Search

Birth weight is considered a major factor when monitoring any signs of abnormalities in the growth of the fetus and taking timely decisions related to labor management. Existing methods involve specialized equipment and training, which makes them less feasible for underdeveloped areas. Therefore, this study proposed a system for prediction of childbirth weight through kernel extreme reservoir machines and optimized the model parameters by the use of particle swarm optimization. Experimental results showed a significant improvement in the recommended method over existing models. The proposed approach is more economical than the traditional ultrasound making it extremely suited to underprivileged communities.

Hypertension is an epidemic restricted not only to the developing but also to the developed nations. It is triggered by various lifestyle choices that depend on each individual based on their personal physiology and lifestyle. Early diagnosis is possible, but it requires continuous blood pressure monitoring. Various machine learning methods have been proposed for early diagnosis of hypertension by predicting blood pressure and detecting high spikes in the values. However, these solutions are built upon the generic guidelines which may not be applicable for every patient. Most of these solutions incorporate batch learning and require all data to be present before prediction and do not support any online learning mechanism. This leads to potentially outdated models. Furthermore, there is also a lack of an intelligent approach to handling incomplete time series while training the model. This paper presents a personalized approach to estimate blood pressure that eliminates the need for continuous monitoring based on the Online recurrent extreme learning machine (OR-ELM). The missing values are imputed using Gaussian mixture models. The prediction model learns from the historical data and learns online as more data becomes available. The proposed scheme is developed and deployed on a mobile application for secured prediction results. The method is used to predict blood pressure in Malaysian population and compared with existing batch-learning and online learning methods. The results show that OR-ELM based model outperforms the existing online techniques such as the Online sequential extreme learning machine and batch learning technique such as Extreme learning machine.

Hypertension is becoming a global epidemic for the developing world and continuous blood pressure monitoring and early diagnosis is vital for the prevention of this disease. However, in real life, patients are usually unable to maintain frequent monitoring because of reasons that include forgetfulness, human error and/or machine error. This paper presents a personalized prediction model for blood pressure using Recurrent Kernel Extreme Reservoir Machine (RKERM). This technique combines reservoir computing with RKELM to perform multistep ahead prediction. We use RKERM for blood pressure prediction and its performance is evaluated with other ELM based prediction algorithms. To evaluate our model, we use real world blood pressure data collected from Malaysian population consisting of hypertensive and non-hypertensive patients. The experimental results show that the proposed prediction mechanism has higher prediction accuracy than existing ELM methods.

The major problem on the road to artificial intelligence is the development of lifelong learning systems. They have the ability to learn new concepts incrementally overtime. They are also able to allocate required resources dynamically without human intervention and are able to store data securely. In this work we have extended the incremental classifier and representation learning method known as iCaRL to meet this criterion. The proposed solution is able to learn strong classifiers and a data representation simultaneously. It is able to allocate an optimal scaling plan to meet its resource requirements without human intervention. It securely stores propriety image data by using state of the art interplanetary file system and block chain technology. Finally, it is able to focus on object of interests in an image using attention network. We have shown by experiments on CIFAR-100 and Image net 2012 that it performs better in terms of accuracy than the existing iCaRL system while satisfying criteria of lifelong learning.

Staying updated about global events is a necessity for the modern day man. Many sources for latest news are available on the web, and individuals can make use of their favorite news source to get the daily news, but most of the time they are unable to get the news of desired interest. There is a need to analyze the news and rank them according to user’s interest. Social media can provide an insight on a user’s likes and dislikes, which used for news recommendation. This paper presents a multi-agent framework [1] that uses a novel methodology for ranking news articles on the basis of user’s interests fetched from social media [2]. To do so, we have modeled the relationship between user’s social media preferences and news categories: we have extracted categories from social media, mapped with general news categories. Our developed solution provides 28% better results than current news websites recommendation. Further experimentations show that our solution provides effective news recommendation as it makes use of the user’s social media profile [3], which always updated and maintained by the user firsthand. Another important objective is to increase positivity in one’s life. These days the world is in turmoil due to terrorism activities [4].These activities naturally attract media coverage, presenting an unpleasant view of various regions of the world. Although there are many good things/activities happening around us, we mostly see violence and hate speech everywhere on the web [5]. Sentiment analysis is a technique used to extract the impact of the statement i.e. weather the statement is positive or negative [6], [7], and [8]. Sentiment analysis used to filter news based on harmful negative activities and displaying positive news of latest inventions in world, advancement in the industry, relief packages from governments and other growth opportunities. Based on these ideas, we have developed an android application and performed a pilot study. Our results show higher satisfaction levels for users when searching news articles through the proposed system.

This paper highlights the design of an embedded telemedicine system and web server for remote health monitoring of patients. It enlightens the technique to remotely monitor patient data. We proposed a real time telemedicine system utilizing GSM/GPRS protocol for the third world countries with the help of which, the patients can be monitored from any part of the world by the doctor via the internet. This system utilizes a set of software simulators and a DAC as a solution to low cost testing. We have used Lab View software as the software simulator for generating the ECG signal and NI equipment's to get a real time analog output. That signal is fed to a GSM modem to transmit data over the internet.