Software Engineering and Artificial Intelligence: Re-Enhancing The Lifecycle

Sabeer Saeed¹ and Asaf Varol², ¹Department of Software Engineering, Firat University, Elazig City, Turkey, ²Department of Computer Engineering, Maltepe University, Istanbul City, Turkey

ABSTRACT

As automation is changing everything in today’s world, there is an urgent need for artificial intelligence, the basiccomponent of today’s automation and innovation to have standardsfromsoftware engineering for analysis and design before it is synthesized to avoid disaster. Artificial intelligence software can make development costs and time easier for programmers. There is a probability that society may reject artificial intelligence unless a trustworthy standard in software engineering is created to make them safe. For society to have more confidence in artificial intelligence applications or systems, researchers and practitioners in computing industry need to work not only on the cross-section of artificial intelligence and software engineering, butalso on software theory that can serve as a universal framework for software development, most especially in artificial intelligence systems. This paper seeks to(a) encourage the development of standards in artificial intelligence that will immensely contribute to the development of software engineering industry considering the fact that artificial intelligence is one of the leading technologies driving innovation worldwide (b) Proposethe need for professional bodies from philosophy, law, medicine, engineering, government, international community (such as NATO, UN), and science and technology bodies to develop a standardized framework on how AI can work in the future that can guarantee safety to the public among others. These standards will boost public confidence and guarantee acceptance of artificial intelligence applications or systems by both the end-users and the general public.

KEYWORDS

Software Engineering (SE), Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), Cross Section between Artificial Intelligence and Software Engineering.

A Proposal of a Fuzzy Methodology to Determine the Best Offloading Day for a Floating Production Storage and Offloading Unit During the Operating Phase

Armando Celestino Gonçalves Neto, Industrial EngineeringDepartament, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil

ABSTRACT

The choice of the correct offloading day during the operating phase of an FPSO is crucial to its economic viability. To be stopped more than needed means severe monetary damages to the oil company, including the big costs of the mobilization and demobilization of the tankers waiting for the right moment to precede the offloading operation. The principal purpose of this paper is to use Fuzzy Logic to treat the main variables, which themselves pursue too much vagueness, intending to optimize the offloading day in its economics and logistics aspects.

KEYWORDS

Brazil Offshore Oil and Gas, Offloading Operation, Approximate Fuzzy Reasoning,, FPSO (Floating Production Storage and Offloading).

A Machine Learning Based Expert System for The Diagnosis of Cardiovascular Diseases

Tazeen Tasneem, Mir Md. Jahangir Kabir and Tabeen Tasneem, Rajshahi University of Engineering and Technology, Bangladesh

ABSTRACT

Diagnosis of cardiovascular disease (CVD) in its early stage can save the lives of millions of people and this is the reason researchers are attracted by this field. Numerous machine learning (ML) algorithms are available which can be proved to be good solutions for the diagnosis of this disease. Although several works have employed ML algorithms for CVD diagnosis task, most of the studies have just discarded the instances containing missing values. Again, selecting important features is a difficult task to do. To this end, this study proposes three models to classify if a person is at risk of having CVD. Heart Disease Dataset has been used for this work which is available at UCI Machine Learning Repository. Before proceeding towards feature selection, a well-known missing value imputation technique has been used for imputing missing values. For feature selection, Chi-square test (CHI), Least Absolute Shrinkage and Selection Operator (LASSO), and Genetic Algorithm (GA) have been used. In order to validate the class, provided by the dataset, Multi-layer Perceptron with Back Propagation (MLP-BP) has been implemented.The proposed models have outperformed all the existing models in case of Cleaveland dataset. For Hungarian and Long Beach Va, CHI MLP-BP has shown high-performance (86.44% and 81.67% accuracy, respectively), and for Switzerland, LASSO MLP-BP has come up with 100% accuracy.

KEYWORDS

Machine learning, Cardiovascular disease, Feature selection, Multi-layer perceptron.

Fuzzy system optimization by simulated annealing method for mobile robot navigation

Fatma Boufera, Tenni Ali and Zeghilet Azeddine, Computer Science Department, Mascara University, Mascara, Algeria

ABSTRACT

This paper deals the navigation problem of a mobile robot. This is to define a strategy that allows it to reach the final destination and avoiding obstacles. Fuzzy logic is considered as an important tool to solve this problem. However a major problem of fuzzy systems is obtaining their parameters which are generally specified by human experts. This process can be long and complex. In order to generate optimal parameters of fuzzy controller, this work propose a learning and optimization process based on simulated annealing method. The simulated results show clearly the impact of the optimization approach improves the fuzzy controller performance mainly in obstacle avoid and detection of the shortest path.

