scholarly journals Does Tail Label Help for Large-Scale Multi-Label Learning

2018 ◽  
Author(s):  
Tong Wei ◽  
Yu-Feng Li
Keyword(s):  
Large Scale ◽  
Performance Metrics ◽  
Learning Algorithm ◽  
Predictive Performance ◽  
Low Complexity ◽  
Tail Distribution ◽  
Prediction Time ◽  
Unseen Data ◽  
Model Size ◽  
Fast Prediction

Large-scale multi-label learning annotates relevant labels for unseen data from a huge number of candidate labels. It is well known that in large-scale multi-label learning, labels exhibit a long tail distribution in which a significant fraction of labels are tail labels. Nonetheless, how tail labels make impact on the performance metrics in large-scale multi-label learning was not explicitly quantified. In this paper, we disclose that whatever labels are randomly missing or misclassified, tail labels impact much less than common labels in terms of commonly used performance metrics (Top-$k$ precision and nDCG@$k$). With the observation above, we develop a low-complexity large-scale multi-label learning algorithm with the goal of facilitating fast prediction and compact models by trimming tail labels adaptively. Experiments clearly verify that both the prediction time and the model size are significantly reduced without sacrificing much predictive performance for state-of-the-art approaches.

scholarly journals Learning Compact Model for Large-Scale Multi-Label Data

2019 ◽  
Vol 33 ◽  
pp. 5385-5392 ◽  
Author(s):  
Tong Wei ◽  
Yu-Feng Li
Keyword(s):  
Large Scale ◽  
Optimization Problem ◽  
Performance Metrics ◽  
State Of The Art ◽  
Optimization Method ◽  
Model Parameters ◽  
Generalization Capability ◽  
Constrained Optimization Problem ◽  
Unseen Data ◽  
Model Size

Large-scale multi-label learning (LMLL) aims to annotate relevant labels from a large number of candidates for unseen data. Due to the high dimensionality in both feature and label spaces in LMLL, the storage overheads of LMLL models are often costly. This paper proposes a POP (joint label and feature Parameter OPtimization) method. It tries to filter out redundant model parameters to facilitate compact models. Our key insights are as follows. First, we investigate labels that have little impact on the commonly used LMLL performance metrics and only preserve a small number of dominant parameters for these labels. Second, for the remaining influential labels, we reduce spurious feature parameters that have little contribution to the generalization capability of models, and preserve parameters for only discriminative features. The overall problem is formulated as a constrained optimization problem pursuing minimal model size. In order to solve the resultant difficult optimization, we show that a relaxation of the optimization can be efficiently solved using binary search and greedy strategies. Experiments verify that the proposed method clearly reduces the model size compared to state-of-the-art LMLL approaches, in addition, achieves highly competitive performance.

scholarly journals Spotting DeepFakes and Face Manipulations by Fusing Features from Multi-Stream CNNs Models

Symmetry ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1352
Author(s):  
Semih Yavuzkilic ◽  
Abdulkadir Sengur ◽  
Zahid Akhtar ◽  
Kamran Siddique
Keyword(s):  
Large Scale ◽  
Performance Metrics ◽  
Learning Algorithm ◽  
Detection System ◽  
Classification Problem ◽  
Detection Methods ◽  
Hair Color ◽  
Third Stream ◽  
Deep Learning Algorithm ◽  
Fully Connected

Deepfake is one of the applications that is deemed harmful. Deepfakes are a sort of image or video manipulation in which a person’s image is changed or swapped with that of another person’s face using artificial neural networks. Deepfake manipulations may be done with a variety of techniques and applications. A quintessential countermeasure against deepfake or face manipulation is deepfake detection method. Most of the existing detection methods perform well under symmetric data distributions, but are still not robust to asymmetric datasets variations and novel deepfake/manipulation types. In this paper, for the identification of fake faces in videos, a new multi-stream deep learning algorithm is developed, where three streams are merged at the feature level using the fusion layer. After the fusion layer, the fully connected, Softmax, and classification layers are used to classify the data. The pre-trained VGG16 model is adopted for transferred CNN1stream. In transfer learning, the weights of the pre-trained CNN model are further used for training the new classification problem. In the second stream (transferred CNN2), the pre-trained VGG19 model is used. Whereas, in the third stream, the pre-trained ResNet18 model is considered. In this paper, a new large-scale dataset (i.e., World Politicians Deepfake Dataset (WPDD)) is introduced to improve deepfake detection systems. The dataset was created by downloading videos of 20 different politicians from YouTube. Over 320,000 frames were retrieved after dividing the downloaded movie into little sections and extracting the frames. Finally, various manipulations were performed to these frames, resulting in seven separate manipulation classes for men and women. In the experiments, three fake face detection scenarios are investigated. First, fake and real face discrimination is studied. Second, seven face manipulations are performed, including age, beard, face swap, glasses, hair color, hairstyle, smiling, and genuine face discrimination. Third, performance of deepfake detection system under novel type of face manipulation is analyzed. The proposed strategy outperforms the prior existing methods. The calculated performance metrics are over 99%.

