Volume 05 Issue 01

2021


Mechanical Properties of Fiber Reinforced Concrete by using Demolition waste as Coarse And Fine Aggregate
A M.Saravanan, M.M.Vijayalakshmi | pp: 01-05 | Purchase PDF

Show Abstract

Abstract: The cost of construction materials are increasing to a high rates for a conventional building and it is a major factor that affects the housing delivery worldwide. This has necessitated research for alternative cost of effective materials in construction. Therefore properties of concrete with Demolished concrete (D&C) waste are used as aggregate replacement of conventional aggregates and the study is done with M25 Grade Concrete. In these studies 3 different combinations of natural materials and D&C Waste content is used at the proportion of 50% Recycled Coarse Aggregate(RCA), 50% RCA & 10% Recycled Fine Aggregate (RFA), 50% RCA & 20% RFA has been replaced with 1% of Steel Fibers Reinforcement . The cube , beam and cylinder are casted as samples and tested , and then the physical & mechanical properties are determined. The samples are tested for density, compressive strength, flexural strength & splitting tensile for 7 ,14 & 28 days and then it is compared with conventional concrete.


Study On Knowledge and Skills About Nutrition Care Process Before and After Hospital Internship Among Dietetic Students
D. Shanthi, Alice C Pauline, Aswathi N S, Kavya Jyothi H, Moirangthem Kripa Devi | pp: 06-11 | Purchase PDF

Show Abstract

Abstract: The aim of the study was to compare the knowledge and skills of the dietetic students about Nutrition Care Process before and after internship. The respondents (n=107) selected were dietetic students who had undergone 6 months internship in a hospital setting. Online questionnaire (type form) was disseminated to the respondents. The data was analyzed using the paired sample t-test. The results of the study revealed that the level of knowledge attained on Nutritional assessment after internship (p=0.005) was high, skills obtained on Nutritional diagnosis showed significant difference (p=0.004) after internship, knowledge gained on Nutritional Intervention after the internship was higher (p=0.003) and there was a noticeable variance (p=0.001) in the skills acquired on Monitoring and Evaluation before and after internship. The study concluded that clinical judgment of the respondents was higher in post internship than in pre-internship and the nutrition care planning skills acquired during internship along with clinical exposure helped the students to enhance their skills.


Inverse [1, 2] – Domination in Graphs
Sathish. T  , Padma Priya. C | pp: 12-15 | Purchase PDF

Show Abstract

Abstract: A vertex subset S of a Graph G = {V, E} is an inverse [1, 2] – dominating set if, 1≤| N(v) ∩ S′ |≤ 2, for every vertex v∈V-S’ (i. e) each vertex v∈V-S’ is adjacent to atleast 1 or 2 vertices in S′. In other way, the distance between any two vertices in V – S′ is either 1 or 2 for any vertex set in S′. The lowest cardinality of an inverse [1, 2]-dominating set of graph G is called an inverse [1, 2]-domination number of G and is denoted by γ′[1, 2](G). In this paper, we extract the perfect values of γ′[1, 2](G) for few standard graphs and additionally, we use the general results to illustrate the interrelation between γ′[1, 2](G) and other criterions.


Docking analysis on pioglitazone analogues and their binding affinity as antidiabetics
Priyaranjini S Rao, Chandana S, Deekshitha | pp: 16-20 | Purchase PDF

Show Abstract

Abstract: The challenges of twenty-first century for the pharmaceutical industry are to deliver new and safe medicines within short span of time. A novel drug discovery is a complex and expensive process with decades of venture. With present technologies and inventions, the task has been swift and effective in the recent years. Computer simulations give the dynamic picture of the reactions along with the potential drug molecule. Quantitative Structure Activity Relationship (QSAR) model and docking techniques ease the identification potential drug molecules. The present work aims at molecular docking studies on derivatives of 4-[2-(5-Ethylpyridin-2-yl)ethoxy]benzaldehyde, which is one of the key intermediates to pioglitazone. All these derivatives possess various biological activities such as antibacterial, antitumor, antifungal etc., Molecular docking studies on the reported phenoxy ethyl pyridine substituents, resulted the authors to design similar novel moieties with promising biological prominence as antidiabetics.


Global Accurate [1, 2] – Domination In Graphs
Sathish T, Reshma S P | pp: 21-23 | Purchase PDF

Show Abstract

Abstract: A [1, 2] – dominating set S of a graph G = {V, E} is an accurate [1, 2] – dominating set, if V – S has no dominating set of cardinality |S|. An accurate [1, 2] – dominating set S of graph G is a global accurate [1, 2] – dominating set, if S is also an accurate dominating set of . The minimum cardinality of a global accurate [1, 2] – dominating set is called the global accurate [1, 2] – domination number and is denoted by . In this paper, we study some bounds for are obtained and exact values of for some standard graphs are found.


