International Journal of Industrial Engineering & Production Research

---

  The unprecedented growth of competition in the banking technology has raised the importance of retaining current customers and acquires new customers so that is important analyzing Customer behavior, which is base on bank databases. Analyzing bank databases for analyzing customer behavior is difficult since bank databases are multi-dimensional, comprised of monthly account records and daily transaction records. Few works have focused on analyzing of bank databases from the viewpoint of customer behavioral analyze. This study presents a new two-stage frame-work of customer behavior analysis that integrated a K-means algorithm and Apriori association rule inducer. The K-means algorithm was used to identify groups of customers based on recency, frequency, monetary behavioral scoring predicators it also divides customers into three major profitable groups of customers. Apriori association rule inducer was used to characterize the groups of customers by creating customer profiles. Identifying customers by a customer behavior analysis model is helpful characteristics of customer and facilitates marketing strategy development .

---

Human-based quality control reduces the accuracy of this process. Also, the speed of decision making in some industries is very important. For removing these limitations in human-based quality control, in this paper, the design of an expert system for automatic and intelligent quality control is investigated. In fact, using an intelligent system, the accuracy in quality control is increased. It requires the knowledge of experts in quality control and design of expert systems based on the knowledge and information provided by human and equipment. For this purpose, Fuzzy Inference System (FIS) and Image Processing approach are integrated. In this expert system, the input information is the images of the products and the results of processing on images for quality control are as output. At first, they may be noisy images; the pre-processing is done and then a fuzzy system is used to be processed. In this fuzzy system, according to the images, the rules are designed to extract the specific features that are required. At second, after the required attributes are extracted, the control chart is used in terms of quality. Furthermore, the empirical case study of copper rods industry is presented to show the abilities of the proposed approach.
 

---

Cognitive based (Chatbot) blood bank provides the communication platform among the stakeholders of blood bank. In the past the blood recipient will have to contact the blood bank and the blood donors individually, which is a time consuming process.  To address this issue in this paper we propose a Secure Dynamic Interactive Blood Bank based on Cognitive Computing which can fulfill the blood request of the needy with less hardship. Hence the proposed work aims to overcome this problem by requesting the recipient to simply send a message to a chatbot.  The motivated individuals who are willing to donate blood can register their name by interacting with the chatbot. If the requested blood group is available at the blood bank / registered donor then the recipient will get contact details of the blood bank / registered donors available at that instant. Donor data will be maintained in Cloud database. The proposed system is a cognitive chatbot, which acts as a communication platform among the stakeholders such as blood bank, blood donor and the needy. This system is built using cognitive technology of Google; it makes conversations using chatbots very similar to human conversations, thereby making the proposed system more efficient compared to the existing ones.

---

The Today’s interconnected world generates huge digital data, while millions of users share their opinions, feelings on various topics through popular applications such as social media, different micro blogging sites, and various review sites on every day. Nowadays Sentiment Analysis on Twitter Data which is considered as a very important problem particularly for various organizations or companies who want to know the customers feelings and opinions about their products and services. Because of the data nature, variety and enormous size, it is very practical for several applications, range from choice and decision creation to product assessment. Tweets are being used to convey the sentiment of a tweeter on a specific topic. Those companies keeping survey millions of tweets on some kind of subjects to evaluate actual opinion and to know the customer feelings. This paper major goal would be to significantly collect, recognize, filter, reduce and analyze all such relevant opinions, emotions, and feelings of people on different product or service could be categorized into positive, negative or neutral because such categorization improves sales growth about a company's products or films, etc. We initiate that the Naïve Bayes classifier be the mainly utilized machine learning method for mining feelings from large data like twitter and popular social network because of its more accuracy rates. In this paper, we scrutinize sentiment polarity analysis on Twitter data in a distributed environment, known as Apache Spark.

---

The Today’s digital world computations are tremendously difficult and always demands for essential requirements to significantly process and store enormous size of datasets for wide variety of applications. Since the volume of digital world data is enormous, this is mostly generated unstructured data with more velocity at beyond the limits and double day by day. In last decade, many organizations have been facing major problems to handling and process massive chunks of data, which could not be processed efficiently due to lack of enhancements on existing and conventional technologies. In this paper address, how to overcome these problems as efficiently by using the most recent and world primary powerful data processing tool, which is hadoop clean open source and one of the core component called Map Reduce, but which has few performance issues. This paper main goal is  address and overcome the limitations and weaknesses of Map Reduce with Apache Spark.

---

This paper considers a customer order scheduling (COS) problem in which each customer requests a variety of products processed in a two-machine flow shop. A sequence-independent attached setup for each machine is needed before processing each product lot. We assume that customer orders are satisfied by the job-based processing approach in which the same products from different customer orders form a product lot (job). Each customer order for a product is processed as a sublot (a batch of identical items) of the product lot by applying the lot streaming (LS) idea in scheduling. We assume that all sublots of the same product must be processed together by the same machine without intermingling the sublots of other products. The completion time of a customer order is the completion time of the product processed as the last product in that order. All products in a customer order are delivered in a single shipment to the customer when the processing of all the products in that customer order is completed. We aim to find an optimal schedule with a product lots sequence and the sequence of the sublots in each job to minimize the sum of completion times of the customer orders. We have developed a mixed-integer linear programming (MILP) model and a multi-phase heuristic algorithm for solving the problem. The results of our computational experiments show that our model can solve the small-sized problem instances optimally. However, our heuristic algorithm finds optimal or near-optimal solutions for the medium- and large-sized problem instances in a short time.

---

Purpose: Non-cancerous prostate lesions such as prostate calcification, prostate enlargement, and prostate inflammation cause too many problems for men’s health. This research proposes a novel approach, a combination of image processing techniques and deep learning methods for classification and segmentation of the prostate in CT-scan images by considering the experienced physicians’ reports.
Methodology: Due to the various symptoms and nature of these lesions, a three-phases innovative approach has been implemented. In the first phase, using Mask R-CNN, in the second phase, considering the age of each patient and comparison with the standard size of the prostate gland, and finally, using the morphology features, the presence of three common non-cancerous lesions in the prostate gland has investigated.
Findings: A hierarchical multitask approach is introduced and the final amount of classification, localization, and segmentation loss is 1%, 1%, and 7%, respectively. Eventually, the overall loss ratio of the model is about 9%.
Originality: In this study, a medical assistant approach is introduced to increase diagnosis process accuracy and reduce error using a real dataset of abdominal and pelvics’ CT scans and the physicians’ reports for each image. A multi-tasks convolutional neural network; also presented to perform localization, classification, and segmentation of the prostate gland in CT scans at the same time.

---

---