Academic literature on the topic 'Network Similarity Score (NSS)'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Network Similarity Score (NSS).'
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.
Journal articles on the topic "Network Similarity Score (NSS)"
1
Lever, James, Robert Brkljača, Colin Rix, and Sylvia Urban. "Application of Networking Approaches to Assess the Chemical Diversity, Biogeography, and Pharmaceutical Potential of Verongiida Natural Products." Marine Drugs 19, no. 10 (October 18, 2021): 582. http://dx.doi.org/10.3390/md19100582.
Full textAbstract:
This study provides a review of all isolated natural products (NPs) reported for sponges within the order Verongiida (1960 to May 2020) and includes a comprehensive compilation of their geographic and physico-chemical parameters. Physico-chemical parameters were used in this study to infer pharmacokinetic properties as well as the potential pharmaceutical potential of NPs from this order of marine sponge. In addition, a network analysis for the NPs produced by the Verongiida sponges was applied to systematically explore the chemical space relationships between taxonomy, secondary metabolite and drug score variables, allowing for the identification of differences and correlations within a dataset. The use of scaffold networks as well as bipartite relationship networks provided a platform to explore chemical diversity as well as the use of chemical similarity networks to link pharmacokinetic properties with structural similarity. This study paves the way for future applications of network analysis procedures in the field of natural products for any order or family.
2
Igumnov, Sergey, Konstantin Zbarousky, Pavel Lapanau, Ruslan Popok, and Ekaterina Grinevich. "ALEXITHYMIA AS RISK FACTOR OF THE DEVELOPMENT OF ADDICTIVE BEHAVIOR OF YOUNG PEOPLE IN THE REPUBLIC OF BELARUS." Visuomenės sveikata 28, no. 4 (November 20, 2018): 47–50. http://dx.doi.org/10.5200/sm-hs.2018.049.
Full textAbstract:
A socio-psychological survey and clinical-psychological research were conducted (level of alexithymia; intensity of internet addiction; individual-characterological personality traits; individual style of coping strategies, behavioral patterns and resources of personality) in the cohort of 150 people at the age of 15-24, average age: 18.9±1.64, M:F= 87:63). As a result of the randomization of subjects, 3 groups were detected: themain group (people with traces of developing anaddiction from “new psychoactive substances” (NPS)) (MG, 50 people); a comparison group (people with “non-chemical” forms of addiction (internet addiction) (CG, 50 people) and a reference group (50 people, without addictions and deviant behavior). The research of coping behavior methods, in the category “Search for social support” groups MG and RG significantly differ statistically (probability of passing similarity p = 0.016, t =2.45, df = 147) has shown the significance of asocial network support as in the case of NPS addiction. The total score of the Toronto Alexithymia Scale-26-R showed that people from MG (average number 67.66±8.01) and RG (average number 58.92±8.36) statistically differ significantly, with a probability of passing similarity being p<0.001, t=5.3, df=147. Indicators of expressed alexithymia noticeably prevailed in MG and CG, in comparison with the RG. While researching internet addiction using a subject oriented scale, there was a statistically significant difference between CG and RG. The probability of a passing similarity is p = 0.006, t=2.82, df =147. The received and analyzed study materials are the basis for the development of acombined preventive and rehabilitation program for those with “NPS” addiction and “internet addiction” among teenagers and youth.
3
Bharti, Puja, and Deepti Mittal. "An Ultrasound Image Enhancement Method Using Neutrosophic Similarity Score." Ultrasonic Imaging 42, no. 6 (October 5, 2020): 271–83. http://dx.doi.org/10.1177/0161734620961005.
Full textAbstract:
Ultrasound images, having low contrast and noise, adversely impact in the detection of abnormalities. In view of this, an enhancement method is proposed in this work to reduce noise and improve contrast of ultrasound images. The proposed method is based on scaling with neutrosophic similarity score (NSS), where an image is represented in the neutrosophic domain through three membership subsets T, I, and F denoting the degree of truth, indeterminacy, and falseness, respectively. The NSS measures the belonging degree of pixel to the texture using multi-criteria that is based on intensity, local mean intensity and edge detection. Then, NSS is utilized to extract the enhanced coefficient and this enhanced coefficient is applied to scale the input image. This scaling reflects contrast improvement and denoising effect on ultrasound images. The performance of proposed enhancement method is evaluated on clinical ultrasound images, using both subjective and objective image quality measures. In subjective evaluation, with proposed method, overall best score of 4.3 was obtained and that was 44% higher than the score of original images. These results were also supported by objective measures. The results demonstrated that the proposed method outperformed the other methods in terms of mean brightness preservation, edge preservation, structural similarity, and human perception-based image quality assessment. Thus, the proposed method can be used in computer-aided diagnosis systems and to visually assist radiologists in their interactive-decision-making task.
4
Cai, Xinlu, Yongming Wang, Hanyu Zhou, Jia Huang, Simon S. Y. Lui, Arne Møller, Henry K. F. Mak, Eric F. C. Cheung, and Raymond C. K. Chan. "M158. ASSOCIATIONS OF NEUROLOGICAL SOFT SIGNS AND CEREBELLAR-CEREBRAL FUNCTIONAL CONNECTIVITY IN PATIENTS WITH FIRST-EPISODE SCHIZOPHRENIA AND THEIR UNAFFECTED SIBLINGS." Schizophrenia Bulletin 46, Supplement_1 (April 2020): S196. http://dx.doi.org/10.1093/schbul/sbaa030.470.
