Browse Items (2150 total)
Sort by:
-
An Intelligent Business Automation with Conversational Web Based Build Operate Transfer (BOT)
The field of AI chatbots with voice help capabilities has seen significant advancements recently because to the usage of NLP (Natural Language Processing), NLG (Natural Language Generation), and (DNN) Deep Neural Networks. Using the expanding skills of chatbots, which are assisted by AI and ML technologies, a variety of business challenges may be handled. Profitability is one of the most crucial features of a business. This is only achievable if top-level management is aware of the company's costs, revenues, and human resource performance. In this case, an AI-powered chatbot with voice help may be utilised to evaluate corporate data and provide a report. The Bot knows the meaning of words and responds to them thanks to the wordnet in the corpus. Corpus is basically a dictionary for ChatBot. Top management may ask the Bot anything, and the Bot will quickly undertake exploratory data analysis and create a report. The Bot first understands the data using feature selection and then performs exploratory data analysis. After the EDA technique, Bot activates the voice recognition mode to understand the question and give answers. The Bot can use a male or female voice (depending on the developer). Then BOT provides a data table and visualisations for better understanding. 2020 Copyright for this paper by its authors. -
An Intelligent Stock Market Automation with Conversational Web Based Build Operate Transfer (BOT)
Zerodha, Upstox, Angel Broking, Groww, etc. Such companies have the most significant users of traders/investors in the equity share market. Their trust is based on their ease of use, less time-consuming process, and accurate graphs and charts of real-Time data. But what if such companies had an algorithm that could predict the future prices of any share? Not just based on historical data but also on sentimental data? This project aims to build a speech recognition chatbot like Alexa Google, which will use Recurring Neural Network-Long Short-Term Memory (RNNLSTM) and Natural Language Processing (NLP) to predict future intra-day prices. 2022 IEEE. -
Optimal Disassembly Sequence Generation Using Tool Information Matrix
Just as the assembly sequence plays an important role in the early part of the product, the disassembly sequence plays an important part in the final stage of the product. The disassembly sequence determines how efficiently the product can be recycled or it can be disassembled for maintenance purposes. In this study, the disassembly sequence is generated using the Tool Information Matrix (TIM) and the contact relations. In this study the feasible sequences are generated using the TIM and contact relations, afterward, the time required is considered as a fitness equation for generating the optimal disassembly sequence. The proposed methodology is applied to 10-part crankshaft assembly to test the performance in generating the optimal disassembly sequences. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Dimensionality reduction based on the classifier models: Performance Issues in the prediction of Lung cancer
Dimensionality reduction is an essential feature to reduce the complexity of the computations in the large data set environment. When handling large quantum of medical data set, as in the case like, Lung cancer prediction, based on symptoms and Risk factors, number of attributes/ dimensions pose a major challenge. Here in this study an attempt is made to compare the performance of the attribute selection models prior and after applying the classifier models. A total of 16 classifier models are chosen, which are based on statistical, rule based, logic based and artificial Neural network approaches. Feature set selection and ranking of attributes are done based on individual models. Confusion matrix of the models before and after dimensionality reduction is computed. Based on the confusion matrix result the models are compared and based on the performance optimal model is chosen. It is found that Multi-layer perceptron based artificial neural network model gives better performance compared to other approaches. 2012 IEEE. -
Rubitics: The Smarter GCMS for Mars
A GCMS stands for a Gas Chromatograph and Mass Spectrometer. These two instruments are used to identify compounds from both soil and atmospheric samples. The GCMS usually has a mass of around 40 kilograms and is the size of a microwave oven, but what if we could downsize it? Downsizing the GCMS means that the number of equipment and instruments that can be used and carried by a rover can drastically increase. Rubitics is essentially a GCMS, only smaller and more efficient. This paper discusses the way Rubitics functions and how a GCMS can be remodeled and used to its fullest potential. The column of the Gas Chromatograph is replaced with composite materials to increase the flexibility of the tube, thereby increasing the number of columns along with finger-like projections on the interiors, which will aid in a much more precise separation of compounds. The inert carrier gas container is changed with a more durable, strong composite that will be instrumental in reducing the mass of the cylinder, and a safer chemically unreactive material will ensure complete pure storage. Rubitics will also contain a cooling system so as to be more power-efficient and aid in obtaining precise results. The material of the oven used