P. Mahalakshmi

Bio: P. Mahalakshmi is an academic researcher from VIT University. The author has contributed to research in topics: Fault (power engineering) & Fault detection and isolation. The author has an hindex of 3, co-authored 6 publications receiving 28 citations.

Smart bin: An intelligent waste alert and prediction system using machine learning approach

Abstract: This work is about creating a smart waste-bin that alerts the authorities to gather the waste which has been piling up in the bins. It guides the garbage-trucks to collect the garbage only from those areas where the bin is critically filled. The ‘machine-learning’ concept has been used to gather information about the waste generation habits in that region and hence predict the amount of waste that will be generated in the near future. Apart from that, the analysis of the continuous data is also done that has been sent over the cloud in the form of graphs. The email alert and the text message have also been sent automatically to the concerned authorities once the level of waste in the dustbin crosses the threshold as set by the authorities. This would save time and money of the authorities considerably. This would also reduce air pollution in the area and prevent spreading of diseases caused by unpicked waste.

Wi-Fi-Based Low-Cost Monitoring of ECG and Temperature Parameters Using Arduino and ThingSpeak

Abstract: Health monitoring is one of the most important parameters to diagnose a patient, and it can be done in many ways. Temperature monitoring and pulse rate of a patient is one of the ways. Temperature sensor and pulse rate sensor have been used to get the physiological data from a patient’s body. These data can be used to monitor the health of the patient. The acquired data is then sent to a website server from which the doctors can check the patient’s vital signs anytime. Therefore, low-cost monitoring can be used in remote areas where people are not able to afford the healthcare. Future improvement can be done by sending an email containing the status of the health parameters to the doctor in case of emergency.

Digital filtering in hearing aid system for the hearing impaired

Abstract: A great proportion of human population suffers from hearing loss. Hearing loss is a measure of shift in auditory system compared to that of a normal ear for detection of a pure tone. But with the availability of modern day technologies and the recent developments in signal processing area, sophisticated artificial hearing aid systems can be designed that relax the job of damaged auditory systems to a great extent and make much of the sound available to the hearing impaired. In this project, the simulation of the simple digital hearing aid was developed using MATLAB programming language. The implementation of this configurable digital hearing aid (DHA) system includes noise reduction filter, frequency-dependent amplification and amplitude compression. We tested our filters on a mock patient and successfully reduced white Gaussian noise, increased the gain for frequencies which were difficult to hear, and shaped the amplitude to prevent any of the frequencies from becoming too loud. Finally, future trends and expected innovations in the hearing aid industry are discussed.

Development of a System for Quantitative Assessment of Vocal Loading

Abstract: Great vocal well-being is a key worry to proficient voice clients such ad instructors and artists. Consequently, to improve the utilization of voice and appropriate recovery to reestablish vocal well-being is the need of the day. A framework has been created to give a way to quantitative vocal stacking appraisal for the avoidance of voice issues. The advancements in signal processing have helped us to achieve this goal. Time dose, cycle dose, energy dose, and distance dose are the vital voice dosage measures citied in writing. The initial two measurements are ascertained in the study. The parameters which determine these measurements are voicing time, fundamental frequency of speech, and intensity of speech. Silence/unvoiced/voiced classification of speech signal has been done. The fundamental frequency has been extracted by cepstrum analysis. Voice doses are calculated using the above parameters, and tests are done on male and female audio samples. In this study, MATLAB platform is used for speech signal recording as well as analysis.

Reduction of Fault Detection Time by Using Fast S-Transform (FST)

Abstract: The target of this paper is to diminish the computational time of separation handing-off of transmission line utilizing Fast S-transform (FST). Separate transferring may require a quicker and more accurate estimation of the phasor of the fault current and voltage signals, which are utilized to register clear hindrance for creating the stumbling signal in case when a fault occurs. Customary S-transform is reversible time–frequency unearthly limitation procedure that integrates the components of wavelet and brief time Fourier transformation. The working (handling) time of traditional S-transform is large and in this manner, not appropriate for applications like advanced assurance of transmission lines. FST decreases the computational weight by using down examining. So FST can unquestionably supplant the current DFT construct calculation for with respect to line computerized separate handing-off undertaking in expansive power transmission organizing.

An Internet of Things Based Smart Waste Management System Using LoRa and Tensorflow Deep Learning Model

Abstract: Traditional waste management system operates based on daily schedule which is highly inefficient and costly. The existing recycle bin has also proved its ineffectiveness in the public as people do not recycle their waste properly. With the development of Internet of Things (IoT) and Artificial Intelligence (AI), the traditional waste management system can be replaced with smart sensors embedded into the system to perform real time monitoring and allow for better waste management. The aim of this research is to develop a smart waste management system using LoRa communication protocol and TensorFlow based deep learning model. LoRa sends the sensor data and Tensorflow performs real time object detection and classification. The bin consists of several compartments to segregate the waste including metal, plastic, paper, and general waste compartment which are controlled by the servo motors. Object detection and waste classification is done in TensorFlow framework with pre-trained object detection model. This object detection model is trained with images of waste to generate a frozen inference graph used for object detection which is done through a camera connected to the Raspberry Pi 3 Model B+ as the main processing unit. Ultrasonic sensor is embedded into each waste compartment to monitor the filling level of the waste. GPS module is integrated to monitor the location and real time of the bin. LoRa communication protocol is used to transmit data about the location, real time and filling level of the bin. RFID module is embedded for the purpose of waste management personnel identification.

