arXiv subjects

Hamid R. Arabnia

Publications and source records attributed to Hamid R. Arabnia.

At least 37 records · Page 2Linked to original sources

arXiv2020

Causes of Misleading Statistics and Research Results Irreproducibility: A Concise Review

Bad statistics make research papers unreproducible and misleading. For the most part, the reasons for such misusage of numerical data have been found and addressed years ago by experts and proper practical solutions have been presented instead. Yet, we still see numerous instances of statistical fallacies in modern researches which without a doubt play a significant role in the research reproducibility crisis. In this paper, we review different bad practices that impact the research process from its beginning to its very end. Additionally, we briefly propose open science as a universal methodology that can facilitate the entire research life cycle.

stat.OT↗

arXiv2020

Evolutionary Algorithms and Efficient Data Analytics for Image Processing

Steganography algorithms facilitate communication between a source and a destination in a secret manner. This is done by embedding messages/text/data into images without impacting the appearance of the resultant images/videos. Steganalysis is the science of determining if an image has secret messages embedded/hidden in it. Because there are numerous steganography algorithms, and since each one of them requires a different type of steganalysis, the steganalysis process is extremely challenging. Thus, researchers aim to develop one universal steganalysis to detect all known and unknown steganography algorithms, ideally in real-time. Universal steganalysis extracts a large number of features to distinguish stego images from cover images. However, the increase in features leads to the problem of the curse of dimensionality (CoD), which is considered to be an NP-hard problem. This COD problem additionally makes real-time steganalysis hard. A large number of features generates large datasets for which machine learning cannot generate an optimal model. Generating a machine learning based model also takes a long time which makes real-time processing appear impossible in any optimization for time-intensive fields such as visual computing. Possible solutions for CoD are deep learning and evolutionary algorithms that overcome the machine learning limitations. In this study, we investigate previously developed evolutionary algorithms for boosting real-time image processing and argue that they provide the most promising solutions for the CoD problem.

cs.CV↗

arXiv2020

A Brief Review of Domain Adaptation

Classical machine learning assumes that the training and test sets come from the same distributions. Therefore, a model learned from the labeled training data is expected to perform well on the test data. However, This assumption may not always hold in real-world applications where the training and the test data fall from different distributions, due to many factors, e.g., collecting the training and test sets from different sources, or having an out-dated training set due to the change of data over time. In this case, there would be a discrepancy across domain distributions, and naively applying the trained model on the new dataset may cause degradation in the performance. Domain adaptation is a sub-field within machine learning that aims to cope with these types of problems by aligning the disparity between domains such that the trained model can be generalized into the domain of interest. This paper focuses on unsupervised domain adaptation, where the labels are only available in the source domain. It addresses the categorization of domain adaptation from different viewpoints. Besides, It presents some successful shallow and deep domain adaptation approaches that aim to deal with domain adaptation problems.

cs.LG↗

arXiv2020

Internet of Things for Current COVID-19 and Future Pandemics: An Exploratory Study

In recent years, the Internet of Things (IoT) has drawn convincing research ground as a new research topic in a wide variety of academic and industrial disciplines, especially in healthcare. The IoT revolution is reshaping modern healthcare systems by incorporating technological, economic, and social prospects. It is evolving healthcare systems from conventional to more personalized healthcare systems through which patients can be diagnosed, treated, and monitored more easily. The current global challenge of the pandemic caused by the novel severe contagious respiratory syndrome coronavirus 2 presents the greatest global public health crisis since the pandemic influenza outbreak of 1918. At the time this paper was written, the number of diagnosed COVID-19 cases around the world had reached more than 31 million. Since the pandemic started, there has been a rapid effort in different research communities to exploit a wide variety of technologies to combat this worldwide threat, and IoT technology is one of the pioneers in this area. In the context of COVID-19, IoT enabled /linked devices/applications are utilized to lower the possible spread of COVID-19 to others by early diagnosis, monitoring patients, and practicing defined protocols after patient recovery. This paper surveys the role of IoT-based technologies in COVID-19 and reviews the state-of-the-art architectures, platforms, applications, and industrial IoT-based solutions combating COVID-19 in three main phases, including early diagnosis, quarantine time, and after recovery.

cs.CY↗

arXiv2020

DeepMSRF: A novel Deep Multimodal Speaker Recognition framework with Feature selection

