B.TECH CS

Certified that training work entitled " Industrial Training On Machine Learning " is a bonafied work carried out in the fifth semester by " Shaurya Tyagi " In partial fulfilment for the award of the degree of Bachelor of Technology in Computer Science Engineering from Inderprastha Engineering College during the academic year 2023-2024. ACKNOWLEDGEMENT The successful completion of any project requires guidance help from a number of people. I take my immense pleasure in expressing a whole hearted thanks to all the officials who guided me all the way through my training in the Inderprastha Engineering College. I therefore take this opportunity to express my profound sense of gratitude to all those who extended their whole hearted help and support to me in carrying out the project work. I express my deep gratitude to Aditya Tandon sir who provided me an insight into the working that enhanced my knowledge and with their support and cooperation this report has taken a presentable form. Shaurya tyagi 2000300100208 ii 32 Applications of Machine Learning Applications of Machine Learning include:  Web Search Engine: One of the reasons why search engines like google, bing etc work so well is because the system has learnt how to rank pages through a complex learning algorithm.  Photo tagging Applications: Be it Facebook or any other photo tagging application, the ability to tag friends makes it even more happening. It is all possible because of a face recognition algorithm that runs behind the application.  Spam Detector: Our mail agent like Gmail or Hotmail does a lot of hard work for us in classifying the mails and moving the spam mails to spam folder. This is again achieved by a spam classifier running in the back end of mail application.  Database Mining for growth of automation: Typical applications include Web-click data for better UX, Medical records for better automation in healthcare, biological data and many more.  Applications that cannot be programmed: There are some tasks that cannot be programmed as the computers we use are not modelled that way. Examples include Autonomous Driving, Recognition tasks from unordered data (Face Recognition/ Handwriting Recognition), Natural language Processing, computer Vision etc.  Understanding Human Learning: This is the closest we have understood and mimicked the human brain. It is the start of a new revolution, The real AI. Now, after a brief insight lets come to a more formal definition of Machine Learning

A cognitive radio by virtue of its ability to sense and adapt to the dynamic spectrum scenario, can increase the spectral efficiency .In order to be non invasive, a cognitive radio must adhere to strict benchmark in the quality of spectrum sensing for primary users of a band.Thus, spectrum sensing has a major role to play in cognitive radio .Many algorithms have been proposed to enable spectrum sensing such as energy detection and cyclostationary detection. IEEE 802.22, the first standard for cognitive radio devices, imposes strict requirements for the detection and false alarm probability on all spectrum sensing devices at SNR up to-20 dB. This requires use of robust spectrum sensing techniques. Energy detection is the simplest and near optimum technique that is widely used for spectrum sensing. However its performance is drastically affected by uncertainty in noise variance due to SNR wall [1]. Cyclostationary detection can exploit detection spectral correlation present in most mo...

BACKGROUND Diabetes has been a major problem in India. Its slow growth is associated with many complications, most common being peripheral neuropathy. An easy and cheap investigation to diagnose the neuropathy may help in early diagnosis and decrease the economic burden on the society. The purpose of the study was to assess the usefulness of ultrasonography (USG) in the evaluation of diabetic peripheral neuropathy (DPN). METHODS Fifty adult diabetic patients with clinically diagnosed DPN and 50 diabetics without DPN were included in the study. USG of the medial, ulnar, and common peroneal nerves was done. The mean cross-sectional area (CSA) of the involved nerves was measured in the two groups at identical positions. The CSA was compared between the two groups, and Student t-test was applied to assess statistical significance. RESULTS The mean thickness of median nerve among diabetics without DPN was significantly less at 5 cms proximal to wrist (7.34 ± 1.24 vs 11.12 ± 1.56, p<0.0001); was significantly less at mid-forearm (6.84 ± 0.77 vs 10.36 ± 1.72, p<0.0001); and was significantly less at elbow (7.36 ± 0.75 vs 10.2 ± 1.64, p<0.0001). The mean thickness of ulnar nerve among diabetics without DPN was significantly less at wrist joint (6.98 ± 0.89 vs 8.44 ± 1.34, p<0.0001); and was significantly less behind medial epicondyle (7.44 ± 0.93 vs 9.36 ± 0.98, p<0.0001). The mean thickness of common peroneal nerve among diabetics without DPN was significantly less at neck of fibula (7.26 ± 1.34 vs 9.3 ± 1.67, P<0.0001); and the mean thickness of posterior tibial nerve was also significantly less at 5 cms above medial malleolus (7.06 ± 1.25 vs 9.16 ± 1.61, P<0.0001). There was a significant increase in the CSA of the median, ulnar, posterior tibial and common peroneal, in DPN patients as compared to diabetics without DPN (p<0.05). CONCLUSIONS USG demonstrates a morphological change in patients with DPN in the form of an increase in CSAs, which was statistically significant. USG can objectively complement other diagnostic investigations such as nerve conduction studies. High resolution ultrasonography of peripheral nerves has the potential to become the investigation of first choice for the evaluation of DPN.

