37 results
Search Results
Now showing 1 - 10 of 37
Article Citation - WoS: 3Citation - Scopus: 4Predictive Rental Values Model for Low-Income Earners in Slums: the Case of Ijora, Nigeria(Taylor & Francis Ltd, 2023) Iroham, Chukwuemeka O.; Misra, Sanjay; Emebo, Onyeka C.; Okagbue, Hilary, IIt is well known most often that values of properties tend to hike at the effluxion of time. This has necessitated the adoption of predictive models in interpreting outcomes in the property market in the future. Earlier studies have been oblivious of such models' outcomes as it affects any focal group, particularly the vulnerable. This present study focuses on the low-income earners found in the slum. The Ijora community in Lagos was the highlight of this study, particularly Ijora Badia and Ijora Oloye, regarded as slums according to the UNDP report. The entire fifty-two (52) local agents in the Ijora community were surveyed in cross-sectional survey research that entailed the questionnaire's issuance. The nexus of data collection, pre-processing, data analysis, algorithm application, and model evaluation resulted in retrieving rental values within the years 2010 and 2019 on two predominant residential property types of self-contain and one-bedroom flats found within the community. Three selected algorithms, Artificial Neural Network (ANN), Support Vector Machine, and Logistic Regression, were essentially used as classifiers but trained to predict the continuous values. These algorithms were implemented through the use of Python's SciKit-learn Library and RapidMiner. The findings revealed that though all three models gave accurate predictions, Logistic Regression was the highest with low error values. It was recommended that Logistic Regression be applied but with much data set of property values of low-income earners over much more period. This study will contribute to the Sustainable development goals(SDG) 11(Sustainable cities and communities) of the United Nations to benefit developing countries, especially in sub-Saharan Africa.Article Citation - WoS: 11Citation - Scopus: 17Software Measurement Activities in Small and Medium Enterprises: an Empirical Assessment(Budapest Tech, 2011) Pusatli, O. Tolga; Misra, Sanjay; Tolga Pusatli, O.; Computer EngineeringAn empirical study for evaluating the proper implementation of measurement/metric programs in software companies in one area of Turkey is presented. The research questions are discussed and validated with the help of senior software managers (more than 15 years' experience) and then used for interviewing a variety of medium and small scale software companies in Ankara. Observations show that there is a common reluctance/lack of interest in utilizing measurements/metrics despite the fact that they are well known in the industry. A side product of this research is that internationally recognized standards such as ISO and CMMI are pursued if they are a part of project/job requirements; without these requirements, introducing those standards to the companies remains as a long-term target to increase quality.Article Citation - WoS: 10Citation - Scopus: 18An Ontology-Based Information Extraction System for Organic Farming(Igi Global, 2021) Abayomi-Alli, Adebayo Adewumi; Arogundade, Oluwasefunmi 'Tale; Misra, Sanjay; Akala, Mulkah Opeyemi; Ikotun, Abiodun Motunrayo; Ojokoh, Bolanle AdefowokeIn the existing farming system, information is obtained manually, and most times, farmers act based on their discretion. Sometimes, farmers rely on information from experts and extension officers for decision making. In recent times, a lot of information systems are available with relevant information on organic farming practices; however, such information is scattered in different context, form, and media all over the internet, making their retrieval difficult. The use of ontology with the aid of a conceptual scheme makes the comprehensive and detailed formalization of any subject domain possible. This study is aimed at acquiring, storing, and providing organic farming-based information available to current and intending software developer who may wish to develop applications for farmers. It employs information extraction (IE) and ontology development techniques to develop an ontology-based information extraction (OBIE) system called ontology-based information extraction system for organic farming (OBIESOF). The knowledge base was built using protege editor; Java was used for the implementation of the ontology knowledge base with the aid of the high-level application programming language for working web ontology language application program interface (OWLAPI). In contrast, HermiT was used to checking the consistencies of the ontology and for submitting queries in order to verify their validity. The queries were expressed in description logic (DL) query language. The authors tested the capability of the ontology to respond to user queries by posing instances of the competency questions from DL query interface. The answers generated by the ontology