Full textAbstract:
Abstract Background Neurological softs signs (NSS) are defined as subtle neurological abnormalities with manifestations of motor coordination, sensory integration and disinhibition. Evidence has suggested NSS as one of the most promising endophenotypes for schizophrenia spectrum disorders. Moreover, accumulating evidence also suggest that NSS may be associated with specific functional connectivity. The present study aimed to examine the cerebellar-cerebral resting-state functional connectivity (rsFC) of NSS in patients with first-episode schizophrenia (FES) and their unaffected siblings (SB). Methods We administered the abridge version of the Cambridge Neurological Inventory (CNI) to 51 FES patients, 20 unaffected SB, and 50 healthy controls (HC) to assess the severity of NSS. All the participants also underwent a resting-state functional magnetic resonance imaging (MRI) scan. Ten regions of interest (ROIs) in the cerebellum were selected to represent cerebellar motor network (MN) and cerebellar executive control network (EN), which corresponded to the “sensorimotor-cognitive” dichotomy of NSS. rsFC between each ROI and the whole brain voxels were constructed, and the linear regression analysis was conducted to examine the cerebellar-cerebral rsFC patterns of NSS in each group. Results Regarding the cerebellar MN, there were positive correlations observed between the rsFC of the cerebellar MN with the default mode network (DMN) and NSS in FES patients group (CNI total score and the motor coordination subscale) and the SB group (CNI total score and the motor coordination and sensory integration subscales). The rsFC of the cerebellar MN and the sensorimotor network were significantly and positively correlated with NSS (CNI total score and the motor coordination and sensory integration subscales) in the SB group. Regarding the cerebellar EN, we found that both the FES and the SB groups exhibited significantly negative correlations between NSS (CNI total score and the motor coordination subscale) and the rsFC of the cerebellar EN with the DMN. Moreover, the rsFC between the cerebellar EN and the sensorimotor network was positively correlated with NSS (CNI total score and the motor coordination and disinhibition subscales) in the SB group. Discussion We found inverse correlations between NSS and the rsFC of the cerebellar EN/MN and the DMN in both FES patients and their unaffected SB, suggesting that altered cerebellar-cerebral rsFC between these networks is correlated with the NSS. Moreover, the SB group exhibited a unique correlational pattern that NSS were correlated with the cerebellar-sensorimotor network rsFC, suggesting that such a network connectivity may serve as a potential biomarker for schizophrenia.
5
Luo, Jiasai, Sen Zhou, Yiming Li, Yu Pang, Zhengwen Wang, Yi Lu, Huiqian Wang, and Tong Bai. "Polarization Orientation Method Based on Remote Sensing Image in Cloudy Weather." Remote Sensing 15, no. 5 (February 22, 2023): 1225. http://dx.doi.org/10.3390/rs15051225.
Full textAbstract:
Autonomous navigation technology is a core technology for intelligent operation, allowing the vehicles to perform tasks without relying on external information, which effectively improves the concealability and reliability. In this paper, based on the previous research on the bionic compound eye, a multi-channel camera array with different polarization degrees was used to construct the atmospheric polarization state measurement platform. A polarization trough threshold segmentation algorithm was applied to study the distribution characteristics and characterization methods of polarization states in atmospheric remote sensing images. In the extracted polarization feature map, the tilting suggestion box was obtained based on the multi-direction window extraction network (similarity-based region proposal networks, SRPN) and the rotation of the suggestion box (Rotation Region of interests, RRoIs). Fast Region Convolutional Neural Networks (RCNN) was used to screen the suggestion boxes, and the Non-maximum suppression (NMS) method was used to select the angle, corresponding to the label of the suggestion box with the highest score, as the solar meridian azimuth in the vehicle coordinate system. The azimuth angle of the solar meridian in the atmospheric coordinate system can be calculated by the astronomical formula. Finally, the final heading angle can be obtained according to the conversion relationship between the coordinate systems. By fitting the measured data based on the least Square method, the slope K value is −1.062, RMSE (Root Mean Square Error) is 6.984, and the determination coefficient R-Square is 0.9968. Experimental results prove the effectiveness of the proposed algorithm, and this study can construct an autonomous navigation algorithm with high concealment and precision, providing a new research idea for the research of autonomous navigation technology.
6
Tuli, Shikhar, Bhishma Dedhia, Shreshth Tuli, and Niraj K. Jha. "FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?" Journal of Artificial Intelligence Research 77 (May 6, 2023): 39–70. http://dx.doi.org/10.1613/jair.1.13942.
Full textAbstract:
The existence of a plethora of language models makes the problem of selecting the best one for a custom task challenging. Most state-of-the-art methods leverage transformer-based models (e.g., BERT) or their variants. However, training such models and exploring their hyperparameter space is computationally expensive. Prior work proposes several neural architecture search (NAS) methods that employ performance predictors (e.g., surrogate models) to address this issue; however, such works limit analysis to homogeneous models that use fixed dimensionality throughout the network. This leads to sub-optimal architectures. To address this limitation, we propose a suite of heterogeneous and flexible models, namely FlexiBERT, that have varied encoder layers with a diverse set of possible operations and different hidden dimensions. For better-posed surrogate modeling in this expanded design space, we propose a new graph-similarity-based embedding scheme. We also propose a novel NAS policy, called BOSHNAS, that leverages this new scheme, Bayesian modeling, and second-order optimization, to quickly train and use a neural surrogate model to converge to the optimal architecture. A comprehensive set of experiments shows that the proposed policy, when applied to the FlexiBERT design space, pushes the performance frontier upwards compared to traditional models. FlexiBERT-Mini, one of our proposed models, has 3% fewer parameters than BERT-Mini and achieves 8.9% higher GLUE score. A FlexiBERT model with equivalent performance as the best homogeneous model has 2.6× smaller size. FlexiBERT-Large, another proposed model, attains state-of-the-art results, outperforming the baseline models by at least 5.7% on the GLUE benchmark.
