mohammadjavad sayadi

Laryngeal disorders are a common health problem that affects people of all ages, genders, and races. One of the main symptoms of laryngeal disorders is changes in the voice, which can be used as an indicator for the presence of such disorders. In this paper, we present a data mining approach for using voice as an indicator for laryngeal disorders.

We collected a dataset of voice recordings from individuals with and without laryngeal disorders including 434 people from two clinical centers in Tehran. The dataset was created using a powerful signal processing program and then based on the difference between male and female voice, the dataset was separated into two datasets. Finally, a Deep Neural Network was implemented for modelling using Python programming language and F1-score, Accuracy, Sensitivity, Specificity, and AUC as the model’s evaluation metrics were reported.

Among all the acoustic features, 23 features were selected for the male dataset and 25 features for the female data set. For the male dataset the final model achieved F1-Score of 0.915 and Accuracy of 0.910. For the female dataset the result was 0.884 of F1-Score and 0.896 of Accuracy.

Our results show that machine learning algorithms can accurately classify voice recordings into two groups: individuals with laryngeal disorders and those without. The high accuracy achieved by the algorithms suggests that voice can be used as an objective and automated diagnostic tool for laryngeal disorders. 

Hepatitis C virus (HCV) is a major public health threat, which can be treated if diagnosed early, but unfortunately, many people with chronic diseases are not diagnosed until the final stages. Machine learning and its techniques can be very helpful in diagnosis. This study examines the factors affecting hepatitis C diagnosis using machine learning.

A total of 27 features were used with a dataset containing 1385 records of patients with different grades of HCV. The dataset was clean and preprocessed to ensure accuracy and consistency. To reduce the dimension of the dataset and determine the effective features three feature selection, Pearson Correlation, ANOVA, and Random Forest, were applied. Among all the algorithms, KNN, random forests, and Deep Neural Networks were selected to be utilized, and then their evaluation metrics, such as Accuracy and Recall. To create prediction models, fifteen features were selected for the mentioned machine learning algorithms.

Performance evaluation of these models based on accuracy showed that Deep Learning with Accuracy = 92.067 had the highest performance. KNN and Random Forest had almost the same performance after Deep Learning. This performance was achieved on dataset containing features that were selected by ANOVA feature selection.

Machine learning has been very effective in solving many challenges in the field of health. This study showed that using data-mining algorithms also can be useful for HCV diagnosing. The proposed model in this study can help physicians diagnose the degree of HCV at an affordable and with high accuracy.

Managing resources is one of the most important challenges that healthcare providers worldwide face during the COVID-19 pandemic. In recent years, machine learning has been developed to provide valuable help in predicting disease and estimating the duration of their stay. This study aimed to identify the machine learning models for predicting length of stay in COVID-19.

Online databases, including Scopus, PubMed, Web of Science, and Science Direct, were searched, and a hand search through Google Scholar and grey literature was done up to August 2023 and updated in December 2023 to identify articles to find all relevant studies. To manage the process and check the quality of included articles PRISMA guidelines and CASP checklist were used and data was extracted using a data extraction form.

Among all 489 research articles, 10 studies met the inclusion criteria. The best models reported in the included articles were random forest (n=3), gradient boosting (n=2), XGBoost (n=2), SVM (n=1), KNN (n=1), and DataRobot (n=1). Except one of the studies that used quantitative modeling and reported MSE and MAE as evaluation criteria, other studies used qualitative modeling and reported accuracy, specificity, and F1-score. The focus of the included articles was on the general and ICU departments as the important resources in the hospital and emphasized the use of machine learning to predict the length of stay.

The results of this systematic review showed that a data mining approach and using a machine learning algorithm can help to manage the critical resources of the hospital especially when we are faced with a pandemic disease like COVID-19.

Jaundice is one of the most common problems in the neonatal period, affecting about 60% of full-term and 80% of premature infants in their first week of life. The present study aimed to develop a system for predicting neonatal jaundice within the first 24 to 72 hours post-delivery by using the Support Vector Machine (SVM) algorithm.

