Abnormal Detection of Cash-Out Groups in IoT Based Payment

With the rise of online/mobile transactions, the cost of cash-out has decreased and the cost of detection has increased. In the world of online/mobile payment in IoT, merchants and credit cards can be applied and approved online and used in the form of a QR code but not a physical card or Point of Sale equipment, making it easy for these systems to be controlled by a group of fraudsters. In mainland China, where the credit card transaction fee is, on average, lower than a retail loan rate, the credit card cash-out option is attractive for people for an investment or business operation, which, after investigation, can be considered unlawful if over a certain amount is used. Because cash-out will incur fees for the merchants, while bringing money to the credit cards’ owners, it is difficult to confirm, as nobody will declare or admit it. Furthermore, it is more difficult to detect cash-out groups than individuals, because cash-out groups are more hidden, which leads to bigger transaction amounts. We propose a new method for the detection of cash-out groups. First, the seed cards are mined and the seed cards’ diffusion is then performed through the local graph clustering algorithm (Approximate PageRank, APR). Second, a merchant association network in IoT is constructed based on the suspicious cards, using the graph embedding algorithm (Node2Vec). Third, we use the clustering algorithm (DBSCAN) to cluster the nodes in the Euclidean space, which divides the merchants into groups. Finally, we design a method to classify the severity of the groups to facilitate the following risk investigation. The proposed method covers 145 merchants from 195 known risky merchants in groups that acquire cash-out from four banks, which shows that this method can identify most (74.4%) cash-out groups. In addition, the proposed method identifies a further 178 cash-out merchants in the group within the same four acquirers, resulting in a total of 30,586 merchants. The results and framework are already adopted and absorbed into the design for a cash-out group detection system in IoT by the Chinese payment processor.

Blood Group Detection using Image Processing MATLAB

Blood grouping is one of the common and most essentiality for many of the major healthcare applications. Traditional way to determine the blood group involve human such as trained medical professionals which generally lead to human error. One of the solutions to overcome this issue is to automate and digitize this method. Image processing and computer vision techniques can be used for this purpose. Therefore, in this paper, we investigate the blood group detection using image processing techniques. For this purpose, experiment starts by taking images of sample blood slide as input and convert it into gray scale followed by binarization and canny edge detection. Finally, it decided the agglutination by counting detected edges. Performance of method is tested on real- time blood sample dataset. Experimental results show the accuracy of proposed method is comparable to real- time test.

Functional Groups Detection: Do Chemistry Teachers Demonstrate Conceptual Difficulties in Teaching?

The chemistry chief examiner of the West African Examination Council has complaint a lot about the weak performance of students on organic chemistry, including functional group detection. The study, therefore, investigated whether senior high school teachers who teach chemical concepts to students also demonstrated conceptual difficulties on functional group detection under organic qualitative analysis. The study adopted convergent mixed methods procedures to collect both quantitative and qualitative data from 47 chemistry teachers. The 47 teachers were sampled through multistage sampling procedures to respond to the Organic Qualitative Analysis Diagnostic Test for Teachers. The quantitative data was analyzed using means, standard deviations, and percentages to reflect no scientific understanding, partial scientific understanding, and scientific understanding of functional group detection. The qualitative data was open-coded and constantly compared to established teachers’ alternative conceptions and factual difficulties on functional group detection.

Spammer group detection and diversification of customers’ reviews

Online reviews regarding different products or services have become the main source to determine public opinions. Consequently, manufacturers and sellers are extremely concerned with customer reviews as these have a direct impact on their businesses. Unfortunately, to gain profit or fame, spam reviews are written to promote or demote targeted products or services. This practice is known as review spamming. In recent years, Spam Review Detection problem (SRD) has gained much attention from researchers, but still there is a need to identify review spammers who often work collaboratively to promote or demote targeted products. It can severely harm the review system. This work presents the Spammer Group Detection (SGD) method which identifies suspicious spammer groups based on the similarity of all reviewer’s activities considering their review time and review ratings. After removing these identified spammer groups and spam reviews, the resulting non-spam reviews are displayed using diversification technique. For the diversification, this study proposed Diversified Set of Reviews (DSR) method which selects diversified set of top-k reviews having positive, negative, and neutral reviews/feedback covering all possible product features. Experimental evaluations are conducted on Roman Urdu and English real-world review datasets. The results show that the proposed methods outperformed the existing approaches when compared in terms of accuracy.

Pendeteksi Golongan Darah Manusia Berbasis Tensorflow menggunakan ESP32-CAM

ABSTRAKPendeteksian golongan darah dilakukan untuk mengetahui golongan darah yang dimiliki. Hingga saat ini pendeteksian golongan darah masih dilakukan oleh petugas analis kesehatan menggunakan kemampuan mata manusia. Pada penelitian ini dilakukan perancangan alat pendeteksi golongan darah menggunakan ESP32-CAM. Alat ini menggunakan kamera OV2640 untuk menangkap citra, yang diproses menggunakan Tensorflow Object Detection API sebagai framework untuk melatih serta mengolah citra darah. Model latih akan digunakan pada kondisi pendeteksian langsung dan ditampilkan dalam bentuk jendela program golongan darah beserta tingkat akurasinya. Dalam penelitian ini pengujian dilakukan menggunakan 20 dataset dengan jarak pengukuran antara ESP32-CAM dengan citra golongan darah yaitu sejauh 20 cm. Hasil yang didapat selama pengujian mayoritas golongan darah yang dapat terdeteksi adalah golongan darah AB.Kata kunci: ESP32-CAM, Tensorflow, Python, Golongan Darah, Pengolahan Citra ABSTRACTBlood group detection is performed to determine the blood group. Currently, in detecting blood type, it still relies on the ability of the human eyeThis paper presents a human blood group detection device using ESP32-CAM. This tool uses ESP32-CAM to capture images, and the Tensorflow Object Detection API as a framework used to train and process an image. The way this tool works is that the ESP32-CAM will capture an image of the blood sample and then send it via the IP address. Through the IP Address, the python program will access the image, then the image will be processed based on a model that has been previously trained. The results of this processing will be displayed in the form of a window program along with the blood type and level of accuracy. In this study, testing was carried out based on the number of image samples, the number of datasets, and the measurement distance. The ideal measurement distance between the ESP32-CAM and the blood group image is 20 cm long. The results obtained during the testing of the majority of blood groups that can be detected are AB blood group.Keywords: ESP32-CAM, Tensorflow, Python, Blood Type, Image Processing

Spammer Group Detection Using Machine Learning Technology for Observation of New Spammer Behavioral Features

Recently, the rapid growth in the number of customer reviews on e-commence platforms and in the amount of user-generated content has begun to have a profound impact on customer purchasing decisions. To counter the negative impact of social media marketing, some firms have begun hiring people to generate fake reviews which either promote their own products or damage their competitor's reputation. This study proposes a framework, which takes advantage of both supervised and unsupervised learning techniques, for the observation of behaviors among spammers. Then, based on the behavior of participants on web forums, the authors build up a post-reply network. The main focus is on the behavior-related features of the reviews, their propagation, and their popularity. The primary objective of this study is to build an effective online spammer detection model and the method detailed in this work can be used to improve the performance of spammer detection models. An experiment is carried out with a real dataset, the results of which indicate that these new features are important for identifying spammers. Finally, random walk clustering is applied to investigate the post-reply network. Some interesting and important features are observed in the interactions between a group of spammers which could be subjected to further research.