in the gas chromatograph will be of much more insulating capacity (thermal resistance), lighter in mass, and smaller in size. Rubitics maintains the optimum shape to provide the most temperature and energy-efficient GCMS ever. Rubitics houses a compact electronic bay with sensors and a microprocessor for analysing the different components. The detectors' values are processed in the onboard microprocessor with the help of TinyML. This light algorithm can help in reducing the bandwidth consumed in transmitting unnecessary data to the ground station through providing in-situ data filtration. The paper also contemplates using such an algorithm to improve the efficiency of GCMS. In conclusion, Rubitics will be the future of GCMS technologies and sample analysis on different planetary terrains. Due to its re-engineered structure, it occupies lesser weight, size, and space. Rubitics thereby changes the number and quality of experiments that can be performed on Mars, leading to better insights for successful future habitation. Copyright 2022 by Ms. Harshini K Balaji. Published by the IAF, with permission and released to the IAF to publish in all forms. -
Artificial Intelligence for Enhanced Anti-Money Laundering and Asset Recovery: A New Frontier in Financial Crime Prevention
The incorporation of artificial intelligence (AI) into asset recovery and anti-money laundering (AML) procedures signifies a revolutionary change in the handling of financial crime. This article investigates the use of AI techniques to improve AML compliance, detect suspicious activity, and improve transaction monitoring. Financial institutions can now analyze massive volumes of transaction data in real-time, find anomalies, and lower false positives thanks to AI-based solutions, which include machine learning algorithms and predictive modeling. The research also outlines the difficulties and advantages of implementing AI, such as enhancing the effectiveness and caliber of suspicious activity reports (SARs) while resolving security and privacy issues with data. The study makes the case that AI's capacity to offer collaborative analytics and dynamic risk assessments is essential for the development of AML frameworks and the overall effectiveness of financial crime prevention. 2024 IEEE. -
A Stacked BiLSTM based Approach for Bus Passenger Demand Forecasting using Smart Card Data
Demand forecasting is crucial in the business sector. Despite the inherent uncertainty of the future, it is essential for any firm to be able to accurately predict the market for both short- and long-term planning in order to place itself in a profitable position. The proposed approach focus on the passenger transport sector because it is particularly vulnerable to fluctuations in consumer demand for perishable commodities. At every stage of the planning process from initial network designs to final pricing of inventory for each vehicle in a route-an accurate prediction of demand is essential. Forecasting passenger demand is crucial since passenger transportation is responsible for a substantial chunk of global commerce. The suggested method relies on three distinct techniques: data preparation, feature selection, and model training. Data modification, cleansing, and reduction are the three sub-processes that make up preprocessing. When it comes to feature selection, partition-based clustering algorithms like k-means are the norm. Let's go on to training the models with stacked BiLSTM. The proposed method is demonstrably superior to both LSTM and BiLSTM, the two most common competing approaches. The proposed method had a success rate of 98.45 percent. 2023 IEEE. -
Analysis of Unintelligible Speech for MLLR and MAP-Based Speaker Adaptation
Speech Recognition is the process of translating human voice into textual form, which in turn drives many applications including HCI (Human Computer Interaction). A recognizer uses the acoustic model to define rules for mapping sound signals to phonemes. This article brings out a combined method of applying Maximum Likelihood Linear Regression (MLLR) and Maximum A Posteriori (MAP) techniques to the acoustic model of a generic speech recognizer, so that it can accept data of people with speech impairments and transcribe the same. In the first phase, MLLR technique was applied to alter the acoustic model of a generic speech recognizer, with the feature vectors generated from the training data set. In the second phase, parameters of the updated model were used as informative priors to MAP adaptation. This combined algorithm produced better results than a Speaker Independent (SI) recognizer and was less effortful for training compared to a Speaker Dependent (SD) recognizer. Testing of the system was conducted with the UA-Speech Database and the combined algorithm produced improvements in recognition accuracy from 43% to 90% for medium to highly impaired speakers revealing its applicability for speakers with higher degrees of speech disorders. 2021, Springer Nature Singapore Pte Ltd. -
Waveform Analysis and Feature Extraction from Speech Data of Dysarthric Persons