A Novel Static Path Planning Method for Mobile Anchor-Assisted Localization in Wireless Sensor Networks

2020 ◽  
Vol 10 ◽  
Author(s):  
Abdelhady M. Naguib ◽  
Shahzad Ali
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Path Planning ◽  
Sensor Node ◽  
Large Scale ◽  
Performance Metrics ◽  
Wireless Sensor ◽  
Anchor Node ◽  
Mobile Anchor ◽  
Planning Methods

Background: Many applications of Wireless Sensor Networks (WSNs) require awareness of sensor node’s location but not every sensor node can be equipped with a GPS receiver for localization, due to cost and energy constraints especially for large-scale networks. For localization, many algorithms have been proposed to enable a sensor node to be able to determine its location by utilizing a small number of special nodes called anchors that are equipped with GPS receivers. In recent years a promising method that significantly reduces the cost is to replace the set of statically deployed GPS anchors with one mobile anchor node equipped with a GPS unit that moves to cover the entire network. Objectives: This paper proposes a novel static path planning mechanism that enables a single anchor node to follow a predefined static path while periodically broadcasting its current location coordinates to the nearby sensors. This new path type is called SQUARE_SPIRAL and it is specifically designed to reduce the collinearity during localization. Results: Simulation results show that the performance of SQUARE_SPIRAL mechanism is better than other static path planning methods with respect to multiple performance metrics. Conclusion: This work includes an extensive comparative study of the existing static path planning methods then presents a comparison of the proposed mechanism with existing solutions by doing extensive simulations in NS-2.

scholarly journals Wireless Sensor Networks for Smart Cities: Network Design, Implementation and Performance Evaluation

Electronics ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 218
Author(s):  
Ala’ Khalifeh ◽  
Khalid A. Darabkh ◽  
Ahmad M. Khasawneh ◽  
Issa Alqaisieh ◽  
Mohammad Salameh ◽  
...  
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Experimental Evaluation ◽  
Large Scale ◽  
Performance Metrics ◽  
Smart Cities ◽  
Field Tests ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Real Field

The advent of various wireless technologies has paved the way for the realization of new infrastructures and applications for smart cities. Wireless Sensor Networks (WSNs) are one of the most important among these technologies. WSNs are widely used in various applications in our daily lives. Due to their cost effectiveness and rapid deployment, WSNs can be used for securing smart cities by providing remote monitoring and sensing for many critical scenarios including hostile environments, battlefields, or areas subject to natural disasters such as earthquakes, volcano eruptions, and floods or to large-scale accidents such as nuclear plants explosions or chemical plumes. The purpose of this paper is to propose a new framework where WSNs are adopted for remote sensing and monitoring in smart city applications. We propose using Unmanned Aerial Vehicles to act as a data mule to offload the sensor nodes and transfer the monitoring data securely to the remote control center for further analysis and decision making. Furthermore, the paper provides insight about implementation challenges in the realization of the proposed framework. In addition, the paper provides an experimental evaluation of the proposed design in outdoor environments, in the presence of different types of obstacles, common to typical outdoor fields. The experimental evaluation revealed several inconsistencies between the performance metrics advertised in the hardware-specific data-sheets. In particular, we found mismatches between the advertised coverage distance and signal strength with our experimental measurements. Therefore, it is crucial that network designers and developers conduct field tests and device performance assessment before designing and implementing the WSN for application in a real field setting.

scholarly journals Combining Regional Habitat Selection Models for Large-Scale Prediction: Circumpolar Habitat Selection of Southern Ocean Humpback Whales

