Applications of Machine Learning in The Field of medical care


Applications of Machine Learning in The Field of medical care

ABSTRACT

These years, with artificial intelligence and machine learning becoming the hotspot of research, several applications have emerged in each of these areas. It exists not only as a kind of academic frontier but also something close to our life. In this trend, the combination of medical care and machine learning becomes more and more tighter. The proposal of its main idea also greatly alleviated the existing situation of unbalanced medical distribution and resources strain. This paper summarizes some application of machine learning and auxiliary tumor treatment in the process of medical resource allocation, and puts forward some new methods of application to realize it closer to human life in the era of artificial intelligence and the explores a good situation of mutual combination of medical industry and computer industry, which is benefit both.

EXISTING SYSTEM:

         In present systems there is hardly any medical service available in remote locations. Persons needing medical services often need to travel long distances. Even in urban areas the service is sometimes not available immediately. Patients and doctors are hardly to communicate with each others.And also patients had to wait for long time in order to communicate to the doctor.This main concern has to do with the confidentiality of the data. There is also concern about non-confidential data however such Systems that deal with these transfers are often referred to as Health Information Exchange.

DISADVANTEGES:

Ø  Data Acquisition. Machine Learning requires massive data sets to train on, and these should be inclusive/unbiased, and of good quality. ...

Ø  Time and Resources. ...

Ø  Interpretation of Results. ...

Ø  High error-susceptibility.


PROPOSED SYSTEM

In today’s society, medical care problems have become a hot topic, and problems such as the unbalance and insufficient allocation of medical resources has become increasingly apparent. In this situation, the application of ML has become the unavoidable trend in the current development of medical care. As early as 1972, the scientists in the University of Leeds in the UK has been trying to use artificial intelligence (ANN) algorithms to judge abdominal pain. Now, more and more researchers are committed to the combination of ML and medical care. The methods of pathological diagnosis of tumors, lung cancer, etc. by ML has gradually entered the field of vision. Some companies, such as Alibaba, Amazon, and Baidu have established their own research team working for it. This introduction of ML in medical care has greatly saved medical resources and provided a new way for citizens to see a doctor and facilitate people’s lives. At the same time, the demand of people also provides a new impetus for the research and development of ML, with promoting its continuous improvement.

ADVANTEGES:

Ø  Identifying Diseases and Diagnosis. ...

Ø  Drug Discovery and Manufacturing. ...

Ø  Medical Imaging Diagnosis. ...

Ø  Personalized Medicine. ...

Ø  Machine Learning-based Behavioral Modification. ...

Ø  Smart Health Records. ...

Ø  Clinical Trial and Research. ...

Ø  Crowdsourced Data Collection.

 

SYSTEM ARCHITECTURE

SYSTEM SPECIFICATION:

HARDWARE REQUIREMENTS:

v  System                        :   Pentium IV 2.4 GHz.

v  Hard Disk        :40 GB.

v  Floppy Drive  :   1.44 Mb.

v  Monitor          :   14’ Colour Monitor.

v  Mouse             :   Optical Mouse.

v  Ram                  :512 Mb.

SOFTWARE REQUIREMENTS:

v  Operating system       :   Windows 7 Ultimate.

v  Coding Language                  :   Python.

v  Front-End                              :   Python.

v  Designing                               :Html,css,javascript.

v  Data Base                               :   MySQL.

 

REFERENCES

[1] G. Eason, B. Noble, and I.N. Sneddon, “On certain integrals ofLipschitz-Hankel type involving products of Bessel functions,” Phil.Trans. Roy. Soc. London, vol. A247, pp. 529-551, April 1955.(references)

[2] Jiang M, Zhang S, Huang J, et al. Scalable histopathological imageanalysis via supervised hashing with multiple features[J]. MedicalImage Analysis, 2016, 34:3-12.

[3] Joanna J K, Pawel K . Automatic Classification of SpecificMelanocytic Lesions Using Artificial Intelligence[J]. BioMedResearch International, 2016, 2016:1-17.

[4] Lu-Cheng, Zhu,Yun-Liang, Ye,Wen-Hua, Luo,Meng, Su,Hang-Ping,Wei,Xue-Bang, Zhang,Juan, Wei,Chang-Lin, Zou.A model todiscriminate malignant from benign thyroid nodules using artificialneural network.[J].PloS one,2013,8(12):e82211.

