Abstract: Human Activity Recognition (HAR) is considered a challenging task in sensor-based monitoring systems. In ambient intelligent environments, such as smart homes, collecting data from multiple sensors is useful for recognizing Activities of Daily Living (ADLs), which can then be used to help provide assistance to inhabitants. ADLs are composed of complex time-series data that has high dimensionality, is large in size, and is updated continuously. Thus, developing methods for analysing these time-series data to extract meaningful features and specific characteristic would help solve the problem of activity recognition. Based on the noticeable success of deep learning in the time-series classification field, we developed a model for classifying ADLs in an ambient environment using deep neural networks. Our model, a Deep One-Dimensional Convolutional Neural Network (Deep 1D-CNN), contains several one-dimensional convolution layers coupled with a max-pooling technique to discover and extract the suitable internal structure to generate the deep features of the input time-series automatically. Such a model can be used as a unified framework for both feature extraction and classification. It performs well on high-dimensional time-series data; it does not require any expert knowledge in feature extraction, and it is able to find relevant and discriminative features for activity recognition. In order to evaluate the performance of our model, we tested it on the new real-life dataset, ContextAct@A4H, and the results showed that our model achieved a high F1 score (0.90). We also compared our results with baseline models for time series classification with deep neural networks. The comparison revealed that, our deep 1D-CNN model achieved the best overall performance in terms of precision, recall, and F1 score.   Keywords: Deep Learning, One-Dimensional Convolutional Neural Networks, Time-series Classification, Activities of Daily Living (ADLs), smart home

Keywords: Data security and privacy, Advance Encryption Standard Technique (AES), Blockchain Technology

Abstract: Failure to talk is viewed as a genuine inability. Individuals with this handicap utilize various modes to speak with others, there is number of strategies accessible for their correspondence one such regular technique for correspondence is gesture based communication. Creating gesture-based communication application for hard of hearing individuals can be significant, as they'll have the option to discuss effectively with even the individuals who don't comprehend gesture-based communication. This work targets making the essential stride in crossing over the correspondence hole between ordinary individuals and not too sharp individuals utilizing gesture-based communication. It is hard for a great many people who are curious about a gesture-based communication to convey without a translator. Accordingly, a framework that interprets images in gesture-based communications into plain content can help with constant correspondence, and it might likewise give intelligent preparing to individuals to get familiar with a gesture-based communication. A gesture-based communication utilizes manual correspondence and non-verbal communication to pass on significance. Keywords: American Sign Language, Hand Gesture Recognition System, Sign Language Detection, Sign Language Recognition, Indian Sign Language

Abstract: Traffic congestion is the one the major issue in the present world. This system aims in developing a real time traffic prediction and detection through social conversations by using the technology of data mining. The aim of the system is to predict appropriate class output to each social conversation, whether it is traffic or non-traffic related content.  This system employs m-KNN (Modified k Nearest Neighbour algorithm) as a classification model and PCA (Principle Component Analysis) is used for Feature Extraction. This system gives information about the current road status and helps the user to take a better route in their journey.

Keywords: PCA, m-KNN

Abstract: Privacy has received increasing concerns in publication of datasets that contain sensitive information. Providing useful information to users for data mining in the main aspect and goals. Generalization and randomized response methods were proposed in database community to tackle this problem. Both the methods has faced the same barriers. These Generalization and randomized response methods usually required to control the tradeoff between privacy and data quality, which may put the data publishers in a dilemma. In these paper, a novel privacy preserving method for data publication is proposed based on conditional probability distribution and machine learning techniques, which can in act different criteria for different transactions. A basic cross sampling algorithm and a complete cross sampling algorithm are designed respectively for the settings of single sensitive attribute and multiple sensitive attributes, and an improved complete algorithm is developed by using Gibbs sampling, in order to enhance data utility when data are not sufficient. Many other methods provide better and strong privacy and better data utility.

