World Academy of Science, Engineering and Technology

Authors: Zhou Luchen, Wu Yubing, Burra Venkata Durga Kumar

Abstract:

As the scale of the network becomes larger and more complex than before, the density of user devices is also increasing. The development of Unmanned Aerial Vehicle (UAV) networks is able to collect and transform data in an efficient way by using software-defined networks (SDN) technology. This paper proposed a three-layer distributed and dynamic cluster architecture to manage UAVs by using an AI-based resource allocation calculation algorithm to address the overloading network problem. Through separating services of each UAV, the UAV hierarchical cluster system performs the main function of reducing the network load and transferring user requests, with three sub-tasks including data collection, communication channel organization, and data relaying. In this cluster, a head node and a vice head node UAV are selected considering the CPU, RAM, and ROM memory of devices, battery charge, and capacity. The vice head node acts as a backup that stores all the data in the head node. The k-means clustering algorithm is used in order to detect high load regions and form the UAV layered clusters. The whole process of detecting high load areas, forming and selecting UAV clusters, and moving the selected UAV cluster to that area is proposed as offloading traffic algorithm.

Keywords: k-means, resource allocation, SDN, UAV network, unmanned aerial vehicles.

Authors: Haowei Chen, Kaiqi Xiong

Abstract:

We have developed a better model for understanding the dynamics of malware spread in WMNs in this paper. The suggested model provides an insight into how viral propagation with energy exhaustion and various dispersed node densities might function. Based on a theoretical examination of the suggested model, we conclude that the threshold parameter could be used to identify the dynamics of viral spread globally. When the threshold is less than 1, the virus may be contained, but if it is greater than 1, a pandemic may result. Lastly, we discuss the various viral propagation strategies in relation to the distributed node densities and communication radii in WMNs. The aforementioned numerical simulation findings could serve as a guarantee of the theoretical analyses’ correctness.

Keywords: Bluetooth Security, Malware Propagation, Wireless Mesh Networks, Stability Analysis.

Authors: Rishabh Garg

Abstract:

Blockchain technology can allow remote, untrusted parties in the banking and financial sector to reach consensus on the state of databases without the involvement of gatekeepers. Like a bookkeeper, it can manage all financial transactions including payments, settlements, fundraising, securities management, loans, credits and trade finance. It can outperform existing systems in terms of identity verification, asset transfers, peer-to-peer transfers, hedge funds, security and auditability. Blockchain-based decentralized finance (DeFi) is a new financial protocol. Being open and programmable, it enables various DeFi use-cases, including asset management, tokenization, tokenized derivatives, decentralized autonomous organizations, data analysis and valuation, payments, lending and borrowing, insurance, margin trading, prediction market, gambling and yield-farming, etc. In addition, it can ease financial transactions, cash-flow, use of programmable currency, no-loss lotteries, etc. This paper aims to assess the potential of decentralized finance by leveraging the blockchain-enabled Ethereum platform as an alternative to traditional finance. The study also aims to find out the impact of decentralized finance on prediction markets, quadratic funding and crowd-funding, together with the potential challenges and solutions associated with its implementation.

Keywords: Advance trading, crowd funding, exchange tokens, fund aggregation, margin trading, quadratic funding, smart contracts, streaming money, token derivatives.

Authors: C. Ardil

Abstract:

Intuitionistic fuzzy sets (IFS), Pythagorean fuzzy sets (PyFS), Picture fuzzy sets (PFS), q-rung orthopair fuzzy sets (q-ROF), Spherical fuzzy sets (SFS), T-spherical FS, and Neutrosophic sets (NS) are reviewed as multidimensional extensions of fuzzy sets in order to more explicitly and informatively describe the opinions of decision-making experts under uncertainty. To handle operations with standard fuzzy sets (SFS), the necessary operators; weighted arithmetic mean (WAM), weighted geometric mean (WGM), and Minkowski distance function are defined. The algorithm of the proposed proximity measure method (PMM) is provided with a multiple criteria group decision making method (MCDM) for use in a standard fuzzy set environment. To demonstrate the feasibility of the proposed method, the problem of selecting the best drone for an Air Force procurement request is used. The proximity measure method (PMM) based multidimensional standard fuzzy sets (SFS) is introduced to demonstrate its use with an issue involving unmanned combat aircraft selection.