[5] Huang W C , Chang C P . Automatic Nasal Tumor Detection by greyprediction and Fuzzy C-Means clustering[C]// IEEE InternationalConference on Systems. IEEE, 2006.M. Young, The TechnicalWriter’s Handbook. Mill Valley, CA: University Science, 1989.

 video file 

 

 



Online Depression Detection using django python



                               Online Depression Detection


Abstract:

In this project we are detecting depression from users post, user can upload post in the form of text file, image file or audio file, this project can help peoples who are in depression by sending motivated messages to them. Now-a-days peoples are using online post services to interact with each other compare to human to human interaction. So by analysing users post this application can detect depression and send motivation messages to them. Administrator of this application will send motivation messages to all peoples who are in depression. To detect depression we are using SVM (support vector machine) algorithm which analyse users post and give result as negative or positive. If users express depression words in post then SVM detect it as a negative post else positive post



Generating Cloud Monitors from Models to Secure Clouds

 

Generating Cloud Monitors from Models to Secure Clouds

 

Authorization is an important security concern in cloud computing environments. It aims at regulating an access of the users to system resources. A large number of resources associated with REST APIs typical in cloud makes an implementation of security requirements challenging and error-prone. To alleviate this problem, in this paper we propose an implementation of security cloud monitor. We rely on model-driven approach to represent the functional and security requirements. Models are then used to generate cloud monitors. The cloud monitors contain contracts used to automatically verify the implementation. We use Django web framework to implement cloud monitor and OpenStack to valid ate our implementation. 

                                                                                                               

EXISTING SYSTEM:

In many companies, private clouds are considered to be an important element of data center transformations. Private clouds are dedicated cloud environments created for the internal use by a single organization. Therefore, designing and developing secure private cloud environments for such a large number of users constitutes a major engineering challenge. Usually, cloud computing services offer REST APIs (REpresentational State Transfer Application Programming Interface) to their consumers. The REST architectural style exposes each piece of information with a URI, which results in a large number of URIs that can access the system.

DISADVANTAGES OF EXISTING SYSTEM:

Ø Data breach and loss of critical data are among the top cloud security threats. 

Ø The large number of URIs further complicates the task of the security experts, who should ensure that each URI, providing access to their system, is safeguarded to avoid data breaches or privilege escalation attacks.

Ø Since the source code of the Open Source clouds is often developed in a collaborative manner, it is a subject of frequent updates. The updates might introduce or remove a variety of features and hence, violate the security properties of the previous releases.

PROPOSED SYSTEM:

We present a cloud monitoring framework that supports a semi-automated approach to monitoring a private cloud implementation with respect to its conformance to the functional requirements and API access control policy. Our work uses UML (Unified Modeling Language) models with OCL (Object Constraint Language) to specify the behavioral interface with security constraints for the cloud implementation. The behavioral interface of the REST API provides an information regarding the methods that can be invoked on it and pre- and post-conditions of the methods. In the current practice, the pre- and post-conditions are usually given as the textual descriptions associated with the API methods. In our work, we rely on the Design by Contract (DbC) framework, which allows us to define security and functionalrequirements as verifiable contracts.

ADVANTAGES OF PROPOSED SYSTEM:

Ø Our methodology enables creating a (stateful) wrapper that emulates the usage scenarios and defines security-enriched behavioural contracts to monitor cloud.

Ø The proposed approach also facilitates the requirements traceability by ensuring the propagation of the security specifications into the code. This also allows the security experts to observe the coverage of the security requirements during the testing phase.

Ø The approach is implemented as a semi-automatic code generation tool in Django a Python web framework.

 

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

 

Ø System                           :         Pentium Dual Core.

Ø Hard Disk                      :         500 GB.

Ø Monitor                         :         15’’ LED

Ø Input Devices                 :         Keyboard, Mouse

Ø Ram                               :         1GB.

 

SOFTWARE REQUIREMENTS:

 

Ø Operating system                    :         Windows 7.

Ø Coding Language           :         Python

Ø Tool                               :         PyCharm, Visual Studio Code

Ø Database                        :         MYSQL

 

REFERENCE:

Irum Rauf A boAkademiUniversity,Turku, Finland, Elena Troubitsyna KTH – Royal Institute of Technology, Stockholm, Sweden,  “Generating Cloud Monitors from Models to Secure Clouds”,  Annual IEEE/IFIP International




Construction site accident analysis using text mining and natural language processing techniques || Constructionsiteaccidentanalysisusingtextminingandnaturallanguageprocessingtechniques

 

Construction site accident analysis using text mining and natural language processing techniques



In this paper author is describing concept to provide safety to workers at construction site from accidents by analysing past accident data by using machine learning algorithms and text mining technique such as TF-IDF (Term Frequency-Inverse Document Frequency) and natural language text processing to remove special symbols, stop words, stemming etc.

