Browse Items (11855 total)
Sort by:
-
Sign Language Recognizer Using HMMs
In our day to day lives, we come across especially abled people who perform their daily chores with the aid of motivation that they get from self-confidence. There are many with hearing impairment. Sign language is the most expressed and natural way for them to communicate. Some chains of restaurants have, in fact, recruited deaf servers providing them with employment opportunities. Therefore, automatic Sign language recognition has become the crux of vision research. This paper is based on a project that builds a system that can recognize words communicated using the American Sign Language (ASL). Having been provided with a preprocessed dataset of tracked hand and nose positions extracted from the video, the set of Hidden Markov Models are trained. Using a part of this dataset, identification of individual words from test sequences is done. It provides them with the ability to communicate better, opening up a lot of opportunities. 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Stock price prediction based on technical indicators with soft computing models
Stock market prediction is a very tough task in the finance world. Since stock prices are dynamic, noisy, non-scalable, non-linear, non-parametric and complicated. In recent years, soft computing techniques are used for developing stock prediction model. The main focus of this study is to develop and compare the efficiency of the three different soft computing techniques for predicting the intraday price of individual stocks. The proposed models are based on Time Delay Neural Network (TDNN), Radial Basis Function Neural Network (RBFNN) and Back Propagation Neural Network (BPNN). The predictive models are developed using technical indicators. Sixteen technical indicators were calculated from the historical price and used as inputs of the developed models. Historical prices from 01/01/2018 to 28/02/2018, where the time interval between samples is one minute, are utilized for developing models. The performance of the proposed models is evaluated by measuring some metrics. Also, this study compares the results with other existing models. The experimental result revealed that the BPNN outperforms TDNN, RBFNN as well as other existing models considered for comparison. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021. -
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. -
Classification of Vehicle Type on Indian Road Scene Based on Deep Learning
In Recent days an intelligent traffic system [ITS] is implemented on indian traffic sytem. Different applications are widely used to improvies the performance of the system. To improve the intelligence of the system deep learning can used to classify the vehicles into three different classes. The combination of Faster RCNN classifier and RPN can used to detect the objects and classify those objects into different classes. Analysis of the experimental results shows the improved accuracy and efficiency in classifying the vehicles on indian roads into different categories. 2021, Springer Nature Singapore Pte Ltd. -
Predicting the Stock Markets Using Neural Network with Auxiliary Input
Predicting the stock market has always been a challenging task and has always had a certain appeal for researchers all around the world. Stock markets are supposed to be quite random and people with experience in the market strongly agree to the fact. Thus, predicting the stock market accurately paves the way for endless money. To date, no such algorithm has been devised that could even predict the stock market with a 90% accuracy rate. The difficulty lies in the randomness of the markets, and the various complexities involved in modeling market dynamics. Nevertheless, there have been algorithms with a decent success rate and researchers around the world have been in a constant attempt to improve over them. Thus, through this paper we attempt at predicting the return of a stock over a period of 10days after a particular news was out regarding the stock using the headlines of the news and certain other features important in determining the direction of a stock. The model was implemented with a sigma score of 0.81. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
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. -
Defluoridation of Drinking WaterFluoride Wars
Fluorine is also known as two-edged sword. At lower doses, it influences tooth by inhibiting tooth caries, while in high doses, it causes dental and skeletal fluorosis. It is known that some quantity of fluoride is important for the formation of tooth enamel and mineralization in tissues. The present work aims at providing safe and potable water to rural areas where this element has created a menace. This work also suggests the use of few adsorbents such as paddy husk and coir pith which are affordable and removes fluorine to greater extent. The study concludes that materials which are used as adsorbents and can be safely inculcated as fluorine removal adsorbents which help people to have safe potable water. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Brief Review of Intelligent Rule Extraction Techniques
Rule extraction is a process of extracting rules which helps in building domain knowledge. Rules plays an important role in reconciling financial transactions. This paper presents a brief study of intelligent methods for rule extraction. The paper touches upon heuristic, regression, fuzzy-based, evolutionary, and dynamic adaptive techniques for rule extraction. This paper also presents the state-of-the-art techniques used in dealing with numerical and linguistic data for rule extraction. The objective of the paper is to provide directional guidance to researchers working on rule extraction. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Mechanical and tribological investigation on al lm4/tic composite fabricated through bottom pouring method