For recognizing speakers in video streams, significant research studies have been made to obtain a rich machine learning model by extracting high-level speaker's features such as facial expression, emotion, and gender. However, generating such a model is not feasible by using only single modality feature extractors that exploit either audio signals or image frames, extracted from video streams. In this paper, we address this problem from a different perspective and propose an unprecedented multimodality data fusion framework called DeepMSRF, Deep Multimodal Speaker Recognition with Feature selection. We execute DeepMSRF by feeding features of the two modalities, namely speakers' audios and face images. DeepMSRF uses a two-stream VGGNET to train on both modalities to reach a comprehensive model capable of accurately recognizing the speaker's identity. We apply DeepMSRF on a subset of VoxCeleb2 dataset with its metadata merged with VGGFace2 dataset. The goal of DeepMSRF is to identify the gender of the speaker first, and further to recognize his or her name for any given video stream. The experimental results illustrate that DeepMSRF outperforms single modality speaker recognition methods with at least 3 percent accuracy.

cs.CV↗

arXiv2020

DRDr: Automatic Masking of Exudates and Microaneurysms Caused By Diabetic Retinopathy Using Mask R-CNN and Transfer Learning

This paper addresses the problem of identifying two main types of lesions - Exudates and Microaneurysms - caused by Diabetic Retinopathy (DR) in the eyes of diabetic patients. We make use of Convolutional Neural Networks (CNNs) and Transfer Learning to locate and generate high-quality segmentation mask for each instance of the lesion that can be found in the patients' fundus images. We create our normalized database out of e-ophtha EX and e-ophtha MA and tweak Mask R-CNN to detect small lesions. Moreover, we employ data augmentation and the pre-trained weights of ResNet101 to compensate for our small dataset. Our model achieves promising test mAP of 0.45, altogether showing that it can aid clinicians and ophthalmologist in the process of detecting and treating the infamous DR.

cs.CV↗

arXiv2020

A survey on subjecting electronic product code and non-ID objects to IP identification

Over the last decade, both research on the Internet of Things (IoT) and real-world IoT applications have grown exponentially. The IoT provides us with smarter cities, intelligent homes, and generally more comfortable lives. However, the introduction of these devices has led to several new challenges that must be addressed. One of the critical challenges facing interacting with IoT devices is to address billions of devices (things) around the world, including computers, tablets, smartphones, wearable devices, sensors, and embedded computers, and so on. This article provides a survey on subjecting Electronic Product Code and non-ID objects to IP identification for IoT devices, including their advantages and disadvantages thereof. Different metrics are here proposed and used for evaluating these methods. In particular, the main methods are evaluated in terms of their: (i) computational overhead, (ii) scalability, (iii) adaptability, (iv) implementation cost, and (v) whether applicable to already ID-based objects and presented in tabular format. Finally, the article proves that this field of research will still be ongoing, but any new technique must favorably offer the mentioned five evaluative parameters.

cs.NI↗

arXiv2020

On Parameter Tuning in Meta-learning for Computer Vision

Learning to learn plays a pivotal role in meta-learning (MTL) to obtain an optimal learning model. In this paper, we investigate mage recognition for unseen categories of a given dataset with limited training information. We deploy a zero-shot learning (ZSL) algorithm to achieve this goal. We also explore the effect of parameter tuning on performance of semantic auto-encoder (SAE). We further address the parameter tuning problem for meta-learning, especially focusing on zero-shot learning. By combining different embedded parameters, we improved the accuracy of tuned-SAE. Advantages and disadvantages of parameter tuning and its application in image classification are also explored.

cs.CV↗

arXiv2019

Deep Learning at the Edge

The ever-increasing number of Internet of Things (IoT) devices has created a new computing paradigm, called edge computing, where most of the computations are performed at the edge devices, rather than on centralized servers. An edge device is an electronic device that provides connections to service providers and other edge devices; typically, such devices have limited resources. Since edge devices are resource-constrained, the task of launching algorithms, methods, and applications onto edge devices is considered to be a significant challenge. In this paper, we discuss one of the most widely used machine learning methods, namely, Deep Learning (DL) and offer a short survey on the recent approaches used to map DL onto the edge computing paradigm. We also provide relevant discussions about selected applications that would greatly benefit from DL at the edge.

cs.LG↗

arXiv2019

An Introduction to Advanced Machine Learning : Meta Learning Algorithms, Applications and Promises