Keywords: standard fuzzy sets (SFS), unmanned combat aircraft selection, multiple criteria decision making (MCDM), proximity measure method (PMM).

Authors: Yitao Lei, Xingxiang Zhai, Burra Venkata Durga Kumar

Abstract:

As the quantity and complexity of computing in large-scale software systems increase, distributed system computing becomes increasingly important. The distributed system realizes high-performance computing by collaboration between different computing resources. If there are no efficient resource scheduling resources, the abuse of distributed computing may cause resource waste and high costs. However, resource scheduling is usually an NP-hard problem, so we cannot find a general solution. However, some optimization algorithms exist like genetic algorithm, ant colony optimization, etc. The large scale of distributed systems makes this traditional optimization algorithm challenging to work with. Heuristic and machine learning algorithms are usually applied in this situation to ease the computing load. As a result, we do a review of traditional resource scheduling optimization algorithms and try to introduce a deep reinforcement learning method that utilizes the perceptual ability of neural networks and the decision-making ability of reinforcement learning. Using the machine learning method, we try to find important factors that influence the performance of distributed system computing and help the distributed system do an efficient computing resource scheduling. This paper surveys the application of deep reinforcement learning on distributed system computing resource scheduling. The research proposes a deep reinforcement learning method that uses a recurrent neural network to optimize the resource scheduling. The paper concludes the challenges and improvement directions for Deep Reinforcement Learning-based resource scheduling algorithms.

Keywords: Resource scheduling, deep reinforcement learning, distributed system, artificial intelligence.

Authors: Nouha Khediri, Mohammed Ben Ammar, Monji Kherallah

Abstract:

Recently, facial emotion recognition (FER) has become increasingly essential to understand the state of the human mind. However, accurately classifying emotion from the face is a challenging task. In this paper, we present a facial emotion recognition approach named CV-FER benefiting from deep learning, especially CNN and VGG16. First, the data are pre-processed with data cleaning and data rotation. Then, we augment the data and proceed to our FER model, which contains five convolutions layers and five pooling layers. Finally, a softmax classifier is used in the output layer to recognize emotions. Based on the above contents, this paper reviews the works of facial emotion recognition based on deep learning. Experiments show that our model outperforms the other methods using the same FER2013 database and yields a recognition rate of 92%. We also put forward some suggestions for future work.

Keywords: CNN, deep-learning, facial emotion recognition, machine learning.

Authors: Husam El-Asfour, Fateh Adhnouss, Kenneth McIsaac, AbdulMutalib Wahaishi, Raafat Aburukba, Idris El-Feghia

Abstract:

Although intelligence is commonly referred to as the observable behavior in various fields and domains, it must also be shown how it develops by exhibiting multiple forms and without observing the inherent behavior. There have been several official and informal definitions of intelligence in various areas; however, no scientific agreement on a definition has been agreed upon. There must be a single definition, structure, and precise modeling for articulating how intelligence is perceived by people and machines in order to comprehend intelligence. Another key challenge is defining the different environment types based on the integral elements (agents) and their possible interactions. On the basis of conceptualization, this paper proposes a formal model for defining and developing intelligence. Forms of intelligence are derived from an ontological view, and thus intelligence is defined, described, and modeled based on the various types of environments.

Keywords: Intelligence, forms, transformation, conceptualization, ontological view.

Authors: Xiao Yihong, Yu Kexin, Burra Venkata Durga Kumar

Abstract:

With the accelerating process of urbanization, the problem of urban road congestion is becoming more and more serious. Intelligent transportation system combining distributed and artificial intelligence has become a research hotspot. As the core development direction of the intelligent transportation system, Cooperative Intelligent Transportation System (C-ITS) integrates advanced information technology and communication methods and realizes the integration of human, vehicle, roadside infrastructure and other elements through the multi-agent distributed system. By analyzing the system architecture and technical characteristics of C-ITS, the paper proposes a distributed multi-agent C-ITS. The system consists of Roadside Subsystem, Vehicle Subsystem and Personal Subsystem. At the same time, we explore the scalability of the C-ITS and put forward incorporating local rewards in the centralized training decentralized execution paradigm, hoping to add a scalable value decomposition method. In addition, we also suggest introducing blockchain to improve the safety of the traffic information transmission process. The system is expected to improve vehicle capacity and traffic safety.

