VOLUME 10, ISSUE 9, SEPTEMBER 2022

Abstract: One of the most vital senses in the human body is vision, which is also the sense that allows people to perceive their surroundings the best. As a result, thousands of articles on these topics have been published, proposing a range of computer vision services and products by creating new electronic assistive devices for the blind. This work tries to create a system that recovers the identification of nearby objects, a crucial function of the visual system. People who are visually challenged heavily rely on their other senses, such as touch and audio stimuli, to interpret their surroundings. It is quite challenging for a blind person to distinguish what is in front of them without touching it with their hands or any item like walking stick. Physical contact between a person and an object occasionally has the possibility to be fatal. This work employs a Neural Network for the recognition of pre-trained objects. A computer system that has the object identification Neural Network installed to carry out real-time object detection receives input from a camera that is oriented in accordance with the system's predetermined orientation.

Keywords: Computer Vision, Machine Learning, Neural Network, Visually Challenged

Abstract: Digital image analysis of eye fundus images has fewer benefits than current viewer-based methods. A symptom of various systemic diseases such as high blood pressure, glaucoma, diabetes and heart disease etc. affects the retinal arteries. Diseases such as diabetes indicate dysfunction and a wide range of changes in the retina. In retinal hypertension the blood vessels show dilation and dilation of the large arteries and veins. Arteriolar to Venular Diameter ratio (AVR) reveals high blood pressure levels, diabetic retinopathy and prematurity retinopathy. Among other image processing AVR measurements require vessel fragmentation, accurate vessel measurement and vein or vein segments [1]. The work is done to automatically detect retina vessels and that is why it is a challenging task.

Keywords: artery and vein classification, graph, retinal images, segmentation.

Abstract: Electrical energy has its applications in each and every domain of our life. It is directly or indirectly involved in every aspect of human life. Its usage has increased to a large scale nowadays. As of now the major portion of electric energy generated is by hydro and thermal energy. There is a danger of its depletion soon. Technical community is consistently searching for renewable, sustainable, and feasible energy source. Generating the energy from the economic and available resources has become very much essential nowadays. Bioenergy, solar energy is yet to prove their efficiency. Hence, we are proposing an idea of generation of the electric power by converting kinetic energy of flowing water in water pipe. This type of power generation is carried out here by one of the natural resources which is water, along with some necessary arrangement of turbines and pipes to produce the desired electric power efficiently. This proves to be one of the smart solutions of converting one form of energy to other and utilizing the converted energy as the basic need in everyday purposes.

Vegetables being the essential part of food need to be adequately included in our daily diet. It is a tedious and time- consuming work to cut vegetables for working class in their busy schedule. Everyone is interested in reducing the time of cooking by preserving the cut vegetables in their free time for future use. Hence there is a huge demand for ready to use fresh cut vegetables. One of the simplest methods is to preserve vegetables in the refrigerator, which is not an effective way. Cut vegetables do not retain real freshness as their flavour and taste reduces with time if it is preserved in refrigerator or kept open. Many methods were proposed by researchers to preserve the freshness of cut vegetables. Some of them include chlorine washing of vegetables, use of antioxidants and modified atmosphere packing. However, none have yet gained widespread acceptance by the industries and people. In this paper, an indigenous, simple and cost-effective method to preserve the freshness of the cut vegetables is proposed. Vegetables are preserved in specially designed glass chamber fitted with controlled suction unit and use them later when needed. This is a regulated method, where the gases liberated by the vegetables kept in glass chamber are pumped out at certain intervals of time by the suction motor. Suction motor is controlled by a relay and Arduino Uno microcontroller. In this way, both quality and freshness of cut vegetables and fruits are preserved.

Keywords: Turbines, Electrical Power, Turbine Flow, Kinetic Generation, Microcontroller, Suction Pump, Preserving Vegetables

Abstract: Speaking with someone who has hearing issues is never simple. Without a doubt, sign language is the most effective means of communication for those who have difficulty hearing or speaking. Their integration with other people is enabled and made simpler. However, only the development of sign language is insufficient. There are many restrictions attached to this blessing. The sign movements typically become confusing and difficult to interpret for someone who has never learned sign language or learns it in a foreign language. This long-standing communication gap can now be closed because to the development of several approaches to automate the detection of sign motions. In this research, we offer a method for identifying signing languages that is based on American SignLanguage.