In [1, 2], we have explored the theoretical aspects of feature extraction optimization processes for solving largescale problems and overcoming machine learning limitations. Majority of optimization algorithms that have been introduced in [1, 2] guarantee the optimal performance of supervised learning, given offline and discrete data, to deal with curse of dimensionality (CoD) problem. These algorithms, however, are not tailored for solving emerging learning problems. One of the important issues caused by online data is lack of sufficient samples per class. Further, traditional machine learning algorithms cannot achieve accurate training based on limited distributed data, as data has proliferated and dispersed significantly. Machine learning employs a strict model or embedded engine to train and predict which still fails to learn unseen classes and sufficiently use online data. In this chapter, we introduce these challenges elaborately. We further investigate Meta-Learning (MTL) algorithm, and their application and promises to solve the emerging problems by answering how autonomous agents can learn to learn?.

cs.LG↗

arXiv2019

Applications of Nature-Inspired Algorithms for Dimension Reduction: Enabling Efficient Data Analytics

In [1], we have explored the theoretical aspects of feature selection and evolutionary algorithms. In this chapter, we focus on optimization algorithms for enhancing data analytic process, i.e., we propose to explore applications of nature-inspired algorithms in data science. Feature selection optimization is a hybrid approach leveraging feature selection techniques and evolutionary algorithms process to optimize the selected features. Prior works solve this problem iteratively to converge to an optimal feature subset. Feature selection optimization is a non-specific domain approach. Data scientists mainly attempt to find an advanced way to analyze data n with high computational efficiency and low time complexity, leading to efficient data analytics. Thus, by increasing generated/measured/sensed data from various sources, analysis, manipulation and illustration of data grow exponentially. Due to the large scale data sets, Curse of dimensionality (CoD) is one of the NP-hard problems in data science. Hence, several efforts have been focused on leveraging evolutionary algorithms (EAs) to address the complex issues in large scale data analytics problems. Dimension reduction, together with EAs, lends itself to solve CoD and solve complex problems, in terms of time complexity, efficiently. In this chapter, we first provide a brief overview of previous studies that focused on solving CoD using feature extraction optimization process. We then discuss practical examples of research studies are successfully tackled some application domains, such as image processing, sentiment analysis, network traffics / anomalies analysis, credit score analysis and other benchmark functions/data sets analysis.

cs.LG↗

arXiv2019

Evolutionary Computation, Optimization and Learning Algorithms for Data Science

A large number of engineering, science and computational problems have yet to be solved in a computationally efficient way. One of the emerging challenges is how evolving technologies grow towards autonomy and intelligent decision making. This leads to collection of large amounts of data from various sensing and measurement technologies, e.g., cameras, smart phones, health sensors, smart electricity meters, and environment sensors. Hence, it is imperative to develop efficient algorithms for generation, analysis, classification, and illustration of data. Meanwhile, data is structured purposefully through different representations, such as large-scale networks and graphs. We focus on data science as a crucial area, specifically focusing on a curse of dimensionality (CoD) which is due to the large amount of generated/sensed/collected data. This motivates researchers to think about optimization and to apply nature-inspired algorithms, such as evolutionary algorithms (EAs) to solve optimization problems. Although these algorithms look un-deterministic, they are robust enough to reach an optimal solution. Researchers do not adopt evolutionary algorithms unless they face a problem which is suffering from placement in local optimal solution, rather than global optimal solution. In this chapter, we first develop a clear and formal definition of the CoD problem, next we focus on feature extraction techniques and categories, then we provide a general overview of meta-heuristic algorithms, its terminology, and desirable properties of evolutionary algorithms.

cs.NE↗

arXiv2018

The SWAG Algorithm; a Mathematical Approach that Outperforms Traditional Deep Learning. Theory and Implementation

The performance of artificial neural networks (ANNs) is influenced by weight initialization, the nature of activation functions, and their architecture. There is a wide range of activation functions that are traditionally used to train a neural network, e.g. sigmoid, tanh, and Rectified Linear Unit (ReLU). A widespread practice is to use the same type of activation function in all neurons in a given layer. In this manuscript, we present a type of neural network in which the activation functions in every layer form a polynomial basis; we name this method SWAG after the initials of the last names of the authors. We tested SWAG on three complex highly non-linear functions as well as the MNIST handwriting data set. SWAG outperforms and converges faster than the state of the art performance in fully connected neural networks. Given the low computational complexity of SWAG, and the fact that it was capable of solving problems current architectures cannot, it has the potential to change the way that we approach deep learning.