Keywords: Distributed system, artificial intelligence, multi-agent, Cooperative Intelligent Transportation System.

Authors: Fateh Adhnouss, Husam El-Asfour, Kenneth McIsaac, Abdul Mutalib Wahaishi, Idris El-Feghia

Abstract:

Conceptualization is an essential component of semantic ontology-based approaches. There have been several approaches that rely on extensional structure and extensional reduction structure in order to construct conceptualization. In this paper, several limitations are highlighted relating to their applicability to the construction of conceptualizations in dynamic and open environments. These limitations arise from a number of strong assumptions that do not apply to such environments. An intensional structure is strongly argued to be a natural and adequate modeling approach. This paper presents a conceptualization structure based on property, relations, and propositions theory (PRP) to the model ontology that is suitable for open environments. The model extends the First-Order Logic (FOL) notation and defines the formal representation that enables interoperability between software systems and supports semantic integration for software systems in open, dynamic environments.

Keywords: Conceptualization, ontology, extensional structure, intensional structure.

Authors: Zahra Ramezanpanah, Joachim Carvallo, Aurelien Rodriguez

Abstract:

This paper aims to detect anomalies in streaming data using machine learning algorithms. In this regard, we designed two separate pipelines and evaluated the effectiveness of each separately. The first pipeline, based on supervised machine learning methods, consists of two phases. In the first phase, we trained several supervised models using the UNSW-NB15 data set. We measured the efficiency of each using different performance metrics and selected the best model for the second phase. At the beginning of the second phase, we first, using Argus Server, sniffed a local area network. Several types of attacks were simulated and then sent the sniffed data to a running algorithm at short intervals. This algorithm can display the results of each packet of received data in real-time using the trained model. The second pipeline presented in this paper is based on unsupervised algorithms, in which a Temporal Graph Network (TGN) is used to monitor a local network. The TGN is trained to predict the probability of future states of the network based on its past behavior. Our contribution in this section is introducing an indicator to identify anomalies from these predicted probabilities.

Keywords: Cyber-security, Intrusion Detection Systems, Temporal Graph Network, Anomaly Detection.

Authors: Joseph Maloba Makokha

Abstract:

Idea generation is an important part of the design process, and many strategies to support this stage have been developed. As artificial intelligence (AI) gains adoption in many domains, we need to understand its role, if any, in the design process. This paper introduces the concept of a “Disruptive Interjector”, an AI system that frequently interjects with suggestions based on observing what a user does. The concept emanates from a study that was conducted with pairs of humans on one hand, and human-AI pairs on the other collaborating on idea generation by sketching. Results from a study show that participants who collaborated with, and took cues from the AI sketch suggestions generated more ideas; and also had more ideas ranked by experts as “creative” compared to two humans working together on the same tasks. It is notable that while researchers from diverse fields of engineering, psychology, art and others have explored conditions and environments that enhance people's creativity - and have provided insights on creativity in general - there still exists a gap on the role that AI can play on creativity. We attempt to narrow this gap.

Keywords: Artificial intelligence, design collaboration, creativity, human-machine collaboration, machine learning.

Authors: Angelica S. Valeriani, Lorenzo Biasiolo

Abstract:

In recent years, the scale of the impact of climate change and its related side effects has become ever more massive and devastating. Sustainable Development Goals (SDGs), promoted by United Nations, aim to front issues related to climate change, among others. In particular, the project CROWD4SDG focuses on a bunch of SDGs, since it promotes environmental activities and climate-related issues. In this context, we developed a prototype of an application, under advanced development considering web design, that focuses on SDG 13 (SDG on climate action) by providing users with useful instruments to face environmental crises and climate-related disasters. Our prototype is thought and structured for both web and mobile development. The main goal of the application, POLI4SDG, is to help users to get through emergency services. To this extent, an organized overview and classification prove to be very effective and helpful to people in need. A careful analysis of data related to environmental crises prompted us to integrate the user contribution, i.e. exploiting a core principle of Citizen Science, into the realization of a public catalog, available for consulting and organized according to typology and specific features. In addition, gender equality and opportunity features are considered in the prototype, in order to allow women, often the most vulnerable category, to have direct support. The overall description of the application functionalities is detailed. Moreover, implementation features and properties of the prototype are discussed.

