Journal of Innovations in Computer Science and Engineering (JICSE)

Abstract This paper presents a comprehensive modeling framework for managing the complexities inherent in modeling dynamic and intelligent embedded and cyber-physical systems (CPSs). Leveraging the scenario-aware dataflow (SADF) model of computation (MoC), our framework effectively captures CPS dynamism through controlled scenario representations. We establish denotational-style semantics within the Formal System Design (ForSyDe) framework and operational-style semantics tailored for practical industrial implementation. Integration of SADF MoC into ForSyDe-SystemC exploits modern C++ language features, offering type- and size-safety, model introspection, parallel simulation, and foreign model integration. The contributed SADF extension possesses the capability to seamlessly interconnect with other MoCs, thereby facilitating heterogeneous system modeling. Demonstrational examples, including an encoder/decoder system and an MPEG-4 decoder algorithm for the simple profile, attest to the framework's correctness and practicality. We also introduce a tool flow for automated synthetic benchmark generation, essential for assessing the scalability and performance of ForSyDe-SystemC SADF models in diverse conditions. The extended modeling framework, examples, and supporting tools are available as public domain code.

Abstract K-means clustering is one of the most prominent clustering methods that is used in many applications. By considering a widespread application of k-means clustering, redesign of this method in the context of high-performance computing has a considerable impact. In this paper, we consider scalability and utilize the available resources at a different level of parallelism. As a result, novel techniques are proposed for different hardware platforms, which are evaluated separately on uniformly random generated datasets and with different sizes. We change classic two-stage Lloyd’s formulation to a three stage that utilizes different techniques for each stage separately. Besides, we use an algebraic technique to reduce the amount of calculation and lay the foundation for consequent ideas. In CPUs, we propose a parallel architecture based on OpenMP and AVX2 instruction set. In GPUs, we utilize atomic operation and shared memory without considering GPU memory, and shared memory capabilities. Proposed method extends to multi-GPU. We merge these techniques and utilize MPI to scale it for multiple-node platforms.

Abstract With growing adoption of Internet of Things (IoT) technologies, the number of connected devices and the complexity of its applications increase. Therefore, novel concepts such as edge and fog computing are suggested to introduce processing, connectivity and storage capabilities between devices and the cloud to overcome the challenge of handling large amounts of data. However, these layers introduce new challenges in their design, especially in the architecture and micro-architecture levels. In this article, a systematic NISC-based (No Instruction Set Computer) micro-architecture design methodology, NIMA, is presented to rapidly and optimally customize a processor architecture for an application domain of interest, based on a representative benchmark. A new utilization metric and a supporting heuristic algorithm are proposed to help with optimizing the processor data-path. We apply our methodology to design optimal processors based on the performance, area or power design objectives for a proposed benchmark in the fog computing domain. Experimental evidence shows the improvement of desired objectives in different scenarios compared to a conventional MIPS-based processor.

Abstract As quantum computers become increasingly powerful, the threat of attacking classical algorithms will become more significant. Hence, post-quantum cryptography algorithms are effective alternatives to previous asymmetric algorithms. NTRU Prime is one of the KEM algorithms based on the attention grid in the NIST competition. Implementing such algorithms involves heavy polynomial multiplications over a ring. Number theoretic transformations allow the multiplication of polynomials to be performed in quasi-linear time O(nlog(n)). Hardware implementations of NTT multipliers are typically implemented using a butterfly structure to increase efficiency. We have proposed an efficient architecture for the NTT multiplier. We have redesigned and modified the method for using and storing the pre-processed data, this idea results in a 7% increase in frequency and a reduction of over 14% in the use of LUTs, compared to the best previous work. As a result of the reduction in delay, as well as the reduction in resources consumed, the efficiency of the process has been increased.

Abstract Augmented reality technology integrates information with the environment in real-time. The capability to add information to objects and interact with users according to their requests can be an enjoyable and useful experience. Most Augmented Reality systems have a fixed static database containing registered objects. To enhance Augmented Reality applications, dynamic information sources can be used. An information source such as the web which has expanded and up-to-date data, could be an appropriate alternative. Using these information sources in real-time enables the use of Augmented Reality on a wider scale.
This paper introduces an Augmented Reality model based on online content is presented. In this research, case studies are human faces and context-based information is a virtual element, i.e., information about the target face. Using web information resources dynamizes the system in a variety of environments. Furthermore, the user interacts with the system through question-answering. Deep learning methods have been used for information retrieval and question-answering. Moreover, Answers to frequently asked questions that are confirmed by users are stored in the database for faster response time.
The experimental results reveal that users can interact with the Augmented Reality system through question-answering and augment the required information with a speed of 0.642 seconds and an F-score of 87.9% on the SQuAD dataset.

Abstract While the growth of technology has greatly benefited humanity, it also brings along several drawbacks that can undermine these benefits. Despite its ability to detect attacks and deter various forms of theft, technology is often regarded as a tool for creating new theft techniques. Conducting a systematic review, this article discusses the current state of the art in terms of identity theft motivations, the techniques employed, and the potential harm inflicted upon victims. The paper findings reveal that the reasons behind such incidents can be categorized into seven main categories: financial, commercial, health and medical, educational, citizenship, Internet of Things (IoT), and informational. Fraudsters employ various methods to steal identity information, which can be categorized as social engineering, vulnerabilities, malware, eavesdropping, and information gathering. However, it is important to note that not all identity theft reasons are a concern for people of all ages. This article addresses the examination of potential threats within different age groups. Tragically, victims of identity theft often endure significant financial, legal, social, and health harm as a result of these malicious activities. One of the primary strategies to combat this crime involves investigating the causes, methods, and age distribution of the potential victim population.