Keywords: Data publication, Privacy preservation, Data utility, Cross sampling, Gibbs sampling

Abstract: Our countries economy is mainly based on agriculture. Farmers plays an important role in agriculture, At present scenario due to variation in climatic change and other price influencing parameter farmers face massive loss due to uncertainties in the price fluctuation. The developed crop price prediction and forecasting system helps farmers to predict price of the commodity. The system gives detailed forecast up to next 12 month .The methodology we use in the system is decision tree regression which is machine learning regression technique. The parameter considered for prediction are:- rainfall, wholesale price index (minimum support price, cultivation cost). Accurate prediction of crop price; plays important role in crop production management. Such prediction will also support the allied industries for strategizing the logistics of their business. In general with help of this application farmers get a beforehand prediction which helps to increase their profit and prevent massive lose. Which in turn increase countries economy.

Keywords: Forecasting System, Decision Tree Regression, Price Prediction

Abstract: With rapid growth of population the need of technologies also increased. Automobiles are one among them. Increase of vehicles has also increase the number of road accidents. These accidents may also result to loss of life of people due to late information reaching to the rescue team. This paper presents an IoT Based Automatic Vehicle Accident Detection and Rescue System that will detect accidents and pass the information to the rescue team. Vibration sensor, Wifi Module and Global Positioning System are used in here.  With the help of vibration sensor signal, a severe accident can be easily detected and the message can be easily passed to required people with the help of micro controller. The system consists Atmega 328 microcontroller along with display.

Keywords: Accident detection system; human rescue system; global positioning system

Abstract: Vehicle Ad-hoc Networks (VANETs) permits vehicles to exchange running information among them. In this paper, we propose a system that can help a vehicle to judge the trustworthiness of a message. Based on the message's trustworthiness, messages are forwarded or discarded. In the proposed system the Intrusion Detection System (IDS) is used to monitor and collect information about the network traffic issues such as sudden brake, lane changing, slow down, etc. The IDS sends the messages to Road Side Unit (RSU). The RSU receives the messages from IDS and it will send the messages to the trust authority. The Trust Authority (TA) will check the messages for its trustworthiness. If the message is false, it will drop a false message. The proposed model compared with the Trust Scheme based on Vehicles Reports of Event model and simulation results shows that the proposed scheme shows better performance in all aspects than the existing model.

Keywords: VANETs, IDS, RSU, TA, and ITS.

Abstract: AVP (Arya Vaidhya Pharmacy) ULTIMATIX is a web based online monitoring system developing for a pharmacy. The system pass through the following procedure that it define projects and its objectives , define organizational units , define the key tasks associated with every employees and  make a list of specific characteristics of their products. This will provide a well-developed environment between employees and authorities. This software project has been developed using the powerful coding tools of HTML, CSS, JAVA and JSP at Front End and Microsoft SQL Server at Back End. The software is very user friendly. The project contains modules like Admin, Employee, Director, Manager and Customer support Team. This version of the software has multi-user approach. For further enhancement or development of the package, user’s feedback will be considered.

Keywords: AVP ultimatix  system, employees, staff, human resources, leave sanction, work recordings

Abstract: Today's life rolls around the concept of automation and the things that are automated are said to be of the next generation because they reduce the interference of human beings. The home automation system technology using IoT is unique from other systems that give the ability to the user to control the system from any location around the world through an internet connection. This project offers a new way of organizing home appliances using IoT by controlling the device by voice (Google Assistant), Android App and a Website with the help of a Wi-FiModule and MQTT server. The primary component is the MQTT server or a cloud server that supports MQTT protocol. Here we use Adafruit IO as the cloud server and it supports MQTT protocol.  The second part is the hardware module which provides an appropriate interface for the home appliances. This system is designed to be low cost and expandable allowing a variety of devices to be controlled.

Keywords: Home automation System, Internet of Things (IoT), Cloud Server, MQTT (MQ Telemetry Transport), Adafruit IO, Wi-Fi network

Abstract: In computer vision problems, identifying an image is one thorny task. This image recognition and feature extraction can be done by using the programming language python and few other machine learning algorithms and python libraries, which are discussed in this paper. This paper also consists of a case study related to bird species identification.  

Keywords: Image processing, sub-sampling, pooling layer, convolutional layer, Decision tree, opencv, scikit learn.

