Deep learning architecture using rough sets and rough neural networks

Kybernetes ◽  
2017 ◽  
Vol 46 (4) ◽  
pp. 693-705 ◽  
Author(s):  
Yasser F. Hassan
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Soft Computing ◽  
Rough Set ◽  
Real World ◽  
Rough Sets ◽  
Decision Table ◽  
Content Type ◽  
Real World Applications ◽  
Decision Tables

Purpose This paper aims to utilize machine learning and soft computing to propose a new method of rough sets using deep learning architecture for many real-world applications. Design/methodology/approach The objective of this work is to propose a model for deep rough set theory that uses more than decision table and approximating these tables to a classification system, i.e. the paper propose a novel framework of deep learning based on multi-decision tables. Findings The paper tries to coordinate the local properties of individual decision table to provide an appropriate global decision from the system. Research limitations/implications The rough set learning assumes the existence of a single decision table, whereas real-world decision problem implies several decisions with several different decision tables. The new proposed model can handle multi-decision tables. Practical implications The proposed classification model is implemented on social networks with preferred features which are freely distribute as social entities with accuracy around 91 per cent. Social implications The deep learning using rough sets theory simulate the way of brain thinking and can solve the problem of existence of different information about same problem in different decision systems Originality/value This paper utilizes machine learning and soft computing to propose a new method of rough sets using deep learning architecture for many real-world applications.

scholarly journals A Survey on Bias and Fairness in Machine Learning

2021 ◽  
Vol 54 (6) ◽  
pp. 1-35
Author(s):  
Ninareh Mehrabi ◽  
Fred Morstatter ◽  
Nripsuta Saxena ◽  
Kristina Lerman ◽  
Aram Galstyan
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Real World ◽  
State Of The Art ◽  
Future Directions ◽  
Discriminatory Behavior ◽  
Real World Applications ◽  
Near Future ◽  
Different Sources

With the widespread use of artificial intelligence (AI) systems and applications in our everyday lives, accounting for fairness has gained significant importance in designing and engineering of such systems. AI systems can be used in many sensitive environments to make important and life-changing decisions; thus, it is crucial to ensure that these decisions do not reflect discriminatory behavior toward certain groups or populations. More recently some work has been developed in traditional machine learning and deep learning that address such challenges in different subdomains. With the commercialization of these systems, researchers are becoming more aware of the biases that these applications can contain and are attempting to address them. In this survey, we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications. We then created a taxonomy for fairness definitions that machine learning researchers have defined to avoid the existing bias in AI systems. In addition to that, we examined different domains and subdomains in AI showing what researchers have observed with regard to unfair outcomes in the state-of-the-art methods and ways they have tried to address them. There are still many future directions and solutions that can be taken to mitigate the problem of bias in AI systems. We are hoping that this survey will motivate researchers to tackle these issues in the near future by observing existing work in their respective fields.

GENERALIZED FUZZY ROUGH SETS BY CONDITIONAL PROBABILITY RELATIONS

2002 ◽  
Vol 16 (07) ◽  
pp. 865-881 ◽  
Author(s):  
ROLLY INTAN ◽  
MASAO MUKAIDONO
Keyword(s):  
Conditional Probability ◽  
Rough Set ◽  
Real World ◽  
Rough Sets ◽  
Similarity Relation ◽  
Fuzzy Rough Set ◽  
Fuzzy Similarity ◽  
Fuzzy Similarity Relation ◽  
Real World Applications ◽  
The Universe

In 1982, Pawlak proposed the concept of rough sets with a practical purpose of representing indiscernibility of elements or objects in the presence of information systems. Even if it is easy to analyze, the rough set theory built on a partition induced by equivalence relation may not provide a realistic view of relationships between elements in real-world applications. Here, coverings of, or nonequivalence relations on, the universe can be considered to represent a more realistic model instead of a partition in which a generalized model of rough sets was proposed. In this paper, first a weak fuzzy similarity relation is introduced as a more realistic relation in representing the relationship between two elements of data in real-world applications. Fuzzy conditional probability relation is considered as a concrete example of the weak fuzzy similarity relation. Coverings of the universe is provided by fuzzy conditional probability relations. Generalized concepts of rough approximations and rough membership functions are proposed and defined based on coverings of the universe. Such generalization is considered as a kind of fuzzy rough set. A more generalized fuzzy rough set approximation of a given fuzzy set is proposed and discussed as an alternative to provide interval-value fuzzy sets. Their properties are examined.