Speech recognition systems provide a natural way of interacting with computers and serve as an alternative to the more popular but less intuitive peripherals (input / output devices). Tools employing the techniques of Automatic Speech Recognition (ASR) can be extended to serve people with speech disabilities so that they can overcome the difficulties faced in their interaction with general public. An attempt is made here to achieve this goal by mapping the distorted speech signals of people with severe levels of dysarthria to that of a normal speech and/or less severe dysarthric speech. The analysis is carried out by comparing the speech waveforms of the people with and without communication disorders and then extracting the features from the audio files. The differences in time, duration, frequency and PSD are used to facilitate the mapping of unintelligible speech data to intelligible ones. When reasonable accuracy levels are achieved in this mapping, the normal voice can be used as the substitute / surrogate of the original distorted voice. 2019 IEEE. -
Speech disabilities in adults and the suitable speech recognition software tools - A review
Speech impairment, though not a major obstacle, is still a problem for people who suffer from it, while they are making public presentations. This paper describes the different speech disabilities in adults and reviews the available software and other computer based tools that facilitate better communication for people with speech impairment. The motivation for this writing has been the fact that stuttering, one of the types of speech disability has affected about 1 percentage of the people worldwide. This fact was provided by the Stuttering Foundation of America, a Non-profit Organization, functioning since 1947. A solution to stuttering is expected to benefit a considerable population. Speech recognition software tools help people with disabilities use their computers and other hand held devices to satisfy their day-to-day needs which otherwise, require dedicated domestic help and also question the person's ability to be independent. ASR (Automatic Speech Recognition) systems are popular among the common people and people with motor disabilities, while using these techniques for the treatment of speech correction is a current research field and is of interest to SLPs/SLTs (Speech Language Pathologist / Speech Language Therapist). On-going research also includes development of ASR based software to facilitate comfortable oral communication with people suffering from speech dysfunctions, i.e., in the domain of AAC (Augmentative and Alternative Communication). 2015 IEEE. -
An IoT-Based System for Fault Detection and Diagnosis in Solar PV Panels
This abstract describes an IoT-based system for fault detection and diagnosis in solar PV panels. The proposed Fuzzy logic-based fault detection algorithms aims to improve the performance and reliability of solar PV panels, which can be affected by various faults such as shading, soiling, degradation, and electrical faults. The system includes wireless sensor nodes that are deployed on the panels to collect data on their electrical parameters and environmental conditions, such as temperature, irradiance, and humidity. The collected data is then transmitted to a central server for processing and analysis using machine learning algorithms. The system can detect and diagnose faults in real-time, and provide alerts and recommendations to maintenance personnel to take appropriate actions to prevent further damage or downtime. The system has several advantages over traditional manual inspection and maintenance methods, including reduced downtime, lower maintenance costs, and improved energy efficiency. The proposed system has been validated through experimental tests, and the results show that it can accurately detect and diagnose faults in solar PV panels with high reliability and efficiency. 2023 EDP Sciences. All rights reserved. -
Approximate Binary Stacking Counters for Error Tolerant Computing Multipliers
To increase the power and efficiency of VLSI circuits, a new, creative multiplying methodology is required. Multiplication is a crucial arithmetic operation for many of these applications. As a result, the newly proposed error-tolerant computing multiplier is a crucial component in the design of approximate multipliers that are both power and gate efficient. We have created approximative multipliers for several operand lengths using this suggested method and a 45-nm library. Depending on their probability, the approximation for the accumulation of changing partial products varies. In compared to approximate multipliers that were previously given, the proposed circuit produces better results. When column-wise generate elements are added to the modified partial product matrix using an OR gate, the output is usually accurate. The amount of energy used, and its silicon area have been considerably reduced in the suggested multiplier when compared to traditional multipliers by 41.92% and 18.47%, respectively. One of the platforms that these suggested multipliers are suitable for is the image processing application. 2024 IEEE. -
VLSI Implementation of Area-Error Optimized Compressor-Based Modified Wallace Tree Multiplier