Abstract: It has been observed that “Stereoscopic Portfolio Optimisation Frameworks” introduce the concept of bottom-up optimisation through the utilization of machine learning ensembles applied to some market micro-structure element. But in contrast to the normal belief, it doesn’t always pan out as expected. One of the popular and widely used “Deep Q-Learning” algorithms is quite unstable due to the shake in the Q-values and also due to the fact that over-estimation action values under certain conditions. These issues tend to affect their performance adversely. Inspired by the breakthroughs in DQN and DRQN, we suggest a modification to the last layers, to handle pseudo-continuous action spaces, as required for the portfolio management task. The implementation used currently, called as the “Deep Soft Recurrent Q-Network (DSRQN)” is dependent on a fixed and implicit policy. In this paper, we have described and developed an Ensembled Deep Reinforcement Learning architecture based on implementation of temporal ensemble, in order to stabilize the training process, achieved by reducing the variance of target approximation error. As a result of ensembling the target values, overestimation is reduced and it also makes the performance better by estimating more accurate Q-value. Our aggregate architecture leads to more accurate and optimized statistical results for this classical portfolio management and optimization problem.

Keywords: Temporal Ensemble, Reinforcement Learning, Deep Learning, Finance Technology, Algorithmic Trading  

Abstract: The Internet of Things is designed using Arduino Uno. Purchasing and shopping at big malls are becomes a daily activity in metro cities. There will be huge rush at malls on the weekends and holidays. Customer will have to purchase various products and keep them into the trolley. After total purchase one needs to go to billing counter for the payments. At the billing counter the cashier prepare the bill using barcode scanner. Which is a time consuming process and it will results in long queues at the billing counters. To avoid this waiting in long queue we introduce a system called smart trolley. The aim of this system is to reduce the waiting of the customer in a long queue. The system consists of a RFID tag, RFID reader, WIFI module. All the products in the supermarket are equipped with RFID tags. When the customer put products in to the trolley its code will be detected and then the product details such as product name, product weight and number of each product will be displayed on LCD. After completing the purchase the customer needs to send the data to the billing software by pressing the corresponding switch in the smart trolley. Then the total bill data will be transferred to PC by wireless RF modules and then the purchasing details will be stored in the memory.

Keywords: RFID Scanner; smart trolley system; supermarket automation

Abstract: Bank Systems require a better security to protect the Accounts, User Information and Money from hackers and intruders. User needs higher level of protection for their data during Money Transaction through Online Payment systems. There are some possible ways for hackers to retrieve user information through SQL (Structured Query Language) injection attacks. By implementing   Blockchain technology, we can overcome SQL injection attacks and it is secure when compared to existing security systems. To prevent from unauthorized users, we use OTP (One Time Password) verification and Automatic generated call alert through Google account instead of SIM (Subscriber Identity Module) card based SMS (Short Message Service) alert.

Keywords: Blockchain, Bank, Transaction, OTP, SQL injection attack.

Abstract: Recent ubiquitous earthquakes have been leading to mass destruction of electrical power and Cellular infrastructures, and deprive the innocent lives across the world. Due to the wide-area earthquake disaster, unavailable power and communication infrastructure, limited man-power and resources. With the increasing proliferation of powerful wireless devices, like smartphones, they can be assumed to be abundantly available among the disaster victims and can act as valuable resource to coordinate disaster rescue operation. In this paper, we propose a smartphone based self-rescue system, also referred to as Rescue Me, to assist the operations of disaster rescue and relief. The basic idea of RescueMe is that a set of smartphones carried by survivors trapped under the collapsed infrastructure forms into a one-hop network and send out distress signal to nearby rescue crews.

Keywords: Disaster management, Smartphone, natural disaster

Abstract: Online Social Networks (OSNs) have become very popular in recent years, such as Facebook and Twitter, which have been part of many people’s daily life. The project starts as simple study on small social clique model, aiming to deeply understand users’ friendship types and reveal the fundamental reasons why collusion attacks can be done successfully. Based on observations made from this model, we further propose to classify social network users into non-popular users and popular users; develop different attacks strategies against them and illustrate the attack effectiveness in a general social network through different scenarios. Experiment results show that our proposed prevention of   collusion attack strategy has achieved high success rate by using limited number of malicious requestors. However, the rise of social network services is also leading to the increase of unwanted, disruptive information from spammers. Negative effects of social spammers do not only annoy users, but also lead to financial loss and privacy issues. Spammers are prevented using an administrator to approve or disapprove contents.