2021 ◽  
Vol 13 (11) ◽  
pp. 2074
Author(s):  
Ryan R. Reisinger ◽  
Ari S. Friedlaender ◽  
Alexandre N. Zerbini ◽  
Daniel M. Palacios ◽  
Virginia Andrews-Goff ◽  
...  
Keyword(s):  
Habitat Selection ◽  
Predictive Models ◽  
Regional Variation ◽  
Large Scale ◽  
Predictive Performance ◽  
Humpback Whale ◽  
Machine Learning Algorithms ◽  
Humpback Whales ◽  
Environmental Covariates ◽  
Animal Habitat

Machine learning algorithms are often used to model and predict animal habitat selection—the relationships between animal occurrences and habitat characteristics. For broadly distributed species, habitat selection often varies among populations and regions; thus, it would seem preferable to fit region- or population-specific models of habitat selection for more accurate inference and prediction, rather than fitting large-scale models using pooled data. However, where the aim is to make range-wide predictions, including areas for which there are no existing data or models of habitat selection, how can regional models best be combined? We propose that ensemble approaches commonly used to combine different algorithms for a single region can be reframed, treating regional habitat selection models as the candidate models. By doing so, we can incorporate regional variation when fitting predictive models of animal habitat selection across large ranges. We test this approach using satellite telemetry data from 168 humpback whales across five geographic regions in the Southern Ocean. Using random forests, we fitted a large-scale model relating humpback whale locations, versus background locations, to 10 environmental covariates, and made a circumpolar prediction of humpback whale habitat selection. We also fitted five regional models, the predictions of which we used as input features for four ensemble approaches: an unweighted ensemble, an ensemble weighted by environmental similarity in each cell, stacked generalization, and a hybrid approach wherein the environmental covariates and regional predictions were used as input features in a new model. We tested the predictive performance of these approaches on an independent validation dataset of humpback whale sightings and whaling catches. These multiregional ensemble approaches resulted in models with higher predictive performance than the circumpolar naive model. These approaches can be used to incorporate regional variation in animal habitat selection when fitting range-wide predictive models using machine learning algorithms. This can yield more accurate predictions across regions or populations of animals that may show variation in habitat selection.

scholarly journals Low-complexity sparse-aware multiuser detection for large-scale MIMO systems

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Rong Ran ◽  
Hayoung Oh
Keyword(s):  
Large Scale ◽  
Mimo Systems ◽  
Minimum Mean Square Error ◽  
Multiple Input Multiple Output ◽  
Low Complexity ◽  
Finite Alphabet ◽  
Multiuser Detectors ◽  
Input Multiple Output ◽  
Error Detector ◽  
Significant Performance

AbstractSparse-aware (SA) detectors have attracted a lot attention due to its significant performance and low-complexity, in particular for large-scale multiple-input multiple-output (MIMO) systems. Similar to the conventional multiuser detectors, the nonlinear or compressive sensing based SA detectors provide the better performance but are not appropriate for the overdetermined multiuser MIMO systems in sense of power and time consumption. The linear SA detector provides a more elegant tradeoff between performance and complexity compared to the nonlinear ones. However, the major limitation of the linear SA detector is that, as the zero-forcing or minimum mean square error detector, it was derived by relaxing the finite-alphabet constraints, and therefore its performance is still sub-optimal. In this paper, we propose a novel SA detector, named single-dimensional search-based SA (SDSB-SA) detector, for overdetermined uplink MIMO systems. The proposed SDSB-SA detector adheres to the finite-alphabet constraints so that it outperforms the conventional linear SA detector, in particular, in high SNR regime. Meanwhile, the proposed detector follows a single-dimensional search manner, so it has a very low computational complexity which is feasible for light-ware Internet of Thing devices for ultra-reliable low-latency communication. Numerical results show that the the proposed SDSB-SA detector provides a relatively better tradeoff between the performance and complexity compared with several existing detectors.

scholarly journals Design and Evaluation of Large-Scale IoT-Enabled Healthcare Architecture

2021 ◽  
Vol 11 (8) ◽  
pp. 3623
Author(s):  
Omar Said ◽  
Amr Tolba
Keyword(s):  
Packet Loss ◽  
Large Scale ◽  
Performance Metrics ◽  
Medical System ◽  
Healthcare Data ◽  
High Altitude Platforms ◽  
Wide Range ◽  
Simulation Results ◽  
Healthcare Architecture ◽  
The Internet Of Things