7
Ding, Jiujie, Jiahuan Zhang, Zongqian Zhan, Xiaofang Tang, and Xin Wang. "A Precision Efficient Method for Collapsed Building Detection in Post-Earthquake UAV Images Based on the Improved NMS Algorithm and Faster R-CNN." Remote Sensing 14, no. 3 (January 29, 2022): 663. http://dx.doi.org/10.3390/rs14030663.
Full textAbstract:
The results of collapsed building detection act as an important reference for damage assessment after an earthquake, which is crucial for governments in order to efficiently determine the affected area and execute emergency rescue. For this task, unmanned aerial vehicle (UAV) images are often used as the data sources due to the advantages of high flexibility regarding data acquisition time and flying requirements and high resolution. However, collapsed buildings are typically distributed in both connected and independent pieces and with arbitrary shapes, and these are generally more obvious in the UAV images with high resolution; therefore, the corresponding detection is restricted by using conventional convolutional neural networks (CNN) and the detection results are difficult to evaluate. In this work, based on faster region-based convolutional neural network (Faster R-CNN), deformable convolution was used to improve the adaptability to the arbitrarily shaped collapsed buildings. In addition, inspired by the idea of pixelwise semantic segmentation, in contrast to the intersection over union (IoU), a new method which estimates the intersected proportion of objects (IPO) is proposed to describe the degree of the intersection of bounding boxes, leading to two improvements: first, the traditional non-maximum suppression (NMS) algorithm is improved by integration with the IPO to effectively suppress the redundant bounding boxes; second, the IPO is utilized as a new indicator to determine positive and negative bounding boxes, and is introduced as a new strategy for precision and recall estimation, which can be considered a more reasonable measurement of the degree of similarity between the detected bounding boxes and ground truth bounding boxes. Experiments show that compared with other models, our work can obtain better precision and recall for detecting collapsed buildings for which an F1 score of 0.787 was achieved, and the evaluation results from the suggested IPO are qualitatively closer to the ground truth. In conclusion, the improved NMS with the IPO and Faster R-CNN in this paper is feasible and efficient for the detection of collapsed buildings in UAV images, and the suggested IPO strategy is more suitable for the corresponding detection result’s evaluation.
8
Galphat, Yugchhaya. "TD score: Time Aware Domain Similarity based Link Prediction." International Journal for Research in Applied Science and Engineering Technology 10, no. 5 (May 31, 2022): 3621–27. http://dx.doi.org/10.22214/ijraset.2022.43176.
Full textAbstract:
Abstract: Online Social Network has gained immense traction of users in past decade. Link prediction across social networks has become a new exploration area for researchers, where existing links are investigated and new links are anticipated among billions of online customers. Majority of work in this area focusses on exploring the current status of a particular network at a specific time, without exploring the behavior of the network links as time goes by. Only a Small amount of work has been performed with the consideration of temporal aspect of network. As the interests and interactions of user change over time, the links among nodes become weaker or noisy which affects the prediction accuracy. This paper intend to explore a new integrated temporal method TD score which includes time stamp of interaction and domain similarity information for each pair of unconnected nodes to predict links. Experiment over co-authorship network reveals that link prediction covering time aware domain similarity is effective and efficient approach than traditional ones. Keywords: Co-authorship network; link prediction; node similarity; global feature; temporal feature; domain similarity.
9
Ghosh, Sambit, Vasundhara Gadiyaram, and Saraswathi Vishveshwara. "Validation of protein structure models using network similarity score." Proteins: Structure, Function, and Bioinformatics 85, no. 9 (June 27, 2017): 1759–76. http://dx.doi.org/10.1002/prot.25332.
Full text
10
Gupta, Anand Kumar, and Neetu Sardana. "Performance Analysis of Naïve Bayes Classifier Over Similarity Score-Based Techniques for Missing Link Prediction in Ego Networks." Journal of Information Technology Research 14, no. 1 (January 2021): 110–22. http://dx.doi.org/10.4018/jitr.2021010107.
Full textDissertations / Theses on the topic "Network Similarity Score (NSS)"
1
Mebratu, Ashagrie Kefyalew. "Does religious similarity influence the direction of trade? : Evidence from US bilateral trade with other 168 countries." Thesis, Södertörns högskola, Institutionen för samhällsvetenskaper, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:sh:diva-17478.
Full textAbstract:
Despite interest in the influence of religion on economic activity by early economists like Adam Smith, modern economists have done little research on the subject. In light of the apparent religious fervour in many parts of the global economy, economists' seeming lack of interest in studying how religious cultures enhance or retard the globalization of economic activity is especially surprising. In general, trade theories have given less weight towards the reason for trade explanation on demand side. As a contrary to H-O theory Linder had proposed a theoretically sound and empirically consistent trade theory with a new claim for the reasons why countries trade on the demand side. To fill this gap, I use international survey data on religiosity for a broad panel of countries trading with US to investigate the effects of church attendance and religious beliefs on trade. The beliefs are, in turn, the principal output of the religion sector, and the believer alignment to a specific denomination measures the inputs to this sector. Hence, I used an extended gravity model of international trade to control for a variety of factors that determine trade, and I used two regression methods, OLS and WLS, to exploit the model to its fullest. I find that the sharing of same religious cultures by people in different countries has a significantly positive influence on bilateral trade, all other things being equal. These results accord with a perspective in which religious beliefs influence individual traits that enhance trade and economic performance in general. And my attempt to magnify religion as a means to trade is only a derivation of Linder’s overlapping demand theory.