Keywords: Collusion attacks, Online Social Networks (OSN’s), Spam.

Abstract: Online service provider or the online bidding and auction becoming the most demanding tools these days worlds many companies are coming up with new product and services. Uber, Ola like companies are providing the cab services which may used by millions of users on daily basis for transportation. In few countries transportation service providers are giving online order accepting facilities, but not possible for all service provider. Yellow pages like services provides online dictionary for transportation service provider with limited information. Information about transportation vehicle type and experiences needs to be share with customer and also bidding options must be there for customers benefits. Proposed system is to design and develop an online transportation service provider bidding system where customer can post a job details to complete and service provider can bid for the job. System will automatically show best option or lowest option to customer where customer can allot work to specific service provider. System will help both service provider and the customer to get the job done. Customer can select right provider on the basis of experience, type of vehicle, budget and rating.

Keywords: Bidding, profiling, OTP

Abstract: Agriculture plays imperative role in the development of a country. In India major population depends upon farming sector accounting of 16% of Gross Domestic Product (GDP) of India. So, in every new technology invented in a new era is created to solve the day to day life issues. We have introduced a new system based on some already made projects but with use of new technology and modern ideas. In old days in the agriculture sector there weren’t many technologies invented. We have worked on the part of agriculture system which intelligently irrigates your yard with dynamic water cycles. It stops watering your yard if it is raining or has rained since your last watering. It uses the light sensor to detect the sunrise time and automatically adjust water start times accordingly. It also stops irrigation if your yard is too cold. Controlling of all these operations will be through any keen gadget or computer associated to Android based Web Applications and the operations will be performed by Soil moisture sensors, Temperature sensors, Wi-Fi modules and Arduino.

Keywords: Arduino, Soil moisture sensor, Temperature Sensors, Wi-Fi-Modules, Android.

Abstract: The population of our present world has raised tremendously which in turn leading to some new changes in the human kind. In accordance with the basic necessities, the comfort living of human life with the luxuries and life styles are also customized in such a way that, instead of using public transportation every individual want to have their own vehicle, which may result in heavy traffic and unnecessary accidents. By this the number of private vehicles increased a lot which resulted in more number of accidents and as well as pollution which is going to be a great loss to this environment. On the other hand there is no security for the vehicles as they are getting stolen by thieves easily. The accident discovery and its identification of exact location is the overall idea of the paper. This introduces accident alerting system which alerts the person who is driving the vehicle. If the person is not in a position to control the vehicle then the accident occurs. Once the accident occurs to the vehicle this system will send information to registered mobile number.

Keywords: Accident detection; Alert system;GSM Module;GPS Module; accelerometer; Android application.

Abstract: The biometrics is the challenging task for researcher. Biometrics based authentication is just impossible to help us if we don't know what are the requirements. Biometrics authentication must provide the security level, unattended system, Spoofing and Reliability. Among all the modalities FKP broadly explored which has not yet attracted significant attention of researchers. Finger knuckle is user centric contactless and unrestricted access control. We have proposed a novel person identification system that uses knuckle print features extracted by using Radon transform. The knuckle print image has been   viewed as a texture image. The local features from the knuckle print represent the  texture information present in the image in better sense .Radon transform computes the line integral along parallel paths in a certain direction.

Keywords: Finger Biometric, Finger Knuckle Methodology, Pattern Recognition, Finger-vein Identification.