Phytoremediation Potential of Bio Adsorbent (Water Hyacinth) Against Dye Industry Effluent
Rajakumari, K. Bhavadharani | pp: 24-29 | Purchase PDF

Show Abstract

Abstract: Water hyacinth was obtained from Tirunelveli pond and it was used to remove dye from effluent water. Water hyacinth plant remove the rhodamine dye which was present in the dye water and the quality of treated and purified water was analyzed by APHA method. The present study clearly indicates that the purified water was more suitable for culturing of both plant (pennisetum glaucum) and fish (oreochromis niloticus) by analyzing the survival and the growth rate. Water hyacinth showed better antimicrobial activity against selected pathogens such as Pseudomonas, E.coli, Micrococcus, Proteus vulgaris, Bacillus subtilis; Micrococcus luteus; Escherichia coli. The present study also showed that the test plant (mung bean seeds) was grown well due to the nutrients which are present in the Compost made from water hyacinth than the Control. Protein profile of plant (pennisetum glaucum) and animal (Oreochromis niloticus) grown in this study indicates that there was a similar fraction was observed in test and control. In this present study water hyacinth used as Bio adsorbent, best antimicrobial agent and Natural manure.


Phytoremediation As a Novel Strategy for Uptake of Fluoride Ions from Environment
Amina Rafeek, Anjala Nazar, Baeyou George Zachariah, Bobit Thomas, Aju Mathew George | pp: 30-32 | Purchase PDF

Show Abstract

Abstract: The According to World Health Organization (WHO), fluoride is considered as one of the drinking water contaminants which cause large-scale health problems through drinking water exposure. The reported tolerance limit of fluoride concentration in drinking water is 1.5 mg/L. Fluorine promotes health benefits at low concentrations, but it promotes adverse effects ranging from fluorosis to carcinogenic problems at high concentrations. Although fluorine removal from environment can occur through processes such as adsorption, reverse osmosis, and electrodialysis, the phytoremediation emerges as an accessible, effective and environmentally friendly treatment. Plant tolerance to fluoride uptake is the essential requisite for phytoremediation and most of the time; it is the invasive species that are great in phytoremediation. However, in the present research work, a detailed understanding of the plants that can perform in phytoremediation for fluoride uptake in significant amounts from the environment and yet perform at the least toxicity, safe and much cheaper, is considered as an approach for a long-term strategy.


Study On Replacement of Bitumen Partially with Waste Cooking Oil and Engine Oil in Bituminous Concrete
Irtiza Khurshid, Neeraj Kumar | pp: 33-45 | Purchase PDF

Show Abstract

Abstract: Bitumen is defined as a gelatinous viscid mixture of hydrocarbons attained naturally or as a residue from petroleum refinement which is used for pavement materialisation and roofing. Bitumen is employed as a binder for flexible pavements throughout the globe. Though bitumen is non-hazardous under normal conditions but when heated it becomes toxic and has consequences of environmental degradation. Also, bitumen being a product of non-renewable source of energy i.e. petroleum will led to depletion of petroleum reserves. It is a key challenge in highway industry to scale back the dependence on fossil fuels & to recycle the highway waste. The asphalt industry is undoubtedly a sector that contains a sustainable environmental impact, one amongst the main component being binder, bitumen, which is produced from petroleum. Bitumen generation results in enormous amounts of carbon dioxide emission which causes hazardous environmental impact. This research work is about the employment of waste oils as the alternative binders. The waste oils employed are waste cooking and waste engine oil. These are studied and analysed as a step towards sustainable environment. This project work will provide an alternative or modified binder as well as will serve with the better way for safe disposal of waste oils generated. Thus, this project is beneficial concerning both the environmental aspects of alternative binder and safe disposal of waste oils.


Development of Clay Tiles with the Addition of Industrial Waste: A Case Study Analysis
Ajmal Shah, Akhila A, Dalia Maria Jaisan, Diya Faizel S, Febin Sam Philip, Aju Mathew George, S N Kumar | pp: 46-48 | Purchase PDF

Show Abstract

Abstract: In recent years, scientific issues of environmental preservation have gained prominence, and recycling of materials abandoned by various productive sectors has emerged as a serious challenge to be handled. Because of the environmental damage caused by industrial growth through waste disposal, this research looks into the idea of employing industrial waste as an alternative raw material in the production of ceramic tiles. The wastes were found to be viable as alternative raw materials in the production of ceramic tiles.