Employment of the Internet of Things (IoT) technology in the healthcare field can contribute to recruiting heterogeneous medical devices and creating smart cooperation between them. This cooperation leads to an increase in the efficiency of the entire medical system, thus accelerating the diagnosis and curing of patients, in general, and rescuing critical cases in particular. In this paper, a large-scale IoT-enabled healthcare architecture is proposed. To achieve a wide range of communication between healthcare devices, not only are Internet coverage tools utilized but also satellites and high-altitude platforms (HAPs). In addition, the clustering idea is applied in the proposed architecture to facilitate its management. Moreover, healthcare data are prioritized into several levels of importance. Finally, NS3 is used to measure the performance of the proposed IoT-enabled healthcare architecture. The performance metrics are delay, energy consumption, packet loss, coverage tool usage, throughput, percentage of served users, and percentage of each exchanged data type. The simulation results demonstrate that the proposed IoT-enabled healthcare architecture outperforms the traditional healthcare architecture.

Leveraging Collaborative-Filtering for Personalized Behavior Modeling

2021 ◽  
Vol 5 (1) ◽  
pp. 1-27
Author(s):  
Xuhai Xu ◽  
Prerna Chikersal ◽  
Janine M. Dutcher ◽  
Yasaman S. Sefidgar ◽  
Woosuk Seo ◽  
...  
Keyword(s):  
College Students ◽  
Collaborative Filtering ◽  
Human Behavior ◽  
Work Performance ◽  
Performance Metrics ◽  
Learning Algorithm ◽  
Model Performance ◽  
Majority Voting ◽  
Behavior Modeling ◽  
Depression Detection

The prevalence of mobile phones and wearable devices enables the passive capturing and modeling of human behavior at an unprecedented resolution and scale. Past research has demonstrated the capability of mobile sensing to model aspects of physical health, mental health, education, and work performance, etc. However, most of the algorithms and models proposed in previous work follow a one-size-fits-all (i.e., population modeling) approach that looks for common behaviors amongst all users, disregarding the fact that individuals can behave very differently, resulting in reduced model performance. Further, black-box models are often used that do not allow for interpretability and human behavior understanding. We present a new method to address the problems of personalized behavior classification and interpretability, and apply it to depression detection among college students. Inspired by the idea of collaborative-filtering, our method is a type of memory-based learning algorithm. It leverages the relevance of mobile-sensed behavior features among individuals to calculate personalized relevance weights, which are used to impute missing data and select features according to a specific modeling goal (e.g., whether the student has depressive symptoms) in different time epochs, i.e., times of the day and days of the week. It then compiles features from epochs using majority voting to obtain the final prediction. We apply our algorithm on a depression detection dataset collected from first-year college students with low data-missing rates and show that our method outperforms the state-of-the-art machine learning model by 5.1% in accuracy and 5.5% in F1 score. We further verify the pipeline-level generalizability of our approach by achieving similar results on a second dataset, with an average improvement of 3.4% across performance metrics. Beyond achieving better classification performance, our novel approach is further able to generate personalized interpretations of the models for each individual. These interpretations are supported by existing depression-related literature and can potentially inspire automated and personalized depression intervention design in the future.

A Scalable Redefined Stochastic Blockmodel

2021 ◽  
Vol 15 (3) ◽  
pp. 1-28
Author(s):  
Xueyan Liu ◽  
Bo Yang ◽  
Hechang Chen ◽  
Katarzyna Musial ◽  
Hongxu Chen ◽  
...  
Keyword(s):  
Large Scale ◽  
Network Science ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Real World Data ◽  
Computational Overhead ◽  
Stochastic Blockmodel ◽  
Np Hard Problem ◽  
Large Scale Networks ◽  
The Cost

Stochastic blockmodel (SBM) is a widely used statistical network representation model, with good interpretability, expressiveness, generalization, and flexibility, which has become prevalent and important in the field of network science over the last years. However, learning an optimal SBM for a given network is an NP-hard problem. This results in significant limitations when it comes to applications of SBMs in large-scale networks, because of the significant computational overhead of existing SBM models, as well as their learning methods. Reducing the cost of SBM learning and making it scalable for handling large-scale networks, while maintaining the good theoretical properties of SBM, remains an unresolved problem. In this work, we address this challenging task from a novel perspective of model redefinition. We propose a novel redefined SBM with Poisson distribution and its block-wise learning algorithm that can efficiently analyse large-scale networks. Extensive validation conducted on both artificial and real-world data shows that our proposed method significantly outperforms the state-of-the-art methods in terms of a reasonable trade-off between accuracy and scalability. 1

Sign in / Sign up

Export Citation Format

Share Document