KEYWORDS

mobile robots, autonomous navigation, obstacle avoidance, fuzzy controller, simulated annealing algorithm, machine learning.

Proof of Authentication based Blockchain Architecture to Meet Challenges in Access Control and Secure Management of Electronic Health Records in IoT based Healthcare Systems

Maria Arif, Megha Kuliha and Sunita Varma, Department of Information Technology, S.G.S.I.T.S., Indore, M.P., India

ABSTRACT

Secure, immutable and transparent feature of blockchain has led researchers to find ways to harness its potential in sectors other than financial services. Blockchain is gaining popularity as a tool that could help solve some of the healthcare industrys age-old problems that have resulted in delayed treatments, inaccessible health records in emergency, wasteful spending and higher costs for health care providers, insurers and patients. Applying blockchain in healthcare brings a new challenge of integrating blockchain with Internet of Things (IoT) networks as sensor based medical and wearable devices are now used to gather information about the health of a patient and provide it to medical applications using wireless networking. This paper proposes an architecture that would provide a decentralized, secure, immutable, transparent, scalable and traceable system for management and access control of electronic health records (EHRs) through the use of consortium blockchain, smart contracts, proof-of-authentication (PoAh) consensus protocol and decentralized cloud.

KEYWORDS

Blockchain, Proof of Authentication, Smart Contracts, Internet of Things, Healthcare.

Performance of Machine Learning and Big Data Analytics paradigms in Cybersecurity and Cloud Computing platforms

Gabriel Kabanda, Secretary General Zimbabwe Academy of Sciences, TREP Building, University of Zimbabwe Harare, Zimbabwe

ABSTRACT

Cybersecurity refers to a combination of technologies, processes and operations that are framed to protect information systems, computers, devices, programs, data and networks from internal or external threats, harm, damage, attacks or unauthorized access. The main characteristic of Machine Learning (ML) is the automatic data analysis of large data sets and production of models for the general relationships found among data. ML algorithms, as part of Artificial Intelligence, can be clustered into supervised, unsupervised, semi-supervised, and reinforcement learning algorithms. The research is purposed to evaluate Machine Learning and Big Data Analytics paradigms for use in Cybersecurity. The Pragmatism paradigm, which is in congruence with the Mixed Method Research (MMR), was used as the research philosophy in this research as it epitomizes the congruity between knowledge and action. The researcher analysed the ideal data analytics model for cybersecurity which consists of three major components which are Big Data, analytics, and insights. The information that was evaluated in Big Data Analytics includes a mixer of unstructured and semi-structured data including social media content, mobile phone records, web server logs, and internet click stream data. Performance of Support Vector Machines, Artificial Neural Network, K-Nearest Neighbour, Naive-Bayes and Decision Tree Algorithms was discussed. To avoid denial of service attacks, an intrusion detection system (IDS) determined if an intrusion has occurred, and so monitored computer systems and networks, and then raised an alert when necessary. A Cloud computing setting was added which has advanced big data analytics models and advanced detection and prediction algorithms to strengthen the cybersecurity system. The researcher presented two models for adopting data analytics models to cybersecurity. The first experimental or prototype model involves the design, and implementation of a prototype by an institution and the second model involves the use serviced provided by cloud computing companies.

KEYWORDS

Cybersecurity, Artificial Intelligence, Machine Learning, Deep Learning, Big Data Analytics, Cloud Computing.

Inter Planetary File System for Document Storage and E-Verification

Rishabh Garg, Department of Electronics & Communication Engineering, Birla Institute of Technology & Science, K.K. Birla Goa Campus, Sancoale, Goa - 403726

ABSTRACT

Every year, millions of candidates submit their educational credentials worldwide for admissions in higher education institutes or getting a dream jobs. Their mark sheets, certificates and degree are verified in order to decide the legitimacy of their education with respect to qualification. An alarming ratio (almost 10%) of applicants, in every recruitment, fabricates their educational history or misrepresent their education in a wide variety of ways - either they overstate their academic qualifications or submit fake degrees, procured from unaccredited institutions. The verification of necessary documents, such as educational degrees, is one of the areas where blockchain can provide tangible results. Ethereum blockchain is a concept in which a credential holder can store all his academic credentials in an encrypted format, on his own device, backed by IPFS; choosing a specific information to share with verifiers without relying on any third party or central data repository to authenticate. The system uses smart contracts and thus, no document can be shared without the explicit consent of its beholder. Blockchain assures trust and ensures authentic data exchange, without storing any kind of verified credential on the system. The blockchain ledger, being irreversible and immutable, does not delete the original version and hence no alteration is possible.

KEYWORDS

Blockchain, Cryptography, Decentralized Applications, Data Portability, Decentralized Public Key Infrastructure, Enrolment, Ethereum, Hash function, Hashgraph, Identity Management System, IPFS, Private Key, Public Key, Self-Sovereign Identity, Validation, Zero Knowledge Proof.

INTERNET OF THINGS: Security Aspects and Potential Solving of Security Threats

Ata Şahan Erdemir, Faculty of Informatics and Statistics, University of Economics & Business, Prague

ABSTRACT

IOT became a required technology with the improved Internet based systems and ipv6 protocol corresponding the communication requirements in real life scenarios. Increasing the usage of IOT devices among the markets should be supported with security assessments to maintain the reliability, privacy accountability of the infrastructure and related systems.The security gaps and the dangers that these gaps may create with the vulnerabilities and dangerous situations for the internet of things devices.This article discusses and highlights the possible security weaknesses of IOT systems as a whole concept and suggests best protective practises for end users.The studied method aims to be used within IoT device manufacturers to produce a safer device and to give ideas for the production of new devices.

KEYWORDS

Internet of Things, Hacking, Security.

An Efficient Consensus Mechanism for Blockchain Peer-to-Peer Networks

Avinash Kshirsagar and Vinod Pachghare, Department of Computer Engineering, College of Engineering, Pune

ABSTRACT

The cryptocurrency bitcoin was proposed as. Bitcoin used a peer-to-peer network without a third trusted party but still maintained trust in the network. The consensus mechanisms do the task of trust-building by executing consensus mechanism, which brings consensus in the nodes of the network. The consensus mechanism used in bitcoin is Proof of Work which involves a massive computation of hashes to validate a block and add it to the blockchain. As the applicability of blockchain increased, the computation-heavy consensus mechanisms were not suitable for real-time transactions. And so, there is a need for a new efficient and high throughput consensus mechanism. This paper proposes a new consensus mechanism using a scope index to mine a new block. This consensus mechanism deals with forking conditions, and the presence of malicious nodes in the network is also studied and compared with other proposed consensus mechanisms.

KEYWORDS

distributed ledger technology, consensus mechanism, efficiency, and throughput of consensus mechanism.

Social Media Network Attacks and Their Preventive Mechanisms: A Review

Emmanuel Etuh, Francis S. Bakpo, Eneh A.H, Department of Computer Science, Faculty of Physical Sciences, University of Nigeria, Nsukka

ABSTRACT

We live in a virtual world where actual lifestyles are replicated. The growing reliance on the use of social media networks worldwide has resulted in great concern for information security. One of the factors popularizing the social media platforms is how they connect people worldwide to interact, share content, and engage in mutual interactions of common interest that cut across geographical boundaries. Behind all these incredible gains are digital crime equivalence that threatens the physical socialization. Criminal minded elements and hackers are exploiting social media platforms (SMP) for many nefarious activities to harm others. As detection tools are developed to control these crimes so also hackers tactics and techniques are constantly evolving. Hackers are constantly developing new attacking tools and hacking strategies to gain malicious access to systems and attack social media network thereby making it difficult for security administrators and organizations to develop and implement the proper policies and procedures necessary to prevent the hackers attacks. The increase in cyber-attacks on the social media platforms calls for urgent and more intelligent security measures to enhance the effectiveness of social media platforms. This paper explores the mode and tactics of hackers mode of attacks on social media and ways of preventing their activities against users to ensure secure social cyberspace and enhance virtual socialization. Social media platforms are briefly categorized, the various types of attacks are also highlighted with current state-of-the-art preventive mechanisms to overcome the attacks as proposed in research works, finally, social media intrusion detection mechanism is suggested as a second line of defense to combat cybercrime on social media networks.

KEYWORDS

Intrusion Detection System, Data Warehouse, Machine Learning, Hackers, Social Media Platform, Online Social Network Intrusion.

Topic Modeling and Sentiment Analysis of Electric Vehicles of Twitter Data

Suresha HP¹ and Krishna Kumar Tiwari², ¹REVA Academy for Corporate Excellence, REVA University Bengaluru, India, ²ML AI Community, Bengaluru, India

ABSTRACT

Twitter is a well-known social media tool for people to communicate their thoughts and feelings about products or services. In this project, I collect electric vehicles related user tweets from Twitter using Twitter API and analyze public perceptions and feelings regarding electric vehicles. After collecting the data, To begin with, as the first step, I built a pre-processed data model based on natural language processing (NLP) methods to select tweets. In the second step, I use topic modeling, word cloud, and EDA to examine several aspects of electric vehicles. By using Latent Dirichlet allocation, do Topic modeling to infer the various topics of electric vehicles. In the third step, the “Valence Aware Dictionary (VADER)” and “sEntiment Reasoner (SONAR)” are used to analyze sentiment of electric vehicles, and its related tweets are either positive, negative, or neutral. Finally, I deploy this project work as a fully functional web app.

KEYWORDS

Twitter, Tweets, Topic Modeling, Sentiment analysis, VADER, SONAR, pyLDA Latent Dirichlet Allocation, Machine Learning, Natural Language Processing, Streamlit, Heroku, Deployment, Polarity, Word Cloud.

Future Sales Estimation using Patents

KOICHI KAMIJO, Department of Information Technology, International Professional University of Technology in Tokyo, Shinjuku-ku, Tokyo, Japan

ABSTRACT

We propose a model to improve estimation accuracy of the future sales volume, focusing on pharmaceutical products, from their patents. Our approach is based on an analysis of patents obtained in the early development stages of the products. The development of pharmaceuticals often takes a long time (up to several decades in some cases), and the costs are huge, even exceeding one billion USD for just one product. Therefore, it is strongly desirable to estimate future sales volume at an early stage. One piece of information potentially useful for the estimation is the brand, i.e., the name of the developing company. Our model learns the sales volume and words used in multiple patent specifications and also focuses on the extent to which “seasonal” words are used. Experiments showed that our model much improved the accurately of the sales volume estimation compared with the case of just estimating from its brand name.

KEYWORDS

Sales Estimation, Pharmaceuticals, Patents, Natural Language Processing, Deep Learning.

A fuzzy ontology for medical decision support and improved communication between the different actors in the context of Alzheimer’s disease

Abir Chihi, Hanen Ghorbel, Higher Institute of Management, Sousse, Tunis

ABSTRACT

A medical ontology is a model of the knowledge of a medical domain. It contains all relevant concepts related to causes, factors, symptoms and other patient data. However, the real world has many uncertainties and imprecisions in the different application domains, precisely in the medical domain that cannot be designed using precise ontologies. Fuzzy ontology is one of the solutions that is used to solve this problem. It is based on the integration of fuzzy logic with precise ontologies. In this paper, we propose an approach based on fuzzy ontology for medical decision support and improvement of communication between different actors in Alzheimers disease.

KEYWORDS

Fuzzy Ontology, Alzheimer’s disease, Fuzzy Logic, Fuzzy Ontology for Alzheimer.

An Innovative Method to Extract Data in a Real-time Data Warehousing Environment

Flavio de Assis Vilela¹, Ricardo Rodrigues Ciferri², ¹Departament of Computing, Federal Institute of Goias, Jatal, GO, ²Departamento of Computing, Federal University of Sao Carlos, Sao Carlos, SP

ABSTRACT

ETL is an essential process required to perform data extraction in knowledge discovery in databases and in data warehousing environments. The ETL process aims to gather data that is available from operational sources, process and store them into an integrated data repository. Also, the ETL process can be performed in a real-time data warehousing environment and store data into a data warehouse. This paper presents a new and innovative method named Data Extraction Magnet (DEM) to perform the extraction phase of ETL process in a real-time data warehousing environment based on non-intrusive, tag and parallelism concepts. DEM has been validated on a dairy farming domain using synthetic data. The results showed a great performance gain in comparison to the traditional trigger technique and the attendance of real-time requirements.

KEYWORDS

ETL, real-time, data warehousing, data extraction.

Majradoc an Image based Disease Detection App for Agricultural Plants using Deep Learning Techniques

Sara Saleh Alfozan¹ And Mohamad Mahdi Hassan², ¹Department of Computer Science, Qassim University, Saudi Arabia, Buraydah, ²Department of Computer Science - College of Computer, Qassim University, Saudi Arabia, Buraydah

ABSTRACT

Infection of agricultural plants is a serious threat to food safety. It can severely damage plants yielding capacity. Farmers are the primary victims of this threat. Due to the advancement of AI, image-based intelligent apps can play a vital role in mitigating this threat by quick and early detection of plants infections. In this paper, we present a mobile app in this regard. We have developed MajraDoc to detect some common diseases in local agricultural plants. We have created a dataset of 10886 images for ten classes of plants diseases to train the deep neural network. The VGG-19 network model was modified and trained using transfer learning techniques. The model achieved high accuracy, and the application performed well in predicting all ten classes of infections.

KEYWORDS

Plant diseases, plant diseases diagnosis, deep learning, VGG19 CNN, mobile application.