Keywords: Crowdsourcing, social media, SDG, climate change, natural disasters, gender equality.

Authors: Sandesh Achar

Abstract:

The cloud computing industry has set new goals for better service delivery and deployment, so anyone can access services such as computation, application, and storage anytime. Cloud computing promises new possibilities for approaching sustainable solutions to deploy and advance their services in this distributed environment. This work explores energy-efficient approaches and how cloud-based architecture can reduce energy consumption levels amongst enterprises leveraging cloud computing services. Adopting cloud-based networking, database, and server machines provide a comprehensive means of achieving the potential gains in energy efficiency that cloud computing offers. In energy-efficient cloud computing, virtualization is one aspect that can integrate several technologies to achieve consolidation and better resource utilization. Moreover, the Green Cloud Architecture for cloud data centers is discussed in terms of cost, performance, and energy consumption, and appropriate solutions for various application areas are provided.

Keywords: Greener Cloud, cloud computing, energy efficiency, energy consumption, metadata tags, Green Cloud Advisor.

Authors: Pratik Dhabal Deo, Manoj P.

Abstract:

With the increasing number of social media users, the amount of video content available has also significantly increased. Currently, the number of smartphone users is at its peak, and many are increasingly using their smartphones as their main photography and recording devices. There have been a lot of developments in the field of video quality assessment in since the past years and more research on various other aspects of video and image are being done. Datasets that contain a huge number of videos from different high-end devices make it difficult to analyze the performance of the metrics on the content from most used devices even if they contain contents taken in poor lighting conditions using lower-end devices. These devices face a lot of distortions due to various factors since the spectrum of contents recorded on these devices is huge. In this paper, we have presented an analysis of the objective Video Quality Analysis (VQA) metrics on contents taken only from most used devices and their performance on them, focusing on full-reference metrics. To carry out this research, we created a custom dataset containing a total of 90 videos that have been taken from three most commonly used devices, and Android smartphone, an iOS smartphone and a Digital Single-Lens Reflex (DSLR) camera. On the videos taken on each of these devices, the six most common types of distortions that users face have been applied in addition to already existing H.264 compression based on four reference videos. These six applied distortions have three levels of degradation each. A total of the five most popular VQA metrics have been evaluated on this dataset and the highest values and the lowest values of each of the metrics on the distortions have been recorded. Finally, it is found that blur is the artifact on which most of the metrics did not perform well. Thus, in order to understand the results better the amount of blur in the data set has been calculated and an additional evaluation of the metrics was done using High Efficiency Video Coding (HEVC) codec, which is the next version of H.264 compression, on the camera that proved to be the sharpest among the devices. The results have shown that as the resolution increases, the performance of the metrics tends to become more accurate and the best performing metric among them is VQM with very few inconsistencies and inaccurate results when the compression applied is H.264, but when the compression is applied is HEVC, Structural Similarity (SSIM) metric and Video Multimethod Assessment Fusion (VMAF) have performed significantly better.

Keywords: Distortion, metrics, recording, frame rate, video quality assessment.

Authors: Silvio R. R. Sanches, Bianca C. Barbosa, Beatriz R. Brum, Cléber G.Corrêa

Abstract:

In order to evaluate the quality of a segmentation algorithm, the researchers use subjective or objective metrics. Although subjective metrics are more accurate than objective ones, objective metrics do not require user feedback to test an algorithm. Objective metrics require subjective experiments only during their development. Subjective experiments typically display to users some videos (generated from frames with segmentation errors) that simulate the environment of an application domain. This user feedback is crucial information for metric definition. In the subjective experiments applied to develop some state-of-the-art metrics used to test segmentation algorithms, the videos displayed during the experiments did not contain audio. Audio is an essential component in applications such as videoconference and augmented reality. If the audio influences the user’s perception, using only videos without audio in subjective experiments can compromise the efficiency of an objective metric generated using data from these experiments. This work aims to identify if the audio influences the user’s perception of segmentation quality in background substitution applications with audio. The proposed approach used a subjective method based on formal video quality assessment methods. The results showed that audio influences the quality of segmentation perceived by a user.

