Recent Patents on Engineering - Volume 16, Issue 2, 2022

Background: In the world of the latest technologies, the blockchain is one of the popular techniques for stopping fraudulent activities. Non-Government Organization (NGO) is increasingly being used to support all the needy people across the globe to shape the world’s responsibility towards society for sustainable development. The existing method of donating money and its monitoring is facing a major corruption problem in several world-renowned NGOs. A Blockchain can transform the way the current business of money transaction is being done in NGOs. The blockchain-based application works on the concept of a decentralized system. Methods: This article presents a blockchain-based transaction system to prevent corruption and money laundering in NGOs and government fundraising organizations. A smart contract has been designed to stop any illegitimate block changes during a financial transaction. Since every node has a copy of the ledger, so it is very difficult to perform malicious activity. Furthermore, the donator can watch how the money flows in the different transactions and everyone can browse the account history. An evaluative judgment, comparing with various consensus algorithms, has also been presented along with their complex nature. The decentralized approach has eliminated the chance of a single point of failure which in turn makes the system robust. Results: The developed framework for the financial transaction using blockchain has been tested using the Rinkeby Test Network. The generators and campaign contracts have been developed and deployed in the Rinkeby testing network. The results indicate that the computing is much more secure and free from the scam in comparison to the traditional client-server financial transaction system. Conclusion: Finally, the proposed approach suggests scenarios such as in NGOs where the introduced security approach should prove to be adequate.

The two most widely used and easily implementable algorithm for clustering and classification- based analysis of data in the unsupervised learning domain are Density-Based Spatial Clustering of Applications with Noise and K-mean cluster analysis. These two techniques can handle most cases effectively when the data has a lot of randomness with no clear set to use as a parameter as in the case of linear or logistic regression algorithms. However, few papers exist that pit these two against each other in a controlled environment to observe which one reigns supreme and the conditions required for the same. In this paper, a renal adenocarcinoma dataset is analyzed and thereafter both DBSCAN and K-mean are applied on the dataset with subsequent examination of the results. The efficacy of both the techniques in this study is compared and based on them the merits and demerits observed are enumerated. Further, the interaction of t-SNE with the generated clusters are explored.

Background: Customer Segmentation is the process of dividing customers into groups based on some demographic factors in order to get an idea of the targeted audience for a product and to best market said product. Objective: Sentiment Analysis on customer reviews is one way that this process can be enhanced to get not just demographic information but subjective information and preferences as well. Methods: In this study, Long Short-Term Memory model, a deep learning technique, has been applied for Sentiment Analysis and its results have been used to perform Customer Segmentation on demographic data containing information such as age and gender. Segmentation was performed using Spectral Clustering. Cluster Labels were extracted to perform supervised classification using different supervised algorithms, such as Support Vector Machines, Random Forests, Decision Trees and Logistic Regression. Results: An accuracy of 90.9% was achieved by the LSTM model. An accuracy of 100% was achieved by the Random Forest and Decision Tree Classifiers.

Backgroung: Seemingly, in the contemporary era, data is the new currency. Facing the exponential explosion of data through its various online sources, there arises a need for the industry to tap into this source. The art of ascribing sentiment to a piece of text is Sentiment Analysis making it relevant to a wide array of fields. The world has witnessed assortments of a wide family of coronaviruses, 229E and NL63 being the alpha coronaviruses and OC43 & HKU1 being the beta coronaviruses. A version of coronavirus MERS-CoV seemed to be identified in Saudi Arabia. Methods: This work focuses on The Deep Neural Network and Natural Language processing to detect depression in COVID-19 patients, and the model is trained with the depression labeled tagged dataset with an accuracy of 98%. Conclusion: The foundation of this work shall be instrumental in aiding the doctors for the timely diagnosis and treatment of their patients.

Background and Objective: Breast cancer is a leading cause of death worldwide, and its early detection is usually performed with low quality clinical images. Due to unpredictable structure of breast and characterization of cancer, disease in early stages is yet a difficult issue for specialists and analysts. The accurate identification of breast cancer is an important step in its early stage to avoid drastic death rate. With the advancement in the field of medical science, advancements have been created to a phase where the medicinal services industry demonstrates to give best outcomes most precisely. Method: It is observed that the breast cancer images are analyzed after decompression during telecommunications. In this paper, first we aimed to compress malignant cancer images so that it could illuminate the motivation behind the telemedicine by applying preprocessing techniques and second identification, classifications of breast cancer disease depend on segmentation using discrete cosine transformation and discrete wavelet transformation. Result: Segmentation addresses the problem to identify the characteristics of malignant cancer. The segmented image eliminates the false positives, to obtain a clear-segmented image. Segmentation methods are based on a structural approach to isolate the breast edge and a region approach to extract the malignant portion. The result of image quality index achieved the output based on fusion techniques. Conclusion: Because of the unpredictable structure of the breast and low quality of clinical images, a precise discovery, position, and characterization of the disease in early stages are considered a difficult issue for specialists and analysts. The breast cancer could detect and segment if highly efficient image compression is achieved successfully. The conclusion procedure of disease infection is time taking and requires storage capacity limit in computer system. A large number of Magnetic Resonance Imaging techniques were assembled as required and an enormous assortment for each wiped out individual required huge space for capacity just as a wide transmission transfer speed for computer system framework and again additionally for transmission over the web. Our proposed method can be useful for accurate and automatic classification of malignant cells from medical images by the specialist, with a goal that genuine cases would create novel outcomes and improve endurance rates.