Abstract: Alzheimer’s Disease (AD), the most common form of dementia, is a degenerative disorder of the brain that leads to memory loss. Anatomical changes observed in samples of Alzheimer’s are dramatic shrinkage of the cerebral cortex, fatty deposits in blood vessels, atrophied brain cells, neuro bifilarly tangles and senile plaques. Neuroimaging is a promising area of research for detecting AD. There are multiple brain imaging procedures that can be used to identify abnormalities in the brain, including PET, MRI, and CT scans. Each scan involves a unique technique and detects specific structures and abnormalities in the brain.  Inference problem (Confusion) in the diagnosis of AD as the Biomarkers obtained from MRI, PET, SPECT  images are similar for the diseases like brain tumor, brain cancer, hormonal disorders etc. Combining the different biomarkers from different neuroimaging techniques at different stages of diagnosis to make it personalize. From the literature review, it is clear that there is need of designing new system for Alzheimer’s disease detection which will be a personalize and help the doctors to detect the AD more accurately, which is reflected in the necessity of developing sensitive and specific biomarkers, specific vector reduction technique and a particular efficient classifier.

Keywords: Alzheimer’s Disease, Neuroimaging, Computer Aided Detection (CAD), Machine Learning.

Abstract: Outwardly Impaired are those individuals who have vision misfortune or vision impedance. Issues looked by outwardly disabled in implementing day by day exercises are in incredibly large. They likewise facing more challenges in money related exchanges. They can't perceive the paper currency forms because of similitude of paper surface and size between various classes. Our application causes outwardly debilitated patients to perceive and identify cash. Utilizing this application blind individuals can talk and provide order to open camera of an advanced mobile phone and camera will click image of the note and tell the client by discourse how a lot of the cash note is. For money recognition, this application utilizes Azure custom vision API utilizing Machine learning arrangement procedure to recognize cash dependent on pictures or paper utilizing mobile camera.

Keywords: Currency Detection, Image Processing, Microsoft custom vision API, Android Studio.

Abstract: Data-driven clock gating is reducing the total power consumption of VLSI chips. Data driven is causing area and power overheads that must be considered to lower the effect of over heads. It is therefore beneficial to group FFs whose switching activities are highly correlated and derive a joint enabling signal.  Clock power is the major contributor to dynamic power for modern integrated circuit design. Experts work clock gating is an astoundingly effective technique to lessen dynamic compel of sit out of rigging timing subsystems. This fragment of article portrays assorted sorts of clock gating strategies considered by various examiners. The work exhibits blueprint of encoder and decoder squares of correspondence structure with clock gating arrangement for power headway without corrupting the system execution. Expanding the control of essential clock gating with a couple circuit level novel pieces is moreover under thought by a couple of pros. A strategy with adaptable Pulse-Initiated Flip-Tumble (PTFF) is presented. The work depicts PTFF with component control streamlining and energetic arranging qualities, inciting to upgraded control concede figure. Makers attest control reducing of 51% in light of the HSPICE multiplications using accelerators for gate clock loop pipelining of binary instruction traces 

Keywords: Data Driven, Logic Gates, Flip-Flops, Clock Gating, AND Clock Gating, NOR Clock Gating, Latch based Clock Gating, Clock Networks, Register, Pulse, Power Estimator, DFD and RDFD.

Abstract: The increasing demand for low power mobile computing and consumer electronics products has refocused VLSI design in the last two decades on lowering power and increasing energy efficiency. Power reduction is treated at all design levels of VLSI chips. From the architecture through block and logic levels, down to gate level circuit and physical implementation, one of the major dynamic power consumers in the system clock signal, typically responsible for up to 50% of the total dynamic power consumption. Clock network design is a delicate procedure and is therefore done in a very conservative manner under worst case assumptions. It incorporates many diverse aspects such as selection of sequential elements, controlling the clock skew, the decision of the topology and physical implementation of the clock distribution network.  

Keywords: Data Driven, Logic Gates, Flip-Flops, Clock Gating, AND Clock Gating, NOR Clock Gating, Latch based Clock Gating.

Abstract: Library staff handle a tedious task involve sorting, lending, returning, tagging, eyeing of books. In addition, library users encounter problems for finding, borrowing, localising, renewing the borrowing, queuing, and so forth. To overcome these obstacles, this paper proposes a smart library management system based on an loT networking. Using low-cost passive tags in libraries reduces the cost of modernisation significantly. As such, integrating loT architecture into library management system makes both the library users and staff’s task easy, smart, convenient, and practical.