Effect of Cobalt Doping Percentage on Structural and Optical Properties of ZnO:Co Films Synthesized via Sol-Gel Method
Jijoy P Mathew | pp: 49-56 | Purchase PDF

Show Abstract

Abstract: In this paper we report the synthesis of Co doped ZnO thin films by a low cost sol-gel dip coating method and the effect of Co dopant concentration on the structural and optical properties of the prepared films. In the structural studies, using XRD measurements, no secondary phases or impurity phases were detected suggests that dopant atoms substitutes for host atoms without altering the crystal structure. The surface morphological studies reveal that morphology of the films was greatly influenced by dopant concentration. The band gap of the films decreases with increase in dopant concentration. The red shift in band gap with increase in dopant concentration is due to the p-d exchange interaction. The PL spectrum of the films shows emission peaks in UV, violet and blue regions. The mechanism behind these PL emission peaks were also explained in detail.


Structural damage detection methods using Finite Element Modeling
Harindranath S, M Beena Mol | pp: 57-61 | Purchase PDF

Show Abstract

Abstract: In the past ten years, the detection of structural damage based on finite element (FE), model updates is an area of study with increased attention to the civil engineering field. Different studies have addressed direct, predictive, empirical, and algorithmic techniques for the update of FE models for the assessment of structural damages. The study examines the structural health monitoring approach using the Response surface method, Bayesian’s Probabilistic Strategy (BPA), Modifying Genetic Algorithms (MGA), and Evolutionary Algorithms (Evolutionary Algorithms). Such approaches are graded according to the list of benefits available in each method. Modeling of finite elements focused upon evolutionary algorithms provides better results than other algorithms.


Mapping of quality of drinking water in various villages of Devanahalli Taluk using GIS
Pallavi M, T M Mohan Kumar | pp: 62-66 | Purchase PDF

Show Abstract

Abstract: One of the important source of water is Ground water, 50% of the world’s population depends on groundwater of which 43% is used for irrigation use. Hence the quality of groundwater is important . In this project the selected area for studies is devanahali taluk which is located in Bengaluru Rural district. Due to the drastic development of Bengaluru urban city and the location of KIA (Kempegowda International Airport) we need to concentrate on this area in all the aspects for the future sustainability of Bengaluru city. There are about 212 villages and 2 towns in this taluk with a population of 2,09,622 lakh. The total area of devanahali taluk is 446sqkm. Identification of bore wells with the respective latitude and longitude and checking physical-chemical parameters of the water sample and mapping in the software the given task can be executed by integrating various shape file and validated collected bore well data using GIS.


Sensors For Structural Health Monitoring: An Experimental Evaluation
Pradeep Kumar, Beena Mol M | pp: 67-71 | Purchase PDF

Show Abstract

Abstract: A Civil Engineering structure’s performance is strongly influenced by its service condition, age, the type of material employed and the structure’s plan. Apart from performance, every structure’s critical characteristic must be serviceability, safety, and reliability. As a result, it is critical to adopt a credible technology that is capable of conducting a thorough study and analysis of the structure. Structural Health Monitoring (SHM) is an internationally accepted technology that is used in a variety of applications. By utilising a damage detection and analysis strategy, SHM advancement aids in extending the service life of the structure. Sensors are critical to the SHM system’s operation. Generally, structures fail as a result of unique geometric traits and material deterioration that impair their performance. The SHM’s major goal is to alert the system during the early stages of damage start and to avoid further disaster propagation by continuous monitoring with structurally implanted sensors. The SHM continuously monitors the structure through displacement, strain estimation, impact, load, pH rate, crack appearance, vibration signatures, humidity, and crack size. The article discusses the experimental evaluation of two types of sensors, fibre optic sensors and piezoceramic sensors, which are widely employed in the majority of applications. This paper emphasises the future metrics and issues in sensor innovation and SHM technology.


Multi Object Image Classification using Student Network
Saleema N P, Meera K | pp: 72-74 | Purchase PDF

Show Abstract

Abstract: By using a deep convolutional neural network, ie, heavy network architecture we can produce impressive accuracy in many applications. Taking a well-trained heavy network architecture as a guiding module or teache network, we can train a student network that is lightweight yet accurate. In this way, we can make a mobile or portable student network that is accurate as of that of a teacher module. This paper proposes a method to classify multi-object images by using a student-teacher network. This model includes a fully convolutional localization architecture to localize the regions that may contain multiple highly dependent labels. The localized regions are further sent to the recurrent neural networks (RNN) to characterize the latent semantic dependencies at the regional level. Experimental results on several benchmark datasets show that our proposed model achieves the best performance compared to the state-of-the-art models, especially for predicting small objects included in the images.