Keywords: Background substitution, influence of audio, segmentation evaluation, segmentation quality.

Authors: Khalid Ali, Manar Jammal

Abstract:

In order to meet the stringent latency and reliability requirements of the upcoming 5G networks, Open Radio Access Networks (O-RAN) have been proposed. The virtualization of O-RAN has allowed it to be treated as a Network Function Virtualization (NFV) architecture, while its components are considered Virtualized Network Functions (VNFs). Hence, intelligent Machine Learning (ML) based solutions can be utilized to apply different resource management and allocation techniques on O-RAN. However, intelligently allocating resources for O-RAN VNFs can prove challenging due to the dynamicity of traffic in mobile networks. Network providers need to dynamically scale the allocated resources in response to the incoming traffic. Elastically allocating resources can provide a higher level of flexibility in the network in addition to reducing the OPerational EXpenditure (OPEX) and increasing the resources utilization. Most of the existing elastic solutions are reactive in nature, despite the fact that proactive approaches are more agile since they scale instances ahead of time by predicting the incoming traffic. In this work, we propose and evaluate traffic forecasting models based on the ML algorithm. The algorithms aim at predicting future O-RAN traffic by using previous traffic data. Detailed analysis of the traffic data was carried out to validate the quality and applicability of the traffic dataset. Hence, two ML models were proposed and evaluated based on their prediction capabilities.

Keywords: O-RAN, traffic forecasting, NFV, ARIMA, LSTM, elasticity.

Authors: Shannon Steinmetz, Ellen Gethner

Abstract:

In this paper a theoretical foundation is developed to segment, analyze and associate patterns within audio. We explore this on imagery via sonified audio applied to our segmentation framework. The approach involves a geodesic estimator within the statistical manifold, parameterized by musical centricity. We demonstrate viability by processing a database of random imagery to produce statistically significant clusters of similar imagery content.

Keywords: Sonification, musical information geometry, image content extraction, automated quantification, audio segmentation, pattern recognition.

Authors: Fathi Taibi

Abstract:

Reusability is a quality desired attribute in software products. Generally, it could be achieved through adopting development methods that promote it and achieving software qualities that have been linked with high reusability proneness. With the exponential growth in mobile application development, software reuse became an integral part in a substantial number of projects. Similarly, software reuse has become widely practiced in start-up companies. However, this has led to new emerging problems. Firstly, the reused code does not meet the required quality and secondly, the reuse intentions are dubious. This work aims to propose a framework to support reuse in Object-Oriented (OO) software development. The framework comprises a process that uses a proposed reusability assessment metric and a formal foundation to specify the elements of the reused code and the relationships between them. The framework is empirically evaluated using a wide range of open-source projects and mobile applications. The results are analyzed to help understand the reusability proneness of OO software and the possible means to improve it.

Keywords: Software reusability, software metrics, object-oriented software, modularity, low complexity, understandability.

Authors: Abeer Aljohani

Abstract:

The COVID-19 virus spread has been one of the extreme pandemics across the globe. It is also referred as corona virus which is a contagious disease that continuously mutates into numerous variants. Currently, the B.1.1.529 variant labeled as Omicron is detected in South Africa. The huge spread of COVID-19 disease has affected several lives and has surged exceptional pressure on the healthcare systems worldwide. Also, everyday life and the global economy have been at stake. Numerous COVID-19 cases have produced a huge burden on hospitals as well as health workers. To reduce this burden, this paper predicts COVID-19 disease based on the symptoms and medical history of the patient. As machine learning is a widely accepted area and gives promising results for healthcare, this research presents an architecture for COVID-19 detection using ML techniques integrated with feature dimensionality reduction. This paper uses a standard University of California Irvine (UCI) dataset for predicting COVID-19 disease. This dataset comprises symptoms of 5434 patients. This paper also compares several supervised ML techniques on the presented architecture. The architecture has also utilized 10-fold cross validation process for generalization and Principal Component Analysis (PCA) technique for feature reduction. Standard parameters are used to evaluate the proposed architecture including F1-Score, precision, accuracy, recall, Receiver Operating Characteristic (ROC) and Area under Curve (AUC). The results depict that Decision tree, Random Forest and neural networks outperform all other state-of-the-art ML techniques. This result can be used to effectively identify COVID-19 infection cases.

