Amin Jalali | Islamic Azad University Of Mashhad (original) (raw)

Papers by Amin Jalali

2016 IEEE Tenth International Conference on Research Challenges in Information Science (RCIS)

Data Visualization is an important area of research including different techniques to enhance the... more Data Visualization is an important area of research including different techniques to enhance the capability of people to understand and use data-driven information. The chord diagram is a technique that aims to support the visualization of relations among different participants in a social network. Although this technique is widely used and adopted in many disciplines, it is not currently implemented in Business Process Management (BPM). In this paper, we show the potential of the visualizing social network in BPM area using the chord diagram. The result shows the potential benefits and strength of this technique to discover social network patterns in BPM area.

Journal of Software: Evolution and Process, 2018

Separation of concerns has long been an important strategy to deal with complexity when developin... more Separation of concerns has long been an important strategy to deal with complexity when developing a system. Some concerns (like security) are scattered through the whole system, and different modules are tangled to such concerns. These concerns are known as cross-cutting concerns. When the system in question is a business process, cross-cutting concerns are aimed at being encapsulated by Aspect-Oriented Business Process Modeling. However, the state-of-the-art techniques in this field lack efficient mechanisms that (1) support composition of cross-cutting concerns that can be defined in parallel to (a part of) a process model and (2) enable specifying both mandatory and optional cross-cutting concerns. To address these limitations, this paper proposes a new Aspect-Oriented Business Process Modeling approach. The approach is hybrid since it is based on declarative rules to relate imperative cross-cutting concerns and imperative business process models. The approach is explained, formally grounded with precise semantics, and used accordingly to implement the artifacts that support modeling and enactment of business processes in the proposed fashion as a proof of concept. In addition, the approach is evaluated on the basis of the Technology Acceptance Model during a workshop session. The result shows that participants perceived the approach usable and easy to use.

Coping with complexity in Information Systems and Software Engineering is an important issue in b... more Coping with complexity in Information Systems and Software Engineering is an important issue in both research and industry. One strategy to deal with this complexity is through a separation of concerns, which can result in reducing the complexity, improving the re-usability, and simplifying the evolution. Separation of concerns can be addressed through the Aspect Oriented paradigm. Although this paradigm has been well researched in the field of programming, it is still in a preliminary stage in the area of Business Process Management. While some efforts have been made to propose aspect orientation for business process modeling, it has not yet been investigated how these models should be implemented, configured, run, and adjusted. Such a gap has restrained the enactment of aspect orientated business process models in practice. Therefore, this book explain how aspect oriented business process models can be executed in Business Process Management Systems. The result enables separation of crosscutting concerns when enacting business process model.

Face recognition is still a challenging issue especially when the images contain various kinds of... more Face recognition is still a challenging issue especially when the images contain various kinds of occlusions, illumination variations, and poses. We propose robust Convolutional Neural Network (CNN) with the new cost function including the back propagated error and gradient of the hidden neuron penalty. The gradient penalty follows Hebb’s learning rule multiplied by the derivative of sigmoid function, which avoids the weights from drastically changing when it feedbacks the small variations of the output error to the input layer. The proposed method compared with I2DKPCA and conventional CNN shows that the proposed approach outperforms existing state of art methods.

ArXiv, 2019

Prior knowledge on properties of a target model often come as discrete or combinatorial descripti... more Prior knowledge on properties of a target model often come as discrete or combinatorial descriptions. This work provides a unified computational framework for defining norms that promote such structures. More specifically, we develop associated tools for optimization involving such norms given only the orthogonal projection oracle onto the non-convex set of desired models. As an example, we study a norm, which we term the doubly-sparse norm, for promoting vectors with few nonzero entries taking only a few distinct values. We further discuss how the K-means algorithm can serve as the underlying projection oracle in this case and how it can be efficiently represented as a quadratically constrained quadratic program. Our motivation for the study of this norm is regularized regression in the presence of rare features which poses a challenge to various methods within high-dimensional statistics, and in machine learning in general. The proposed estimation procedure is designed to perform ...