were promising and serve as positive pointers to its usefulness as a knowledge repository.Article Citation - WoS: 38Citation - Scopus: 59Career Abandonment Intentions among Software Workers(Wiley, 2014) Colomo-Palacios, Ricardo; Casado-Lumbreras, Cristina; Misra, Sanjay; Soto-Acosta, PedroWithin the software development industry, human resources have been recognized as one of the most decisive and scarce resources. Today, the retention of skilled IT (information technology) personnel is a major issue for employers and recruiters as well, since IT career abandonment is a common practice and means not only the loss of personnel, knowledge, and skills, but also the loss of business opportunities. This article seeks to discover the main motivations young practitioners abandon the software career. To achieve this objective, two studies were conducted. The first study was qualitative (performed through semistructured interviews) and intended to discover the main variables affecting software career abandonment. The second study was quantitative, consisting of a Web-based survey developed from the output of the first study and administered to a sample of 148 IT practitioners. Results show that work-related, psychological, and emotional variable are the most relevant group of variables explaining IT career abandonment. More specifically, the three most important variables that motivate employees to abandon the career are effort-reward imbalance, perceived workload, and emotional exhaustion. In contrast, variables such as politics and infighting, uncool work, and insufficient resources influence to a lesser extent the decision to leave the career. (c) 2012 Wiley Periodicals, Inc.Article Citation - WoS: 104Citation - Scopus: 163Cassava Disease Recognition From Low-Quality Images Using Enhanced Data Augmentation Model and Deep Learning(Wiley, 2021) Abayomi-Alli, Olusola Oluwakemi; Damasevicius, Robertas; Misra, Sanjay; Maskeliunas, RytisImprovement of deep learning algorithms in smart agriculture is important to support the early detection of plant diseases, thereby improving crop yields. Data acquisition for machine learning applications is an expensive task due to the requirements of expert knowledge and professional equipment. The usability of any application in a real-world setting is often limited by unskilled users and the limitations of devices used for acquiring images for classification. We aim to improve the accuracy of deep learning models on low-quality test images using data augmentation techniques for neural network training. We generate synthetic images with a modified colour value distribution to expand the trainable image colour space and to train the neural network to recognize important colour-based features, which are less sensitive to the deficiencies of low-quality images such as those affected by blurring or motion. This paper introduces a novel image colour histogram transformation technique for generating synthetic images for data augmentation in image classification tasks. The approach is based on the convolution of the Chebyshev orthogonal functions with the probability distribution functions of image colour histograms. To validate our proposed model, we used four methods (resolution down-sampling, Gaussian blurring, motion blur, and overexposure) for reducing image quality from the Cassava leaf disease dataset. The results based on the modified MobileNetV2 neural network showed a statistically significant improvement of cassava leaf disease recognition accuracy on lower-quality testing images when compared with the baseline network. The model can be easily deployed for recognizing and detecting cassava leaf diseases in lower quality images, which is a major factor in practical data acquisition.Article Citation - WoS: 10Citation - Scopus: 18Evaluation Criteria for Object-Oriented Metrics(Budapest Tech, 2011) Misra, Sanjay; Computer EngineeringIn this paper an evaluation model for object-oriented (OO) metrics is proposed. We have evaluated the existing evaluation criteria for OO metrics, and based on the observations, a model is proposed which tries to cover most of the features for the evaluation of OO metrics. The model is validated by applying it to existing OO metrics. In contrast to the other existing criteria, the proposed model is simple in implementation and includes the practical and important aspects of evaluation; hence it suitable to evaluate and validate any OO complexity metric.Review Citation - WoS: 22Citation - Scopus: 39Cybersecurity Deep: Approaches, Attacks Dataset, and Comparative Study(Taylor & Francis inc, 2022) Barik, Kousik; Misra, Sanjay; Konar, Karabi; Fernandez-Sanz, Luis; Murat, Koyuncu; Koyuncu, MuratCyber attacks are increasing rapidly due to advanced digital technologies used by hackers. In addition, cybercriminals are conducting cyber attacks, making cyber security a rapidly growing field. Although machine learning techniques worked well in solving large-scale cybersecurity problems, an emerging concept of deep learning (DL) that caught on during this period caused information security specialists to improvise the result. The deep learning techniques analyzed in this study are convolution neural networks, recurrent neural networks, and deep neural networks in the context of cybersecurity.A framework is proposed, and a real-time laboratory setup is performed to capture network packets and examine this captured data using various DL techniques. A comparable interpretation is presented under the DL techniques with essential parameters, particularly accuracy, false alarm rate, precision, and detection rate. The DL techniques experimental output projects improvise the performance of various real-time cybersecurity applications on a real-time dataset. CNN model provides the highest accuracy of 98.64% with a precision of 98% with binary class. The RNN model offers the second-highest accuracy of 97.75%. CNN model provides the highest accuracy of 98.42 with multiclass class. The study shows that DL techniques can be effectively used in cybersecurity applications. Future research areas are being elaborated, including the potential research topics to improve several DL methodologies for cybersecurity applications.Article Citation - WoS: 49Citation - Scopus: 69Deep Learning Based Fall Detection Using Smartwatches for Healthcare Applications(Elsevier Sci Ltd, 2022) Sengul, Gokhan; Karakaya, Murat; Misra, Sanjay; Abayomi-Alli, Olusola O.; Damasevicius, RobertasWe implement a smart watch-based system to predict fall detection. We differentiate fall detection from four common daily activities: sitting, squatting, running, and walking. Moreover, we separate falling into falling from a chair and falling from a standing position. We develop a mobile application that collects the acceleration and gyroscope sensor data and transfers them to the cloud. In the cloud, we implement a deep learning algorithm to classify the activity according to the given classes. To increase the number of data samples available for training, we use the Bica cubic Hermite interpolation, which allows us to improve the accuracy of the neural network. The 38 statistical data features were calculated using the rolling update approach and used as input to the classifier. For activity classification, we have adopted the bi-directional long short-term memory (BiLSTM) neural network. The results demonstrate that our system can detect falling with an accuracy of 99.59% (using leave-one-activityout cross-validation) and 97.35% (using leave-one-subject-out cross-validation) considering all activities. When considering only binary classification (falling vs. all other activities), perfect accuracy is achieved.Article Citation - WoS: 36Citation - Scopus: 58A Suite of Object Oriented Cognitive Complexity Metrics(Ieee-inst Electrical Electronics Engineers inc, 2018) Misra, Sanjay; Adewumi, Adewole; Fernandez-Sanz, Luis; Damasevicius, RobertasObject orientation has gained a wide adoption in the software development community. To this end, different metrics that can be utilized in measuring and improving the quality of object-oriented (OO) software have been proposed, by providing insight into the maintainability and reliability of the system. Some of these software metrics are based on cognitive weight and are referred to as cognitive complexity metrics. It is our objective in this paper to present a suite of cognitive complexity metrics that can be used to evaluate OO software projects. The present suite of metrics includes method complexity, message complexity, attribute complexity, weighted class complexity, and code complexity. The metrics suite was evaluated theoretically using measurement theory and Weyuker's properties, practically using Kaner's framework and empirically using thirty projects.Article Citation - WoS: 18Citation - Scopus: 24Fusion of Smartphone Sensor Data for Classification of Daily User Activities(Springer, 2021) Sengul, Gokhan; Ozcelik, Erol; Misra, Sanjay; Damasevicius, Robertas; Maskeliunas, RytisNew mobile applications need to estimate user activities by using sensor data provided by smart wearable devices and deliver context-aware solutions to users living in smart environments. We propose a novel hybrid data fusion method to estimate three types of daily user activities (being in a meeting, walking, and driving with a motorized vehicle) using the accelerometer and gyroscope data acquired from a smart watch using a mobile phone. The approach is based on the matrix time series method for feature fusion, and the modified Better-than-the-Best Fusion (BB-Fus) method with a stochastic gradient descent algorithm for construction of optimal decision trees for classification. For the estimation of user activities, we adopted a statistical pattern recognition approach and used the k-Nearest Neighbor (kNN) and Support Vector Machine (SVM) classifiers. We acquired and used our own dataset of 354 min of data from 20 subjects for this study. We report a classification performance of 98.32 % for SVM and 97.42 % for kNN.
