Sharif Digital Repository

Background: Type-2 diabetes mellitus is characterized by insulin resistance and impaired insulin secretion in the human body. Many endeavors have been made in terms of controlling and reducing blood glucose via the medium of automated controlling tools to increase precision and efficiency and reduce human error. Recently, reinforcement learning algorithms are proved to be powerful in the field of intelligent control, which was the motivation for the current study. Methods: For the first time, a reinforcement algorithm called normalized advantage function (NAF) algorithm has been applied as a model-free reinforcement learning method to regulate the blood glucose level of type-2 diabetic... 

Coming up with a model which matches biological observations more closely has always been one of the main challenges in the field of artificial neural networks. Lately, an ionic model of reservoir networks containing spiking neurons (ILS-based reservoir network) has been proposed which seems to replicate some of the biological processes we have observed up until now. This paper presents a local learning rule for the ILS-based reservoir inspired by the biological fact that each incoming stimulus causes the formation of new dendritic spines, producing new synapses. This property may result in a higher degree of neuroplasticity, leading to a higher learning capacity. To evaluate the proposed... 

By generalising dictionary learning (DL) algorithms to multidimensional (MD) mode and using them in applications where signals are inherently multidimensional, such as in three-dimensional (3D) inverse synthetic aperture radar (ISAR) imaging, it is possible to achieve much higher speed and less computational complexity. In this study, the formulation of the multidimensional dictionary learning (MDDL) problem is expressed and two algorithms are proposed to solve it. The first one is based on the method of optimum directions (MOD) algorithm for 1D dictionary learning (1DDL), which uses alternating minimisation and gradient projection approach. As the MDDL problem is non-convex, the second... 

Recently, remote sensing considered as important tool in studies of water quality issues. The Aras River flows across a transboundary basin in northern Iran. In this study, the aim is to model the water quality parameters (WQPs) using remote sensing and an artificial neural network (ANN), which is a new method proposed to find WQPs based on multivariate regression approaches. The relationship between WQPs and digital data from the Sentinel-2 satellite was determined to estimate and map the WQPs in this river. Using the field data and digital image data, the obtained results show that multivariate regression approaches and high-resolution remote sensing could monitor and predict the... 

Public-key plays a significant role in today's communication over the network. However, current state-of-the-art public-key encryption (PKE) schemes are too complex to be efficiently employed in resource-constrained devices. Moreover, they are vulnerable to quantum attacks and soon will not have the required security. In the last decade, lattice-based cryptography has been a progenitor platform of the post-quantum cryptography (PQC) due to its lower complexity, which makes it more suitable for Internet of Things applications. In this article, we propose an efficient implementation of the binary learning with errors over ring (Ring-BinLWE) on the reduced instruction set computer-five (RISC-V)... 

Internet traffic recognition is essential for access providers since it helps them define adapted priorities in order to enhance user experience, e.g., a high priority for an audio conference and a low priority for a file transfer. As internet traffic becomes increasingly encrypted, the main classic traffic recognition technique, payload inspection, is rendered ineffective. Hence this paper uses machine learning techniques looking only at packet size and time of arrival. For the first time, Spiking neural networks (SNNs), which are inspired by biological neurons, were used for this task for two reasons. Firstly, they can recognize time-related data packet features. Secondly, they can be... 

Cost overrun risks are declared to be dynamic and interdependent. Ignoring the relationship between cost overrun risks during the risk assessment process is one of the primary reasons construction projects go over budget. Conversely, recent studies have failed to account for potential interrelationships between risk factors in their machine learning (ML) models. Additionally, the presented ML models are not interpretable. Thus, this study contributes to the entire ML process using a Bayesian network (BN) classifier model by considering the possible interactions between predictors, which are cost overrun risks, to predict cost overrun and assess cost overrun risks. Furthermore, this study... 

In this paper, a target parameter estimation problem is addressed for the recently emerging frequency diverse array multiple-input multiple-output (FDA-MIMO) radar system, utilizing sparse learning. The scene is modeled as a two dimensional (2D) angle-incremental range grid. To solve the resulting sparse problem, the recently proposed user-parameter free algorithms including block sparse learning via iterative minimization (BSLIM), iterative adaptive approach (IAA), sparse iterative covariance-based estimation (SPICE), likelihood-based estimation of sparse parameters (LIKES), and orthogonal matching pursuit (OMP) are applied which achieve excellent parameter estimation performance. However,... 

The quality of fresh apple fruits is a major concern for consumers and manufacturers. Classification of these fruits according to their ripening stage is one of the most decisive factors in determining their quality. In this regard, the aim of this work is to develop a new method for non-destructive classification of the ripening state of Fuji apples using hyperspectral information in the visible and near-infrared (Vis/NIR) regions. Spectra of 172 apple samples in the range from 450 to 1000 nm were studied, which were selected from four different ripening stages. A convolutional neural network (CNN) model was proposed to perform the classification of the samples. The proposed method was... 

We study the problem of experiment design to learn causal structures from interventional data. We consider an active learning setting in which the experimenter decides to intervene on one of the variables in the system in each step and uses the results of the intervention to recover further causal relationships among the variables. The goal is to fully identify the causal structures with minimum number of interventions. We present the first deep reinforcement learning based solution for the problem of experiment design. In the proposed method, we embed input graphs to vectors using a graph neural network and feed them to another neural network which outputs a variable for performing... 