A Survey on Human Detection and Counting
Adarsh K V, Abhijith A, Adarsh Balan V V, Advait Nikesh, Priya V V | pp: 75-79 | Purchase PDF

Show Abstract

Abstract: Identifying people vulnerable to COVID-19 infections is crucial in stopping the spread of the virus. The key to avoid the fast spreading of virus is to keep social distance. But it becomes difficult to keep distance in public places. Because so many people will visit frequently for full-filling their needs. Counting people and Detecting Humans are important problems in visual surveillance. In recent years, the field has seen many advances, but the solutions have restrictions: people must be moving, the background must be simple, and the image resolution must be high. Main focus of this work is to find methods that effectively deal with the above mentioned real-time issues. Machine Learning algorithms are utilized to identify the individual persons in a video frame. The dataset is thenceforth utilized to analyze the individual persons and count of individual persons are displayed into mobile application. Developing to build an efficient system to avoid rush in institutions, organization and even public places will help people for better time management.


Forecasting of Future Academic Records Using Bayesian Network and Data Secured By Blockchain
Sahla K.V, Afsar P | pp: 80-84 | Purchase PDF

Show Abstract

Abstract: The combination of Machine Learning and Blockchain technology in forecasting future academic record of a student. The authors forecast the future academic records of students in this study using past grade data. As a forecasting method, we use a Bayesian network. During construction of the Bayesian network forecasting model, unnecessary variables become noise and so lower the forecasting accuracy. Therefore, here used data gain to decrease the number of variables in the model to improve forecast accuracy. As a result, the accuracy was improved. The input for this study was past grade data that were recorded by using ledgers called blocks. The Blockchain was a technology in which the data are divided and converted into blocks through novel cryptography algorithms and it guarantee privacy as well as security.


A Survey on Healthcare Chatbot using NLP and Machine Learning
S J Aadithyan, U Sreelakshmi, Jeeshna K, Athulya N, Nisha Rose HA | pp: 85-89 | Purchase PDF

Show Abstract

Abstract: As the demand in Machine Learning and Artificial Intelligence keeps growing, new technologies will keep coming in the market which will impact our daily lives and one such technology is Virtual Assistants or Chatbots. Chatbots have evolved over years from being Menu or Button based to Keywords based and now Contextual based chatbots. The most advanced among these chatbots is contextual based because it uses Machine Learning and Artificial Intelligence techniques.ML and AI is used in these type of chatbots is to store and process the training models which will help the chatbot to give most accurate response when user asks domain specific questions to the bot. The aim is to create a healthcare chatbot using Artificial Intelligence that can diagnose the disease and provide basic details about the disease before consulting a doctor. This will help to reduce healthcare costs and improve accessibility to medical knowledge and as it is the time of pandemic it becomes very useful as the users doesn’t required to go to hospitals for small issues . The chatbots are computer programs that use natural language processing to interact with users. Our project aims to provide the users immediate and most accurate disease prediction based on the symptoms that user is or are facing .The disease prediction chatbot is developed by using natural language processing concepts and machine learning algorithms. For the prediction of diseases, we have used Decision tree algorithm. Healthcare chatbots are a gamechanger for healthcare industry.


Smart Parking System with Automatic Payment
Amal VS, Antony Pavu, Neeraj VN, Sneha George | pp: 90-95 | Purchase PDF

Show Abstract

Abstract: Internet of Things (IoT) plays a major role in today’s world by connecting day to day things to the networking system, thus providing a way for accessing electronic devices from any distant location. The growth of population and commercial development leads to a huge increase in number of vehicles. So that, spending too much time for searching a parking area/slot in the city is time consuming and also lead to substantial financial costs. Hence, in this paper we present an IoT based smart parking management system that would help the user to find a perfect parking space without wasting any time. The system consists of a smart phone application which have a mobile wallet and a user can search parking areas nearby the user’s location, choose and book for a slot in a parking area from the smartphone. With the help of RFID technology and cloud Integration, the system can provide real-time detection of improper parking and automatic parking payment collection. We also implement a way to incorporate non-booked users into the system. The proposed system will surely help users to overcome the difficulty of parking and also saves much of user’s time.