2
Gadiyaram, Vasundhara. "Graph Spectral Methods for Analysis of Protein Structures." Thesis, 2017. http://etd.iisc.ac.in/handle/2005/4280.
Full textAbstract:
Network representation of protein structures is an information-rich mode of examining protein structure, dynamics and its interactions with biomolecules. Graph spectral methods are extremely useful and powerful in analysing complex networks. This thesis is concerned with development of graph spectral methods for analysing networks and applying them to protein structure analysis. Some of the key problems of network science that are addressed here are network similarity assessment and identification of key components in networks. A new network similarity score (NSS) has been developed and has shown to be useful in comparing different networks considering both local and global changes. The applicability of this scoring scheme as a protein structure model validation tool has been demonstrated using models from various sources such as CASP experiments, mutant structures and molecular simulation trajectories. Also, a method to identify nodes and edges crucial in the network has been developed using NSS and perturbation analysis.
Although the methods developed in the thesis are inspired by the topology and functions related to protein structures, they are general and are applicable to problems in many other disciplines.
3
Dighe, Anasuya. "Studies on Dynamic Plasticity of Ligand Binding Sites in Proteins." Thesis, 2017. http://etd.iisc.ac.in/handle/2005/4236.
Full textAbstract:
Molecular recognition between proteins and their associated ligands constitutes ligand-induced protein rewiring thereby enabling the formation of a stable protein-ligand complex. The studies presented in this thesis address the conformational plasticity inherent to proteins by virtue of which they adapt to diverse ligands and orchestrate complex biological processes like signal transduction, transcription and protein-protein interaction. Adopting network theory based formalisms for understanding protein-ligand associations involve deconstructing the three-dimensional structure of a protein in terms of nodes and edges. With this view, Protein Structure Networks (PSNs) of ligand-bound complexes are studied by considering their side-chain non-covalent interactions. Agonist and antagonist-bound G-Protein Coupled Receptors (GPCRs) are investigated to gain mechanistic insights into allostery and its role in signal transduction. The degree of similarity between PSNs of these complexes is quantified by means of Network Similarity Score (NSS). The physical nature of these networks is inspected by subjecting them to perturbations and major players in maintaining the stability of such networks are identified. Residue-wise groupings (at backbone and side-chain level) are obtained by applying graph spectral methods.
All-atom Molecular Dynamics (MD) simulations are carried out to gain a better understanding of protein-ligand binding by analysing conformational ensembles of these complexes. In this scenario, two members from a highly versatile ligand-inducible transcription factor superfamily, i.e., Nuclear Receptors (NR) are studied, that are known to exhibit extremes of ligand binding behavior ranging from promiscuity to specificity.
Diverse ligands are known to bind to proteins and the overall nature of their binding site is investigated. In particular, similarities among binding sites of diverse proteins are analysed by using PocketMatch. Percolation of these similarities to regions surrounding the binding site is reported and examples depicting this extended similarity are discussed.
Overall, studies presented in this thesis provide a structural perspective into the adaptability of proteins for recognizing diverse ligands and undergoing local or global re-organizations in their framework to regulate complex biological processes.
Book chapters on the topic "Network Similarity Score (NSS)"
1
Xie, Bo, and Long Chen. "Automatic Scoring Model of Subjective Questions Based Text Similarity Fusion Model." In Proceeding of 2021 International Conference on Wireless Communications, Networking and Applications, 586–99. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-2456-9_60.
Full textAbstract:
AbstractAI In this era, scene based translation and intelligent word segmentation are not new technologies. However, there is still no good solution for long and complex Chinese semantic analysis. The subjective question scoring still relies on the teacher's manual marking. However, there are a large number of examinations, and the manual marking work is huge. At present, the labor cost is getting higher and higher, the traditional manual marking method can't meet the demand The demand for automatic marking is increasingly strong in modern society. At present, the automatic marking technology of objective questions has been very mature and widely used. However, by reasons of the complexity and the difficulty of natural language processing technology in Chinese text, there are still many shortcomings in subjective questions marking, such as not considering the impact of semantics, word order and other issues on scoring accuracy. The automatic scoring technology of subjective questions is a complex technology, involving pattern recognition, machine learning, natural language processing and other technologies. Good results have been seen in the calculation method-based deep learning and machine learning. The rapid development of NLP technology has brought a new breakthrough for subjective question scoring. We integrate two deep learning models based on the Siamese Network through bagging to ensure the accuracy of the results, the text similarity matching model based on the birth networks and the score point recognition model based on the named entity recognition method respectively. Combining with the framework of deep learning, we use the simulated manual scoring method to extract and match the score point sequence of students’ answers with standard answers. The score recognition model effectively improves the efficiency of model calculation and long text keyword matching. The loss value of the final training score recognition model is about 0.9, and the accuracy is 80.54%. The accuracy of the training text similarity matching model is 86.99%, and the fusion model is single. The scoring time is less than 0.8s, and the accuracy is 83.43%.