This applied-developmental study employed a quantitative method. First, based on a literature review, a questionnaire containing effective factors for predicting jaundice in newborns was designed. Data analysis was performed using descriptive statistics, and factors that were recognized as necessary by at least 50% of the experts were included in the model. Then, data from 1178 newborns delivered at Lolagar hospital in Tehran were extracted from birth records, and several machine learning algorithms were used to predict neonatal jaundice.

The findings of this research showed that the proposed model based on the SVM algorithm is the best output due to the distance between classes. Therefore, the final model of the SVM algorithm was created using the Gaussian kernel, with a sigma value of 1.2360605. Thirty percent of the samples (354 cases) were tested, and 321 cases were correctly predicted. In the proposed SVM model, parameters such as precision, the area under the Receiver Operating Characteristic (ROC), and F1 score were 92.7%, 93%, and 88% respectively.

Incorporating SVM into a system for predicting jaundice in newborns can aid doctors with timely prediction of jaundice in newborns and provide the possibility of taking preventive measures and preventing possible risks caused by jaundice in newborns.

Diabetes is a disease associated with high levels of glucose in the blood. Diabetesmake many kinds of complications, which also leads to a high rate of repeated admission of patients with diabetes. The aim of this study is to diagnose Diabetes with machine learning techniques.

The datasets of the article contain several medical predictor variables and one target variable,Outcome. Predictor variables includes the number of pregnancies the patient has had, their BMI, insulin level, age. The main objective of the machine learning models is to classify of the diabetes disease.

Six classifiers have been also adapted and compared their performance based on accuracy, F1-score, recall, precision and AUC. And Finally, Adaboost has the most accuracy 83%.

In this paper a performance comparison of different classifier models for classifying diagnosis is done. The models considered for comparison are logistic regression, Decision Tree, support vector machine (SVM), xgboost, Random Forest and Adaboost. Finally, in the comparison flow, Adaboost, Logistic Regression, SVMand Random Forest, usually has had a high amount; and their amounts has little differences normally.

Nowadays, it can be seen that changes have taken place in the process of diseases and their clinical parameters. Accordingly, in some cases, general medical science and the use of clinical statistics based on the experiences of the physicians are not enough for the provision of sufficient tools for an early and accurate diagnosis. Therefore, medical science increasingly seeks to use unconventional methods and machine learning techniques. The issue of diagnosis in the medical world and the error rate of physicians in this regard are among the main challenges of the condition of patients and diseases. For this reason, in recent years, artificial intelligence tools have been used to help physicians. However, one of the main problems is that the effectiveness of machine learning tools is not studied much. Due to the sensitivity and high prevalence of diseases, especially gastrointestinal cancer, there is a need for a systematic review to identify methods of machine learning and artificial intelligence and compare their impact on the diagnosis of lower gastrointestinal cancers.

This systematic review aimed to identify the machine learning methods used for the diagnosis of lower gastrointestinal cancers. Moreover, it aimed to classify the presented methods and compare their effectiveness and evaluation indicators.

This systematic review was conducted using six databases. The systematic literature review follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement for systematic reviews. The search strategy consisted of four expressions, namely “machine learning algorithm”, “lower gastrointestinal”, “cancer”, and “diagnosis and screening”, in that order. It should be mentioned that studies based on treatment were excluded from this review. Similarly, studies that presented guidelines, protocols, and instructions were excluded since they only require the focus of clinicians and do not provide progression along an active chain of reasoning. Finally, studies were excluded if they had not undergone a peer-review process. The following aspects were extracted from each article: authors, year, country, machine learning model and algorithm, sample size, the type of data, and the results of the model. The selected studies were classified based on three criteria: 1) machine learning model, 2) cancer type, and 3) effect of machine learning on cancer diagnosis.

In total, 44 studies were included in this systematic literature review. The earliest article was published in 2010, and the most recent was from 2019. Among the studies reviewed in this systematic review, one study was performed on the rectum (rectal cancer), one was about the small bowel (small bowel cancer), and 42 studies were on the colon (colon cancer, colorectal cancer, and colonic polyps). In total, 19 out of the 44 (43%) articles from the systematic literature review presented a deep learning model, and 25 (57%) articles used classic machine learning. The models worked mostly on image and all of them were supervised learning models. All studies with deep learning models used Convolutional Neural Network and were published between 2016 and 2019. The studies with classic machine learning models used diverse methods, mostly Support Vector Machine, K-Nearest Neighbors, and Artificial Neural Network.