scholarly journals ProtTox: Toxin identification from Protein Sequences

2020 ◽  
Author(s):  
Sathappan Muthiah ◽  
Debanjan Datta ◽  
Mohammad Raihanul Islam ◽  
Patrick Butler ◽  
Andrew Warren ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Synthetic Biology ◽  
Real World ◽  
Protein Sequences ◽  
Structural Diversity ◽  
Manual Annotation ◽  
Real World Applications ◽  
Automated Machine Learning

AbstractToxin classification of protein sequences is a challenging task with real world applications in healthcare and synthetic biology. Due to an ever expanding database of proteins and the inordinate cost of manual annotation, automated machine learning based approaches are crucial. Approaches need to overcome challenges of homology, multi-functionality, and structural diversity among proteins in this task. We propose a novel deep learning based method ProtTox, that aims to address some of the shortcomings of previous approaches in classifying proteins as toxins or not. Our method achieves a performance of 0.812 F1-score which is about 5% higher than the closest performing baseline.

On Variable Precision Generalized Rough Sets and Incomplete Decision Tables

2021 ◽  
Vol 179 (1) ◽  
pp. 75-92
Author(s):  
Yu-Ru Syau ◽  
Churn-Jung Liau ◽  
En-Bing Lin
Keyword(s):  
Rough Set ◽  
Rough Sets ◽  
Decision Table ◽  
Necessary Condition ◽  
Weak Consistency ◽  
Decision System ◽  
Variable Precision ◽  
Generalized Rough Set ◽  
Decision Tables ◽  
Generalized Rough Sets

We present variable precision generalized rough set approach to characterize incomplete decision tables. We show how to determine the discernibility threshold for a reflexive relational decision system in the variable precision generalized rough set model. We also point out some properties of positive regions and prove a statement of the necessary condition for weak consistency of an incomplete decision table. We present two examples to illustrate the results obtained in this paper.

scholarly journals Deep Learning Classification of Canine Behavior Using a Single Collar-Mounted Accelerometer: Real-World Validation

Animals ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1549
Author(s):  
Robert D. Chambers ◽  
Nathanael C. Yoder ◽  
Aletha B. Carson ◽  
Christian Junge ◽  
David E. Allen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Real World ◽  
Learning Algorithm ◽  
Drinking Behavior ◽  
True Positive Rate ◽  
Training Dataset ◽  
Activity Levels ◽  
Accelerometer Data ◽  
Activity Monitors

Collar-mounted canine activity monitors can use accelerometer data to estimate dog activity levels, step counts, and distance traveled. With recent advances in machine learning and embedded computing, much more nuanced and accurate behavior classification has become possible, giving these affordable consumer devices the potential to improve the efficiency and effectiveness of pet healthcare. Here, we describe a novel deep learning algorithm that classifies dog behavior at sub-second resolution using commercial pet activity monitors. We built machine learning training databases from more than 5000 videos of more than 2500 dogs and ran the algorithms in production on more than 11 million days of device data. We then surveyed project participants representing 10,550 dogs, which provided 163,110 event responses to validate real-world detection of eating and drinking behavior. The resultant algorithm displayed a sensitivity and specificity for detecting drinking behavior (0.949 and 0.999, respectively) and eating behavior (0.988, 0.983). We also demonstrated detection of licking (0.772, 0.990), petting (0.305, 0.991), rubbing (0.729, 0.996), scratching (0.870, 0.997), and sniffing (0.610, 0.968). We show that the devices’ position on the collar had no measurable impact on performance. In production, users reported a true positive rate of 95.3% for eating (among 1514 users), and of 94.9% for drinking (among 1491 users). The study demonstrates the accurate detection of important health-related canine behaviors using a collar-mounted accelerometer. We trained and validated our algorithms on a large and realistic training dataset, and we assessed and confirmed accuracy in production via user validation.

scholarly journals A rough set theory and deep learning based predictive system for gender recognition using audio speech

2021 ◽  
Author(s):  
Ghazaala Yasmin ◽  
ASIT KUMAR DAS ◽  
Janmenjoy Nayak ◽  
S Vimal ◽  
Soumi Dutta
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Set Theory ◽  
Rough Set ◽  
Gender Discrimination ◽  
Rough Set Theory ◽  
Recognition System ◽  
Gender Recognition ◽  
Learning Techniques