Background: Researchers for data hiding using the various encrypting techniques to improve the security of transmission of confidential information through an unsecured channel have been carried out. Methods: In this paper, a new higher recognition Least Significant Bit (LSB) audio data concealment is suggested in this framework. This technique is used to embed the hidden audio into cover audio of the same size. Results: The altered speech file appears as the original carrier file after embedding the secret message. This model strengthens hiding capability and audio quality. Conclusion: The strategy outperforms similar studies by enhancing hiding capability up to 30% and preserving stego audio transparency with the SNR value at 72.2 and SDG at 4.8.

Background: The development of the tire/road friction coefficient measurement and estimation system has far-reaching significance for the active electronic control safety system of automobiles and is one of the core technologies for autonomous driving in the future. Objective: Estimating the road friction coefficient accurately and in real-time has become prominent in research. Researchers have used different tools and proposed different algorithms and patents. These methods are widely used to estimate the road friction coefficient or other related parameters. This paper gives a comprehensive description of the research status in the field of road friction coefficient estimation. Method: According to the current research status of Chinese and foreign scholars in the field of road friction coefficient recognition, the recognition methods are mainly divided into two categories: cause-based and effect-based. Results: This literature review will discuss the existing two types of identification methods (causebased and effect-based) and analyze the applicable characteristics of each algorithm. Conclusion: The two recognition methods are analyzed synthetically, and the development direction of road friction coefficient recognition technology is discussed.

Background: Software-Defined Networks (SDNs) are a new architectural approach to smart centralized control networks that were introduced alongside Open Flow in 2011. SDNs are programmed using software applications that help operators manage the network in a fully consistent and comprehensive way. Centralization in these networks is considered a weakness, especially if it is accessed by a Distributed Denial of Service (DDoS) attack - which is the process of uploading huge floods of various sorts of traffic to a website, from multiple sources, in order to make it and its services inaccessible to users. Methods: In our current research, we will build an SDN through a Mininet virtualization simulator, and by using Python. A DDoS attack will be detected depending on two facts: firstly, Traffic State - which normally sees traffic packets sent at around 30 packets per second (DDoS packets are about 250 packets per second and will completely disrupt the network if the attack persists). Secondly, the number of IP Hits. The method used in the research appears very effective in detecting DDoS, according to the results we have achieved. Results: The proposed performance of the system: The Precision (PREC), Recall (REC), and FMeasure (F1) metrics have been used for assessment. Conclusion: The novelty of the current research lies in the detection of penetration in SDN networks, by calculating the number of hits by the hacker's device and the number of times they enter the main device in the network, in addition to the large amount of data sent by the hacker's device to the network. The experimental results are promising as compared with the datasets like CIC-DoS, CICIDS2017, CSE-CIC-IDS2018, and customized dataset. The results ranged between 90% and 96%.

Background: Pedestrian detection and tracking are an important area of study in realworld applications, such as mobile robots, human-computer interaction, video surveillance, pedestrian protection systems, etc. As a result, it has attracted the interest of the scientific community. Objective: Certainly, tracking people is critical for numerous utility areas which cover unusual situations detection, like vicinity evaluation, and sometimes change direction in human gait and partial occlusions. Researchers' primary focus is to develop a surveillance system that can work in a dynamic environment, but there are major issues and challenges involved in designing such systems. So, it has become a significant issue and challenge to design a tracking system that can be more suitable for such situations. To this end, this paper presents a comparative evaluation of the tracking-by-detection system along with the publicly available pedestrian benchmark databases. Method: Unlike recent works where person detection and tracking are usually treated separately, our work explores the joint use of the popular Simple Online and Real-time Tracking (SORT) method and the relevant visual detectors. Consequently, the choice of the detector is an important factor in the evaluation of the system's performance. Results: Experimental results demonstrate that the performance of the tracking-by-detection system is closely related to the optimal selection of the detector and should be required prior to a rigorous evaluation. Conclusion: The study demonstrates how sensitive the system performance as a whole is to the challenges of the dataset. Furthermore, the efficiency of the detector and the detector-tracker combination is also depending on the dataset.