Keywords: Supervised machine learning, COVID-19 prediction, healthcare analytics, Random Forest, Neural Network.

Authors: Md. Sohidul Islam, Ahmad Fartheen Khan

Abstract:

In recent times, Non-Orthogonal Multiple Access (NOMA) has received significant attention as an upcoming candidate in the world of 5G systems. The main reason for getting NOMA in 5G is because of its capacity to provide services to many users who have the same time and frequency resources. It is best used as "multiple-input, multiple-output" (MIMO) technology. In this paper, we are going to investigate outage probability as a function of signal-to-noise ratio (SNR) and target rate user. These methods will be implemented using cooperative communication and fair power allocation, respectively.

Keywords: Non-orthogonal Multiple Access, Fair Power Allocation, Outage Probability, Target Rate User, Cooperative Communication, massive multiple input multiple output, MIMO, Successive Interference Cancellation.

Authors: A. M. John-Otumu, M. M. Rahman, O. C. Nwokonkwo, M. C. Onuoha

Abstract:

Online social media networks have long served as a primary arena for group conversations, gossip, text-based information sharing and distribution. The use of natural language processing techniques for text classification and unbiased decision making has not been far-fetched. Proper classification of these textual information in a given context has also been very difficult. As a result, a systematic review was conducted from previous literature on sentiment classification and AI-based techniques. The study was done in order to gain a better understanding of the process of designing and developing a robust and more accurate sentiment classifier that could correctly classify social media textual information of a given context between hate speech and inverted compliments with a high level of accuracy using the knowledge gain from the evaluation of different artificial intelligence techniques reviewed. The study evaluated over 250 articles from digital sources like ACM digital library, Google Scholar, and IEEE Xplore; and whittled down the number of research to 52 articles. Findings revealed that deep learning approaches such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Bidirectional Encoder Representations from Transformer (BERT), and Long Short-Term Memory (LSTM) outperformed various machine learning techniques in terms of performance accuracy. A large dataset is also required to develop a robust sentiment classifier. Results also revealed that data can be obtained from places like Twitter, movie reviews, Kaggle, Stanford Sentiment Treebank (SST), and SemEval Task4 based on the required domain. The hybrid deep learning techniques like CNN+LSTM, CNN+ Gated Recurrent Unit (GRU), CNN+BERT outperformed single deep learning techniques and machine learning techniques. Python programming language outperformed Java programming language in terms of development simplicity and AI-based library functionalities. Finally, the study recommended the findings obtained for building robust sentiment classifier in the future.

Keywords: Artificial Intelligence, Natural Language Processing, Sentiment Analysis, Social Network, Text.

Authors: Akshit Singhal, Xuan Wang, Zhijun Wang, Hao Che, Hong Jiang

Abstract:

Multiple Path Transmission Control Protocols (MPTCPs) allow flows to explore path diversity to improve the throughput, reliability and network resource utilization. However, the existing solutions may discourage users to adopt the solutions in the face of multipath scenario where different paths are charged based on different pricing structures, e.g., WiFi vs. cellular connections, widely available for mobile phones. In this paper, we propose a Hybrid MPTCP (H-MPTCP) with a built-in mechanism to incentivize users to use multiple paths with different pricing structures. In the meantime, H-MPTCP preserves the nice properties enjoyed by the state-of-the-art MPTCP solutions. Extensive real Linux implementation results verify that H-MPTCP can indeed achieve the design objectives.

Keywords: Congestion control, Network Utility Maximization, Multipath TCP, network.