stat.ML↗

arXiv2018

Solving Minimum k-supplier in Adleman-Lipton model

In this paper, we consider an algorithm for solving the minimum k supplier problem using the Adleman Lipton model. The procedure works in polynomial steps for the minimum k supplier problem of an undirected graph with n vertices, which is an NP hard combinatorial optimization problem.

cs.DS↗

arXiv2017

Considerations on Interdisciplinary Instruction and Design Influenced by Adaptive Learning. A Case Study Involving Biology, Computer Science, Mathematics, and Statistics

ALICE (Adaptive Learning for Interdisciplinary Collaborative Environments) is an open-source web based adaptive learning system designed for interdisciplinary instruction. ALICE has the potential to transform education by empowering transdisciplinary knowledge acquisition. This is particularly important in fields that accept newcomers with diverse scholastic backgrounds, e.g. Systems Biology. With traditional interdisciplinary instruction, the instructor must cover pre-requisite information from multiple disciplines to ensure all students begin at a common baseline - slowing the learning process. With ALICE, students follow a personalized syllabus based on their previous knowledge and work towards individual goals. Implementing an adaptive learning system in an interdisciplinary course requires careful considerations of the instructional design. Structuring material, formulating assessments, and other instructional design aspects must be carefully considered. These considerations are detailed through the exploration of a case study implementing ALICE in a graduate level Systems Biology course.

physics.ed-ph↗

arXiv2016

Ancilla-Input and Garbage-Output Optimized Design of a Reversible Quantum Integer Multiplier

A reversible logic has application in quantum computing. A reversible logic design needs resources such as ancilla and garbage qubits to reconfigure circuit functions or gate functions. The removal of garbage qubits and ancilla qubits are essential in designing an efficient quantum circuit. In the literature, there are multiple designs that have been proposed for a reversible multiplication operation. A multiplication hardware is essential for the circuit design of quantum algorithms, quantum cryptanalysis, and digital signal processing (DSP) applications. The existing designs of reversible quantum integer multipliers suffer from redundant garbage qubits. In this work, we propose a reversible logic based, garbage-free and ancilla qubit optimized design of a quantum integer multiplier. The proposed quantum integer multiplier utilizes a novel add and rotate methodology that is specially suitable for a reversible computing paradigm. The proposed design methodology is the modified version of a conventional shift and add method. The proposed design of the quantum integer multiplier incorporates add or no operation based on multiplier qubits and followed by a rotate right operation. The proposed design of the quantum integer multiplier produces zero garbage qubits and shows an improvement ranging from 60% to 90% in ancilla qubits count over the existing work on reversible quantum integer multipliers.

quant-ph↗

arXiv2007

Combined Integer and Variable Precision (CIVP) Floating Point Multiplication Architecture for FPGAs

In this paper, we propose an architecture/methodology for making FPGAs suitable for integer as well as variable precision floating point multiplication. The proposed work will of great importance in applications which requires variable precision floating point multiplication such as multi-media processing applications. In the proposed architecture/methodology, we propose the replacement of existing 18x18 bit and 25x18 bit dedicated multipliers in FPGAs with dedicated 24x24 bit and 24x9 bit multipliers, respectively. We have proved that our approach of providing the dedicated 24x24 bit and 24x9 bit multipliers in FPGAs will make them efficient for performing integer as well as single precision, double precision, and Quadruple precision floating point multiplications.

cs.AR↗

arXiv2007

Partial Reversible Gates(PRG) for Reversible BCD Arithmetic

IEEE 754r is the ongoing revision to the IEEE 754 floating point standard and a major enhancement to the standard is the addition of decimal format. Furthermore, in the recent years reversible logic has emerged as a promising computing paradigm having its applications in low power CMOS, quantum computing, nanotechnology, and optical computing. The major goal in reversible logic is to minimize the number of reversible gates and garbage outputs. Thus, this paper proposes the novel concept of partial reversible gates that will satisfy the reversibility criteria for specific cases in BCD arithmetic. The partial reversible gate is proposed to minimize the number of reversible gates and garbage outputs, while designing the reversible BCD arithmetic circuits.

cs.AR↗