Template-Type: ReDIF-Article 1.0 Author-Name: Selim Corekcioglu Author-X-Name-First: Selim Author-X-Name-Last: Corekcioglu Author-Name: Bekir Polat Author-X-Name-First: Bekir Author-X-Name-Last: Polat Title: Estimation of success of entrepreneurship projects with data mining Abstract: This study aimed to prevent waste of resource and to estimate the success and failure of proposed entrepreneurship projects with data mining algorithms. Thereby, the accuracy of the estimates increased and decisions about the projects were based on a scientific approach. As a result of the analysis of the data, it has been examined whether entrepreneurial projects were successful or not. The dataset was classified using 10-fold cross-validation with C4.5, Naive Bayes, logistic regression, random forest and support vector algorithms. The results of the classification were compared and the C4.5 algorithm was found as the most successful algorithm with 70.75% prediction accuracy. In consequence of the C4.5 algorithm, the features affecting the tree were found as capital, partner, location, and age, respectively. The features that did not affect the tree were gender, education, market, sector, and personnel. Journal: Int. J. of Data Science Pages: 85-108 Issue: 2 Volume: 6 Year: 2021 Keywords: entrepreneurship; SME; small and medium-sized enterprise; data mining; classification; Naive Bayes; logistic regression; random forest; support vector algorithms. File-URL: http://www.inderscience.com/link.php?id=118941 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:6:y:2021:i:2:p:85-108 Template-Type: ReDIF-Article 1.0 Author-Name: Karina Munari Pagan Author-X-Name-First: Karina Munari Author-X-Name-Last: Pagan Author-Name: Natália Munari Pagan Author-X-Name-First: Natália Munari Author-X-Name-Last: Pagan Author-Name: Janaina De Moura Engracia Giraldi Author-X-Name-First: Janaina De Moura Engracia Author-X-Name-Last: Giraldi Author-Name: Jorge Henrique Caldeira De Oliveira Author-X-Name-First: Jorge Henrique Caldeira De Author-X-Name-Last: Oliveira Title: A theoretical study on the ways of analysing electroencephalography in marketing research Abstract: The objective of this paper is to identify the existing forms of electroencephalographic analysis that have been used in marketing research and to see how they can be used in future marketing research. An exploratory research was carried out on papers that used the electroencephalography (EEG) tool for research in the marketing area. The search period was between 2007 and 2017. Three types of EEG analysis were found for research in the marketing area: ERP, time-frequency analysis and frontal asymmetry. Each one of these analyses was used to identify an element of the marketing mix. This study can help future academics and neuromarketing practitioners to identify the appropriate technique to analyse the data and to attain the research objectives. Journal: Int. J. of Data Science Pages: 109-128 Issue: 2 Volume: 6 Year: 2021 Keywords: marketing; neuromarketing; electroencephalography; methods of analysis; neurofeedback; ERP; Event-related potentials; time-frequency analysis; frontal asymmetry. File-URL: http://www.inderscience.com/link.php?id=118944 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:6:y:2021:i:2:p:109-128 Template-Type: ReDIF-Article 1.0 Author-Name: Mustafa Yildirim Author-X-Name-First: Mustafa Author-X-Name-Last: Yildirim Author-Name: Mehmet Mutlu Yenisey Author-X-Name-First: Mehmet Mutlu Author-X-Name-Last: Yenisey Title: Mathematical model structures of supply chain optimisation studies and an innovative approach proposal Abstract: Supply chain optimisation has been the subject of many scientific studies due to its mathematical structure. In this study, some optimisation studies that consider the components of the supply chain for modelling and to help to make decisions for supply chain management problems are examined. These studies in the literature have been classified in terms of mathematical model structures. Optimisation of supply chain problems and complexity of problems are mentioned. For the optimisation of the supply chain, a new innovative approach has been proposed by using the succession relationship between the components of the supply chain. In accordance with the proposed approach, a solution method has been described and its results are shown on