Keywords: loT Networking; loT networking; information engineering; software engineering; UML; database

Abstract: Creating short summaries of documents is obtaining salient information from an authentic text document. The extracted information is attained as a summarized report and consulted as a concise summary to the user. It is very crucial for us to understand and to describe the content of the text. The extractive summarization technique focuses on choosing how paragraphs, essential sentences, etc., creates the original documents in precise form and presents a summary that only contains parts of the original document. The efficiency of summarization resides in having identifying and presenting the key entities in the document. The proposed system aims at creating an extractive summary of multiple documents and enables us to find the relevance of the contents in those documents. This is enabled with a user interface to pose a query on set of multiple documents and present the most relevant documents in the order. Simple machine learning algorithms are used to perform this and the performance evaluation of the system could help the progress of research activities further to do the same as abstractive summarization using deep neural networks.

Keywords: Summarization, Machine Learning, Tokenization, Algorithms, Spacy

Abstract: Fatal Road accidents can be easily avoided by understanding the psychological condition of drivers. Majority of road accidents occur during night driving due to the state of drowsiness. Existing system uses EEG signals which has low spatial resolution by which there is a serious time delay between the neuron signals and actions generated by it. This makes the system tough for the real time prediction. The above problem can be resolved by using data fusion technique where an eye blink and heart rate monitoring system that alerts the driver during the state of drowsiness. With the aid of a eye blink sensor, when the driver closes his eyes for more than 5 seconds ,the driver's data along with the heart rate variability is sent to the cloud. The driver is monitored and the wake-up message is translated to speech and sent to the driver. Health care system monitors the health and psychological condition of driver from departure of the vehicle.  Genuine follow-up of the driver will also be monitored with robust GPS.

Keywords: Data Fusion, Cloud Data Analysis, GPS, Reliable Data Management.

Abstract: Breast cancer holds the second position for cancer deaths in women [12]. There are several Computer Aided Detection and Diagnosis (CAD) systems used today in order to aid radiologists in detecting malignant cancers at the early stage. Such systems along with suitable classifiers yield better prediction of cancerous masses. This paper presents a logistic regression model based mass detection and classification based on selected geometrical features from breast DICOM images with an accuracy of 93%. Previous work of Alima et al, resulted in an accuracy of 91% using ANN[4]. The performance of the feature extraction and classification system is developed using the database collected as a part of the dream challenge[2]. Performance results are given in terms of confusion matrices.

Keywords: Microcalcifications, Compactness, Malignancy, Neoplasy, Craniocaudal, Mediolateral  

Abstract: This study investigates the performance of Chaotic Baker Map and Double Random Phase Encoding (DRPE) encryption schemes in comparison with wireless communication channel. A comparison is drawn between the discrete Fourier transform (DFT)-Orthogonal Frequency-Division Multiplexing (OFDM) system on one hand, and the Discrete Wavelet Transform (DWT)-OFDM system and the discrete cosine transform (DCT)-OFDM system in an ADDITIVE WHITE GAUSSIAN NOISE (AWGN) environment on the other.  The Haar wavelet and quadrature phase shift keying (QPSK) modulation format are also considered. The study includes detailed mathematical calculations designed to measure the Peak Signal To Noise Ratio (PSNR) of two encryption schemes over OFDM system on AWGN channels. The results obtained through these simulations demonstrate clearly that the DFT-OFDM system yields the best performance.

Keywords: AWGN, Chaotic Baker Map, DRPE

Abstract: 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.

Abstract: Accidents in the workplace are a major problem, with potentially devastating consequences for workers and employers alike. Despite of clear safety regulations and procedures enforced by the authorities, risk management remains a huge challenge for employers in many industries. The proposed embedded system is expected to potentially reduce the chances of accidents happening in factories. The system consists of three modules: Worker module, Power tool module and Server module. The Worker module restricts access to dangerous power tools for workers without wearing proper gears. The glove with the worker unit will act as a security measure in such a way that each tool will have restricted access, according to the level of expertise of the worker. All of which is controlled by a Web Server unit which gives command to the Power tool unit.

Keywords: IoT, Raspberry PI, NodeMcu, RFID, Power Tools, Client-Server.

