5-fold cross-validation. In external validation, we obtained a comparable AUC of 0.9396 and classification accuracy of 0.8757 to other cross-validation studies in the ADNI cohorts. Furthermore, we observed the possibility of broad clinical application through LRMRI image validation by achieving a mean AUC and classification accuracy of 0.9404 and 0.8765 at cross-validation and AUC and classification accuracy of 0.8749 and 0.8281 at the ADNI cohort external validation.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Adaptive Sharpness Aware Minimization'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles