The purpose of the Smart Cities Mission as mentioned by Govt. of Indiais " to promote cities that provide core infrastructure and give a decent quality of life to its citizens, a clean andsustainable environment and application of " Smart " Solutions " . Accordingly, mission is aimed at driving economic growth and improving the quality of life of citizens by enabling local area development leveraging technology that leads to Smart outcomes. The, purpose of this study is to explore current state of these parameters in Pune city form citizens perspective.

School of Management PG

Management

World University root node

Khoj Journal Indian Management Research and Practices

Exploring the Challenges of Implimenting Smart City Project in Pune

Emotions play an essential role in human life for planning and decision making. Emotion identification and recognition is a widely explored field in the area of artificial intelligence and affective computing as a means of empathizing with humans and thereby improving human machine interaction. Though audio visual cues are vital for recognizing human emotions, they are sometimes insufficient in identifying emotions of people who are good at hiding emotions or people suffering from Alexithymia. Considering other dimensions like Electroencephalogram (EEG) or text, along with audio visual cues can aid in improving the results in such situations. Taking advantage of the complementarity of multiple modalities normally helps capture emotions more accurately compared to single modality. However, to achieve precise and accurate results, correct fusion of these multimodal signals is solicited. This study provides a detailed review of different multimodal fusion techniques that can be used for emotion recognition. This paper proposes in-depth study of feature-level fusion, decision-level fusion and hybrid fusion techniques for identifying human emotions based on multimodal inputs and compare the results. The study concentrates on three different modalities i.e., facial images, audio and text for experimentation; at least one of which differs in temporal characteristics. The result suggests that hybrid fusion works best in combining multiple modalities which differ in time synchronicity.

School of Computer Engineering & Technology

Engineering and Technology

Fulltext

International Journal of Advanced Computer Science and Applications

Review on Multimodal Fusion Techniques for Human Emotion Recognition

In healthcare machine learning is used mainly for disease diagnosis or acute condition detection based on patient data analysis. In the proposed work diabetic patient dataset analysis is done for hypoglycemia detection which means the lowering of blood glucose level (BGL). Often in healthcare it is observed that the dataset is imbalanced. Therefore, an Ensemble Approach using imbalanced dataset techniques synthetic minority over-sampling technique and adaptive synthetic oversampling methods with different evaluation methods like train-test, K-fold, stratified K-Fold and repeat traintest were used. This ensemble approach was implemented on diabetic dataset using K-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), Naïve Bayes (NB) and logistic regression classifiers with average Stacking-C method thereafter to conclude. Comparative analysis was done using three different considerations. The results showed that KNN and random forest gives more stable metric values both on balanced and imbalanced dataset. The confusion matrix consideration concluded that KNN and random forest were found to be better with least false negative and maximum true positive count. But if average train and test time is taken into consideration then Naïve Bayes and random forest had least average traintest time. Thus, the three different considerations concluded that the proposed ensemble approach gives better clarity for different classifier implementation using machine learning.

Indonesian Journal of Electrical Engineering and Computer Science

<a href="https://www.researchgate.net/profile/Deepali-Javale-2/publication/364961953_Machine_learning_ensemble_approach_for_healthcare_data_analytics/links/6369dd2054eb5f547cb0d55b/Machine-learning-ensemble-approach-for-healthcare-data-analytics.pdf">Machine learning ensemble approach for healthcare data analytics</a>

Any design engineer or coating formulator’s primary objective is to protect metals. Large investments in terms of money, time, labour, and other resources are necessary for constructing large-scale machinery and structures. In terms of economy, the structure’s lifespan should be as long as feasible to create revenue. It is becoming essential to protect metal substrates from corrosion to prolong the lifespan of such huge structures. One of the most exciting, durable, useful, and effective methods to protect metals from corrosion is the application of corrosion-resistant coating. Graphene is a novel material with a wide range of applications because of its extraordinary features. The use of graphene in coating creates an obstacle and complicates the path for corrosive medium to reach the metal. As the path to the metal elongates, the corrosion medium takes longer to reach the metal. Thus, metal corrosion can be avoided. In this paper, the importance of graphene in coating formulation is discussed, including chemical modifications of graphene, the effect of graphene concentration on corrosion inhibition, and the contact angle of coating. This review also highlights the significance of water-based corrosion-resistant coating for preventing environmental damage. Keywords: Graphene, Corrosion resistance, Water base coating, Metal protection, Corrosive media

School of Chemical Engineering

CORROSION SCIENCE AND TECHNOLOGY

A State-of-the-Art Review of Graphene-Based Corrosion Resistant Coatings for Metal Protection

The continuous and significant excavation of subsurface soil and rock for structural backfilling, impacts the environment negatively. The present study attempts on the exploitation of non-biodegradable and hard-to-dispose waste materials (in different capacities) such as fly ash (FA), rock quarry dust (RQD), and refurbished Polyethylene Terephthalate (PET) bottles were used as an alternative for structural backfill and reinforcement. For model testing, two phase novel methodology was proposed (Unreinforced and reinforced FA system). A total of 29 systems were examined, encompassing a broad range of boundary conditions like FA subgrade system, unreinforced FA system (FA&nbsp;+&nbsp;RQD) with varying RQD layer thickness “H”, and reinforced FA system (FA&nbsp;+&nbsp;RQD with PET bottle mattress as an interface between the FA subgrade and the RQD layer). The parameters pertaining to the reinforcement (width “b”) are varied with respect to the constant value of “H”. Loading was applied on isolated footings for both phases. The model testing demonstrates that the performance of footings resting on RQD laid over stabilized FA subgrade with PET bottle mattress as an interface outperforms other systems significantly. Optimum values for boundary conditions were obtained in case of both the systems. It is observed that in case of reinforced FA system with optimum boundary conditions, the bearing capacity was increased by 10&nbsp;% and the RQD layer’s thickness was reduced by 47&nbsp;% as compared to optimum values of an unreinforced FA system. Further, the optimized values of the phases were validated by using PLAXIS 3D software.

School of Civil Engineering

Construction and Building Materials

Effect of isolated footing on fly ash subgrade reinforced with PET bottles: An experimental and analytical study

Single-point incremental forming is a versatile process. It is being studied by many researchers and industries because of its ability to form various geometric shapes without the need for specific tooling. In the current research work, numerical and experimental investigation on thinning in parts formed using the incremental forming process is done. The influence of three-process parameters specifically pitch, tool diameter, and feed on thinning (minimum thickness) is investigated. A hemispherical-ended forming tool with an 8 mm tool diameter made of high-speed steel and aluminum blank Al-6061 with 0.8 mm thickness is used for experimental work. Results show that all the process parameters have a major influence on the minimum sheet thickness of formed surfaces. It is observed that small tool and high feed result in improved thickness, whereas the medium value of pitch results in less thinning.

School of Mechanical Engineering

Soft Computing in Materials Development and its Sustainability in the Manufacturing Sector

Numerical and Experimental Investigation on Thinning in Single-Point Incremental Sheet Forming

In the domain of image captioning, many pre-trained datasets are available. Using these datasets, models can be trained to automatically generate image descriptions regarding the contents of an image. Researchers usually do not spend much time in creating and training the new dataset before using it for a specific application, instead, they simply use existing pre-trained datasets. MS COCO, ImageNet, Flicker, and Pascal VOC, are well-known datasets that are widely used in the task of generating image captions. In most available image captioning datasets, image textual information, which can play a vital role in generating more precise image descriptions, is missing. This paper presents the process of creating a new dataset that consists of images along with text and captions. Images of the nearby vicinity of the campus of MIT World Peace University-MITWPU, India, were taken for the new dataset named MITWPU-1K. This dataset can be used in object detection and caption generation of images. The objective of this paper is to highlight the steps required for creating a new dataset. This necessitated a review of the existing dataset models prior to creating the new dataset. A sequential convolutional model for detecting objects on a new dataset is also presented. The process of creating a new image captioning dataset and the gained insights are described.

