VOLUME 10, ISSUE 9, SEPTEMBER 2021

Abstract: The purpose of this study is to classify the performance of lecturers from a dataset taken from the bkd.ubharajaya.ac.id application. Many universities have not been effective in assessing the performance of lecturers so that the data that has been obtained from each lecturer's report only becomes stored data, not yet into knowledge that will be used as decision makers. The research method used in this research is to start by acquiring data from the bkd.ubharajaya.ac.id application which will then be analysed through data mining stages by pre-processing data that is feasible to create a dataset. The dataset that has been created is then analysed using the 10-fold cross validation method which will divide the data into training data and testing data which will then be made a classification model using the Support Vector Machine (SVM) and Artificial Neural Network (ANN) algorithms. The expected research results with this application can classify the performance of lecturers who have the best accuracy to be used as a decision-making system.

Keywords: Lecturer Performance, Artificial Neural Network, Support Vector Machine, 10-Fold Cross Validation, Classification

Abstract: Artificial Intelligence is that the computational complexity of general intelligence may be exponentially hard which happens with Machine Learning. The field itself, and the evolution of natural Water is basic pre-condition for life. Water of good drinking quality is of basic importance to human physiology and the existence of human being is very much depends on its availability. The assessment of Tiptur lake water quality for suitability for drinking and domestic purpose was carried out during November 2020 to August 2021 and evaluate the water quality status through its physicochemical parameters such as AT, WT, PH, TDS, EC, TA, TH Ca++ , Mg++ , Cl-,DOM , SALINIITY, DO ,BOD, Na+, K+, PO4, SO4 and Fe. The results were compared with BIS Standard [1991]and WHO [1993] drinking water standards. The results revealed that most of the parameters were in normal range and indicated suitability for drinking purposes, and Artificial Intelligence applied for processing the samples with attributes and parameters with the test set. A total of 37genera of phytoplankton were recorded, of which chlorophycean and diatoms were found to be dominant among four classes. Four protozoa were recorded. Key words: Tiptur-Lake, water quality, Human physiology, physicochemical parameters, suitability, BIS and WHO, Phytoplankton oligotrophic, Artificial Intelligence.

Abstract: Keystroke dynamics is a biometric that has been explored as a means of making user authentication more secure. However, studies have indicated that the performance of such a system might be influenced by the demography of the user population. The purpose of this study is to investigate the relationship between the age and gender of the users of a keystroke dynamics-based mobile phone user authentication and the performance of the scheme. Using a mobile keystroke dynamics dataset containing the age and gender information of the participants, an anomaly detector algorithm was used to test whether an impostor user would have been recognised or not. A False Acceptance Rate (FAR) is calculated for the genuine user and impostors' combination. A Two-Way Analysis of Variance (ANOVA) was used to test the hypotheses whether there are significance differences and interaction between the FARs obtained with respect to the age group and gender categories. The result suggests that the age and gender of the users of a keystroke dynamics user authentication system on a mobile phone is not expected to have significant impact on the performance of such a system. Unlike previous studies that were based on keystroke dynamics data from desktop computer users, this investigation focused on keystroke dynamics for mobile phones. The results obtained in this paper has further improved our understanding that demographic bias relating to age and gender may be eliminated from the concerns that may arise from the use of a keystroke dynamics user authentication on a mobile phone.

Keywords: Biometrics, User Authentication, Keystroke Dynamics, Classification, Machine Learning.

Abstract: Covid-19 is an ongoing worldwide pandemic caused by severe acute respiratory syndrome coronavirus (Covid). The virus was first identified in late December 2019 in Wuhan China. As of (01/Jul/2021) 183 million people were infected with the Covid -19 and encountered moderate to severe respiratory sickness, 3.9 million died of this infection. Elderly people, adults, kids, and those with underlying medical conditions heart disease, diabetes, chronic respiratory disease, and cancer are at high risk of developing serious illnesses from covid-19. The current scenario documented the Multiple variants of the virus that causes Covid-19 which spreads faster than usual and remains a high threat to mankind. Despite the high-risk covid-19 variant, numerous ongoing clinical trials for diagnosis and treatment of coronavirus infection have been involved to treat the Patients. The current clinical trial tools are time-consuming, staggering a high cost, and requiring a well-equipped laboratory for analysis. Fast diagnostic methods can control, prevent the spread of covid-19 variants and reduce the workload of the physicians to better manage the patients. A computed tomography scan (CT) is the fastest method to diagnose patients with covid-19 variants. Nevertheless, the radiologist's performance is moderate in diagnosing the virus and time-consuming due to the overwhelmed patients. Discern the impact of covid-19 threats, computer science researchers have started using artificial intelligence techniques to detect the presence of covid-19 infection using CT scan. This study furnishes an elaborate response with various Deep Learning (DL) techniques of Artificial intelligence to combat the novel coronavirus. Furthermore, this study can improve the performance of introduced techniques towards the best responses in practical applications Keywords Covid -19, Computed Tomography scan, Deep Learning, Artificial Intelligence.

Abstract: Testing plays an important role to assure quality of the product and to provide better business optimization. The following paper gives an overview regarding Behaviour Driven Development (BDD) framework using cucumber tool. The main purpose of this paper is to differentiate how BDD is more efficient than Test Driven Development (TDD).

Keywords: BDD, Cucumber, TDD, Testing.

Abstract: Cloud computing is an on demand availability of cloud system resources such as data storage and computing power without direct active management by the user. The word cloud is used as a metaphor for internet and a standardized cloud like shape was used to denote a network on schematic’s. [1] Cloud is about where you compute, not how you compute. Here, we will discuss about difference between and On-premises and Cloud-based computing, Scalability, server storage with cloud service providers, data security, maintenance in terms of infrastructure as well as cost efficiency. It is described as the delivery of on-demand services over the internet works on “pay-as-you-go” basis. Cloud computing has two type of models: • deployment model: public cloud private cloud hybrid cloud • Service model: infrastructure as a service platform as a service software as a service Cloud computing service models are hassle-free. The most popular cloud computing models AWS, Microsoft’s azure, Google cloud platform are as discussed below. SLAs, instances, container, Kubernetes, Regions, storage are all important factors also discussed in this paper. How cloud providers provide services over the cloud and what are the importance of those services in the modern day infrastructure. The data usage has been discussed providing a large dependency in processing the programs. The future introduction is also mentioned giving new research aspects to the field of cloud computing.

Abstract: Artificial neural networks (ANNs) and Deep Learning have shown great improvement in recognizing and classifying objects and images. Convolutional Neural Networks (CNNs) can be exploited to automatically extract features from images using the hierarchical structure. Specifically, we investigate image classification in the context of every day small scale emergency events, where images associated with tweets during the target emergency events were used to train and test classification approaches. We present a method of classifying images using convolutional neural networks that perform classification in layers in order to determine whether or not the image relates to an emergency event and if the image is incident-related, then which category of the target emergency events it belongs to. Experiments on a home-grown dataset show that these methodologies can classify images into the different classes with an F1 score of 88.12%.

Keywords: Image classification, convolutional neural networks, social media, Twitter, Emergency events

Abstract: Optimal solving of the NP-hard problems strongly motivates both the researchers and the practitioners to try to solve such problems heuristically, by making a trade-off between computational time and solution’s quality.  Among the classes of heuristic methods for NP-hard problems, the polynomial approximation algorithms aim at solving a given NP-hard problem in polynomial time by computing feasible solutions that are, under some predefined criterion, as near to the optimal ones as possible. P is the class of decision problems that we can solve in polynomial time and NP is the class of problems for which we can check the solution in polynomial time. Visually, problems that are easy to solve are also problems that are easy to test. Therefore, P NP. In this paper, we propose an approach to the P vs NP question through a class of the most difficult problems among the problems in the NP class. Such problems are called NP-complete problems.

Keywords: NP class, NP-complete class, Karp, NP-hard problems, heuristics.

Abstract: Poor medication adherence is one of the major causes of illness and of treatment failure. The main purpose of our project is to help the elderly and visually impaired, take their medications on time in an easy way without the possibility of missing pills, also reduce the risk of over or under dosing accidentally. It provides direct communication between the system and the caregiver as it will immediately notify the care giver in case the patient missed his/her pill. In this project we have developed a mobile application wherein caregivers have to register to track their patient’s medical adherence. They will be notified when their patient misses a dose or they can also track the complete history.

Keywords: medication adherence, SMD architecture, Medication Dispensing Device

Abstract: This system proposes an intelligent system to track the detection of illegal smuggling of trees in forest. Existing system makes use of various technologies such as RFID, GPS, GSM etc,. RFID based systems lack in rain if passive tax are used or lack in cost effectiveness. Similarly, GSM based system becomes costlier and require constant network connection. Hence this project proposes a wifi based tracking system. The stationary wifi transceiver consist of ESP8266 node MCU development board which detects the mobile transceiver. The mobile transceiver detects mobile transceivers under its vicinity and sends the data to other stationary transceiver and ultimately the data stored in data base

Abstract: We live in an exciting time where more and more everyday items “things” are becoming smart! “Things” have sensors and can communicate to other “things” and can provide control to more “things”. The Internet of Things, IOT, is upon us in a huge way and people are rapidly inventing new gadgets that enhance our lives. The price of microcontrollers with the ability to talk over a network keeps dropping and developers can now build things inexpensively using the concept of IOT technology and also android mobile application. Main objective is all about protecting the farm from animals that causes lot of damages to the crops and also to financial status of farmers who depends completely on the yield of crop. The android mobile application helps for the better interaction with user and to access the data and manage the system.

Keywords: Agriculture Crop Security, IoT, SMD, Google Firebase

Abstract: ‘Atulyam Bharat’ or we can say Incredible India is the dream of every Indian including our own Prime Minister Mr. Narendra Damodardas Modi. But this dream can never be achieved without the ‘Swastha Bharat’ or Healthy India. Health and well-being of its citizens is the first priority of any country and so as India. No one can deny the fact that India seeks to become a world power. Better population health is one among the vital considerations in India. All those who are living in cities and massive cities have no doubt access to high finish health services, the ample people living in rural India, notably within the remote elements of the country face issues of inadequate facilities and poor access to attention. The inefficiencies and inequities within the public health care access in India have pushed forward the necessity for power and innovative solutions to strengthen a similar. Paper identifies the large deficiency and scarcity of right and timely health care facilities to our Rural India. We also point the addresses a way to give bigger access to primary health care services in rural India. In this paper, it conjointly addresses the important computing and analytical ability of Big Data in process huge volumes of transactional information in real time things to show the dream of Swastha Bharat (Healthy India) into reality. We have proposed a model to predict the diseases based on the various symptoms provided by experts.

Keywords: Big Data Analytics, Health care in India, Big Data Challenges, Big Data, Rural Health Care, e-Health Care, Swastha Bharat, Atulyam Bharat.

Abstract: Uniqueness or individuality of an individual is his face. In this project face of an individual is used for the purpose of attendance making automatically. Attendance of the student is very important for every college, universities and school. Conventional methodology for taking attendance is by calling the name or roll number of the student and the attendance is recorded. Time consumption for this purpose is an important point of concern. Assume that the duration for one subject is around 60 minutes or 1 hour & to record attendance takes 5 to 10 minutes. For every tutor this is consumption of time. To stay away from these losses, an automatic process is used in this project which is based on image processing. In this project face detection and face recognition is used. Face detection is used to locate the position of face region and face recognition is used for marking the understudy’s attendance. The database of all the students in the class is stored and when the face of the individual student matches with one of the faces stored in the database then the attendance is recorded.

Keywords: Face Recognition, Attendance System, Face detection, PCA, Database.

Abstract: Prevention is better than cure in the same way prevention during cure is also important. Due to the increasing population the burden of the health system is also increasing. The doctors have to face critical patients on a regular basis. The health system is the only system which is under tremendous pressure. A survey suggests that India has a single doctor for a population of 1700 people. Such conditions force the engineers to build a system that more or less help the doctors to fight with critical conditions. It is observed that the doctors spend a large portion of time in monitoring the patients and then thinking about the treatment. A system which can monitor the patient’s health and directly provide data to the doctor, can reduce the time of action and the treatment can start quickly. Our system does the same thing. It enables the doctors to monitor patient’s health parameters (temp, heartbeat, ECG, position) in real time. Here the parameters of patient are measured continuously (temp, heartbeat, ECG) and wirelessly transmitted using Zigbee. This results in reducing the monitoring time due to which the doctors can directly focus on treatment.

Keywords: Patient monitoring, ECG, temperature, PIC microcontroller.

Abstract: Internet of Things (IOT) portrays the arrange of physical objects that are inserted with sensor, program additionally it makes a difference in exchange between gadgets over the web. Within the current world, encryption plays a noteworthy part in securing pertinent data from aggressors. The applications of such conventions drop beneath various categories extending from web banking to Internet of Things (IoT). Subsequently, there's a need to construct solid and complex encryption calculations. In this paper, we propose a customized encryption calculation like AES, RSA, DES, TWOFISH and a confirmation conspire to securely change data.

Keywords: Internet of Things (IOT), encryption standard, AES and security, DES, Cipher

Abstract: Plug-in electric vehicles play a vital role in the extended range and potential for refueling of conventional hybrids. PHEV can be a good option, provides a backup of a fuel engine for longer runs. The hybrid vehicles are the combinations of internal combustion engine and electric motors that use energy stored in batteries.

Keywords: Plug-in HEV, Battery, Charge depletion, SoC, Internal combustion engine, Energy storage system.

Abstract: The use of neural network on different diseases has been used on large scale since last two decades. This expert system offers a helping hand for the accurate decision over a certain diagnosis. A medical training may not have enough experience to deal and tackle with some high risk diseases like heart, kidney and brain. This case study includes details about patient’s data, coding, normalization and tabulation. It describes various heart disease diagnostic techniques such as Feed Forward Back- propagation (FFBP), Support Vector Machine (SVM), Generalized Regression Neural Network (GRNN) and Radial Basis Function (RBF) has been applied over the data for the experiment. Additionally it represents different tables of symptoms used for heart disease diagnosis. In this case study, expert system for diagnosis of heart disease useful for the new researcher to understand how to collect the data and perform experimental analysis using different neural network techniques.

Keywords: Data Mining, Expert system, Heart disease, SVM, RBF, GRNN, FFBP

Abstract: One of the most pressing issues of everyday life is security. A novel human–machine interface is being implemented into a protection framework in this project. To open a door without using keys, the machine uses the motion of knocking as the input interface. The unlock areas on the door must first be placed. When a person taps on the threshold, sound sensors in the door provide input to the device. Following that, a pattern-recognition algorithm determines the user's knocking pattern, including the knocking areas and series. The precision of determining the right knocking areas is between 85 and 90 percent, according to simulation data. Corporate facilities, ATMs, and home surveillance are the perfect applications for this device. A Piezo sensor and an ARDUINO are used in a Knock Based Security Scheme (KBSS). The machine is managed by the ARDUINO Leonardo. Due to synchronization, a continuous picture is transmitted to the mail.

Keywords: ARDUINO, Algorithm, Door Lock and GSM

Abstract: Voting has been a fundamental part of democracies around the world; it has been the voice to their opinions for individuals in a community. Indian constitution was founded upon the beliefs in individual rights. But in recent years, voter turnout has plummeted while the ever-increasing concerns regarding integrity, security, and accessibility of voting systems haven’t been addressed. E-Voting can solve this problem; however, it requires supervision by central authority. In this paper, the available open source Blockchain technology is used to propose a design for a new electronic voting system that could be used in future electronic elections. The Blockchain-based system will be secure, reliable, and anonymous, and will help increase the number of voters as well as the trust of people in their governments.