In many settings, we can accurately model high-dimensional data as lying in a union of subspaces.... more In many settings, we can accurately model high-dimensional data as lying in a union of subspaces. Subspace clustering is the process of inferring the subspaces and determining which point belongs to each subspace. In this paper we study a robust variant of sparse subspace clustering (SSC) [1]. While SSC is well-understood when there is little or no noise, less is known about SSC under significant noise or missing entries. We establish clustering guarantees in the presence of corrupted or missing entries. We give explicit bounds on the amount of additive noise and the number of missing entries the algorithm can tolerate, both in deterministic settings and in a random generative model. Our analysis shows that this method can tolerate up to$O(n/d)$ missing entries per column instead of$O(n/d^{2})$ as previous analyses show, where we have$d$-dimensional subspaces in an$n$-dimensional ambient space. Moreover, our method and analysis work by simply filling in the missing entries with zero...

In recent release of the new cellular standard known as 5G New Radio (5G-NR), the physical downli... more In recent release of the new cellular standard known as 5G New Radio (5G-NR), the physical downlink control channel (PDCCH) has adopted polar codes for error protection. Similar to 4G-LTE, each active user equipment (UE) must blindly detect its own PDCCH in the downlink search space. This work investigates new ways to improve the accuracy of PDCCH blind detection in 5G-NR. We develop a novel design of joint detection and decoding receiver for 5G multiple-input multiple-output (MIMO) transceivers. We aim to achieve robustness against practical obstacles including channel state information (CSI) errors, noise, co-channel interferences, and pilot contamination. To optimize the overall receiver performance in PDCCH blind detection, we incorporate the polar code information during the signal detection stage by relaxing and transforming the Galois field code constraints into the complex signal field. Specifically, we develop a novel joint linear programming (LP) formulation that takes int...

Given samples lying on any of a number of subspaces, subspace clustering is the task of grouping ... more Given samples lying on any of a number of subspaces, subspace clustering is the task of grouping the samples based on the their corresponding subspaces. Many subspace clustering methods operate by assigning a measure of affinity to each pair of points and feeding these affinities into a graph clustering algorithm. This paper proposes a new paradigm for subspace clustering that computes affinities based on the corresponding conic geometry. The proposed conic subspace clustering (CSC) approach considers the convex hull of a collection of normalized data points and the corresponding tangent cones. The union of subspaces underlying the data imposes a strong association between the tangent cone at a sample xxx and the original subspace containing xxx. In addition to describing this novel geometric perspective, this paper provides a practical algorithm for subspace clustering that leverages this perspective, where a tangent cone membership test is used to estimate the affinities. This alg...

This report demonstrates how storing events in a data ware-house can facilitate mining business p... more This report demonstrates how storing events in a data ware-house can facilitate mining business process models. The data warehouseis designed based on dimensional modelling principles for the Busin ...

Proceedings of the 3rd International Conference on Human-Agent Interaction, 2015

Palmprint recognition is a challenging problem, mainly due to low quality of the patterns, variat... more Palmprint recognition is a challenging problem, mainly due to low quality of the patterns, variation in focal lens distance, large nonlinear deformations caused by contactless image acquisition system, and computational complexity for the large image size of typical palmprints. This paper proposes a new contactless biometric system using features of palm texture extracted from the single hand image acquired from a digital camera. In this work, we propose to apply convolutional neural network (CNN) for palmprint recognition. The results demonstrate that the extracted local and general features using CNN are invariant to image rotation, translation, and scale variations.

Pattern Recognition Letters, 2020

In this paper, we propose integrated adaptive sensitivity and robustness terms for the cost funct... more In this paper, we propose integrated adaptive sensitivity and robustness terms for the cost function of a convolutional neural network (CNN). The sensitivity term considers the slight variations and high frequency components of the input image samples. It distinguishes between images that look similar but belong to different classes. This regularizer is designed to enhance the between-class distance which is a biological definition for the simple cells of the visual system. On the other hand, the robustness term is used to develop a more stable CNN structure against disturbances and perturbations. The robust term provides better within-class features because it recognizes images that look different but are actually from the same class. The robust term symbolizes the complex cell characteristics of the visual system. The coefficients of the sensitivity and robustness regularization terms are adaptively tuned along with the network parameters using gradient descent. Two optimizers are assigned to tune the parameters: one for tuning the model parameters and the other one to adjust the sensitivity and robustness coefficients. This approach is applied to Korean traditional documents for character classification. The results show better within-and between-class classification ability for highly complex character styles with imbalanced number of samples.