Abstract Speech is one of the most delicate medium through which gender of the speakers can easily be identified. Though the related research has shown very good progress in machine learning but recently, deep learning has imparted a very good research area to explore the deficiency of gender discrimination using traditional machine learning techniques. In deep learning techniques, the speech features are automatically generated by the reinforcement learning from the raw data which have more discriminating power than the human generated features. But in some practical situations like gender recognition, it is observed that combination of both types of features sometimes provides comparatively better performance. In the proposed work, we have initially extracted and selected some informative and precise acoustic features relevant to gender recognition using entropy based information theory and Rough Set Theory (RST). Next, the audio speech signals are directly fed into the deep neural network model consists of Convolution Neural Network (CNN) and Gated Recurrent Unit network (GRUN) for extracting features useful for gender recognition. The RST selects precise and informative features, CNN extracts the locally encoded important features, and GRUN reduces the vanishing gradient and exploding gradient problems. Finally, a hybrid gender recognition system is developed combining both generated feature vectors. The developed model has been tested with five bench mark and a simulated dataset to evaluate its performance and it is observed that combined feature vector provides more effective gender recognition system specially when transgender is considered as a gender type together with male and female.

Efficient inference for agent-based models of real-world phenomena

2021 ◽  
Author(s):  
Andreas Christ Sølvsten Jørgensen ◽  
Atiyo Ghosh ◽  
Marc Sturrock ◽  
Vahid Shahrezaei
Keyword(s):  
Machine Learning ◽  
Case Studies ◽  
Parameter Space ◽  
Real World ◽  
Autonomous Agents ◽  
Stochastic Simulations ◽  
Model Parameters ◽  
Learning Approaches ◽  
Real World Applications ◽  
Real World Problems

AbstractThe modelling of many real-world problems relies on computationally heavy simulations. Since statistical inference rests on repeated simulations to sample the parameter space, the high computational expense of these simulations can become a stumbling block. In this paper, we compare two ways to mitigate this issue based on machine learning methods. One approach is to construct lightweight surrogate models to substitute the simulations used in inference. Alternatively, one might altogether circumnavigate the need for Bayesian sampling schemes and directly estimate the posterior distribution. We focus on stochastic simulations that track autonomous agents and present two case studies of real-world applications: tumour growths and the spread of infectious diseases. We demonstrate that good accuracy in inference can be achieved with a relatively small number of simulations, making our machine learning approaches orders of magnitude faster than classical simulation-based methods that rely on sampling the parameter space. However, we find that while some methods generally produce more robust results than others, no algorithm offers a one-size-fits-all solution when attempting to infer model parameters from observations. Instead, one must choose the inference technique with the specific real-world application in mind. The stochastic nature of the considered real-world phenomena poses an additional challenge that can become insurmountable for some approaches. Overall, we find machine learning approaches that create direct inference machines to be promising for real-world applications. We present our findings as general guidelines for modelling practitioners.Author summaryComputer simulations play a vital role in modern science as they are commonly used to compare theory with observations. One can thus infer the properties of a observed system by comparing the data to the predicted behaviour in different scenarios. Each of these scenarios corresponds to a simulation with slightly different settings. However, since real-world problems are highly complex, the simulations often require extensive computational resources, making direct comparisons with data challenging, if not insurmountable. It is, therefore, necessary to resort to inference methods that mitigate this issue, but it is not clear-cut what path to choose for any specific research problem. In this paper, we provide general guidelines for how to make this choice. We do so by studying examples from oncology and epidemiology and by taking advantage of developments in machine learning. More specifically, we focus on simulations that track the behaviour of autonomous agents, such as single cells or individuals. We show that the best way forward is problem-dependent and highlight the methods that yield the most robust results across the different case studies. We demonstrate that these methods are highly promising and produce reliable results in a small fraction of the time required by classic approaches that rely on comparisons between data and individual simulations. Rather than relying on a single inference technique, we recommend employing several methods and selecting the most reliable based on predetermined criteria.

