Recent Advances in Computer Science and Communications - Volume 14, Issue 9, 2021

Background: At present, financial Credit Scoring (CS) is considered as one of the hottest research topics in finance domain, which assists in determining the credit value of individual persons as well as organizations. Data mining approaches are found to be useful in banking sectors, which assist them in designing and developing proper products or services to the customer with minimal risks. Credit risks are linked to loss and loan defaults, which are the main source of risks that exist in the banking sector. Aim: The current research article aims at presenting an effective credit score prediction model for banking sector which can assist them to foresee the credible customers, who have applied for loan. Methods: An optimal Deep Neural Network (DNN)-based framework is employed for credit score data classification using Stacked Autoencoders (SA). Here, SA is applied to extract the features from the dataset. These features are then classified using SoftMax layer. Besides, the network is also tuned Truncated Backpropagation Through Time (TBPTT) model in a supervised way using the training dataset. Results: The proposed model was tested using a benchmark German credit dataset, which includes the necessary variables to determine the credit score of a loan applicant. The presented SADNN model achieved the maximum classification while the model attained high accuracy rate of 96.10%, F-score of 97.25% and kappa value of 90.52%. Conclusion: The experimental results pointed out that a maximum classification performance was attained by the proposed model on all different aspects. The proposed method helped in determining the capability of a borrower in repaying the loan and computing the credit risks properly.

Background: As a known keyphrase extraction algorithm, TextRank is an analog of the PageRank algorithm, which relies heavily on the statistics of term frequency in the manner of cooccurrence analysis. Objective: The frequency-based characteristic made it a bottleneck for performance enhancement, and various improved TextRank algorithms were proposed in recent years. Most of the improvements incorporated semantic information into the keyphrase extraction algorithm and achieved improvement. Method: In this research, taking both syntactic and semantic information into consideration, we integrated syntactic tree algorithm and word embedding and put forward an algorithm of Word Embedding and Syntactic Information Algorithm (WESIA), which improved the accuracy of the TextRank algorithm. Results: By applying our method on a self-made test set and a public test set, the result implied that the proposed unsupervised keyphrase extraction algorithm outperformed the other algorithms to some extent.

Background: Nowadays, information security is one of the most significant issues of social networks. The multimedia data can be tampered with, and the attackers can then claim its ownership. Image watermarking is a technique that is used for copyright protection and authentication of multimedia. Objective: We aim to create a new and more robust image watermarking technique to prevent illegal copying, editing and distribution of media. Method: The watermarking technique proposed in this paper is non-blind and employs Lifting Wavelet Transform on the cover image to decompose the image into four coefficient matrices. Then Discrete Cosine Transform is applied which separates a selected coefficient matrix into different frequencies and later Singular Value Decomposition is applied. Singular Value Decomposition is also applied to the watermarking image and it is added to the singular matrix of the cover image, which is then normalized, followed by the inverse Singular Value Decomposition, inverse Discrete Cosine Transform and inverse Lifting Wavelet Transform respectively to obtain an embedded image. Normalization is proposed as an alternative to the traditional scaling factor. Results: Our technique is tested against attacks like rotation, resizing, cropping, noise addition and filtering. The performance comparison is evaluated based on Peak Signal to Noise Ratio, Structural Similarity Index Measure, and Normalized Cross-Correlation. Conclusion: The experimental results prove that the proposed method performs better than other state-of-the-art techniques and can be used to protect multimedia ownership.

Introduction: The notion of electronic voting has evolved over a period of time, replacing the traditional system, which was based on paper ballots. Several types of electronic voting systems exist, still the implementation is partial and there is a scope for improvement for making it more secure and user-friendly. Method In this paper, a proof-of-concept is presented which aims to address the issues and challenges in the electoral system by using the concept of Ethereum blockchain and smart contracts. Result: These electronic electoral processes propose a centralized solution that can be easily tampered, thus increasing the problem of distrust in the citizens. To overcome this, blockchain technology can be used for implementing mobile-based electronic voting system. Blockchain technology is aiding in the development of novel digital services that are more secure and reliable. Discussion: The main objective of this paper is to depict how a feasible, secure, and reliable mobile voting system can be built by implementing the concept of blockchain and smart contracts. Conclusion: The issue of security and transparency in the voting system can be addressed using blockchain technology. The present study aims to fulfill these gaps partially by providing use-case for the voting process, which is based on mobile and blockchain technology.

Background: In the new era of wireless communications new challenges emerge including the provision of various services over the digital television network. In particular, such services become more important when referring to the tele-medical applications through terrestrial Digital Video Broadcasting (DVB). Objective: One of the most significant aspects of video broadcasting is the quality and information content of data. Towards that end, several algorithms have been proposed for image processing in order to achieve the most convenient data compression. Methods: Given that medical video and data are highly demanding in terms of resources it is imperative to find methods and algorithms that will facilitate medical data transmission with ordinary infrastructure such as DVB. Results: In the present work we have utilized a quantization algorithm for data compression and we have attempted to transform video signal in such a way that would transmit information and data with a minimum loss in quality and succeed a near maximum End-user approval. Conclusions: Such approaches are proven to be of great significance in emergency handling situations, which also include health care and emergency care applications.