Keywords: Voting, Blockchain, Smart contracts, Decentralized application, ledger.

Abstract: Since we are currently residing in Computing Technology, it is essential for everyone and everything to be connected to the internet. IOT is a technology that brings us more and more close to this goal. Our project comprises of smart water monitoring system which is a small prototype for flood detection and avoidance system. This paper explains the working and the workflow of all the components present inside this project. The sensors sense the environment and sends real-time data to the cloud (firebase cloud) and users can view and access this data via their mobile platform. The model gives a warning after the water level rises to a particular height. Since it is a small scaled prototype for flood detection and avoidance system, the working of this model is good. The data are uploaded and changed in the cloud in precision to the sensor and a real-time change in the mobile application is achieved. This model can be used to greatly reduce the casualties in a devastating event of flood.

Keywords: sensors, level

Abstract: Brain tumour is the most commonly occurring malignancy among human beings. The detection of tumour means identify the affected part of the brain along with size, shape, boundary and position. Brain tumour is a serious disease occurring in human being. Medical treatment process mainly depends on tumour types and its location. Brain tumour detection is the most significant method to describe the early tumour. Enlarging the tumour is being a huge challenge due to the complex characteristics of the MRI images which gives highly intensive, divergence and uncertain boundaries.

Keywords: Brain Tumour, Image Processing, Magnetic Resonance Imaging (MRI)

Abstract: In interconnection and automation of different physical gadgets, vehicles, home machines and different things, the internet of things (IoT) innovation plays a critical role. These objects associate and deal information with the assistance of software, different sensors, and actuators. A human's standard of life and living are improved with this automation of gadgets, which is a forthcoming need. In this paper we talked about a similar requirement for instance, a smart car parking system which empowers a driver to discover a parking area and a free slot in that parking area inside a city. This paper focus on decreasing the time squandered on discovering parking area. This in turn diminishes the fuel utilization and way of life. With the exponential increment in the quantity of vehicles and total population, vehicle accessibility, use out, about starting late, finding a space for parking the vehicle is turning out to be increasingly more troublesome with realizing the amount of conflicts, for example, automobile overloads. This paper is connected to making a trustworthy system that accept authority over the undertaking of recognizing free slots in a parking area and keeping the record of vehicles left in an extremely methodical way. The predicted system decreases human effort at the parking area generally, for example, in case of looking of free slots by the driver and calculating the portion for each vehicle using parking area. The different advances engaged with this system are vehicle unique proof utilizing RFID labels; free slot discovering utilizing Ultrasonic sensors and payment count is done based on time of parking.

Keywords: IOT, RASPBERY PI, RFID, IR SENSOR, POWER SUPPLY,LCD, BLUETOOTH.

Abstract: H5 model in Convolutional Neural Networks (CNN) is a new innovation done by us. CNN (Convolutional Neural Network) is a popular NN algorithm and it clearly outperforms Artificial Neural Networks (ANN) and Recurrent Neural Networks (RNN) in this project. Inception V3, ResNet50, MobileNet and Xception [1] are the existing CNN models but are found to be less accurate and more time consuming. In our R&D lab we have developed a new CNN model called the H5 model. It is the best fit after the output is obtained from Haar Cascade Classifiers. A model which was developed for facial detection and distinction is now used for all objects detection with more accuracy focusing on five regions with different pixel Intensity scheme. The encouragingly high classification accuracy of our proposal implies that it can efficiently automate COVID-19 detection from radiograph images to provide a fast and reliable evidence of COVID-19 infection in the lung that can complement existing COVID-19 diagnostics modalities. In our previous paper on CNN we had exhibited one channel output. In this paper we are interested to know the performance of multichannel output with cascading.

Keywords: Multichannel output with cascading, H5 Convolutional Neural Network model, Convolution Neural Network (CNN) architecture, COVID-19, Severe Acute Respiratory Syndrome corona virus 2 (SARS cov-2), deep learning based chest radiograph classification (DL-CRC), Tensorflow, Haar Cascade Classifiers and one channel output.