Real Environment WPA/WPA2 Reaver/Airgeddon Hack and The Enhanced Methods for Preventing Authentication Hacking
Adithiya Alagarraj, Balaji Radhakrishnan, Riyaz Ahmed | pp: 96-100 | Purchase PDF

Show Abstract

Abstract: This paper covers the various methods that are available today to hack the real environment wireless networks and the ways to prevent such attacks on the wifi systems. As, wifi serves as a fundamental component of our daily day life in which various transactions occurs as a part of it. In order to prevent the loss of information and to take care of the data hacking by hacking he keys that WPA/WPA2 uses, the hackers are able to sniff the data across the wireless network. There is a very serious weakness that prevails in the current scenario that employees WPA/WPA2 encryption mechanism. A hacker who sits within the range where the user lies has a low hanging fruit to easily hack the network system. The most easily used method for the attack is Reaver attack which is an easier, step by step phenomenon to hack the wifi network wherever it could be.


TASTEDIARY – A WORLD TO FIND YOUR TASTE
Abhirami C A, Gayathri S, Aparna Rajan, Agheel Kareem ,Gayathry S Warrier | pp: 101-104 | Purchase PDF

Show Abstract

Abstract: Most of the day, our generation uses a phone. Consequently, phones now have become an “assistant” rather than just a communication tool. With this aspect in mind, we wanted to use the phone as a personal assistant for helping users easily prepare delicious meals even if they don’t know anything about cooking. Using TasteDiary, it is possible to find a recipe specific to a dish the user would like. The Internet offers us many solutions to help us plan our meals, and, right now, there are many web sites that help us organize the food we eat. TasteDiary makes it easier to find recipes easily and faster. The user can either log in as a beginner or as a professional. The application not only allows the user to search for recipes and preparation but also allows them to check on the calories consumed by them daily. Along with this the professionals are provided with an additional feature to upload the recipe of their dish. Despite the fact that there are food search resources, none of them have recipe addition capabilities. In TasteDiary we added large-scale recipes which will be helpful for the user to find their favourite dishes. During this pandemic situation, the taste diary application helps the user to learn more about cooking and stay healthy at home.


Spinal Injury Detection with Crow Search – DCNN Method
Munavar Jasim K, T Brindha | pp: 105-108 | Purchase PDF

Show Abstract

Abstract: Any damage to the spinal cord may fully or partially affect the sensation of a human. Damage is may be because of vertebral fractures. To identify the injuries present in the spinal cord, first we need to segment the spinal cord. In terms of image registration, the segmented spines provide important features that are helpful to the correct alignment of corresponding anatomical structures across individual subjects. Furthermore, it becomes easier to conduct disease-oriented analysis given the segmented topologies/shapes of the spines. This paper proposes a spinal cord segmentation and injury detection system based on the proposed Crow search- DCNN method that has the capability to detect the injury in the spinal cord in an effective manner.


A Comparative study of Text Classification methods: TF-IDF, FastText and BERT Embedding
Asmi P, Gaya Nair and Shireen M T | pp: 109-111 | Purchase PDF

Show Abstract

Abstract: In social media information, text classification is an important role. Deeper understanding of text in machine learning methods to be able to accurately classify texts in many applications. Documents or Articles contain many words that are irrelevant for text classification. In this paper we discuss a comparative study of different classifications methods. 1)TF-IDF: Weight words method, translate each document into vector and evaluate the number of words in the document in a corpus. 2) FastText Embedding: feature learning technique where each word is represented as a bag of character n-grams. 3)BERT Embedding: one of the strong context and word representation.


Touchless ATM using Augmented Reality
Sahina M M, Sandra K M, Geogy George, Abdul Latheef M M | pp: 112-115 | Purchase PDF

Show Abstract

Abstract: Prevent spreading of COVID-19 is very critical to flatten the curve. Research has found that COVID-19 virus can transmit through public objects used by many people in similar fashion during the course of a day such as ATM keypad, Gas station keypad, self-checkout at grocery stores. Sanitizing keypad after every use is simply not feasible. So we need a technology which can help us operate the keypad without physically touching it. At the same time, we need to consider cost of new system or enhancement. Using Augmented Reality, we can impose virtual keypad on digital image at real time. There is no need for any additional hardware or camera to be installed. All we are talking about is mobile app powered by augmented reality.


Medi-Cloud
Kiran Xavier, Praveena P Prabhu, Rohann Tom Soney, Sanjay Suresh, Angitha George | pp: 116-118 | Purchase PDF

Show Abstract

Abstract: We had investigated the feasibility of treating a patient when he/she is under critical emergency care. Having hardcopy of their health history or medical status is not practical and not handy in these cases and we have concluded that if all the data could be provided on a digital device with an easy to understand interface it would help the hospital staff in quickly judging the condition and deciding on the treatments to be followed. By providing a centralized cloud storage to store these data provided by the patients before-hand we can provide access to it for the doctors. This data is secured using encryption algorithms so as not to lead to a breach in privacy. Using the unique key provided to patients, the doctors can access their health details and decide on the course of treatment according to this.


Automatic Detection of Diabetic Retinopathy
Athulya Valsan T P, Sarang K C, Rishikesh S K, Vyshna M P, Rashma T V | pp: 119-122 | Purchase PDF

Show Abstract

Abstract: When a person’s body fails to respond to insulin produced in their body, it leads to diabetes. In recent years diabetes has become more and more common disease and diabetic retinopathy has become the major reason for permanent blindness. Manual diagnosis is performed on retinal fundus images to find the diabetic retinopathy, but it requires experienced clinicians and by quantifying the importance of several small details which makes this an exhaustive and time-consuming task. As machine learning emerges as a powerful tool for analyzing medical images it is very much beneficial to detect the diabetic retinopathy in early stages to avoid the permanent blindness. This survey provides a comprehensive study about different approaches to detect diabetic retinopathy.


An Adaptive Model For Runway Detection and Localization in Unmanned Aerial Vehicle
Barakkath Nisha U, Razila A R, Landrea Bayer, Devika K P, Aparna K R | pp: 123-128 | Purchase PDF

Show Abstract

Abstract: Unmanned aerial vehicles is gaining more popularity in recent years due to its ability in performing dangerous task that cannot be done using manned aerial vehicles. Apart from military purpose they are also effectively used in urban planning too. Lots of data that are stored in hardware of uav is destroyed during accidents in landing time. It’s all because we don’t have an efficient system for the detecting the landing sites. Here in our work we provide an excellent mechanism using CNN models to detect the runway and to provide its exact location. Apart from that we are also providing methods to detect the runway even in bad weather condition, also augmentation is done on the dataset to increase the accuracy of the model.


A Survey on Authorship Attribution
Sona Joseph, Sudhina P. N, Swathy Sivan, Merin K Antony | pp: 129-132 | Purchase PDF

Show Abstract

Abstract: Over the internet huge amount of data is available in the form of blogs, emails, books, etc. The correct Identification of this data is a difficult task. Authorship Identification (AI) is the technique used to identify the actual author of an anonymous text, which has undergone a remarkable evolution in recent years. This is based on the idea that every person unconsciously follows his own writing style, which human readers can understand. This paper presents the literature review about advances in authorship identification. Also, various techniques used in AI, significant problems in this field, and our further research direction.


Detection and Prevention of Phishing Websites Using Machine Learning Approach A Survey
Renjitha P.F, Thasleema Sherif, Noumiya Noufal, Beema Shaji | pp: 133-136 | Purchase PDF

Show Abstract

Abstract: Phishing is a type of cyber-crime that aims to steal personals information, Data, Bank details, passwords, etc. For example, a person can lose their money or information by accessing a fake website that looks familiar to the original one. Phishing is of different types like vishing, Spear phishing, whaling, email phishing, etc in this the most common form of phishing through email. Many kinds of research are going on in this area to detect and prevent the types of cyber-crime still there is no complete solution for it. This paper helps to identify and classifies the various methods that can be used for phishing detection.


A Review of Fruit Classification Techniques
Rhea Salih, Respa R S, Teresa George, Shibreeze K Sebastian | pp: 137-139 | Purchase PDF

Show Abstract

Abstract: In today’s world, where everyone is concerned about their health, the ability to recognise fruits based on their quality is quite vital. Fruits are of different types. Finding the best-quality fruits, on the other hand, is a difficult undertaking. Several fruit recognition techniques based on colour and form properties have been developed. Colour-based and shape-based analysis approaches are the most commonly utilised analysis techniques for both the recognition and classification of fruit images. Different fruit images, on the other hand, may have similar or identical colour and shape values. This study demonstrates a variety of strategies for classifying fruits.


Wick: AI and IoT based portable bot for interactive computation and analysis of data
Jobel Johny, Mary Siby, Mayrose Antony, Melwin George, Krishnadas J | pp: 140-145 | Purchase PDF

Show Abstract

Abstract: Chatbots are now part of cultural narrative and are even more sophisticated. It is hard to find who has not had an interaction with a chatbot or virtual assistant. This project is to extend what chatbots can offer in the new digital era. Wick is an intelligent chatbot for mobile devices with extensive functions like data analysis, visualization, prediction and training ML models. It can also communicate to IoT devices and hardware. It has an interface with a user friendly interaction including speech and voice recognition capability. The application processes user queries with the help of Natural Language Processing and Networking, thus providing the user with the most relevant results including text, images, files etc. The application also has a cloud server which is in sync with the local databases of all personal devices. This project aims to build a much more enhanced chatbot that is not bounded to any servers and also provides sophisticated functionalities like training and deploying ML Models from any datasets, controlling IoT devices with interactive functions etc.