Engineering, Technology and Applied Science Research (ETASR)

The New Dataset MITWPU-1K for Object Recognition and Image Captioning Tasks

It’s been around two years from the outbreak of the coronavirus, thus labeled as Covid- 19, and there has been an explosion of literature being published by research scholars related to work done on Covid-19. Covid- 19 as a keyword has been mentioned in the titles of most of these papers. It was thought to analyse the number of papers and the titles of papers which include Covid- 19 in the title of the research papers. The various combinations of other words like, prefixes, suffixes, N-gram combinations with the keyword Covid- 19 in the titles of these papers were also analysed. The research publication repositories analysed were: IEEE Explore, ACM Digital Library, Semantic Scholar, Google Scholar, Cornel University etc. The domains of research publication title analysis were restricted to computer science / computer engineering related papers. As the term labeling the corona virus outbreak as Covid-19 was labeled in 2020, the timeline of title analysis was restricted from 2019 till December 2021.

Ubiquitous Intelligent Systems

Analysis of Research Paper Titles Containing Covid-19 keyword using Various Visualization Techniques

The fusion of normalized difference vegetation index (NDVI) and land surface temperature (LST) provides very important information for analyzing systems such as agricultural drought monitoring system or drought early warning system. This research paper focuses on the study of the relation amongst land surface temperature and normalized difference vegetation indices using time series composed of Landsat 8 satellite OLI/TIRS sensor data. For deriving LST, the Radiative Transfer Equation (RTE) algorithm and the Planck’s function have been used with a PyQGIS plugin of Landsat 8 TIRS data. Along with LST and (NDVI), at-sensor reflectance, Land Surface Emissivity (LSE) and brightness temperature are also calculated using the PyQGIS plugin. TIMESAT software is used for estimation of phenological parameters which helpsin understanding the growth of crops at different stages, effects of climate changes on crops and finding the relation between LST and NDVI. It has been observed that LST and NDVI are strongly negatively correlated. Planck’s function gives the best negative correlation result as compared to the RTE algorithm. Also, various adjustment methods such as Savitzky Golay and Double Logistic Function are used for computation of seasonality parameters and it can be observed that Double logistic gives results.

School of Electronics & Communication Engineering

Journal of Xidian University

Normalized Difference Vegetation Index and Land Surface Temperature Evaluation of Agricultural Land near Ujani Dam Solapur District using TIMESAT Software

Proposed a smart doorbell system using webservers for making life easy and secure. In the proposed model, we are using Raspberry Pi for managing different types of interfaces and communications. We have used HTTP (Hypertext Transfer Protocol) for communication purpose. We have also used different types of software, including device software, control services, data derives and core services making this model efficient and salable. The overall aim of this paper is to make appropriate use of the technology for the needy and coming generations to come. In the proposed paper Histogram of Oriented Gradients (HOG) algorithm is used for Face Recognition.

Smart Doorbell Using web server IoT And AI

Face recognition system has become an integral a part of our modern-day to life. Varied applications of face recognition system. Digital image process could be an evolving field with growing applications in science and engineering. Image process holds the chance of developing the final word machine that might perform the visual perform all living beings It is employed in video surveillance, human pc interface and image management. Image or Video process has become a serious demand in current world. this method is majorly accustomed sight, acknowledge and track varied objects. Face sighting and following is that the section wherever we tend to detect someone's face from a image or in video sequence and track him/her throughout the video. It plays very important role in video corrections, police work, military following thus on.