Abstract Over the past few years, the study of complex networks as an interdisciplinary subject has yielded numerous insights. Communication links within these networks have been found to play a crucial role in shaping the implementation of dynamic processes. Recursive graphs are a class of complex networks whose internal structure is governed by recurrent relations. Among these, line graphs are especially important because they represent the communication links within the network as nodes. Studying the heterogeneity, or irregularity, of different graph models is a fundamental research issue in complex and social network analysis. In this article, we investigate the mapping between graph robustness and heterogeneity metrics and their equivalent metrics in line graphs. Specifically, we analyze the distribution of eigenvalues and important indices of heterogeneity in recursive and line graphs. We also examine the changes in heterogeneity of recursive line graphs with the introduction of a set of important heterogeneity indices. Our approach is broadly applicable to a wide range of indicators and complex networks beyond those discussed in this study.

Abstract Image captioning aims at automatically generating description of an image in natural language. This is a challenging problem in the field of artificial intelligence that has recently received significant attention in the computer vision and natural language processing. Among the existing approaches, visual retrieval based methods have been shown to be highly effective. These approaches search for similar images, then build a caption for the query image based on the captions of the retrieved images. In this study, we present a method for visual retrieval based image captioning, in which we use a multi criteria decision making algorithm to effectively combine several criteria with proportional impact weights to retrieve the most relevant caption for the query image. The main idea of the proposed approach is to design a mechanism to retrieve more semantically relevant captions with the query image and then selecting the most appropriate caption by imitation of the human act based on a weighted multi-criteria decision making algorithm. Experiments conducted on MS COCO benchmark dataset have shown that proposed method provides much more effective results compared to the state-of-the-art models.

Abstract Covering all edges in a graph with a small set of vertices is one of the most fundamental graph problems which is called the minimum vertex cover problem. In the literature different strategies have been employed to find near-optimal minimum vertex cover set in different kinds of graphs.
In this work, two efficient algorithms (i.e., MAxA and MAxAR) are introduced to find the minimum vertex cover set in any unweighted undirected graph. The proposed construction algorithms have two main steps in each iteration which explore neighborhoods of minimum degree vertices to find and select appropriate vertices for the cover set. Until all of the edges are removed or selected in the algorithms, these two steps are performed iteratively. The proposed algorithms have been implemented on DIMACS, BHOSLIB, and other benchmarks where experimental results show that the proposed algorithms outperform other relevant methods in terms of time and cardinality of vertex cover set.

Abstract In this paper, all-optical photonic crystal two bit adder based on nonlinear ring resonator is designed. The proposed structures includes threshold detectors and junctions. In our proposed structure, in order to resolve the low transmission problem in input junction, an enhanced junction is cascaded by a threshold detector to implement full adder cells. By cascading two optimized full adder a two bit adder has been designed. Nonlinear rods of the proposed structures are made of Silicon nanocrystal to create the required frequency shift for implementation of the proposed structures. In order to evaluate the performance of the proposed structures, the plane wave expansion and finite difference time domain methods are used. The proposed optimized full adder cell occupy an area about 340 µm2 with maximum power 5 W for switching mechanism. Our simulation results show that the proposed full adder can operate with a bit rate of more than 580 Gbits/s.

Abstract Protection of computer systems is a challenge facing the users, who usually define passwords, fingerprints, face detection patterns, and other identification solutions in order to secure their systems against the misuse and unauthorized access. Nevertheless, these solutions are effective in preventing anonymous people from logging in to the system. If a user leaves a system unlocked for a while or a password has already been disclosed for any reason, such trivial solutions will then fail to secure the system. In this study we introduces new dynamic features considering the time, category and type of the applications a user uses and use them in combination with existing operation-related features in a anomaly detection framework for user authentication. A combination of operation-related and application-related features are then taken into account to create a base profile for each authenticated user in order to detect any unauthorized access. The proposed method can secure systems even if an unauthorized access occurs. In other words, this method compares the current user’s behaviour with the base profile of authenticated user momentarily. If an anomaly is detected, that user is recognized as an unauthorized user and will then be prohibited from working with the system or asked to undergo a two-step authentication process.

Abstract In this paper, a neural approach based on Long Short-Term Memory (LSTM) neural networks is proposed to diagnose patients suffering from Parkinson’s Disease (PD). Considering the movement disorders caused by PD, the proposed method investigates the gait cycle pattern of subjects based on vertical Ground Reaction Force (vGRF) measured by 16 wearable sensors placed in subjects' shoes. In this study, it is shown that the temporal patterns of the gait cycle are different for healthy persons and patients. Therefore, by using a recurrent structure like LSTM, able to analyze the dynamic nature of the gait cycle, the proposed method extracts the temporal patterns to diagnose patients from healthy persons. To reduce the number of data dimensions, the sequences of corresponding sensors measuring vGRF in different feet are combined by subtraction. This method analyzes the temporal pattern of time series collected from different sensors, without extracting special features representing statistics of different parts of the gait cycle. Indeed, the method can extract temporal features based on learning, without using expert knowledge. Finally, the Accuracy and F1 Score of the model trained with all data is $99.87\%$, and $96.66\%$ respectively.