MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

In restaurant industry many of them do not have automated tool for monitoring the customers. Machine learning helps to predict information from the data and Data analysis will provide data in well visualized manner. This project is divided into 3 parts as descriptive learning, predictive learning and prescriptive learning. The application is prepared using php and Data analysis using Google Data Studio and python. With this product restaurant can find their weakness focus on it and can increase the revenue after filling it up. In the project descriptive analysis focuses on customer data and sales data. Predictive analytics focus on in store analysis and expense tracking by visualizations. Lastly, predictive analytics includes Apriori algorithm for making combos of menu and XGBoost and Random Forest Classifier algorithm. The project also includes NLP analysis on reviews given by the customers.

School of Computer Engineering & Technology

Engineering and Technology

World University root node

International Journal for Research in Applied Science & Engineering Technology (IJRASET)

Machine Learning and Data Analytics based Restaurant Management System for Improving Customer Experience

Detection, and mapping of potholes in a precise and punctual manner is an essential task in avoiding road accidents. Today, roadway distresses are manually detected, which requires time and labor. In this paper, we introduce a system which uses deep learning algorithms and is integrated with smartphones to detect potholes in real-time. The user interface of the system is a smartphone application which maps all potholes on a route that the user is traveling. Simultaneously, deep learning object detection algorithm: Single Shot Multi-box Detector (SSD) looks for potholes using a mobile camera in the background. As soon as an unregistered pothole is detected by SSD, coordinates of the pothole are updated to the database in real-time. Accelerometer and gyroscope readings are continuously taken and assessed by a Deep Feed Forward Neural Network model to detect unregistered potholes. This dual mechanism of camera-based as well as accelerometer-gyroscope based detection not only cross validates detections but also provides stable results even if one mechanism fails. The pothole co-ordinates are rendered on the map user interface that can be accessed in the same application. This system with map/navigation feature as front end and two-fold deep learning pothole detection algorithm in backend is an efficient and a zero cost solution for real-time pothole detection.

IEEE Xplore

Deep Learning Approach to Detect Potholes in Real-Time using Smartphone

An exoskeleton, also known as powered exoskeleton, is a movable machine that primarily consists of an outer mechanical framework to be worn by a person. It is energized by using a system consisting of mechanical and electrical parts that deliver at least a part of the energy for the body movements. The development in exoskeleton is considered as the embodiment in development of military applications. In this paper, we have discussed the smart exoskeleton using vital engineering applications. The paper underscores the smartness of the exoskeleton using RFID and heat signature, GPS tracking, piezoelectric shoes and provide the Indian military with a cost effective smart exoskeleton with load reducing capability allowing the bearer to carry about 40kg weight with ease.

International Journal of Computer Engineering and Applications (IJCEA)

Smart Exoskeleton Primarily For Light Weighting Of Load

The Landmines are one of the deadliest weapons used in war which has killed millions of people during the world war period. Specifically, even at the current scenario the landmines spares around 15000 to 20000 lives each year as per the report from UN. There are lot of devices, technologies roaming around the fields to detect the landmines and it is not sufficient or sometimes unpredictable. Few reports from UN suggests that still there are lot of landmines which is leftover without exploding and it may explode when it is triggered with pressure on it. To locate the landmines the devices like Metal detectors were used initially and later used with sensors to improve the prediction. But, all these detectors or technology goes in vain while some of the mines couldn’t be recognized due to unusual physical or chemical properties. Ultimately to overcome these drawbacks and save millions of lives of the soldiers and people who lives near war affected areas, the new proposal on “Landmine Detector drone’s using Machine Learning” is proposed in this paper. The Drone with sensor’s attached will determine the physical and chemical properties of the object present beneath the soil.

Landmine Detector Drone's Using Machine Learning

Automatic emotion recognition has always been the talk of the town, for it finds numerous contributions to the welfare of different sectors of the society and enhances the standard of living. Emotion detection based on facial expression analysis, ECG, EEG and psychological signal processing are prevalent. Due to the drawbacks of the existing vision system for facial muscle action detection, such as it deals only with the frontal-view face images and is unable to handle the temporal dynamics of facial actions, emotion recognition using facial expression analysis is not always accurate. However, with the analysis of various psychological, EEG and ECG signal processing based emotion detection models, better efficiency, applicability to multiple users and that cause minimum amount of user inconvenience, have become plausible. As ECG signals are involuntary reactions of the body, and as such are very difficult to mask, unlike facial expressions, we intend this survey paper to be useful for the research communities working on affect detection using ECG signals processing. The paper covers automatic emotion detection model description, various linear and non-linear techniques of emotion detection specifically based on ECG signal processing. Furthermore, its limitations and applications are also explored.

A Survey on Emotion Recognition Using ECG Signals : Techniques And Its Applications

—“Botnet” is a network of computers that are compromised and controlled by an attacker. Botnets are one of the most serious threats to today’s Internet. Most current botnets have centralized command and control (C&C) architecture. However, peer-to-peer (P2P) structured botnets have gradually emerged as a new advanced form of botnets. Without central C&C servers, P2P botnets are more resilient to defences and countermeasures than traditional centralized botnets. In this paper, we systematically study P2P botnets along multiple dimensions: bot candidate selection, network construction, C&C mechanisms and communication protocols, and mitigation approaches. We carefully study two defence approaches: index poisoning and Sybil attack. According to the common idea shared by them, we are able to give analytical results to evaluate their performance. We also propose possible counter techniques which might be developed by attackers against index poisoning and Sybil attack defences. In addition, we obtain one interesting finding: compared to traditional centralized botnets, by using index poisoning technique, it is easier to shut down or at least effectively mitigate P2P botnets that adopt existing P2P protocols and rely on file index to disseminate commands.