Approximate multiplier designs can improve their energy efficiency and performance with only a slight loss in accuracy by using approximate arithmetic circuits. This method is appropriate for applications where an approximative answer is acceptable because it uses a range of calculation approaches to those priorities, returning a potentially erroneous result above one that is assured to be exact. The basic idea underlying approximate computing is that, while accurate calculation may require a lot of resources, bounded approximation can result in considerable speed and energy efficiency advantages without sacrificing accuracy. The approximate 4:2 compressor and exact compressors, as well as half adders and full adders, make up the proposed approximate multiplier. The steps of the multiplier architecture are optimised using the recently suggested modified Wallace Tree Multiplier Architecture. When compared to previous designs, the proposed multiplier architecture can generate outcomes with the least amount of inaccuracy. The multiplier architecture is also finished in just two steps. The Modified Wallace Tree Architecture used in the suggested approximate multiplier excels by providing an error rate of 71.80% and a mean error of 173.82. As a result, the mean ? error Product improved by 10%, the error rate improved by 23.3%, and the mean error increased by 31.04%. This is accomplished by the proposed approximate multiplier with a small increase of 22.36% in total power consumption. 2023 IEEE. -
Secured Cloud Computing for Medical Database Monitoring Using Machine Learning Techniques
A growing number of people are calling on the health-care industry to adopt new technologies that are becoming accessible on the market in order to improve the overall quality of their services. Telecommunications systems are integrated with computers, connectivity, mobility, data storage, and information analytics to make a complete information infrastructure system. It is the order of the day to use technology that is based on the Internet of Things (IoT). Given the limited availability of human resources and infrastructure, it is becoming more vital to monitor chronic patients on an ongoing basis as their diseases deteriorate and become more severe. A cloud-based architecture that is capable of dealing with all of the issues stated above may be able to provide effective solutions for the health-care industry. With the purpose of building software that would mix cloud computing and mobile technologies for health-care monitoring systems, we have assigned ourselves the task of designing software. Using a method devised by Higuchi, it is possible to extract stable fractal values from electrocardiogram (ECG) data, something that has never been attempted previously by any other researcher working on the development of a computer-aided diagnosis system for arrhythmia. As a result of the results, it is feasible to infer that the support vector machine has attained the best classification accuracy attainable for fractal features. When compared to the other two classifiers, the feed forward neural network model and the feedback neural network model, the support vector machine excels them both. Furthermore, it should be noted that the sensitivity of both the feed forward neural network and the support vector machine yields results that are equivalent in quality (92.08% and 90.36%, respectively). 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Transforming towards 6G: Critical Review of Key Performance Indicators
With the experiences acquired upon the successful implementation of 5G networks academia, researchers, and industry are envisioning the need for 6G networks. The vision of the 6G communication network is supposed to completely assist the creation of a Ubiquitous Intelligent Mobile Society. Already 5G technologies are in place and still few extended features of 5G are continuously being introduced. Even though the 6G communication network is expected to have greater capabilities than the existing 5G, there are no clear specifications on how far these capabilities shall be capitalized in 6G. The 6G technologies shall move past ordinary mobile internet services and advance to support ubiquitous Artificial Intelligent (AI) services from the network's core to end-to-end service devices/applications. The architecture, protocols, and operations which are the primary constituents of the 6G network shall implement AI technologies for self-optimization and actualization. This article brings an all-inclusive deliberation of 6G based on an assessment of preceding generations' evolving technology developments. 2022 IEEE. -
Resource Aware Weighted Least Connection Load Balancing Technique in Cloud Computing
Cloud computing became a pivotal for the most of the real time applications. In cloud computing, the customer demands the services with the best performance even when the application is expanding rapidly. Therefore, it is essential to manage the resources effectively because the number of users and services growing proportionately. The main aim of the load balancing technique is to allocate the customers' requests with the large pool of resources efficiently. The problem is how to evenly distribute the load of requests among the compute nodes according to their capacity. Therefore, there is a need for an effective load balancing technique for smooth continuity of operations in a distributed environment with a heterogeneous server configuration. This paper presents a novel load balancing technique, namely, Resource aware weighted least connection load balancing which addresses the above said problem efficiently. The essence of this work is to assign the requests across multiple servers based on the requested resource and the status of the number of connections presently served by each server. This work used standard score technique to enumerate the weight of each node. Experiments were conducted using Cloud Analyst, a famous cloud simulator breed from CloudSim. Appropriate performance parameters were analysed to measure the effectiveness of the proposed technique. Future directions for the extension of the implemented technique also identified. 2023 IEEE. -