Abstract: This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain. Existing methods are primary to reduce the inter-domain shift between the domains, which however usually overlook the relations among target samples. This paper investigates into the intra-domain variations of the target domain and proposes a novel adaptation framework w.r.t three types of underlying invariance, i.e., Exemplar-Invariance, Camera-Invariance, and Neighborhood- Invariance. Specifically, an exemplar memory is introduced to store features of samples, which can effectively and efficiently enforce the invariance constraints over the global dataset.

Keywords: Re identification, Machine Learning, Person identification, Invariance properties, GPP.

Abstract: Time series classification models have been garnering significant importance in the research community. However, not much research has been done on generating adversarial samples for these models. These adversarial samples can become a security concern. In this paper, we propose utilizing an adversarial transformation network (ATN) on a distilled model to attack various time series classification models. The proposed attack on the classification model utilizes a distilled model as a surrogate that mimics the behavior of the attacked classical time series classification models. Our proposed methodology is applied onto 1-Nearest Neighbor Dynamic Time Warping (1-NNDTW) and a Fully Convolutional Network (FCN), all of which are trained on 42 University of California Riverside (UCR) datasets. In this paper, we show both models were susceptible to attacks on all 42 datasets. When compared to Fast Gradient Sign Method, the proposed attack generates a larger faction of successful adversarial black-box attacks. A simple defense mechanism is successfully devised to reduce the fraction of successful adversarial samples. Finally, we recommend future researchers that develop time series classification models to incorporating adversarial data samples into their training data sets to improve resilience on adversarial samples.

Abstract: Battery management systems (BMS) are employed in electric vehicles to monitor and regulate the charging and discharging of rechargeable batteries, which increases efficiency. Battery management system maintains the battery's security, dependability, and senility without putting it in a harmful state. Various monitoring approaches are employed to maintain the battery's status, including monitoring of voltage, current, and ambient temperature. Different analog/digital sensors with microcontrollers are utilised for monitoring purposes. This paper discusses a battery's maximum capacity as well as its state of charge, health, and longevity. Future problems and potential solutions can be discovered by reviewing all of these approaches. This study proposes the computation and monitoring of three important indices for EVs BMS, namely state of charge (SOC), state of health (SOH), and state of function (SOF). The accuracy of residual capacity is questionable because the majority of SOC definitions are directly tied to nominal capacity. In order to reduce the mistake in the SOC estimation, the SOC is redefined using the current maximum capacity.

Keywords: Electric vehicle, Battery Management System (BMS), Lithium-ion Battery, Fuel Cell Electric Vehicles (FCEVs)

Abstract: India is an agriculture based country which takes various types of crops. Similarly, in Maharashtra Millet, Jowar, wheat, paddy and maize are the main crops. Nowadays various agricultural machines are available which are very costly. Due to this it is not suitable for poor farmers. And all farmers remove crops by hands which require much efforts and its time consuming process. Sometimes, while cutting or removing crops by hands results into damage due to blisters and crops on hands. Because of this labors are not available for work, in order to overcome this situation we introduced a new simple, but more efficient machine for farmers. Currently there are some jowar cutting machines are available in Market. Those machines works on the principle of cutting the jowar near the base. But due to this sucrose content in the jowar reduces. It also effects on grain weight. So to overcome all these problems we are designing new harvesting technique. This new technique is focused on uprooting and handling jowar crops by using uprooter and conveyor mechanism. It uproots jowar crop and transfers the crop by conveyor mechanism for further stacking process.

Abstract: This application is an Internet based application that can be accessed through internet and can be accessed by anyone who has a device. This project is based on online ordering services such as groceries, medicines, foods, bakery and sweet items, homemade products. However, the delivery process through these companies is costly and/or requires the customer's physical attendance at the company to get the sent shipments. There is a persistent need to improve the delivery process Udupi & Manipal to reduce the effort, cost, and time that the customer spends to get the shipped products. This paper presents a new delivery approach in Udupi & Manipal developing an Android-based Mobile Application that allows the customers to use their mobile devices to send and receive shipped products at their doorstep by submitting online requests through the developed Mobile Application. The proposed Mobile Application, named as NAMWAY product delivery Mobile Application, guarantees fast and costless service among its competitors. The Mobile Application will provide its customers a reliable delivery process. It aims to provide a domestic delivery chain with whomever to wherever within Udupi & Manipal. Moreover, the proposed NAMWAY delivery Mobile Application is easy to install and use, it provides a friendly GUI and has a powerful steady performance.