Automatic Attendance System Using Face Recognition And RFID Verification
Shaz Mohamed Paravakkal, Suhani Sanam K, Nikhil Mathew, Riza Ayisha.P, Athira.B Kaimal | pp: 146-150 | Purchase PDF

Show Abstract

Abstract: RFID and face recognition-based attendance system is the need in today’s digital world and age for universities and schools. Automatic attendance systems make the daily practice of marking attendance easy and highly efficient thus helping reduce time wasted during lectures for such administrative work. Face recognition-based attendance systems are one such biometric based attendance systems which provides more security and can evade multiple fake or proxy attendance practices easily. This paper presents a model of an automatic attendance system to alleviate the manual effort of recording data eliminating the probabilities of fraudulence. The model focuses on how face recognition incorporated with radio frequency Identification (RFID) detect the authorized students and counts as they get in and obtain out form the category room. Smart Attendance System keeps the authentic record of each registered student and eradicates greatly the normal tedious task. Moreover, this smart system keeps the details of each student registered for a specific course within the attendance log and provides necessary information consistent with the necessity. By recognizing the face of the individual and verified by RFID simultaneously in our project, the limitations in the existing manual attendance system are eliminated.


Review on Facial Expression Recognition Methods
Renju Renjith, Joby P P | pp: 151-155 | Purchase PDF

Show Abstract

Abstract: Facial Expression Recognition is an innovation which utilizes biometric markers to recognize feelings in human faces. All the more unequivocally, this innovation is a supposition investigation device and can naturally distinguish the six fundamental or general articulations. Facial Expression is one of the significant non verbal channels through which human feeling state is conveyed, it includes the examination and acknowledgment of facial highlights. Facial Expression Recognition is classified as social biometrics and furthermore relevant in the field of computer vision .This paper presents an audit of exhibitions and impediment of different Facial Expression Recognition techniques and analyze the performance and limitation of each method on the basis of accuracy of detecting the emotion.


Emotion Based Music Player
Anu John, Chinju P Bijoy, Simoniya P V, Sivadarsh S, Magniya Davis | pp: 156-164 | Purchase PDF

Show Abstract

Abstract: Emotions are a vital part of every living being. The information field combines emotions with the machine, to produce assistance and improve user experience. With emotional recognition, which reflects facial expression to detect a specific emotion, new approaches are taken on how human communication with a computer is often done. Emotions are played within the field of Music Information Retrieval, where music is categorized and supported on the emotion conveyed. Additionally, with in-depth meta-data analysis, better visibility is formed and more relevant recommendations are provided. The abstract provides a review on emotional awareness and classification of music, highlighting the various strategies utilized in these two learning areas.
Everyone likes to hear music, people of all ages enjoy music everyday. Recent studies confirm that humans reply to music and it plays a high impact on a person’s brain activity. Music plays an extremely important role in extracting an individual’s life because it is a crucial medium of entertainment for music lovers and listeners and sometimes even imports a therapeutic approach.


A Systematic Survey on Fake News Detection methods
Anjana C V | pp: 165-169 | Purchase PDF

Show Abstract

Abstract: The growing reputation of social media, an increasing number of human seat information from social media as opposed to conventional information media. However, social media has additionally been used to unfold fake information. The good sized unfold of fake news has the ability for extra ordinarily poor effects on people and society. Detection of fake information is critical in state-of-the-art society as sparkling information content material is swiftly being produced due to the abundance of to be had technology. This paper presents a review of performances and limitation of various fake news detection methods.


Platform To Connect Daily Labourers and Customers
Seena Binth K T, Nishana K T, Athul Prasad, Muhammed Shabeer T, Jerrin Joe Francis | pp: 170-173 | Purchase PDF

Show Abstract

Abstract: In this scenario where we have trouble in looking for labourers on a daily basis, an alternative method for contacting is of utmost importance. The platform helps customers book reliable services like cleaning, plumbing, painting, construction, beauty services etc. This helps to connect to the labourers within our fingertips. Professionals from your neighborhood will be able to connect according to the need. This also helps to solve the lack of employment as thousands of people get employed. In this way, this platform helps both customers and labourers mutually.