Deep learning (DL) has been employed for a wide range of tasks in dentistry. We aimed to systematically review studies employing DL for periodontal and implantological purposes. A systematic electronic search was conducted on four databases (Medline via PubMed, Google Scholar, Scopus, and Embase) and a repository (ArXiv) for publications after 2010, without any limitation on language. In the present review, we included studies that reported deep learning models' performance on periodontal or oral implantological tasks. Given the heterogeneities in the included studies, no meta-analysis was performed. The risk of bias was assessed using the QUADAS-2 tool. We included 47 studies: focusing on... 

Supply chain management integrates planning and controlling of materials, information, and finances in a process which begins from suppliers and ends with customers. Optimal planning decisions made in such a distribution network usually include transportation, facilities location, and inventory. This study presents a new approach for considering customers’ differentiation in an integrated location-allocation and inventory control model using transfer recurrent neural network (RNN). In this study, a location and allocation problem is integrated with inventory control decisions considering two classes of strategic and non-strategic customers. For the first time, a novel transfer RNN is applied... 

Increasing usage of Solid-State Drives (SSDs) has greatly boosted the performance of storage backends. SSDs perform many internal processes such as out-of-place writes, wear-leveling, and garbage collection. These operations are complex and not well documented which make it difficult to create accurate SSD simulators. Our survey indicates that aside from complex configuration, available SSD simulators do not support both sync and discard requests. Past performance models also ignore the long term effect of I/O requests on SSD performance, which has been demonstrated to be significant. In this article, we utilize a methodology based on machine learning that extracts history-aware features at... 

Studying the mechanical performance of concrete after being exposed to high temperatures is an important step in the damage assessment of buildings and fire safety applications. However, predicting the compressive strength of GPC accurately after exposure to high temperatures is a challenging task. In this paper, artificial neural network (ANN) and support vector regression (SVR) models were developed to predict the compressive strength of geopolymer concrete (GPC) at high temperatures ranging from 100 °C to 1000 °C. A series of experiments consisting of different mix designs were conducted at elevated temperatures to prepare a dataset. Besides experiments' results, the data of previously... 

Pretrained representations have recently gained attention in various machine learning applications. Nonetheless, the high computational costs associated with training these models have motivated alternative approaches for representation learning. Herein we introduce TripletProt, a new approach for protein representation learning based on the Siamese neural networks. Representation learning of biological entities which capture essential features can alleviate many of the challenges associated with supervised learning in bioinformatics. The most important distinction of our proposed method is relying on the protein-protein interaction (PPI) network. The computational cost of the generated... 

Deep learning-based graph generation approaches have remarkable capacities for graph data modeling, allowing them to solve a wide range of real-world problems. Making these methods able to consider different conditions during the generation procedure even increases their effectiveness by empowering them to generate new graph samples that meet the desired criteria. This paper presents a conditional deep graph generation method called SCGG that considers a particular type of structural conditions. Specifically, our proposed SCGG model takes an initial subgraph and autoregressively generates new nodes and their corresponding edges on top of the given conditioning substructure. The architecture... 

Aim of study: Glioblastoma Multiforme (GBM) is an aggressive brain cancer in adults that kills most patients in the first year due to ineffective treatment. Different clinical, biomedical, and image data features are needed to analyze GBM, increasing complexities. Besides, they lead to weak performances for machine learning models due to ignoring physicians' knowledge. Therefore, this paper proposes a hierarchical model based on Fuzzy C-mean (FCM) clustering, Wrapper feature selection, and twelve classifiers to analyze treatment plans. Methodology/Approach: The proposed method finds the effectiveness of previous and current treatment plans, hierarchically determining the best decision for... 

After a significant earthquake, the updated status of the structural elements is usually determined based on a qualitative visual inspection. Although visual inspection provides a prompt assessment of the damaged elements, the output of this subjective method is influenced by the experience and decision of a trained inspector, which may vary from case to case. In this study, an innovative machine learning-based procedure is developed to automate damage state identification of non-ductile reinforced concrete moment frames (RCMFs) utilizing visual indices of crack patterns of the concrete surface. An extensive database including 264 surface crack patterns is constructed corresponding to 61... 

One of the technologies based on information technology used today is the VANET network used for inter-road communication. Today, many developed countries use this technology to optimize travel times, queue lengths, number of vehicle stops, and overall traffic network efficiency. In this research, we investigate the critical and necessary factors to increase the quality of VANET networks. This paper focuses on increasing the quality of service using multi-agent learning methods. The innovation of this study is using artificial intelligence to improve the network's quality of service, which uses a mechanism and algorithm to find the optimal behavior of agents in the VANET. The result... 

Adding memory to artificial intelligence systems in an effective way has been addressed by researchers for many years. Recurrent neural networks and long short-term memories (LSTMs), among other neural network systems, have some inherent memory capabilities. Recently, in memory augmented neural networks, such as neural Turing machine (NTM) and its variants, a separate memory module is implemented, which can be accessed via read and write heads. Despite its capabilities in simple algorithmic tasks, such as copying and repeat copying, neural Turing machines fail when doing complex tasks with long-term dependencies due to their limited memory capacity. In this paper, we propose a new memory...