Intelligent ubiquitous computing model for energy optimization of cloud IOTs in sensor networks

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Deepa S.N.
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Energy Level ◽  
Computational Model ◽  
Ubiquitous Computing ◽  
Sensor Network ◽  
Research Study ◽  
Content Type ◽  
Computing Model ◽  
Learning Techniques

Purpose Limitations encountered with the models developed in the previous studies had occurrences of global minima; due to which this study developed a new intelligent ubiquitous computational model that learns with gradient descent learning rule and operates with auto-encoders and decoders to attain better energy optimization. Ubiquitous machine learning computational model process performs training in a better way than regular supervised learning or unsupervised learning computational models with deep learning techniques, resulting in better learning and optimization for the considered problem domain of cloud-based internet-of-things (IOTs). This study aims to improve the network quality and improve the data accuracy rate during the network transmission process using the developed ubiquitous deep learning computational model. Design/methodology/approach In this research study, a novel intelligent ubiquitous machine learning computational model is designed and modelled to maintain the optimal energy level of cloud IOTs in sensor network domains. A new intelligent ubiquitous computational model that learns with gradient descent learning rule and operates with auto-encoders and decoders to attain better energy optimization is developed. A new unified deterministic sine-cosine algorithm has been developed in this study for parameter optimization of weight factors in the ubiquitous machine learning model. Findings The newly developed ubiquitous model is used for finding network energy and performing its optimization in the considered sensor network model. At the time of progressive simulation, residual energy, network overhead, end-to-end delay, network lifetime and a number of live nodes are evaluated. It is elucidated from the results attained, that the ubiquitous deep learning model resulted in better metrics based on its appropriate cluster selection and minimized route selection mechanism. Research limitations/implications In this research study, a novel ubiquitous computing model derived from a new optimization algorithm called a unified deterministic sine-cosine algorithm and deep learning technique was derived and applied for maintaining the optimal energy level of cloud IOTs in sensor networks. The deterministic levy flight concept is applied for developing the new optimization technique and this tends to determine the parametric weight values for the deep learning model. The ubiquitous deep learning model is designed with auto-encoders and decoders and their corresponding layers weights are determined for optimal values with the optimization algorithm. The modelled ubiquitous deep learning approach was applied in this study to determine the network energy consumption rate and thereby optimize the energy level by increasing the lifetime of the sensor network model considered. For all the considered network metrics, the ubiquitous computing model has proved to be effective and versatile than previous approaches from early research studies. Practical implications The developed ubiquitous computing model with deep learning techniques can be applied for any type of cloud-assisted IOTs in respect of wireless sensor networks, ad hoc networks, radio access technology networks, heterogeneous networks, etc. Practically, the developed model facilitates computing the optimal energy level of the cloud IOTs for any considered network models and this helps in maintaining a better network lifetime and reducing the end-to-end delay of the networks. Social implications The social implication of the proposed research study is that it helps in reducing energy consumption and increases the network lifetime of the cloud IOT based sensor network models. This approach helps the people in large to have a better transmission rate with minimized energy consumption and also reduces the delay in transmission. Originality/value In this research study, the network optimization of cloud-assisted IOTs of sensor network models is modelled and analysed using machine learning models as a kind of ubiquitous computing system. Ubiquitous computing models with machine learning techniques develop intelligent systems and enhances the users to make better and faster decisions. In the communication domain, the use of predictive and optimization models created with machine learning accelerates new ways to determine solutions to problems. Considering the importance of learning techniques, the ubiquitous computing model is designed based on a deep learning strategy and the learning mechanism adapts itself to attain a better network optimization model.

Deep Learning and Biomedical Engineering

Biotechnology ◽  
2019 ◽  
pp. 562-575
Author(s):  
Suraj Sawant
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Deep Learning ◽  
Real World ◽  
Biomedical Engineering ◽  
Input Data ◽  
Reference Source ◽  
Data Input ◽  
Essential Information

Deep learning (DL) is a method of machine learning, as running over artificial neural networks, which has a structure above the standards to deal with large amounts of data. That is generally because of the increasing amount of data, input data sizes, and of course, greater complexity of objective real-world problems. Performed research studies in the associated literature show that the DL currently has a good performance among considered problems and it seems to be a strong solution for more advanced problems of the future. In this context, this chapter aims to provide some essential information about DL and its applications within the field of biomedical engineering. The chapter is organized as a reference source for enabling readers to have an idea about the relation between DL and biomedical engineering.

Sign in / Sign up

Export Citation Format

Share Document