Machine learning methods are suitable tools in the field of cancer diagnosis, especially in cases related to the lower gastrointestinal tract. These methods can not only increase the accuracy of diagnosis and help the doctor to make the right decision, but also help in the early diagnosis of cancer and reduce treatment costs. The methods presented so far have focused more on image data and more than anything else have helped to increase the accuracy of physicians in making the correct diagnosis. Achievement of the right method for early diagnosis requires more accurate data sets and analyses.

Studying trends in observed rates provides valuable information in terms of need assessment, planning of programs and development indicators of each country. The purpose of the present study was to apply the regression model and the Fourier series in terms of predicting the trends in growth and mortality rate of coronavirus disease.

In this study, two linear analysis methods were used to predict the incidence and mortality rate of coronavirus disease in Iran and China. The methods used are linear regression and Fourier transform. The data used were collected by referring to the official media of the mentioned countries, the general form of which is a time series of the incidence and mortality rate in recent days and the model implemented to estimate the incidence and mortality rate for the coming days. Python programming language version 3.7 is used to implement models.

The results of this study show that the rates of coronavirus disease incidence and mortality are still increasing. Meanwhile, the Fourier transform-based analytical method is more accurate than the linear regression method and on the other hand, the accuracy of both algorithms for predicting mortality wasmuch higher than the prediction rate. This indicates that the mortality rate is higher than that of its linearity over time. The other point is that based on the results of this study, however, linear methods are very suitable for future prediction, due to the nature of epidemic diseases whose growth chart is nonlinear, linear methods cannot be used to predict the rate and mortality used in distant times.

The accuracy of the mathematics-based methods for predicting the trajectory of COVID-19 was really high. We predicted that the epidemics of COVID-19will be high during 10 days. If the data are reliable and there are no second transmissions, we can accurately predict the transmission dynamics of the COVID-19across the cities in China and Iran. The mathematics-inspired methods are a powerful tool for helping public health planning and policymaking.

The evolving mobile networks are envisioned to have a flexible and reliable network to meet all design requirements needed for the fifth generation (5G) of networks. The cloud radio access network, as an evolution in mobile networks, changes the traditional architecture of the network by moving the BBUs to the central office. This comes with new challenges that are addressed by new technologies like Radio over Fiber and now Radio over Ethernet, which proposes a technique to transmit all radio data types over a traditional Ethernet based front-haul network. In this paper, we focus on the architecture and the design considerations of Radio-over-Ethernet to have a more flexible and reliable front-haul network in Centralized Radio Access Network.

In this paper we tried to use Ethernet protocol as a universal and public network protocol in radio based networks to make it flexible and reliable. This combination allows us to focus only on the access points and propose a new architecture to encapsulation (retrieve) radio data into (from) an Ethernet frame.

This study resulted in a new architecture for radio access networks to disseminate radio data over a reliable network protocol and infrastructure. Some Ethernet header fields was modified and a mapper was included into the model in BBUs to create an adaption between radio and Ethernet infrastructures.

The result shows that although this new architecture may apply additional overhead in both information and process, but having an independent front-haul network is a necessity for Centralized Radio Access Network. However if industry implements this architecture and its processes regarding latency requirement, Radio over Ethernet will be a revolution in Centralized Radio Access Network to meet two main key design principles in 5G.

in the past, traffic safety was addressed by traffic awareness and passive safety measures like solid chassis, seat belts, air bags and etc. Thanks to the ongoing progresses in the concept of vehicular ad hoc networks (VANET), propitious conditions for finding efficient solutions for traffic safety are meeting. Safety messaging is the most important aspect of VANETs where the passive safety (accident readiness) in vehicles was reinforced with the idea of active safety (accident prevention). In safety messaging vehicles message each other over wireless media and update each other on traffic conditions and hazards. Owing to the importance of the QOS in safety messaging, many researchers have focused on this topic. Earlier related works have scrutinized the aspect of increasing the service rate by changing the properties and parameters of scheduler algorithms but this paper with a new look at the issue of quality of service tries to increase the performance of VANET by removing the useless or unused packets.