Asian Journal of Convergence in Technology (AJCT)

P2P Botnet Prevention With The Help Of Sybil Attack

Service orientation system has been treated as one the important technologies for designing, implementing deploying large scale service provision software systems. The main idea of SOC is to explicitly separate softwareEngineering from programming, toemphasizeon software Engineering and to de-emphasize on programming. Service-Oriented Computing (SOC) is becoming the mainstream development paradigm ofapplications overthe Internet, taking advantage of remote independent functionalities. The cornerstone of SOC’s success lies in the potential advantage of composing services on the fly. When the control over the communication and the elements of the information system is low, developing solid systems is challenging. In particular, developingreliable Webservice compositions usually requires the integration ofboth composition languages, suchas theBusiness Process ExecutionLanguage (BPEL), and ofcoordination protocols, such as WS-Atomic Transactionand WS-Business Activity. Unfortunately, the composition and coordination ofWeb services currently have separate languages and specifications. A list of potential challenges for the maintenance and reengineering of service-oriented systems is presented for discussion.

International Journal of Advanced Technology in Engineering and Science (IJATES)

Requirements Proposals and Challenges in transaction Management Service-Oriented Systems

The biggest threat to the Internet is the fact that it was never really designed. For e.g., the BGP protocol is used by Internet routers to exchange information about changes to the Internet's network topologies. However, it also is among the most fundamentally broken; as Internet routing information can be poisoned with bogus routing information. Instead, it evolved in fits and start, thanks to various protocols that have been cobbled together to fulfill the needs of the moment. Few of protocols from them were designed with security in mind. or if they were sported no more than was needed to keep out a nosy neighbor, not a malicious attacker. The result is a welter of aging protocols susceptible to exploit on an Internet scale. Here are six Internet protocols that could standto be replaced sooner rather than later or are (mercifully) on the way out.

International Journal of Modern Trends in Engineeringand Research (IJMTER)

Aging protocols that could incapacitate the Internet

Today, centralized botnets are still widely used. In a centralized botnet, bots are connected to several servers (called C&amp;C servers) to obtain commands. This architecture is easy to construct and efficient in distributing botmaster’s commands; however, it has a weak link - the C&amp;C servers. Shutting down those servers would cause all the bots lose contact with their botmaster. In addition, defenders can easily monitor the botnet by creating a decoy to join a specified C&amp;C channel. Today several P2P botnets have emerged Just like P2P networks, which are resilient to dynamic churn (i.e., peers join and leave the system at high rates), P2P botnet communication won’t be disrupted when losing a number of bots. In a P2P botnet, there is no central server, and bots are connected to each other and act as both C&amp;C server and client. P2P botnets have shown advantages over traditional centralized botnets. As the next generation of botnets, they are more robust and difficult for security community to defend. Researchers have started to pay attention to P2P botnets. However, in order to effectively fight against this new form of botnets, enumerating every individual P2P botnet we have seen in the wild is not enough. Instead, we need to study P2P botnets in a systematic way.

IOSR Journal of Computer Engineering (IOSR-JCE)

Study of P2P Botnet

Proceedings of Third Post Graduate Conference on “Computer Engineering“ cPGCON 2014

Botnet - A Network of Compromised Systems

New generation business models impose additional requirements on the IT support of business processes. In particular, quickly responding to new business requirements, continuously reducing IT cost, and dynamically integrating new business partners and customers are highly demanded. Recently, the trend in software development has shifted from developing software systems to developing service-oriented systems that are composed of ready to use services. The Service-Oriented Architecture (SOA) architectural style has been widely adopted in industry thanks to its ability of providing seamless integration among software services Service-based applications are constructed by integrating heterogeneous services that are developed using various programming languages and running on different operating systems from a range of service providers. Services are loosely coupled entities, often designed under open-world assumptions, distributed across organizational boundaries, and executed remotely at their service providers’ environment. They require a smoother transition from development to operation than traditional applications. The objective of the paper is to look at the requirements of transaction management for Service oriented systems and the systematic requirements from the starting point for an analysis of current standards and technologies in the field of Web services

International Journal of Scientific & Engineering Research (IJSER)

Transaction Management in Service–Oriented Systems : Implementation

In sensor network a large amount of data need to be collected for future information retrieval. The data centric storage has become an important issue in sensor network.Storage nodes are used in this paper to store and process the collected data. This paper considers the storage node placement problem aiming to place unlimited storage nodes in sensor network to minimize the total energy cost for collecting the raw data and replying queries at the storage nodes. In this paper a strong data access model for placing storage nodes in sensor network is presented.We consider an application in which sensor networks provide real time data services to user. The main aim of this paper is to reduce the cost for raw data transfer,query diffusion, query reply by defining the best location of storage nodes in sensor network.