Abstract:  The Smart Fishpond Monitoring System’s main objective is to check the quality of the water by using pH, turbidity and temperature sensors. As the conventional system has some shortness in practise, this is done in Internet of Things (IoT) and some additional features have been included in this system for efficient management. In most of the aquaculture industries, manual water quality monitoring test is employed in order to assess the water quality of the pond. Only trained personnel can conduct the test. Test will need to be repeated if samples used are spoiled or no longer usable. Thus, the process is time and cost consuming. Fish is an important protein rich food resource. there has been sharp increase in demand of fish products due to increasing population pressure in this century. Thus, to meet the demand of present food supply, water quality management in fish pond is a necessary step that is required to be taken up. The graphical user interface was designed, so that the users and investigators can observe, investigate and analyze the related data. The user interface allows us to convey the analyzed data in the form of a message to the users in their respective local languages to their Mobile Phones and alerts them in unhygienic environmental condition.

Keywords: Internet of Things (IoT), pH, Arduino,ISP,WiFi

Abstract: Oral cancer is the most common type of cancer. It was an irrecoverable disease but now the progress in technology has made it curable if it is diagnosed in early stages. Oral cancer is increase in the number of cells which has the capability to affect its neighbor cells or tissues. It happens when cells divide out of control and form a growth, or tumor. In spite of having various advancements in fields like radiation therapy and chemotherapy the mortality rate is persistent. Therefore, early detection of cancer is important. In this paper we are using Machine Learning as domain for detection of oral cancer considering the datasets of a victim. Then it is classified using apriori algorithm. We are developing a health sector application which also uses Data Mining and data extraction for prediction techniques, classification rules for oral cancer prediction and uses association rules to perceive the relationship between the oral cancer attributes.

Keywords: Oral cancer detection, machine learning, web-crawler,data mining technique, association rule mining, apriori algorithm.

Abstract: This Paper presents the design of an e-agriculture model for the selling and buying of the agricultural products. The products are of high quality and trade value. Generally, through E-commerce, users can browse, compare and select the product items that they like in a more convenient manner, which brings great facility to the Ecommerce users. The main concept is that no intermediator act as a buyer or seller. The price of the product can be fixed only by the product owner. Another important feature of this model is that the product owner (i.e. the farmer) can get a solution for their queries. They can upload the image of an infected product to know about the type of disease that it has and also can get feedback for its cure. The owner can also feed in the information about the agricultural land to get a suggestion on which crop suits the best for that particular type of land. The agricultural information system provides its users and researchers to get online information about, the crop, statistical details and new tendencies. The trends of the crops act so that these will be pretty important to the users who access to this via the Internet.

Keywords: Online Trading, Weather Prediction, Online feedback and Soil Testing.

Abstract: This study investigates the performance of Chaotic Baker Map and Double Random Phase Encoding (DRPE) encryption schemes in comparison with wireless communication channel. A comparison is drawn between the discrete Fourier transform (DFT)-orthogonal frequency-division multiplexing (OFDM) system on one hand, and the discrete wavelet transform (DWT)-OFDM system and the discrete cosine transform (DCT)-OFDM system in an additive white Gaussian noise (AWGN) environment on the other.  The Haar wavelet and quadrature phase shift keying (QPSK) modulation format are also considered. The study includes detailed mathematical calculations designed to measure the peak signal to noise ratio (PSNR) of two encryption schemes over OFDM system on AWGN channels. The results obtained through these simulations demonstrate clearly that the DFT-OFDM system yields the best performance.

Keywords: AWGN, Chaotic Baker Map, DRPE

Abstract: This study attempt to explore the elements that impact the female buyer preferences towards various cosmetics brands present in the market. This study will help the cosmetics producers to know the view of the restorative customers towards distinctive purpose of purchase. The study is conducted in plain region of Uttarakhand and a survey method is used to collect the data. The personal care industry is one of the biggest purchaser divisions in the nation. The buying force and dispensable Income of the Indian female buyers have significantly expanded and it has made a specialty for driving associations in this fragment in the most recent decade, bringing about remarkable development in this segment. Key words: Consumer preferences, Cosmetics, Buying forces, Dispensable Income