a sample problem. It is aimed that the proposed method will bring a new approach suitable for solving complex problems, especially supply chain optimisation problems, and contribute to finding better solutions. Development opportunities are evaluated by examining the results. Journal: Int. J. of Data Science Pages: 129-146 Issue: 2 Volume: 6 Year: 2021 Keywords: optimisation; complex problems; supply chain management; production and transportation planning; heuristic algorithms; genetic algorithm; butterfly effect algorithm. File-URL: http://www.inderscience.com/link.php?id=118945 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:6:y:2021:i:2:p:129-146 Template-Type: ReDIF-Article 1.0 Author-Name: Didem Guleryuz Author-X-Name-First: Didem Author-X-Name-Last: Guleryuz Author-Name: Sakir Esnaf Author-X-Name-First: Sakir Author-X-Name-Last: Esnaf Title: Effects of discount policies on economic order quantity and total cost for perishables: a case study Abstract: The classical economic order quantity (EOQ) model assumes that demand stays constant over time. This study examined the effect of changes in the economic order quantities resulting from discount policies in perishable goods on total cost, making a discount suggestion. Discounts due to shelf life and additional perishing costs were added to the EOQ formula via the Weiss Model to calculate the order quantity of play dough. Then the total cost is determined, and both costs were compared by trying different discount rates. As a result, the total cost for classical order quantity and order quantities, including discount policies, are calculated as 634.43 TRY, 641.32 TRY, and 1672.695 TRY, 1732.830 TRY for decorative and standard play doughs, respectively. Although the classic model has a lower cost as it does not consider the discount policy or the perishing rates, this is not suitable for perishables in real life. Journal: Int. J. of Data Science Pages: 172-187 Issue: 2 Volume: 6 Year: 2021 Keywords: economic order quantity model; perishables; Weiss model; total cost; discount rate; revenue management; inventory management; dynamic pricing. File-URL: http://www.inderscience.com/link.php?id=118947 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:6:y:2021:i:2:p:172-187 Template-Type: ReDIF-Article 1.0 Author-Name: Zeynep Burcu Kizilkan Author-X-Name-First: Zeynep Burcu Author-X-Name-Last: Kizilkan Author-Name: Ahmet Erdogan Asliyuce Author-X-Name-First: Ahmet Erdogan Author-X-Name-Last: Asliyuce Author-Name: Tugay Cengiz Author-X-Name-First: Tugay Author-X-Name-Last: Cengiz Author-Name: Uğur Can Ersen Author-X-Name-First: Uğur Can Author-X-Name-Last: Ersen Title: A study on severity of traffic accidents using road, weather and time characteristics Abstract: Mortality and severe injuries caused by traffic accidents are vital threats to society, therefore contributing factors to accidents are a major concern. Accident severity can be understood by attributes like human factors, the impact of road characteristics, weather, and accident time. Artificial neural networks (ANNs) are more practical and efficient to implement compared to other algorithms while computing risk levels using categorical data. Accordingly, ANNs are a well-researched and applied technique in traffic accident prediction models and determining contributing factors of traffic accidents. Previous research includes predominantly human impact. This paper aims to build a model to observe the impact of road, weather, and time characteristics rather than human factors on risk levels. Two models are constructed using ANNs, performance comparison indicates that both models reached a satisfactory certainty level. For further development, this model can be developed as a prevention system to enable the use of governmental institutions. Journal: Int. J. of Data Science Pages: 147-171 Issue: 2 Volume: 6 Year: 2021 Keywords: accident severity; ANNs; artificial neural networks; traffic accident; machine learning; supervised learning; prevention system. File-URL: http://www.inderscience.com/link.php?id=118948 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:6:y:2021:i:2:p:147-171 Template-Type: ReDIF-Article 1.0 Author-Name: A. John Author-X-Name-First: A. Author-X-Name-Last: John Author-Name: Shubham Kumar Singh Author-X-Name-First: Shubham Kumar Author-X-Name-Last: Singh Author-Name: M. Adimoolam Author-X-Name-First: M. Author-X-Name-Last: Adimoolam Author-Name: T. Ananth Kumar Author-X-Name-First: T. Ananth Author-X-Name-Last: Kumar Title: Dynamic sorting and average skyline method for query processing in spatial-temporal data Abstract: With the continuous advancement in mobile computing and development of positioning in devices, querying of moving objects on road networking is an important task in the internet world. As a result of this development, huge amount of data management and query processing plays a vital role in spatial and temporal applications. Large amount of data which is being coupled with different query processing requires efficient indexing. The main problems in spatiotemporal is managing data indexing, updation and query processing. In this work related to the query processing in spatiotemporal data to update different dynamic queries of users. The previous work of query processing will not support to all the end users. The proposed dynamic sorting and average skyline (DSAS) method will support different kinds of query. This method is DSAS and it produces effective query processing to different users at different locations. The skyline query processing technique produces the result for the dominating objects, when compared with the other query processing techniques. Journal: Int. J. of Data Science Pages: 1-18 Issue: 1 Volume: 6 Year: 2021 Keywords: spatial-temporal data; query processing; skyline query processing; MOMS; moving object managing system; query; average skyline; data structure; shortest path. File-URL: http://www.inderscience.com/link.php?id=117460 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:6:y:2021:i:1:p:1-18 Template-Type: ReDIF-Article 1.0 Author-Name: T. Ananth Kumar Author-X-Name-First: T. Ananth Author-X-Name-Last: Kumar Author-Name: R. Rajmohan Author-X-Name-First: R. Author-X-Name-Last: Rajmohan Author-Name: M. Adithya Author-X-Name-First: M. Author-X-Name-Last: Adithya Author-Name: R. Sunder Author-X-Name-First: R. Author-X-Name-Last: Sunder Title: A novel security scheme using deep learning based low overhead localised flooding algorithm for wireless sensor networks Abstract: A wireless specially appointed system is a self-sorting out, self-arranging confederation of remote frameworks. Wireless ad-hoc network gadgets (WANET) will interface and leave the system non-concurring freely, and there are no predefined customers or server. The dynamic topologies, portable correspondence's structure, decentralised control, and namelessness makes numerous-difficulties to the security of frameworks and system in a WANET domain. So, by this alternative approach is requiring a revaluation of traditional approaches to security protocols. A deep learning-based low overhead localised flooding (DL-LOLF) strategy dependent on the query localisation system is proposed. The directing packets, which increase back to a source, are disposed of to lighten superfluous rebroadcasting. The improvement while using the network algorithm is making it easier to transmit security information. The results show that the proposed technique can decrease steering overhead and medium access control (MAC) impact rate without giving up parcel conveyance proportion contrasted with existing conventions. Journal: Int. J. of Data Science Pages: 19-32 Issue: 1 Volume: 6 Year: 2021 Keywords: WANET; wireless ad-hoc network; deep learning; bait message; LOLF; low overhead localised flooding; dropper node; AODV; LSTM; long short-term memory; secure transmission; dark-gap; NS2. File-URL: http://www.inderscience.com/link.php?id=117464 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:6:y:2021:i:1:p:19-32 Template-Type: ReDIF-Article 1.0 Author-Name: K. Suresh Kumar Author-X-Name-First: K. Suresh Author-X-Name-Last: Kumar Author-Name: A.S. Radhamani Author-X-Name-First: A.S. Author-X-Name-Last: Radhamani Author-Name: S. Sundaresan Author-X-Name-First: S. Author-X-Name-Last: Sundaresan Title: Proficient approaches for scalability and security in IoT through edge/fog/cloud computing: a survey Abstract: Cloud computing has evolved to the extent of 5G and the Internet of Things (IoT). For data warehousing, cloud computing paves an essential role in processing and implementation. The security-related issues are identified when the information is stored in the cloud. Be involved in sorting