In the present investigation LM4 reinforced 6 wt% Titanium Carbide particles composite was developed by stir casting bottom pouring method. The cast composite specimen was obtained in a cylindrical shape of dimensions 50 mm dia and 100 mm length. The composite specimens were prepared for mechanical and tribological test as per ASTM standards. The obtained results reveal that the mechanical properties are high as compared to the as cast LM4 alloy specimens. Microstructure analysis confirms that the uniform distribution of TiC particles. Tribological test was performed using pin-on-disc machine based on Taguchi's design of experiments. L27 orthogonal array was selected by changing test parameter like applied load (10, 20, 30 N), sliding distance (600, 800, 1000 m) and sliding velocity (1.5 m/s, 2.5 m/s and 3.5 m/s). The most influencing test parameters were identified by using S/N ratio and ANOVA. The wear results reveled that wear rate increases as applied load increases, and it decreases with decrease in velocity. Also wear rate decreases as sliding distance increases and at some point, it became linear. The applied load was found to be most dominating (77.61%), sliding velocity (10.44%) and sliding distance (4.47%) are less dominating factors. Worn surface morphology was studied to understand the type of wear. 2021 elsevier ltd. all rights reserved. -
Design and Development of Terahertz Medical Screening Devices
This paper highlights the prospect of design and development of a terahertz medical screening system, giving an overview of existing devices, systems, for THz spectroscopy and imaging of biological samples (e.g., cell, tissue imaging or screening). Considering the non-ionizing nature of THz waves along with its reasonable soft-tissue sensitivity, terahertz instrumentation has opened up possibilities for medical screening devices. Some THz imaging systems presently use raster scanning for calculation of image region of interest. Here, a particular system is proposed as a medical screening device and factors like signal-to-noise ratio, image resolution, image contrast, etc., have been described and correlated with relevant clinical results for exploring possible prospects in medical applications of terahertz waves. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Securing medical images using encryption and LSB steganography
Medical imaging plays a vital role in the healthcare industry. Due to the advancements in the healthcare industry medical images are being transferred between geographically spread regions. As the medical images are transmitted through public networks several security challenges may arise such as authentication, integrity, and confidentiality. In this paper, the research focus is on preserving the confidentiality and integrity of the medical images. In general, integrity and confidentiality can be achieved by encryption (a piece of cryptography). To incorporate one more layer of security, steganography is applied to the medical image. In this paper, a one-time pad encryption algorithm is used to encrypt the medical image, then the encrypted image is implanted into a cover image to give a stego image making the system more resilient to the attacker. Further in this paper, the above said method is being implemented using MATLAB and the experimental results are compared with hiding the medical image using LSB steganography without encryption (one layer of security). Various formats of medical images have been taken into consideration such as DICOM, TIFF, BMP, and JPEG. Results show that the combination of encryption and steganography performs better than applying only steganography, concerning MSE and PSNR values. 2021 IEEE -
Content Based Scientific Article Recommendation System Using Deep Learning Technique
The emergence of the era of big data has increased the ease with which scientific users can access academic articles with better efficiency and accuracy from a pool of papers available. With the exponential increase in the number of research papers that are getting published every year, it has made scholars face the problem of information overload where they find it difficult to conduct comprehensive literature surveys. An article recommendation system helps in overcoming this issue by providing users with personalized recommendations based on their interests and choices. The common approaches used for recommendation are Content-Based Filtering (CBF) and Collaborative Filtering (CF). Even though there is much advancement in the field of article recommendation systems, a content-based approach using a deep learning technology is still in its inception. In this work, a C-SAR model using Gated Recurrent Unit (GRU) and association rule mining Apriori algorithm to provide a recommendation of articles based on the similarity in the content were proposed. The combination of a deep learning technique along with a classical algorithm in data mining is expected to provide better results than the state-of-art model in suggesting similar papers. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Hybrid Renewable Road Side Charging Station with I2V Communication Functionality
The faster adoption of Renewable-based Energy Sources for charging Electric Vehicles is highly required. The paper proposes a novel strategy of design and developing a hybrid Road Side Unit (RSU) that would be easy to install and provides easy access to Electric Vehicle charging. The system inculcates Infrastructure to Vehicle (I2V) communication framework enabling communication between the Infrastructure and the Vehicle to identify the nearest charging station based on the availability. The communication framework is based on Wi-Fi communication and enables bidirectional communication between the Vehicle and the Infrastructure as well. The modelling and development of the RSU, and the active power flow regulation from the RSU to the Charging Station is also developed, using a Fuzzy Controller. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Captcha-Based Defense Mechanism to Prevent DoS Attacks
The denial of service (DoS) attack, in the current scenario, is more vulnerable to the banking system and online transactions. Conventional mechanism of DoS attacks consumes a lot of bandwidth, and there will always be performance degradation with respect to the traffic in any of the communication networks. As there is an advent over the network bandwidth, in the current era, DoS attacks have been moved from the network to servers and API. An idea has been proposed which is CAPTCHA-based defense, a purely system-based approach. In the normal case, the protection strategy for DDoS attacks can be achieved with the help of many session schedulers. The main advantage is to efficiently avoid the DoS attacks and increase the server speed as well as to avoid congestion and data loss. This is majorly concerned in a wired network to reduce the delays and to avoid congestion during attacks. 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Pad Vending Machine with Cashless Payment