IEEE Transactions on Wireless Communications, 2020

Évolution et enjeux de l' enseignement supérieur à Madagascar Ewolucja i wyzwania szkolnictwa wyż... more Évolution et enjeux de l' enseignement supérieur à Madagascar Ewolucja i wyzwania szkolnictwa wyższego na Madagaskarze Résumé : L'objet du présent article est de contribuer à la réflexion sur le développement et le rôle de l'enseignement supérieur en Afrique. Nous étudions l'évolution du nombre total d'étudiants dans les universités publiques à Madagascar depuis le début des années 1960, période pendant laquelle des établissements d'enseignement supérieur ont acquis le statut universitaire. Les statistiques révèlent globalement une expansion des effectifs. La massification dans les établissements universitaires s'explique par des facteurs politiques, démographiques, sociologiques et économiques. Cette étude examine également les effets de l'augmentation en nombre des étudiants dans le pays. Elle agit négativement sur la qualité des formations. L'enseignement supérieur public joue un rôle déterminant dans l'insertion professionnelle des jeunes. En effet, il participe à la formation des ressources humaines dont l'économie nationale a besoin. En accroissant le niveau moyen d'éducation et de qualification de la population, les universités peuvent enfin constituer un outil pour favoriser le développement économique et social.

IEEE Journal of Biomedical and Health Informatics, 2019

Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia. The atrial beat is irregular d... more Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia. The atrial beat is irregular during AF, which causes blood flow hardly. This may cause blood clot formation and cardioembolic strokes. Computer-aided devices may assist cardiologists in diagnosing heart rhythm disorders better. From this viewpoint, we attempt to identify the premature atrial complexes (PACs) to predict the occurrence of AF by using electrocardiogram (ECG) spectrograms. Convolutional neural networks (CNN) models such as ResNet and Wide-ResNet are used to predict the prelude of AF. Regularization constraints are used to deal with the imbalanced and small number of samples in the minority premature AF class. Sensitivity regularization investigates small variations in premature AF samples. It highlights more representative features that distinguish the PACs from the normal rhythm. On the other hand, orthogonality regularization removes the interference between negatively correlated feature weights. It places constraints on capturing similar patterns with slight differences. This constraint allows convergence to a better feature representation with fewer weight redundancies. We propose a combination of sensitivity and orthogonality penalty terms to the cost function of ResNet to decrease the overfitting and obtain a superior representation. The re-sampling class distribution method is also utilized to mitigate the issue of imbalanced data. The proposed method shows better AF prediction for highly imbalanced data with a small number of samples.

SIAM Journal on Optimization, 2017

We propose a new class of convex penalty functions, called variational Gram functions (VGFs), tha... more We propose a new class of convex penalty functions, called variational Gram functions (VGFs), that can promote pairwise relations, such as orthogonality, among a set of vectors in a vector space. These functions can serve as regularizers in convex optimization problems arising from hierarchical classification, multitask learning, and estimating vectors with disjoint supports, among other applications. We study convexity for VGFs, and give efficient characterizations for their convex conjugates, subdifferentials, and proximal operators. We discuss efficient optimization algorithms for regularized loss minimization problems where the loss admits a common, yet simple, variational representation and the regularizer is a VGF. These algorithms enjoy a simple kernel trick, an efficient line search, as well as computational advantages over first order methods based on the subdifferential or proximal maps. We also establish a general representer theorem for such learning problems. Lastly, numerical experiments on a hierarchical classification problem are presented to demonstrate the effectiveness of VGFs and the associated optimization algorithms.

International Journal of u- and e-Service, Science and Technology, 2015

Following the developments in industrial robot technology, robotics has found its way into the me... more Following the developments in industrial robot technology, robotics has found its way into the medical field and is used in a range of surgical disciplines. The main purpose of the use of robots is to increase the precision, quality and safety of surgical procedures. Robotics is not yet used in dentistry even though all the necessary technologies have already been developed and could easily be adapted. Some of the technologies are already used in dentistry, such as image-based simulation of implant surgery followed by the use of surgical guides, and creating digital impressions of pre parathions using an intra-oral scanner, after which a milling device produces the restoration, but we have not yet seen any robot able to prepare teeth for crowns, inlays or bridges. Such a robot would fundamentally be a dental drilling device coupled with a navigation device to determine the correct position of the device in relation to the patient. The robot would either be operated directly by a dentist or be preprogrammed to perform its functions based on imaging data (CT scan). Finally, an intra-oral scanner would be used to make digital impressions. This data would then be transferred to the lab to produce temporary crowns or bridges in a very short time using a milling machine and to manufacture the final restorations in much shorter time than with conventional procedures. Robotics could offer dentistry improved accuracy, predictability, safety, quality of care and speed of treatment. One might wonder why robots have not yet been introduced to dentistry, as the functions needed are relatively simple. An explanation could be that robotics in dentistry is an example of a disruptive technology, meaning that the current manufacturers of dental equipment might fear a negative effect on their current business and the alienation of dentists, as robots might be seen as a threat to dental professionals. The passive robotic arm will sense the patient's movement, sending feedback in the form of translation and rotation data to the dental robot giving it the capability to adjust. This device will address the age-old problem in dentistryprecision and safety. This research focuses on the intelligent control of dental drilling procedures on a stationary object. This project addresses the ability of the system to detect movement of the object and accordingly adjust the drill before continuing the procedure.