2
Banu, Syeda Furruka, Md Mostafa Kamal Sarker, Mohamed Abdel-Nasser, Hatem A. Rashwan, and Domenec Puig. "WEU-Net: A Weight Excitation U-Net for Lung Nodule Segmentation." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2021. http://dx.doi.org/10.3233/faia210154.
Full textAbstract:
Lung cancer is a dangerous non-communicable disease attacking both women and men and every year it causes thousands of deaths worldwide. Accurate lung nodule segmentation in computed tomography (CT) images can help detect lung cancer early. Since there are different locations and indistinguishable shapes of lung nodules in CT images, the accuracy of the existing automated lung nodule segmentation methods still needs further enhancements. In an attempt towards overcoming the above-mentioned challenges, this paper presents WEU-Net; an end-to-end encoder-decoder deep learning approach to accurately segment lung nodules in CT images. Specifically, we use a U-Net network as a baseline and propose a weight excitation (WE) mechanism to encourage the deep learning network to learn lung nodule-relevant contextual features during the training stage. WEU-Net was trained and validated on a publicly available CT images dataset called LIDC-IDRI. The experimental results demonstrated that WEU-Net achieved a Dice score of 82.83% and a Jaccard similarity coefficient of 70.55%.
3
Ung, Hieu Trung, Huy Quang Ung, Trung T. Nguyen, and Binh T. Nguyen. "An Efficient Insect Pest Classification Using Multiple Convolutional Neural Network Based Models." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2022. http://dx.doi.org/10.3233/faia220287.
Full textAbstract:
Accurate insect pest recognition is significant to protect the crop or take the early treatment on the infected yield, and it helps reduce the loss for the agriculture economy. Designing an automatic pest recognition system is necessary as manual recognition is slow, time-consuming, and expensive. The Image-based pest classifier using the traditional computer vision method is not efficient due to the complexity. Insect pest classification is difficult because of various kinds, scales, shapes, complex backgrounds in the field, and high appearance similarity among insect species. With the rapid development of deep learning technology, the CNN-based method is the best way to develop a fast and accurate insect pest classifier. We present different convolutional neural network-based models for solving challenges in the insect pest recognition problem, including attention, feature pyramid, and fine-grained models. We evaluate our methods on two public datasets: the large-scale insect pest dataset, the IP102 benchmark dataset, and a smaller dataset, namely D0 in terms of the macro-average precision (MPre), the macro-average recall (MRec), the macro-average F1- score (MF1), the accuracy (Acc), and the geometric mean (GM). The experimental results show that combining these convolutional neural network-based models can better perform than the state-of-the-art methods on these two datasets. For instance, the highest accuracy we obtained on IP102 and D0 is 72.91% and 99.89%, respectively, bypassing the corresponding state-of-the-art accuracy: 67.1% (IP102) and 98.8% (D0). We also publish our codes for contributing to the current research related to the insect pest classification problem.
4
Oliveira, Rosinei, Ádamo L. Santana, João C. W. A. Costa, Carlos R. L. Frances, Elisangela Aguiar, Paulo Bezerra, Allan Costa, Eduardo Cerqueira, and Antônio J. G. Abelém. "Recent Advances and Challenges in Wireless QoE-Aware Multimedia Streaming Systems." In Advances in Multimedia and Interactive Technologies, 224–43. IGI Global, 2012. http://dx.doi.org/10.4018/978-1-61350-144-3.ch011.
Full textAbstract:
It is expected that multimedia applications will be the most abundant application in the Internet and thousands of new wireless and mobile users will produce and share multimedia streaming content ubiquitously. In this multimedia-aware system, it is important to assure the end-to-end quality level support for video and voice applications in wireless systems. Traditional Quality of Service techniques assure the delivery of those services with packet differentiation assurance and indicate the impact of multimedia traffic only on the network performance; however, they do not reflect the user’s perception. Recent advances in multimedia are exploring new Quality of Experience approaches and including metrics and control schemes in wireless networking systems in order to increase the user´s satisfaction and optimize network resources. Operations based on Quality of Experience can be used as an indicator of how a networking environment meets the end-user’s needs and new assessment and packet control approaches are still important challenges. This chapter presents an overview of the most recent advances and challenges in assessment and traffic conditioner procedures for wireless multimedia streaming systems. In addition, an intelligent packet dropper mechanism for IEEE 802.11e systems is proposed and evaluated by using the Network Simulator 2, real video sequences and Evalvid tool. The benefit and the impact of the proposed solution is evaluated by using well-know objective and subjective Quality of Experience metrics, namely, Peak Signal-to-Noise Ratio, Video Quality Metric, Structural Similarity Index and Mean Option Score.
Conference papers on the topic "Network Similarity Score (NSS)"
1
Belkhirat, Ahmed, Abdelghani Bouras, and Abdelkader Belkhir. "A New Similarity Measure for the Anomaly Intrusion Detection." In 2009 Third International Conference on Network and System Security. IEEE, 2009. http://dx.doi.org/10.1109/nss.2009.20.
Full text
2
Bonti, Alessio, Ming Li, and Wen Shi. "Improving P2P IPTV random peers search through user similarity." In 2011 5th International Conference on Network and System Security (NSS). IEEE, 2011. http://dx.doi.org/10.1109/icnss.2011.6059970.
Full text
3
Jin, Di, Luzhi Wang, Yizhen Zheng, Xiang Li, Fei Jiang, Wei Lin, and Shirui Pan. "CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning." In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/292.