 

Past accident data contains details of accidents and by building machine learning algorithms model we can analyse data to identify cause of accident and can prevent future accident by giving test data of new work to predict causes of accidents and can avoid such causes. This machine learning algorithms can help in extracting dangerous objects such as misused tools, sharp objects nearby, damaged equipment etc.

 

In this paper to provide safety to workers author covering below points

 

1)    Various texting mining and NLP techniques are explored with respectto construction site accidents analysis. Using this technique we will remove stop words, punctuations, special symbols and apply stemming technique to clean past accident data. After data cleaning we will convert all text data to numeric vector by using TF-IDF technique. TF-IDF contains frequency weight of each word in vector and using this vector we will build machine learning train model. Whenever we give new test data then that test data also convert to TF-IDF and then apply on train model to search for similar data and give output of similar data as prediction. Below example describe how to convert text to TF-IDF vector.

 

Suppose I have 3 sentences

Sentence 1: An apple a day keep doctor away

Sentence 2: apple good for health

Sentence 3: shipment of gold damage in fire

 

First we remove stop words such as ‘an, a, of, in’ from sentences and then take remaining words and form columns of vector. After forming columns put each word count as values of that vector. See below vector columns

 

 

 

Apple day  keep doctor away good health shipment gold damage fire

Sentence1     1         1       1       1           1        0        0           0              0       0            0

Sentence2     1          0       0      0            0        1        1           0              0       0           0

Sentence3     0           0      0      0             0        0        0           1              1        1          1

 

So I convert all 3 sentences to TF-IDF vector just by putting count of each word as vector values, if sentence contains that column word then we will put its count, if sentence not contains work then we put 0 as that column values. Now to check similarity we can multiply one row with other and if multiply value greater than 0 then two sentences contains similarity otherwise not.

 

In above matrix if multiply sentence 1 row with sentence 2 row then we get value greater than 0 and similarity is there as both sentences contains 1 common word called ‘apple’. Similarly if we multiply sentence1 row with sentence3 row then we will get value 0 which means similarity not there between sentence 1 and 3 and we can see there is no common words in sentence 1 and 3.

 

2)    Ensemble algorithm which has not been well studied in this field isproposed to classify the causes of accidents and SQP algorithm isutilized to search for optimal weighs of the ensemble model. In this technique we will use ensemble algorithms such as random forest and voting classifier with SQP (Sequential Quadratic Programming) to classify causes of accidents. Using SQP we can assign weight to the classifier which can help classifier in predicting correct causes of accident.

3)     A rule based chunker is developed for dangerous objects extraction.Neither SQP optimization algorithm nor rule based chunker withregard to this field is found in the state of the art. Rule based chunker means getting Part Of Speech (POS) of each sentence to find dangerous object detection. When we apply POS on sentence then all dangerous objects will come under NOUN POS and by extracting noun phrases from sentences we can identify what are the dangerous objects which causes accidents.

To implement this project author using OSHA dataset and effectiveness ofthe proposed approaches is verified by the experiment results. OSHA dataset contains past accident data and by using this dataset we will analyse performance of various machine learning algorithms such as SVM, Decision Tree, Naïve Bayes, Logistic Regression, KNN, Ensemble Random Forest and Propose Voting Classifier which will build on all 5 base classifiers such as SVM, Naïve Bayes, Decision Tree, KNN and Logistic Regression. Voting classifier take all 5 classifier and then vote each classifier and whatever classifier give better accuracy then voting will choose that classifier for future data prediction.

 

Dataset saved inside ‘dataset/OSHA.csv’ folder and you can open and see the details and below are some data of new work and it has no details what accident can cause by doing that work but machine learning can predict and display future accident cause.

 

cutting down a large horizontal pipe block

installing roof decking on a flat roof by carrying and placing decking material

portable storage tank and a running powered industrial truck Caught in or between

electrical transformer box distribution line electrocuted electric ladder work onto a 13800 volt power line work electrical parts

 

In above bold sentences some work details are there and while doing such work what accident can happen can be predicted with machine learning algorithms.


video output