Authors: H. Baskar, A. S. Chakravarthy, P. Garg, D. Goel, A. S. Raj, K. Kumar, Lakshya, R. Parvatham, V. Sushant, B. Kumar Rout

Abstract:

In this paper, we present a computer vision task called nighttime dehaze-enhancement. This task aims to jointly perform dehazing and lightness enhancement. Our task fundamentally differs from nighttime dehazing – our goal is to jointly dehaze and enhance scenes, while nighttime dehazing aims to dehaze scenes under a nighttime setting. In order to facilitate further research on this task, we release a benchmark dataset called Reside-β Night dataset, consisting of 4122 nighttime hazed images from 2061 scenes and 2061 ground truth images. Moreover, we also propose a network called NDENet (Nighttime Dehaze-Enhancement Network), which jointly performs dehazing and low-light enhancement in an end-to-end manner. We evaluate our method on the proposed benchmark and achieve Structural Index Similarity (SSIM) of 0.8962 and Peak Signal to Noise Ratio (PSNR) of 26.25. We also compare our network with other baseline networks on our benchmark to demonstrate the effectiveness of our approach. We believe that nighttime dehaze-enhancement is an essential task particularly for autonomous navigation applications, and hope that our work will open up new frontiers in research. The code for our network is made publicly available.

Keywords: Dehazing, image enhancement, nighttime, computer vision.

Authors: Vasileios Anastopoulos

Abstract:

Cyber threat intelligence assists organisations in understanding the threats they face and helps them make educated decisions on preparing their defences. Sharing of threat intelligence and threat information is increasingly leveraged by organisations and enterprises, and various software solutions are already available, with the open-source malware information sharing platform (MISP) being a popular one. In this work, a methodology for the production of cyber threat intelligence using the threat information stored in MISP is proposed. The methodology leverages the discipline of social network analysis and the diamond model, a model used for intrusion analysis, to produce cyber threat intelligence. The workings of the proposed methodology are demonstrated with a case study on a production MISP instance of a real organisation. The paper concludes with a discussion on the proposed methodology and possible directions for further research.

Keywords: Cyber threat intelligence, diamond model, malware information sharing platform, social network analysis.

Authors: Nicholas Milburn, Yu Liang, Dalei Wu

Abstract:

Athlete performance scoring within the climbing domain presents interesting challenges as the sport does not have an objective way to assign skill. Assessing skill levels within any sport is valuable as it can be used to mark progress while training, and it can help an athlete choose appropriate climbs to attempt. Machine learning-based methods are popular for complex problems like this. The dataset available was composed of dynamic force data recorded during climbing; however, this dataset came with challenges such as data scarcity, imbalance, and it was temporally heterogeneous. Investigated solutions to these challenges include data augmentation, temporal normalization, conversion of time series to the spectral domain, and cross validation strategies. The investigated solutions to the classification problem included light weight machine classifiers KNN and SVM as well as the deep learning with CNN. The best performing model had an 80% accuracy. In conclusion, there seems to be enough information within climbing force data to accurately categorize climbers by skill.

Keywords: Classification, climbing, data imbalance, data scarcity, machine learning, time sequence.

Authors: T. T. Manikandan, Rajeev Sukumaran

Abstract:

Coral Reefs are very important for the majority of marine ecosystems. But, such vital species are under major threat due to the factors such as ocean acidification, overfishing, and coral bleaching. To conserve the coral reefs, reef restoration activities are carried out across the world. After reef restoration, various parameters have to be monitored in order to ensure the overall effectiveness of the reef restoration. Underwater Wireless Sensor Network (UWSN) based  monitoring is widely adopted for such long monitoring activities. Since monitoring of coral reef restoration activities is time sensitive, the QoS guarantee offered by the network with respect to delay is vital. So this research focuses on the analytical modeling of network layer delay using Stochastic Network Calculus (SNC). The core focus of the proposed model will be on the analysis of stochastic dependencies between the network flow and deriving the stochastic delay bounds for the flows that traverse in tandem in UWSNs. The derived analytical bounds are evaluated for their effectiveness using discrete event simulations.

Keywords: Coral Reef Restoration, SNC, SFA, PMOO, Tandem of Queues, Delay Bound.