Full textAbstract:
Graph similarity learning refers to calculating the similarity score between two graphs, which is required in many realistic applications, such as visual tracking, graph classification, and collaborative filtering. As most of the existing graph neural networks yield effective graph representations of a single graph, little effort has been made for jointly learning two graph representations and calculating their similarity score. In addition, existing unsupervised graph similarity learning methods are mainly clustering-based, which ignores the valuable information embodied in graph pairs. To this end, we propose a contrastive graph matching network (CGMN) for self-supervised graph similarity learning in order to calculate the similarity between any two input graph objects. Specifically, we generate two augmented views for each graph in a pair respectively. Then, we employ two strategies, namely cross-view interaction and cross-graph interaction, for effective node representation learning. The former is resorted to strengthen the consistency of node representations in two views. The latter is utilized to identify node differences between different graphs. Finally, we transform node representations into graph-level representations via pooling operations for graph similarity computation. We have evaluated CGMN on eight real-world datasets, and the experiment results show that the proposed new approach is superior to the state-of-the-art methods in graph similarity learning downstream tasks.
4
Maji, Subhadeep, Rohan Kumar, Manish Bansal, Kalyani Roy, and Pawan Goyal. "Logic Constrained Pointer Networks for Interpretable Textual Similarity." In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. California: International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/333.
Full textAbstract:
Systematically discovering semantic relationships in text is an important and extensively studied area in Natural Language Processing, with various tasks such as entailment, semantic similarity, etc. Decomposability of sentence-level scores via subsequence alignments has been proposed as a way to make models more interpretable. We study the problem of aligning components of sentences leading to an interpretable model for semantic textual similarity. In this paper, we introduce a novel pointer network based model with a sentinel gating function to align constituent chunks, which are represented using BERT. We improve this base model with a loss function to equally penalize misalignments in both sentences, ensuring the alignments are bidirectional. Finally, to guide the network with structured external knowledge, we introduce first-order logic constraints based on ConceptNet and syntactic knowledge. The model achieves an F1 score of 97.73 and 96.32 on the benchmark SemEval datasets for the chunk alignment task, showing large improvements over the existing solutions. Source code is available at https://github.com/manishb89/interpretable_sentence_similarity
5
Guo, Yuchen, Guiguang Ding, Jungong Han, Sicheng Zhao, and Bin Wang. "Implicit Non-linear Similarity Scoring for Recognizing Unseen Classes." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/680.
Full textAbstract:
Recognizing unseen classes is an important task for real-world applications, due to: 1) it is common that some classes in reality have no labeled image exemplar for training; and 2) novel classes emerge rapidly. Recently, to address this task many zero-shot learning (ZSL) approaches have been proposed where explicit linear scores, like inner product score, are employed to measure the similarity between a class and an image. We argue that explicit linear scoring (ELS) seems too weak to capture complicated image-class correspondence. We propose a simple yet effective framework, called Implicit Non-linear Similarity Scoring (ICINESS). In particular, we train a scoring network which uses image and class features as input, fuses them by hidden layers, and outputs the similarity. Based on the universal approximation theorem, it can approximate the true similarity function between images and classes if a proper structure is used in an implicit non-linear way, which is more flexible and powerful. With ICINESS framework, we implement ZSL algorithms by shallow and deep networks, which yield consistently superior results.
6
Liew, Alison Shu Lien, and Khai Yin Lim. "Gesture Recognition-Malaysian Sign Language Recognition with Convolutional Neural Network." In International Conference on Digital Transformation and Applications (ICDXA 2020). Tunku Abdul Rahman University College, 2020. http://dx.doi.org/10.56453/icdxa.2020.1010.
Full textAbstract:
Sign language is a communication medium for the deaf and vocally impaired. However, this language is not practised in public due to the deaf community being a minority and it takes time to learn and skilled manpower to assist the deaf in public interaction. Thus, this study aims to produce a Malaysian Sign Language Recognition (MSLR) application to recognise MSL alphabets to help normal people communicate with the deaf. The proposed work involves a few stages that consist of background subtraction to detect the moving hand, skin segmentation based on skin tones using YCbCr (Luminance, Chrominance) colour space for robustness in illumination and a 2D Convolutional Neural Network (CNN) model for feature extraction and classification of 24 alphabets. As MSL alphabets are similar to American Sign Language (ASL) alphabets, the ASL FingerSpelling Dataset from the University of Surrey’s Center for Vision, Speech and Signal Processing is used for model training and testing. Evaluation criteria include micro averages in Precision, Recall and F1-Score. The test accuracy is 79.54% with misclassifications on letters such as ‘E’ and ‘Q’ due to the signing orientation and similarity in finger articulation. Keywords: 2D CNN, Computer Vision, Fingerspelling, Machine Learning, Malaysian Sign Language Recognition
7
Park, David Keetae, Seungjoo Yoo, Hyojin Bahng, Jaegul Choo, and Noseong Park. "MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/122.
Full textAbstract:
Recently, generative adversarial networks (GANs) have shown promising performance in generating realistic images. However, they often struggle in learning complex underlying modalities in a given dataset, resulting in poor-quality generated images. To mitigate this problem, we present a novel approach called mixture of experts GAN (MEGAN), an ensemble approach of multiple generator networks. Each generator network in MEGAN specializes in generating images with a particular subset of modalities, e.g., an image class. Instead of incorporating a separate step of handcrafted clustering of multiple modalities, our proposed model is trained through an end-to-end learning of multiple generators via gating networks, which is responsible for choosing the appropriate generator network for a given condition. We adopt the categorical reparameterization trick for a categorical decision to be made in selecting a generator while maintaining the flow of the gradients. We demonstrate that individual generators learn different and salient subparts of the data and achieve a multiscale structural similarity (MS-SSIM) score of 0.2470 for CelebA and a competitive unsupervised inception score of 8.33 in CIFAR-10.