School of Polytechnic and Skill Development

IJCA-International Journal of Computer Applications

Visual Media based CCTV Victim Tracker

n the modern era of technology and with increasing dependency on smart techniques like mobile phones, there is a requirement of solving daily life tasks in quick and easy ways. Smart technology is becoming the need of the hour to take control over the different tasks at home and in industries. The system proposed is based on detection and recognition algorithms. The main function of the algorithms is to automatically detect the smell and generate a message to the user that the food is spoiled. The key feature of computer vision is Arduino for reasons like marketability &amp; law-abiding apps. Secondly, after a lot of research on the accessibility of realistic technologies, this area of research finds an important place among different types of researchers and scientists like computers, food &amp; different organizations. The microcontroller panel can perform functions that include interpreting inputs and outputs and making the sensor activated. Generally, food is stored in the refrigerator which lowers the bacteria rate of production. Certain items which are perishable or not used for long-term storage are to be detected and informed to the user. This project is based to solve the food spoilage through sensors by continuously sensing the signals from the food and sending the alert message to the registered mobile phone.

International Journal of Scientific Research and Engineering Trends

Interactive and Smart Refrigerator using IOT

In the present research work, parts are formed using two-step hybrid incremental sheet forming (HISF) process. The effect of process parameters such as preform tool size, tool diameter, and preforming depth on thinning in the formed part is studied. A simulation model is developed and simulation results are compared with the experimental results. Also, results of HISF process are compared with the results of single point incremental sheet forming. The simulation results are in good agreement with the experimental results. It is observed that HISF process results in lower thinning as compared to SPIF process. Further, it is found that preform tool size has considerable influence on the minimum thickness of formed part. Large preform tools result in relatively lower thinning.

Engineering Research Express

Experimental and simulation studies on hybrid incremental sheet forming

Forming is the process in which deformation of the material takes place in a requisite die cavity without any failure. During this, bi-directional stretching and compression of the material takes place which results in defects necking, cracking and wrinkling. The challenges are different when same process is carried out at micro level with thin sheets below 100 microns. It has become imperative for many engineering fields to manufacture micro-sized components, due to growing miniaturization. It is also observed that the mechanical behavior of thin sheets differs greatly at the micro-level. Forming limit curve (FLC) is one way by which the formality of material can be assessed. The FLC can be plotted using three approaches—experimentally, empirically, and numerically. In this research, FLC is plotted experimentally for an ultra-thin Titanium sheet of 50&nbsp;µm. A newly designed tool with hemispherical punch of 4&nbsp;mm diameter was used for experimentation according to ASTM-2218-14 standard using samples of Uni-Axial, Intermediate Uni-Axial, Bi-Axial, Intermediate Bi-Axial, and Plane Strain paths to obtain limit strains. The objective of this research is to plot FLC with microstructural study to assess the behavior of Titanium Grade-II (TiG-II). For Numerical simulation M–K model was applied. The Numerical results and experimental results achieved are in good agreement. Micro structural study reveals phase identification and grain size assessment.

International Journal on Interactive Design and Manufacturing (IJIDeM)

<a href="https://link.springer.com/article/10.1007/s12008-022-00903-3">Novel product design of tool for investigating formability with microstructural study of bio-material titanium grade-II thin foils</a>

Blockchain architecture is a promise of finality and non-repudiation. It has distinct advantages over the traditional client-server or distributed systems, which have made various organizations explore use cases where blockchain can be applied. This chapter explores the key nuances of the blockchain architecture. It begins with an overview of the hash functions, hashing and how it plays an important role in blockchain architecture. While blockchain is well known as a P2P architecture, the chapter explores other aspects of the blockchain architecture, which are responsible for the strength of the blockchain. The chapter presents a deep dive into the block structure, use of Merkle trees for transactions and the blockchain structure. The power of decentralization, the built-in redundancy in the blockchain architectures and how it helps establish a trustless system is explained. It presents the challenges of distributed consensus and how they are dealt with via various consensus algorithms in the blockchain architecture. The chapter ends with a sample use case discussion of Maintenance and Service Supply Chain over a permissioned blockchain architecture using Hyperledger framework.