Keywords: Online Delivery, Namway, online delivery app, Online order service, Product Delivery

Abstract: This application is an Internet based application that can be accessed through internet and can be accessed by anyone who has a device. This project is based on online ordering services such as meat delivery, Nowadays there has been a great surge in on demand meat delivery app development .The reason behind it is offering the meat delivery services to customers through online meat delivery software. Business owners from the middle east are constantly demanding best meat delivery business management software for their business as it is helpful in building their brand identity online.

Keywords: Online Delivery, Namway, online delivery app, Online order service, Product Delivery

Abstract: Identifying statistical dependence between the features and the label is a fundamental problem in supervised learning. This paper presents a framework for estimating dependence between numerical features and a categorical label using generalized Gini distance, an energy distance in reproducing kernel Hilbert spaces (RKHS). Two Gini distance based dependence measures are explored: Gini distance covariance and Gini distance correlation. Unlike Pearson covariance and correlation, which do not characterize independence, the above Gini distance-based measures define dependence as well as independence of random variables. The test statistics are simple to calculate and do not require probability density estimation. Uniform convergence bounds and asymptotic bounds are derived for the test statistics. Comparisons with distance covariance statistics are provided. It is shown that Gini distance statistics converge faster than distance covariance statistics in the uniform convergence bounds, hence tighter upper bounds on both Type I and Type II errors. Moreover, the probability of Gini distance covariance statistic underperforming the distance covariance statistic in Type II error decreases to 0 exponentially with the increase of the sample size. Extensive experimental results are presented to demonstrate the performance of the proposed method.

Keywords: Estimating Feature-Label Dependence, Gini covariance and correlation, Gini Distance, RKHS.

Abstract: Data sincerity plays a vital role in easing evidence-based decision making in organizations and governments (e.g., policy making) within a fog environment. One of the main data sources is the Internet of Things (IoT) devices and systems. The ecosystem of the manufacturing industry is expected to be activated through autonomous and intelligent systems such as self-organization, self-monitoring and self-healing. The Fourth Industrial Revolution is beginning with an attempt to combine the myriad elements of the industrial system with Internet communication technology to form a future smart factory. The related technologies derived from these attempts are creating new value. However, the existing Internet has no effective way to solve the problem of cyber security and data information protection against new technology of future industry. In a future industrial environment where a large number of IoT devices will be supplied and used, if the security problem is not resolved, it is hard to come to a true industrial revolution.

Keywords: Block Chai , IOT Data Credibility, Fog Environment, Block Chain for IOT, Secure Block Chain

Abstract: There are a wide range of robots that are used for many kinds or many varieties of tasks to be accomplished according to their field of work, such as fixing parts, drilling, item categorizing (based on colours, shape, sizes etc), high accuracy task and so on. In most of the case, the tasks are driven by the Robotic Arm, as it is the most flexible option for performing the previously mentioned tasks. One of the main parts of a robotic arm in such work is the Holder (or Gripper). In some cases, the gripper will be designed in a particular type so that it will perform the same repeated process with the same object size and shape. This type of operation will be done by providing the work piece's dimension as an input that will never change while performing the task. But the limitation here is, these type of robotic arms will work only with the provided data and cannot work with an objected of a different dimension. So there should be an option that a single robotic arm will be able to manage and grasp objects of unknown dimensions and shape. And based on the problem above, the research is carried with a lot of reference and published as a simplified version in this paper.

Abstract: The proposed system is a crop harvesting system based on the Internet of Things (IoT), object recognition and automation technologies. The system helps to reduce the manual labour of the farmers by automating the identification and plucking of ripened fruit without a direct visit to the field. The system aims to reduce the tiresome tasks in the agricultural scenario. Harvesting using robotic arms reduces the amount of time spend by farmers in performing repetitive task. The proposed system includes object detection in the server side and harvesting using robotic arm in the hardware side.

Keywords: IoT (Internet of Things), Robotic arm