Software & Systems Modeling, 2015

Coping with complexity is an important issue in both research and industry. One strategy to deal ... more Coping with complexity is an important issue in both research and industry. One strategy to deal with complexity is separation of concerns, which can be addressed using aspect-oriented paradigm. Despite being well researched in programming, this paradigm is still in a preliminary stage in the area of business process management (BPM). While some efforts have been made to introduce aspect orientation in business process modelling, there is no holistic approach with a formal underlying foundation to support aspect-oriented business process design and enactment, and this gap restricts aspect-oriented paradigm from being practically deployed in the area of BPM. Therefore, this paper proposes a sound systematic approach which builds on a formal syntax for modelling aspect-oriented business processes and a Petri Net-based operational semantics for enacting these processes. The approach enables the implementation of software system artefacts as a proof of concept to support design and enactment of aspect-oriented business processes in practice. The approach is demonstrated using a banking case study, where processes are modelled using a concrete notation that conforms to the proposed formal syntax and then executed in a state-of-the-art BPM system where the implemented artefacts are deployed.

On the Move to Meaningful Internet Systems: OTM 2013 Conferences, 2013

The original publication is available at SpringerLink Notice: Changes introduced as a result of p... more The original publication is available at SpringerLink Notice: Changes introduced as a result of publishing processes such as copy-editing and formatting may not be reflected in this document. For a definitive version of this work, please refer to the published source

Lecture Notes in Computer Science, 2012

Aspect orientation is an important approach to address complexity of cross-cutting concerns in In... more Aspect orientation is an important approach to address complexity of cross-cutting concerns in Information Systems. This approach encapsulates these concerns separately and compose them to the main module when needed. Although there are different works which shows how this separation should be performed in process models, the composition of them is an open area. In this paper, we demonstrate the semantics of a service which enables this composition. The result can also be used as a blueprint to implement the service to support aspect orientation in Business Process Management area.

Information Systems and e-Business Management, 2014

The traditional way of business process development is via creating a detailed model of a busines... more The traditional way of business process development is via creating a detailed model of a business process in question, acquiring an IT-system to support it, and then implementing it in the organizational practice. Acquiring a system can be done via designing and manufacturing it by the business itself, or via commissioning it to somebody else. Alternatively, a generic system can be bought and configured according to the business process model created. The traditional approach has a number of risks that become visible only during the latest phase of introducing the system in the organizational practice, e.g., when it becomes clear that the system does not fit the business and/or people who work in it. These risks could be mitigated by using an agile approach to the development of business processes. In agile approach: (a) the phases of process modeling, IT-system design, and manufacturing are merged into one, and (b) instead of using one big cycle, a series of smaller development cycles is used. The paper discusses what is needed to implement the agile approach, and in which business situations the agile approach is the most appropriate. Examples of tools to support agile development are presented and analyzed. The results presented in the paper have been achieved based on the knowledge transformation perspective along the lines suggested by Nonaka in SECI model. The modification of this model has been used to understand the risks and requirements connected to a particular process development strategy.

A Field Programmable Gate Array (FPGAs) is a small Field Programmable Device (FPD) that supports ... more A Field Programmable Gate Array (FPGAs) is a small Field Programmable Device (FPD) that supports thousands of logic gates. FPGA is a high speed, low cost, short time to market and small device size. Technically speaking an FPGA can be used to solve any problem which is computable. This is trivially proven by the fact FPGA can be used to implement a Soft microprocessor. Their advantage lies in that they are sometimes significantly faster for some applications due to their parallel nature and optimality in terms of the number of gates used for a certain process. Specific applications of FPGAs include digital signal processing, software-defined radio, ASIC prototyping, medical imaging, computer vision, speech recognition, nonlinear control, cryptography, bioinformatics, computer hardware emulation, radio astronomy, metal detection and a growing range of other areas. Traditionally, FPGAs have been reserved for specific vertical applications where the volume of production is small. For t...