and in preparing the data for data warehousing. Until information is encrypted, security questions are raised. Therefore, it has been determined that the cloud-accessible data is essentially unexploitable because of limitations such as bandwidth restrictions, inactivity, inadequate resources, and various security problems. Fog computing and edge computing are other means of resolving these types of problems. In this paper, the IoT secrecy is analysed using it along with edge/cloud/fog computing. The various algorithms used, objectives, the proposed methodologies and their advantages are discussed in this paper. This paper paves the way to an integrated system in which scalability and security are enhanced. Journal: Int. J. of Data Science Pages: 33-44 Issue: 1 Volume: 6 Year: 2021 Keywords: IoT; Internet of Things; cloud computing; FOG computing; edge computing; RFID; BNA; broad network access; deep learning. File-URL: http://www.inderscience.com/link.php?id=117465 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:6:y:2021:i:1:p:33-44 Template-Type: ReDIF-Article 1.0 Author-Name: S. Theetchenya Author-X-Name-First: S. Author-X-Name-Last: Theetchenya Author-Name: Somula Ramasubbareddy Author-X-Name-First: Somula Author-X-Name-Last: Ramasubbareddy Author-Name: S. Sankar Author-X-Name-First: S. Author-X-Name-Last: Sankar Author-Name: Syed Muzamil Basha Author-X-Name-First: Syed Muzamil Author-X-Name-Last: Basha Title: Hybrid approach for content-based image retrieval Abstract: Content-based image retrieval (CBIR) is one of the vital research areas in image processing. The CBIR, also known as query by image content, i.e., the problem searching for similar digital images in a large database. The existing CBIR system used to retrieve the relevant images lack inaccuracy. To improve the accuracy level of CBIR, the proposed system introduces an unsupervised Hybrid Approach. The proposed system gets the input images as colour image. The pre-processing is performed using the median filter. This system is extracted the feature such as colour, texture, brightness distribution, Euclidean distance from hybrid approach. While the user gives the query on this system, the real time comparison is made with feature stored database. Finally the proposed system retrieves the related image from database. The proposed system compared with various dataset Corel 10000, IMAGENET1M and also increased the accuracy level by 5%. Journal: Int. J. of Data Science Pages: 45-56 Issue: 1 Volume: 6 Year: 2021 Keywords: CBIR; content-based image retrieval; query by image content; colour histogram; texture detection algorithm; brightness distribution algorithm. File-URL: http://www.inderscience.com/link.php?id=117467 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:6:y:2021:i:1:p:45-56 Template-Type: ReDIF-Article 1.0 Author-Name: Owen P. Hall Author-X-Name-First: Owen P. Author-X-Name-Last: Hall Title: Managing employee turnover: machine learning to the rescue Abstract: Organisations continue to face ongoing employee retention and recruiting challenges, which have become even more acute due to the COVID-19 pandemic. In today's unstable economy, employee retention is still one of the hot button issues facing many HR managers. Employee turnover has cost organisations billions of dollars each year. The empirical results from the current study, which included employee demographic, preference, and performance data, suggests that machine learning-based predictive models can provide automatic and timely employee assessments, which allow for both the identification of employees that may be planning to leave and the implementation of appropriate amelioration initiatives. Job engagement, work satisfaction, experience, and compensation are but four of the factors found to be closely aligned with an employee's decision to leave. The primary purpose of this paper is to highlight how machine learning can reduce employee turnover through early detection and intervention. Journal: Int. J. of Data Science Pages: 57-82 Issue: 1 Volume: 6 Year: 2021 Keywords: machine learning; human resource management; employee turnover; actionable knowledge discovery; intervention strategies; cost optimisation; market churn; decision trees. File-URL: http://www.inderscience.com/link.php?id=117472 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:6:y:2021:i:1:p:57-82