Authors: Maha Jazouli

Abstract:

Suicide is one of the leading causes of death among prisoners, both in Canada and internationally. In recent years, rates of attempts of suicide and self-harm suicide have increased, with hangings being the most frequently used method. The objective of this article is to propose a method to automatically detect suicidal behaviors in real time. We present a gesture recognition system that consists of three modules: model-based movement tracking, feature extraction, and gesture recognition using machine learning algorithms (MLA). Tests show that the proposed system gives satisfactory results. This smart video surveillance system can help assist staff responsible for the safety and health of inmates by alerting them when suicidal behavior is detected, which helps reduce mortality rates and save lives.

Keywords: Suicide detection, Kinect Azure, RGB-D camera, SVM, gesture recognition.

Authors: Rongli Gai, Zhiyuan Chang, Xiaohong Wang, Jingyu Liu

Abstract:

In view of various situations in the interpolation process, most researchers use self-adaptation to adjust the interpolation process, which is also one of the current and future research hotspots in the field of CNC (Computerized Numerical Control) machining. In the interpolation process, according to the overview of the spline curve interpolation algorithm, the adaptive analysis is carried out from the factors affecting the interpolation process. The adaptive operation is reflected in various aspects, such as speed, parameters, errors, nodes, feed rates, random period, sensitive point, step size, curvature, adaptive segmentation, adaptive optimization, etc. This paper will analyze and summarize the research of adaptive imputation in the direction of the above factors affecting imputation.

Keywords: Adaptive algorithm, CNC machining, interpolation constraints, spline curve interpolation.

Authors: Taylan Kabbani, Ekrem Duman

Abstract:

Deep Reinforcement Learning (DRL) algorithms can scale to previously intractable problems. The automation of profit generation in the stock market is possible using DRL, by combining  the financial assets price ”prediction” step and the ”allocation” step of the portfolio in one unified process to produce fully autonomous systems capable of interacting with its environment to make optimal decisions through trial and error. This work represents a DRL model to generate profitable trades in the stock market, effectively overcoming the limitations of supervised learning approaches. We formulate the trading problem as a Partially observed Markov Decision Process (POMDP) model, considering the constraints imposed by the stock market, such as liquidity and transaction costs. We then solved the formulated POMDP problem using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm and achieved a 2.68 Sharpe ratio on the test dataset. From the point of view of stock market forecasting and the intelligent decision-making mechanism, this paper demonstrates the superiority of DRL in financial markets over other types of machine learning and proves its credibility and advantages of strategic decision-making.

Keywords: Autonomous agent, deep reinforcement learning, MDP, sentiment analysis, stock market, technical indicators, twin delayed deep deterministic policy gradient.

Authors: Sergey Kopysov, Nikita Nedozhogin, Leonid Tonkov

Abstract:

The article presents a parallel iterative solver for large sparse linear systems which can be used on a heterogeneous platform. Traditionally, the problem of solving linear systems do not scale well on cluster containing multiple Central Processing Units (multi-CPUs cluster) or cluster containing multiple Graphics Processing Units (multi-GPUs cluster). For example, most of the attempts to implement the classical conjugate gradient method were at best counted in the same amount of time as the problem was enlarged. The paper proposes the pipelined variant of the conjugate gradient method (PCG), a formulation that is potentially better suited for hybrid CPU/GPU computing since it requires only one synchronization point per one iteration, instead of two for standard CG (Conjugate Gradient). The standard and pipelined CG methods need the vector entries generated by current GPU and other GPUs for matrix-vector product. So the communication between GPUs becomes a major performance bottleneck on miltiGPU cluster. The article presents an approach to minimize the communications between parallel parts of algorithms. Additionally, computation and communication can be overlapped to reduce the impact of data exchange. Using pipelined version of the CG method with one synchronization point, the possibility of asynchronous calculations and communications, load balancing between the CPU and GPU for solving the large linear systems allows for scalability. The algorithm is implemented with the combined use of technologies: MPI, OpenMP and CUDA. We show that almost optimum speed up on 8-CPU/2GPU may be reached (relatively to a one GPU execution). The parallelized solver achieves a speedup of up to 5.49 times on 16 NVIDIA Tesla GPUs, as compared to one GPU.

Keywords: Conjugate Gradient, GPU, parallel programming, pipelined algorithm.