8
Gupta, Aman, and Yadul Raghav. "Deep Learning Roles based Approach to Link Prediction in Networks." In 9th International Conference on Natural Language Processing (NLP 2020). AIRCC Publishing Corporation, 2020. http://dx.doi.org/10.5121/csit.2020.101416.
Full textAbstract:
The problem of predicting links has gained much attention in recent years due to its vast application in various domains such as sociology, network analysis, information science, etc. Many methods have been proposed for link prediction such as RA, AA, CCLP, etc. These methods required hand-crafted structural features to calculate the similarity scores between a pair of nodes in a network. Some methods use local structural information while others use global information of a graph. These methods do not tell which properties are better than others. With an in-depth analysis of these methods, we understand that one way to overcome this problem is to consider network structure and node attribute information to capture the discriminative features for link prediction tasks. We proposed a deep learning Autoencoder based Link Prediction (ALP) architecture for the latent representation of a graph, unified with non-negative matrix factorization to automatically determine the underlying roles in a network, after that assigning a mixed-membership of these roles to each node in the network. The idea is to transfer these roles as a feature vector for the link prediction task in the network. Further, cosine similarity is applied after getting the required features to compute the pairwise similarity score between the nodes. We present the performance of the algorithm on the real-world datasets, where it gives the competitive result compared to other algorithms.
9
Jiang, Haiyun, Li Cui, Zhe Xu, Deqing Yang, Jindong Chen, Chenguang Li, Jingping Liu, et al. "Relation Extraction Using Supervision from Topic Knowledge of Relation Labels." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/698.
Full textAbstract:
Explicitly exploring the semantics of a relation is significant for high-accuracy relation extraction, which is, however, not fully studied in previous work. In this paper, we mine the topic knowledge of a relation to explicitly represent the semantics of this relation, and model relation extraction as a matching problem. That is, the matching score between a sentence and a candidate relation is predicted for an entity pair. To this end, we propose a deep matching network to precisely model the semantic similarity between a sentence-relation pair. Besides, the topic knowledge also allows us to derive the importance information of samples as well as two knowledge-guided negative sampling strategies in the training process. We conduct extensive experiments to evaluate the proposed framework and observe improvements in AUC of 11.5% and max F1 of 5.4% over the baselines with state-of-the-art performance.
10
Edwards, Kristen M., Vaishnavi L. Addala, and Faez Ahmed. "Design Form and Function Prediction From a Single Image." In ASME 2021 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. American Society of Mechanical Engineers, 2021. http://dx.doi.org/10.1115/detc2021-71853.
Full textAbstract:
Abstract Estimating the form and functional performance of a design in the early stages can be crucial for a designer for effective ideation Humans have an innate ability to guess the size, shape, and type of a design from a single view. The brain fills in the unknowns in a fraction of a second. However, humans may struggle with estimating the performance of designs in the early stages of the design process without making prototypes or doing back-of-the-envelope calculations. In contrast, machines need information about the full 3D model of a design to understand its structure. Machines can estimate the performance using pre-defined rules, expensive numerical simulations, or machine learning models. In this paper, we show how information about the form and functional performance of a design can be estimated from a single image using machine learning methods. Specifically, we leverage the image-to-image translation method to predict multiple projections of an image-based design. We then train deep neural network models on the predicted projections to provide estimates of design performance. We demonstrate the effectiveness of our method by predicting the aerodynamic performance from images of aircraft models. To estimate ground truth aero-dynamic performance, we run CFD simulations for 4045 3D aircraft models from the ShapeNet dataset and use their lift-to-drag ratio as the performance metric. Our results show that single images do carry information for both form and functional performance. From a single image, we are able to produce six additional images of a design in different orientations, with an average Structural Similarity Index score of 0.872. We also find image-translation methods provide a promising direction in estimating the performance of design. Using multiple images of a design (gathered through image-translation) to predict design performance yields a recall value of 47%, which is 14% higher than a base guess, and 3% higher than using a single image. Our work identifies the potential and provides a framework for using a single image to predict the form and functional performance of a design during the early-stage design process. Our code and additional information about our work are available at http://decode.mit.edu/projects/formfunction/.
Reports on the topic "Network Similarity Score (NSS)"
1
Wilson, A. M., and M. C. Kelman. Assessing the relative threats from Canadian volcanoes. Natural Resources Canada/CMSS/Information Management, 2021. http://dx.doi.org/10.4095/328950.