A vending machine aims to provide required product or the service to the customer with certain ease, wherein not much effort is required. This research work aims to design a pad vending machine with an option of payment using QR code which is implemented using blockchain to make the system much more efficient and reliable than the existing systems present in the Indian market. The system is divided into two parts, first being the working of the machine and second being the mode of payment which is implemented using a blockchain. It is noticed many times that due to unpredictable menstrual flow women tend to face a lot problems. To overcome this problem, a pad vending machine is proposed with certain advancements through which women can help themselves in the stated circumstances. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Fraud Detection in Credit Card Transaction Using ANN and SVM
Digital Payment fraudulent cases have increased with the rapid growth of e-commerce. Masses use credit card payments for both online and day-to-day purchasing. Hence, payment fraud utilizes a billion-dollar business, and it is growing fast. The frauds use different patterns to make the transactions from the cardholders account, making it difficult for the organization or the users to detect fraudulent transactions. The studys principal purpose is to develop an efficient supervised learning technique to detect credit card fraudulent transactions to minimize the customers and organizations losses. The respective classification accuracy compares supervised learning techniques such as deep learning-based ANN and machine learning-based SVM models. This studys significant outcome is to find an efficient supervised learning technique with minimum computational time and maximum accuracy to identify the fraudulent act in credit card transactions to minimize the losses incurred by the consumers and banks. 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. -
A Mathematical Correlation of Compressive Strength Among Silica, Alumina and Calcia Present in Composite Red Mud and Iron Ore Tailingbricks
Waste Red Mud generated from bauxite beneficiation in aluminium industry contains sodium oxide in minor amount along with silica and alumina in significant quantities. Waste iron ore tailings from beneficiation of iron ore in steel industry contain silica and alumina in significant quantities. A combination of both these materials in different amounts along with GGBS and lime addition resulted in complex alkali-activated reaction products consisting of (Si/Al), (Ca/Si) and (Ca/(Si+Al)) complexes which influence compressive strength of the test samples on curing for extended time periods at room temperature. Individual correlation coefficients of these complexes with compressive strength yielded high values with (Si/Al) and (Ca/Si+Al) ratios (0.92 and 0.96, respectively) while showing a poor correlation coefficient with (Ca/Si) ratio (0.88). A direct regression analysis between compressive strength and (Si/Al) ratio and (Ca/Si+Al) ratio indicated negative values with (Si/Al) ratios but positive values with (Ca/ (Si+Al)) ratios. It is therefore concluded that the addition of lime and GGBS (contributed from both GGBS and lime addition) resulted in Ca-Si-Al complex formations which are responsible for improved compressive strength of the samples. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Butterfly Optimization Algorithm-Based Optimal Sizing and Integration of Photovoltaic System in Multi-lateral Distribution Network for Interoperability
In this paper, a new and simple nature-inspired meta-heuristic search algorithm, namely butterfly optimization algorithm (BOA), is proposed for solving the optimal location and sizing of solar photovoltaic (SPV) system. An objective function for distribution loss minimization is formulated and minimized via optimally allocating the SPV system on themain feeder. At the first stage, the computational efficiency of BOA is compared with various other similar works and highlights its superiority in terms of global solution. In thesecond stage, the interoperability requirement of SPV system while determining the location and size of SPV system among multiple laterals in a distribution system is solved without compromises in radiality constraint. Various case studies on standard IEEE 33-bus system have shown the effectiveness of proposed concept of interline-photovoltaic (I-PV) system in improving the distribution system performance in terms of reduced losses and improved voltage profile via redistributing the feeder power flows effectively. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Survey on Solution of Imbalanced Data Classification Problem Using SMOTE and Extreme Learning Machine
Imbalanced data are a common classification problem. Since it occurs in most real fields, this trend is increasingly important. It is of particular concern for highly imbalanced datasets (when the class ratio is high). Different techniques have been developed to deal with supervised learning sets. SMOTE is a well-known method for over-sampling that discusses imbalances at the level of the data. In the area, unequal data are widely distributed, and ensemble learning algorithms are a more efficient classifier in classifying imbalances. SMOTE synthetically contrasts two closely connected vectors. The learning algorithm itself, however, is not designed for imbalanced results. The simple ensemble idea, as well as the SMOTE algorithm, works with imbalanced data. There are detailed studies about imbalanced data problems and resolving this problem through several approaches. There are various approaches to overcome this problem, but we mainly focused on SMOTE and extreme learning machine algorithms. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Stability Analysis of AFTI-16 Aircraft by Using LQR and LQI Algorithms
The stability analysis of the dynamical system of linearized plant model of Advanced Fighter Technology Integration (AFTI)-16 aircraft was proposed along with the optimal control methods by applying linear quadratic regulator (LQR) and linear quadratic algorithm (LQI) algorithms. The LQR and LQI algorithms results were compared with state-space model analysis results. The state-space methods like pole placement method, without using the LQR algorithm the negative feedback system were found to be unstable. By the application of LQR and LQI algorithms to the linearized plant AFTI-16 aircraft open-loop system having negative feedback found to be stable. The stability parameters were verified by using MATLAB programming software. The eigenvalues play a key role in finding closed-loop system stability analysis. MIMO dynamical system with state feedback gain matrices is calculated by using MATLAB programming software. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.