In this paper, we have put forward a system which will detect workload of brain. Different classification algorithms will evaluate the real time workload of a person. User will perform certain task at the same time frequency from the brain will be gathered. On the basis of trained data and classification algorithm will help system to determine the workload of the person. A 2d brain image will be final hard copy report of the person. System will help various individual and organization to know the work related load of a person and to reduce the stress level thereby increasing productivity. IndexTerms EEG machine, Neural networks, Brain image

In this age, when we have well-connected roads, commercial building and increasing number of vehicles, parking is still a matter of concern. Still we are using manual procedure of parking. Because of this, a huge traffic jam takes place. While parking and retrieving it out, vehicles suffer dent by bumping with each other as there is lack of sufficient space. Keeping this chaos in mind, we are introducing automated parking systems as a solution of these problems. In addition, existing parking system in commercial spaces is creating hurdle and causing wastage of time and economical losses as well. This Smart Parking System is a solution of all these problems as well as replacement to the manual parking system. The aim of this paper is to presents a miniature model of an automated parking system that can regulate and manage the number of vehicles that can be parked in a given space at any given time based on the availability of parking slot. Keywords—automated,smart,parking,Iot,Javabeans

Now a day with the rapid development in various developing countries, all over the world there is an increase in energy demand with each passing time .The problem of food crisis in most part of the developing countries takes place due to inability to preserve food surpluses rather than low production. This article is concentrated on the solar dryer and the experimentation of different samples (food stuffs).Drying is a process of removal of liquid by evaporation from the food stuffs like apples, grapes etc and other agricultural products. Mechanical methods for separating a liquid from a solid are not generally considered drying. In the following section an attempt is made to provide an overview of the solar dryer (prototype) for agricultural products.In our experiment average dryer efficiency for one day is found to be 13% for different samples while the moisture content for various samples like chilli, grapes and apples is found 64%, 58% and 60% respectively. All the readings are o...

CO2 is one of the rediscovered, ecologically safe refrigerants with very low global warming potential which has favorable thermo-physical properties. The CO2 booster refrigeration system has already been identified as a suitable choice for the supermarket application to replace the conventional R404A (high GWP) system. However, the performance of the CO2 booster system is still comparatively lower than the conventional R404A system, especially when operated at high ambient temperature, which compels to improve the performance of the CO2 system with suitable modification. In the present work, an attempt has been made to examine the year-round performance of the basic booster system and basic booster system with the integrated modified evaporative cooling system for Ahmedabad city weather conditions (Hot and Dry climate region). The experimentally investigated and validated data are used for the modified evaporative cooling system with real-time weather data taken from the weather sta...

suffering through a business pitch or a classroom presentation or enjoying an evening of home theaterblockbuster thrills, there's a good chance an LCD (liquid crystal display) projector is responsible for the light show. The technology behind the LCD projector is nearly three decades old in 2012, but it remains one of the top digital projection technologies, alongside Digital Light Processing (

This work done is aimed at developing an Online Web-based "Department Management System" that is of importance to a specific department of a college. The system is a web-based application that can be accessed throughout the department of an organization. This system may be used for monitoring the overall activities as well as performance of the students. This work is being developed for an engineering to maintain and facilitate easy access to information. For this the users must be registered with the system after which they can access as well as modify data as per the permissions given to them. DMS is a web based application that aims at providing information to all the levels of department in an organization. This system also contains department yearly magazine "BYTE" and all other books in the library module which are related to the department. For a given student/faculty can access the system to either upload or download some information from the database.

This work done is aimed at developing an Online Web-based "Department Management System" that is of importance to a specific department of a college. The system is a web-based application that can be accessed throughout the department of an organization. This system may be used for monitoring the overall activities as well as performance of the students. This work is being developed for an engineering to maintain and facilitate easy access to information. For this the users must be registered with the system after which they can access as well as modify data as per the permissions given to them. DMS is a web based application that aims at providing information to all the levels of department in an organization. This system also contains department yearly magazine "BYTE" and all other books in the library module which are related to the department. For a given student/faculty can access the system to either upload or download some information from the database.

Trace contents of uranium in various commercial fertilizers e.g. ureas, superphosphates, diammonium phosphates have been determined using fission track etch technique. The uranium content in ureas varies from .05 to 1.3 mg kg-~ whereas in superphosphates it varies linearly with phosphate content.

The Era of Big data and Information security tends to both opportunity and risk management for every business activities. In Big data, Information security standpoint big data has ushered in new possibilities in terms of analytics and security solutions to protect data and prevent future cyber attacks. In Information security point of view big data is a very large data set that is mined and analyzed to find patterns and behavioral trends. In this paper we focus on process involved in data processing and overlook the security issues of big data and describes the scope of big data in business field.