Full textAbstract:
This report presents an analysis of the threat posed by active volcanoes in Canada and outlines directives to bring Canadian volcano monitoring and research into alignment with global best practices. We analyse 28 Canadian volcanoes in terms of their relative threat to people, aviation and infrastructure. The methodology we apply to assess volcanic threat was developed by the United States Geological Survey (USGS) as part of the 2005 National Volcano Early Warning System (NVEWS). Each volcano is scored on a number of hazard and exposure factors, producing an overall threat score. The overall threat scores are then assigned to five threat categories ranging from Very Low to Very High. We adjusted the methodology slightly to better suit Canadian volcano conditions by adding an additional knowledge uncertainty score; this does not affect the threat scoring or ranking. Our threat assessment places two volcanoes into the Very High threat category (Mt. Meager and Mt. Garibaldi). Three Canadian volcanoes score in the High threat category (Mt. Cayley, Mt. Price and Mt. Edziza) and two volcanoes score in the Moderate threat category (the Nass River group and Mt. Silverthrone). We compare the ranked Canadian volcanoes to similarly scored volcanoes in the USA and assess the current levels of volcano monitoring against internationally recognised monitoring strategies. We find that even the most thoroughly-studied volcano in Canada (Mt. Meager) falls significantly short of the recommended monitoring level (Mt. Meager is currently monitored at a level commensurate with a Very Low threat edifice, according to NVEWS recommendations). All other Canadian volcanoes are unmonitored (other than falling within a regional seismic network emplaced to monitor tectonic earthquakes). Based on the relative threat and scientific uncertainty surrounding some Canadian volcanoes, we outline five strategies to improve volcano monitoring in Canada and lower the uncertainty about eruption style and frequency: installation of real-time seismic stations at all Very High and High threat volcanoes, comprehensive lithofacies studies at Mt. Garibaldi in order to reduce uncertainty surrounding the frequency and style of volcanism, hazard mapping at Mt. Garibaldi and Mt. Cayley and publication of existing hazard analyses and mapping for Mt. Meager as a comprehensive hazard map, regular satellite-based ground deformation monitoring at all Very High to Moderate threat edifices, and, finally, installation of a landslide detection and alerting system at Mt. Meager.
2
Wilson, A. M., and M. C. Kelman. Assessing the relative threats from Canadian volcanoes. Natural Resources Canada/CMSS/Information Management, 2021. http://dx.doi.org/10.4095/328950.
Full textAbstract:
This report presents an analysis of the threat posed by active volcanoes in Canada and outlines directives to bring Canadian volcano monitoring and research into alignment with global best practices. We analyse 28 Canadian volcanoes in terms of their relative threat to people, aviation and infrastructure. The methodology we apply to assess volcanic threat was developed by the United States Geological Survey (USGS) as part of the 2005 National Volcano Early Warning System (NVEWS). Each volcano is scored on a number of hazard and exposure factors, producing an overall threat score. The overall threat scores are then assigned to five threat categories ranging from Very Low to Very High. We adjusted the methodology slightly to better suit Canadian volcano conditions by adding an additional knowledge uncertainty score; this does not affect the threat scoring or ranking. Our threat assessment places two volcanoes into the Very High threat category (Mt. Meager and Mt. Garibaldi). Three Canadian volcanoes score in the High threat category (Mt. Cayley, Mt. Price and Mt. Edziza) and two volcanoes score in the Moderate threat category (the Nass River group and Mt. Silverthrone). We compare the ranked Canadian volcanoes to similarly scored volcanoes in the USA and assess the current levels of volcano monitoring against internationally recognised monitoring strategies. We find that even the most thoroughly-studied volcano in Canada (Mt. Meager) falls significantly short of the recommended monitoring level (Mt. Meager is currently monitored at a level commensurate with a Very Low threat edifice, according to NVEWS recommendations). All other Canadian volcanoes are unmonitored (other than falling within a regional seismic network emplaced to monitor tectonic earthquakes). Based on the relative threat and scientific uncertainty surrounding some Canadian volcanoes, we outline five strategies to improve volcano monitoring in Canada and lower the uncertainty about eruption style and frequency: installation of real-time seismic stations at all Very High and High threat volcanoes, comprehensive lithofacies studies at Mt. Garibaldi in order to reduce uncertainty surrounding the frequency and style of volcanism, hazard mapping at Mt. Garibaldi and Mt. Cayley and publication of existing hazard analyses and mapping for Mt. Meager as a comprehensive hazard map, regular satellite-based ground deformation monitoring at all Very High to Moderate threat edifices, and, finally, installation of a landslide detection and alerting system at Mt. Meager.
3
Griffin, Andrew, Sean Griffin, Kristofer Lasko, Megan Maloney, S. Blundell, Michael Collins, and Nicole Wayant. Evaluation of automated feature extraction algorithms using high-resolution satellite imagery across a rural-urban gradient in two unique cities in developing countries. Engineer Research and Development Center (U.S.), April 2021. http://dx.doi.org/10.21079/11681/40182.
Full textAbstract:
Feature extraction algorithms are routinely leveraged to extract building footprints and road networks into vector format. When used in conjunction with high resolution remotely sensed imagery, machine learning enables the automation of such feature extraction workflows. However, many of the feature extraction algorithms currently available have not been thoroughly evaluated in a scientific manner within complex terrain such as the cities of developing countries. This report details the performance of three automated feature extraction (AFE) datasets: Ecopia, Tier 1, and Tier 2, at extracting building footprints and roads from high resolution satellite imagery as compared to manual digitization of the same areas. To avoid environmental bias, this assessment was done in two different regions of the world: Maracay, Venezuela and Niamey, Niger. High, medium, and low urban density sites are compared between regions. We quantify the accuracy of the data and time needed to correct the three AFE datasets against hand digitized reference data across ninety tiles in each city, selected by stratified random sampling. Within each tile, the reference data was compared against the three AFE datasets, both before and after analyst editing, using the accuracy assessment metrics of Intersection over Union and F1 Score for buildings and roads, as well as Average Path Length Similarity (APLS) to measure road network connectivity. It was found that of the three AFE tested, the Ecopia data most frequently outperformed the other AFE in accuracy and reduced the time needed for editing.