A Conversational UI Integration using NLU for Telepresence Robots
Abbas AM, Abhishek K, Akhil Biju, Athul VA, Shahna Abdul Hassan | pp: 174-177 | Purchase PDF

Show Abstract

Abstract: Telepresence Video conferencing technology is usually integrated with mobile robot devices that may be guided from afar in robotic systems. These technologies, which are primarily intended to promote social contact between individuals, are gaining popularity in a variety of application areas, including health care, independent living for the elderly, and workplace contexts. The major issue here is that in telepresense robot a person should remotely access the robot and the robot is inactive if the person is not available. In this paper, we have focused to solve the problem where major conversation has been done through Natural Language Processing and we integrate the same to the telepresense robot. Our system consist of a hardware part for implementing the telepresense robot and for conversation part we used dialogflow to implement the Natural Language Processing.


An Efficient Machine learning technique used for paddy disease and pest detection – A review
A.Pushpa Athisaya Sakila Rani, N.Suresh Singh | pp: 178-182 | Purchase PDF

Show Abstract

Abstract: Paddy diseases can cause sufferers of up to 30% of crops. Timely detection and proper preventative measures can help minimize the spread of these organisms. Symptoms of Paddy diseases appear in the plant leaf and stem. Early detection helps minimize the spread of these diseases and improve the quality of the crop. Paddy diseases and pests are vital aspects defining the yield and superiority of plants. Paddy diseases and pests identification can be supported out by means of digital image processing. In recent years, machine learning has made step forward in the field of digital image processing, far greater to existing methods. How to use machine learning technology to study Paddy diseases and pests identification has become a research matter of great anxiety to researchers. According to the difference of network structure, this study outlines the research on Paddy diseases and pests finding based on machine learning and the advantages and disadvantages of each methods are summarized. Collective datasets are presented, and the performances of existing studies are compared. In addition, possible solutions and research ideas are proposed for the challenges, and several suggestions are given. Finally, this study gives the investigation and viewpoint of the future trend of Paddy diseases and pests detection based on machine learning.


A Virtual Navigation android application based on Augmented Reality
Karthic T R, Nithin Mathews, Sanjana Martin, Sona John K, Vishnu Chandran, Uma E S | pp: 183-188 | Purchase PDF

Show Abstract

Abstract: The virtual navigation app is a location-based augmented reality navigation application for Android. It features an AR-powered point-of-interest browser and real-time AR navigation apps that have long been popular with users like tourists, car drivers, businessmen during their trips way around the unfamiliar terrain and build the route to the desired point. However, recently user location systems have been improved through such sought-after technology as augmented reality. Now it’s time to expand our research and provide detailed information on implementing AR solutions for geolocation.


IOT Assisted Electronic Device Controlling System
Justine Francis, Subin M, Stebin Paul, Kichu Sebastian, Ashly Thomas | pp: 189-192 | Purchase PDF

Show Abstract

Abstract: The project proposes an efficient implementation of IoT(Internet of Things) for monitoring and controlling electronic appliances via a mobile application. In the existing scenario, a large amount of energy and time is consumed in powering up appliances, mainly due to the location and confusing assembly of the switchboard. The proposed system works on IoT, where the controlling device will be a smartphone with an application to scan the device for a unique, preinstalled image on the device. In the application already added rooms are visible to the user. The user can select whichever room he needs to access. The components are added within the room. The application should identify the device and a control panel would be available to the user for further actions. The signals from the phone will be received at the IoT module attached to the switchboard which will control the powering of each device. Also, there would be a troubleshooting mechanism that is to be used in case of any malfunctioning. It would give an error message if components are not working properly. This would be a great help for the user to identify the components that are not working. Either he could fix the problem or replace the component. We can manage the room according to our needs. This would be a great help for everyone, especially people who have difficulty moving around.


An Improved Collaborative Filtering Algorithm Using Support Values
Perez Jose Laiju, Rachel Philo Jojo, Resi T Reji, Vimal K, Mrs. Priya K V | pp: 193-198 | Purchase PDF

Show Abstract

Abstract: Internet has a large number of data which are widely diverse and huge. The Recommendation System is used to filter out these contents according to the preference of intended users. It is an information filtering system that helps in prediction or rating, based on user preference. Conventionally, collaborative filtering is the common approach to the design of recommendation system. This approach uses the similarity measures which rely on the similarities between users. The method that we use here is a combination of multiple similarity measures, that are used to find similarities between users. Some of the similarity measures that we have used here are Pearson Correlation Coefficient, Mean Square Difference, Cosine Similarity, etc. Using the method of aggregation, we divide it into super similar and super dissimilar users and different similarity values are assigned to each. We use Root Mean Square Error to evaluate the predictive accuracy.