Abstract: Credit risk is the probability of a loss resulting from a creditor’s failure to repay a loan or fulfil any other contractual obligations towards the investor. Traditionally, it relates to the hazard that a lender may not receive the owed head and premium, which follows a disruption of incomes and expanded expenses for collection. Unnecessary cash may be written to create additional income to cover for credit risk. Despite it is being impossible to know exactly who will default on commitments, satisfactorily surveying and overseeing credit risk can diminish the seriousness of a loss. The lender or investor earn a bonus for risking credit default and lending money in the form of interest from the borrower or issuer of a debt obligation. When lenders or banks provide mortgages, credit cards, visas or various types of credit or loans, there is a hazard that the borrower is probably not going to reimburse the loan. Likewise, if an organization provides credit to a client, there is a hazard that the client is not going to pay their solicitations. Credit risk additionally clarifies the risk that a guarantor may stall to make payment when asked or that an insurance company will be unable to pay a claim. Credit risks are determined based on the borrower’s general ability to reimburse an advance as indicated by its unique terms. To assess credit risk on a consumer loan, loan specialists inspect the five Cs: credit history, capacity to repay, capital, the loan’s conditions, and associated collateral. Banks have been the most important institutions of money lending and deposits. Primary functions include accepting deposits, offering loans, credit, overdraft, providing liquidity and discounting of bills. Secondary functions include providing safe custody of valuables, loans on valuables, corporate and consumer finances. Though the structure of banks has remained the same, the functionalities have been boosted. Automated tools, bots and computers have modernized the banking system. The dataset accumulated over a period of time is so huge that, automation tools and computer programs are the need of the day. In this paper we have tried to enhance the present bank credit-debit system by the use of Artificial Intelligence. Machine learning is a subset of AI and directly trains the machine by feeding the historic and runtime data collected during transactions. The machine which is trained is now capable of taking decisions, thereby making predictions. This would characterize the dataset as stored and predicted outcomes. Every business enthusiast would have keen interest to carefully study the performance of a financial institute for his/her benefit. In this assignment we have used both classification and regression algorithms to create a ML model of prediction. Linear regression model is designed from scratch using formula method. Classification algorithms like Support Vector Machine (SVM), Random Forest Classifier and KNN algorithms are effectively applied to fit to the dataset. Comparisons must be made during implementation to understand the pattern of predicted data. Regression algorithms like linear regression (developed from scratch) will be a boost to the accuracy of the assignment (categorical data excluded).

Keywords: accepting deposits, offering loans, credit, overdraft, providing liquidity and discounting of bills, Automated tools, bots and computers, Machine learning, Support Vector Machine (SVM), Random Forest Classifier and KNN algorithms, linear regression (developed from scratch) , historic and runtime data collected during transactions, AI, five Cs: credit history, capacity to repay, capital, the loan’s conditions, and associated collateral.

Abstract: The Internet of Things paradigm envisions the pervasive interconnection and cooperation of smart things over the current and future Internet infrastructure. The Internet of Things is, thus, the evolution of the Internet to cover the real-world, enabling many new services that will improve people’s everyday lives, spawn new businesses and make buildings, cities and transport smarter. Improper device updates, lack of efficient and robust security protocols, user unawareness, and active device monitoring are among the challenges that IoT is facing. Due to the pervasiveness of always connected devices, large amounts of heterogeneous data are continuously being collected. Beyond the benefits that accrue for the users, there are private and sensitive information that is exposed. Therefore, Privacy-Preserving Mechanisms (PPMs) are crucial to protect users' privacy. In this paper, we explore the background of IoT systems and security measures, and identify (a) different security and privacy issues, (b) approaches used to secure the components of IoT-based environments and systems, (c) existing security solutions, and (d) the best privacy models necessary and suitable for different layers of IoT driven applications.

Keywords: IoT, Data security, Data Privacy.