Smart garbage management system for a sustainable urban life: An IoT based application

Abstract: Proper waste management is one of the major problems for densely populated urban areas. It is getting difficult day by day to lead a healthy, sustainable living in urban areas because of environmental contamination. Due to the lack of proper waste management approach, problems like an overflow of waste occurs that badly harm our environment. Polluted surroundings result in the spread of various kinds of diseases in an epidemic form. For developed and developing countries, waste management is a challenge to long-term development. Proper management of waste is getting tougher because of increasing population, urbanization, and industrialization. In this modern era of technology, we need to apply technology-based solutions to handle large amounts of waste for overpopulated urban areas. We have reviewed several recent research articles related to the smart waste management system, and almost all of them have some major limitations as well as progress. To ensure environmental hygiene and sustainable urban life, we have presented a smart IoT based integrated system consists of an identification system, an automated lid system, a display system, and a communication system. Arduino Uno is used as a microcontroller to synchronize all of the four systems. Sensors are used for identification and measuring the garbage level. The system provides the facility of continuous monitoring of the status of waste inside the garbage bin and shows the percentage filled up on liquid crystal display (LCD). The communication system uses a global system for mobile communications (GSM) module that will inform the corresponding authority to collect the waste when the garbage bin is filled up. The proposed waste management system is much more efficient than any other conventional waste management system as it reduces the use of manpower, avoids spillover of waste, saves time, more economical, and most importantly it is a completely automated system.

Occupational voice is a work in progress: active risk management, habilitation and rehabilitation

Abstract: Purpose of review The current article reviews recent literature examining occupational voice use and occupational voice disorders (January 2018-July 2019). Recent findings Our understanding of the prevalence of voice disorders and work-related vocal use, vocal load and vocal ergonomics (environmental and person influences) across different occupations is continuing to build. There is encouraging evidence for the value of intervention programs for occupational voice users, particularly of late with performers, teachers and telemarketers. Education and prevention programs are emerging for other 'at risk' occupations. Summary Occupational health and workforce legislation does not adequately acknowledge and guide educational, preventive and intervention approaches to occupational voice disorders. Voice disorders are prevalent in certain occupations and there is an urgent need for research to support occupational voice health and safety risk measurement, prevention and intervention. Large population-based studies are required with a focus on the health and economic burden of occupational voice disorders.

Analysis of IoT-Enabled Solutions in Smart Waste Management

Abstract: Internet of Things (IoT) has attracted widespread applicability not only limited to smart cities and communities but also in water, waste management and so on. It strength lies in the high impacts it created in the daily life and the potential user's behavior. However, for it to be more effective and increase its adoption, it is require to be energy efficient, able to communicate and share information across extended coverage. Existing technology such as Low Power Wide Area Network (LPWAN) with Long Range (LoRa) has been promising. In the perspective of waste management, several different IoT-enable solutions have been proffered with each having its own strengths and weaknesses that requires improvements. Therefore, this paper performs a review of existing IoT-enabled solutions in smart cites' waste management to bring together the state-of-the-art. The objective is to gain insights into the strengths and weaknesses in order to bring improvements and innovations to manage waste effectively and efficiently as well as maintain a healthy environment in our cities. We performed reviews on 15 research articles in the literature and the results obtained shows that existing solutions were similar in the technologies used but have some drawbacks such as sensing accuracy hindered by various weather conditions, users prone to unauthorized access and short range capabilities. This thus, calls for further improvement and innovation.

Smart Dustbin-An Efficient Garbage Monetoring System

Abstract: In the recent decades, Urbanization has increased tremendously. At the same phase there is an increase in waste production. Waste management has been a crucial issue to be considered. This paper is a way to achieve this good cause. In this paper, smart bin is built on a microcontroller based platform Aurdino Uno board which is interfaced with GSM modem and Ultrasonic sensor. Ultrasonic sensor is placed at the top of the dustbin which will measure the stature of the dustbin. The threshold stature is set as 10cm. Aurdino will be programmed in such a way that when the dustbin is being filled, the remaining height from the threshold height will be displayed. Once the garbage reaches the threshold level ultrasonic sensor will trigger the GSM modem which will continuously alert the required authority until the garbage in the dustbin is squashed. Once the dustbin is squashed, people can reuse the dustbin. At regular intervals dustbin will be squashed. Once these smart bins are implemented on a large scale, by replacing our traditional bins present today, waste can be managed efficiently as it avoids unnecessary lumping of wastes on roadside .Foul smell from these rotten wastes that remain untreated for a long time, due to negligence of authorities and carelessness of public may lead to long term problems. Breeding of insects and mosquitoes can create nuisance around promoting unclean environment. This may even cause dreadful diseases.