Blockchain for Smart Systems - Computing Technologies and Applications

Basics of Blockchain Architecture

Lecture Notes in Electrical Engineering

Moisture Sensor Using Microstrip Patch Antenna

The global seasonal change and continued rapid growth have maximized the need to assess the urban dwellers’ depend on vegetation for their lives, and also in the urban ecosystem resources. The conventional outcomes devoted to cropland mapping, with the help of high-quality remote sensing data’s. This paper is to investigate and develop a new methodology that pertains to time series analysis for classifying the type of vegetation in a farm area of Ujani Dam located in Solapur District, Maharastra. The proposed model develops a novel adaptive time-weighted dynamic time warping (ATWDTW) for the time series analysis using the satellite images. The gathered satellite images from the farm are processed initially and subjected to analysis by ATWDTW. The TWDTW concept is optimally tuned by the new hybrid meta-heuristic algorithm termed moth flame-based bird swarm optimization (MF-BSA) for enhancing the classification performance. Regarding the false omission rate of the proposed MF-BSA-ATWDTW model attains 5.56% and 29.9% lower than SVM and K-means respectively. From the analysis, it is possible to get a deep insight into the vegetation to be done in each year, and the comparative analysis proves that the proposed model is further adaptable for experimental use in relating and explaining environmental and ecological time-series information.

The ComputerJournal

Development of Adaptive Time-Weighted Dynamic Time Warping for Time Series Vegetation Classification Using Satellite Images in Solapur District

Globally, SLM is changing the way organizations design and manufacture products. It is an emerging manufacturing technique. This technique is classified as additive layered manufacturing, as the component is built by adding material in layers. Components/parts manufactured by Selective Laser Melting (SLM) find a lot of applications in many industries like aerospace, biomedical and automobile. Proposed research work investigates the effect of various process parameters on the mechanical properties manufactured by the SLM process of Stainless Steel 316L [SS316L]. The literature indicates that process parameters having maximum impact on mechanical properties includes Laser Power (P), Exposure Time (T), Border Power (BP) and Hatch Spacing (HS). The effect of these process parameters on Ultimate Tensile Strength (UTS) and Surface Roughness (SR) was investigated. This research work aims to enhance the performance measures, by optimizing the process parameters used in SLM with Grasshopper Optimization Algorithm (GOA) technique. GOA was used to achieve maximum ultimate tensile strength and minimum surface roughness in a single set of experimentation through a multiobjective approach.

Nature inspired multi objective optimization of selective laser melting of SS316L with the microstructural investigations

Nickel based superalloys belong to a special class of high performance alloys that feature large amounts of nickel. The uniqueness of superalloys lies in their design features, most notably mechanical strength, durability, etc. Inconel 718 (IN718) is a nickel based superalloy that exhibits high tensile and impact resistant properties, along with good high temperature corrosion resistance. Selective Laser Melting (SLM) is additive manufacturing (AM) technology aimed at melting and fusing metal powders using high power density lasers to produce precision functional parts. The accuracy and functional characteristics of manufactured parts are highly dependent on process parameters. The processing parameters that control the SLM process comprise laser power (P), hatch spacing (HS), exposure time (t), and border power (BP). This work primarily focuses on finding the combined effect of these process parameters on the surface roughness (SR) and ultimate tensile strength (UTS) of IN718 manufactured by SLM using the design of experiments (DOE).

Journal of Electrochemical Science and Engineering

<a href="https://pub.iapchem.org/ojs/index.php/JESE/article/view/1286">Relationship modelling for surface finish for laser-based additive manufacturing</a>

<ul><li>via non-commercial hosting platforms such as their institutional repository</li><li>via commercial sites with which Elsevier has an agreement</li></ul>

Testing Journal

Test Article - For the Webinar

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;