A structured approach to implementing Robotic Process Automation in HR
Technological innovations are changing the industrial landscape. As technology transforms the world, the HR function needs to focus on embracing automation and other technologies that promise efficiency, service effectiveness and cost savings. Deployment of robotic process automation (RPA) can help (a) to offer better service to employees and managers (b) ensure compliance of HR processes with standards and regulations (c) facilitate rapid initiation and completion of HR processes (d) enhance efficiencies by digitizing data and auditing process data (e) improve HR productivity and cost savings by automating manual and repetitive tasks. A robust and structured approach needs to be in place to identify HR processes that can be automated using the RPA approach. In this paper the authors (a) suggest a four step approach - validation, assessment, evaluation and classification - to analyze processes and verify their suitability for automation using RPA (b) identify HR processes that has relevance for the RPA approach within the broad areas of HR Strategy, Talent Acquisition, Talent Development & Performance Management, Compensation & Benefits, HR Operations and Employee Relations (c) recommend a process for mapping HR RPA propensity. A case study is also presented for greater clarity on adoption of RPA in HR processes. Published under licence by IOP Publishing Ltd. -
A Review on Utilization of Construction and Demolition Waste (CDW) Toward Green and Circular Economy
Globally, policy makers have realized the significance of infrastructure development with respect to safety and environment-friendly approach. This has resulted in reuse and recycling initiatives in various industries including construction and building sector. Further, it is imperative to understand new techniques and methods to improve the effectiveness of recycling, keeping environment and carbon emissions in check. Recently, utilization of construction and demolition waste (CDW) as precursors in synthesizing alkali-activated and geopolymer binders have caught attention of researchers as green building material. This review paper discusses the findings of the latest research and promotes the use of CDW as a potential starting or precursor material in alkali-activated or geopolymer concrete toward green and circular economy. If processed appropriately, CDW can be used to produce environment-friendly binders that can reduce our dependence on conventional binders like Portland cement, thus promoting recycling in sustainable and eco-friendly manner. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Comparison of Affine and DCGAN-based Data Augmentation Techniques for Chest X-Ray Classification
Data augmentation, also called implicit regularization, is one of the popular strategies to improve the generalization capability of deep neural networks. It is crucial in situations where there is a scarcity of high-quality ground-truth data. Also getting new samples is expensive and time consuming. This is a typical issue in the medical domain. Therefore, this study compares the performance of Affine and Generative Adversarial Networks (GAN)- based data augmentation techniques on the chest image X-Ray dataset. The Pneumonia dataset contains 5863 chest X-Ray images. The traditional Affine data augmentation technique is applied as a pre-processing technique to various deep learning-based CNN models like VGG16, Inception V3, InceptionResNetV2, DenseNet-169 and DenseNet-202 to compare their performance. On the other hand, DCGAN architecture is applied to the dataset for augmentation. Evaluation measures like accuracy, recall and AUC depict that DCGAN outperforms other traditional models. The most important advantage of DCGAN is that it is able to identify fake images with 100% accuracy. This is especially relevant for the medical domain as it deals with the life of individuals. Thus, it can be concluded that DCGAN has better performance as compared to affine transformations applied to traditional CNN models. 2023 The Authors. Published by Elsevier B.V. -
Food Detection and Recognition Using Deep Learning - A Review
Studies show poor lifestyle choices and unhealthy eating patterns cause issues like obesity and other ongoing illnesses that raise the risk of heart attacks, such as hypertension, abnormal blood sugar levels, and diabetes. To improve this situation a lot of health apps have been built which use modern dietary monitoring systems that automatically evaluate dietary intake using machine learning and deep learning techniques rather. For these reasons indepth investigations on food detection, classification, and analysis have been conducted. Some of the top methods for automatic food recognition created have been discussed in this paper. We also propose an idea for detection of Indian food items using image classification. According to our findings of the papers we reviewed, convolutional neural networks (CNN) have been extensively been used in food detection as it has been giving better results compared to other models. We also observed that Vision transformers perform better in situations where the dataset is large and a hybrid model would give better accuracy. A review of potential applications for food image analysis, shortfalls in the area, and open issues concludes the paper. 2022 IEEE.