Background: According to the WHO report, around 4.07% of the world's population is visually impaired. About 90% of the visually impaired users live in the lower economic strata. In the fast technological era, most of the inventions miss the need of these people. Mainly the technologies are designed for mainstream people; visually impaired people are always unable to access it. This inability arises primarily for reasons such as cost, for example, Perkins Brailler costs 80-248 dollars for the simple purpose of Braille input. Another major reason is the hassle of carrying the big equipment. Objective: Keeping all this in mind and making technology available to their doors, MAGIC-1 has been designed. The goal is to provide a solution in terms of an application, which helps the visually impaired people in their daily life activities. Method: The proposed solution assists visually impaired users through smartphone technology. If visually impaired users ever wished to have a touched guide in a smartphone, MAGIC-1 has the solution that consolidates all the important features related to their daily activities. Results: The performance of the proposed technology as a whole and its individual features in terms of usability, utility and other metrics, etc. have been tested based on a sample of visually impaired users. Moreover, performances in term of Errors per Word and Words per Minute have been observed. Conclusion: MAGIC-I, the proposed solution, works as an assistant of visually impaired users to overcome their daily struggles and let them stay more connected to the world. A visually impaired user can communicate via their mobile devices with features like eyes free texting using braille, voice calling, etc. They can easily take help in an emergency situation with the options of SOS emergency calling and video assistance.

Background: Wireless Sensor Network (WSN) is an arising field for research and development. It has various applications ranging from environmental monitoring to battlefield surveillance and more. WSN is a collection of multiple sensor nodes used for sensing the environment. But these sensing nodes are deployed in such areas where it is not that easy to reach, therefore, the battery used in these nodes becomes quite impossible to change, hence there is a need to utilize this energy to get the maximum sensing for a long time. Objective: To use the Fuzzy approach in the clustering algorithm. Clustering is a key approach to prolong the network lifetime with minimum energy utilization. In this paper, the focus is on the Cluster Head (CH) selection. So, we are proposing a clustering algorithm which is based on some of the attributes, including Average Residual Energy of CHs, Average Distance from nodes to CHs, Standard Deviation of member nodes, and Average Distance from CH to Base Station(BS). Methods: Initially, some of the nodes are found to have greater residual energy than the average network energy, and fifteen populations are made, each having an optimum number of CHs. The final and best CHs set is chosen by determining the maximum fitness value using a fuzzy approach. Result: The result positively supports the energy-efficient utilization with lifetime maximization, which is compared with the Base algorithm [1] and LEACH [2] protocol based on residual energy and the number of nodes that die after performing some rounds. Conclusion: The proposed algorithm determines a fuzzy-based fitness value, provides loadbalancing among all the networking nodes, and performs a selection of best Cluster Heads, resulting in prolonged network lifetime and maximized efficiency.

Introduction: Mobile Robot is a kind of robot system consisting of sensors, remote control operators and automatic control mobile carriers. It is a product of the integrated application of integrated disciplines developed in recent years. In the research of mobile robot-related technology, navigation technology is its core, and path planning is an important link and subject of navigation research. Objective: An improved firefly algorithm is proposed for path planning of Mobile Robots in this paper. Methods: In this paper, an improved firefly algorithm is proposed. Compared with the traditional firefly algorithm, this algorithm has three main improvements: (1) using Sobol sequence to initialize population; (2) adding a dynamic disturbance coefficient to enhance the global search ability of the algorithm; (3) considering the uncertainty of search, the attraction between individuals is strong. Fuzzy control is carried out by setting the membership function. Results: The new algorithm takes advantage of the uniformity of Sobol sequence sampling and starts to optimize in a wider range, which makes the initial path of the algorithm longer, but because the new algorithm introduces the dynamic disturbance coefficient and the fuzzy control strategy, the average running time is shorter. Conclusion: In the simulation experiment of the mobile robot path planning problem, the improved firefly algorithm proposed in this paper is easier to jump out of local optimum than the traditional firefly algorithm and has a more robust search ability. Discussion: It is obvious from the graph that in 100 iterations, the FaFA algorithm takes advantage of the uniformity of Sobol sequence sampling and starts to optimize in a wider range, which makes the initial path of the algorithm longer, but because the FaFA algorithm introduces the dynamic disturbance coefficient and the fuzzy control strategy, it makes the algorithm able.

Background: As an important branch of computer vision, visual measurement is a fast developing cutting-edge technology, which has been widely used in the manufacturing field. In recent years, the visual measurement of feature size of probes through small IC probes has aroused wide concern. Objective: This study aims to take small shaft parts as the research object in order to provide a full set of novel and reliable technical means for the three-dimension measurement of mechanical parts. Methods: Firstly, the trinocular vision measurement system based on the curved cantilever mechanism was designed and constructed. Secondly, the measurement system was used to collect the part images from different angles, and the images derived from the four categories of segmentation algorithms such as threshold-based, region-based segmentation algorithm were compared and analyzed. Lazy Snapping image segmentation algorithm was used to extract the foreground parts of each image. After comparing and analyzing SfM-based algorithm and Visual Hull-based algorithm, the SfM-based algorithm was adopted to reconstruct the 3D morphology of the parts. The measurement of the relevant dimensions was performed. Results: The results show that Lazy Snapping's human-computer interaction brush function improves the accuracy and stability of image segmentation of different algorithms, such as threshold value method, regional method, Grab Cut, and Dense Cut. The SfM-based 3D reconstruction algorithm is of high robustness and fast speed. Conclusion: This study provides an effective method for measuring small mechanical parts, which will shorten the measurement cycle, improve the measurement speed, and reduce the measurement cost.

Introduction: In this paper, we address the issue of network connectivity inside an airplane. Around several thousand feet above the earth’s surface, where ground-based infrastructure failed to provide an internet connection, we proposed a solution to integrate Network Mobility Basic support (NEMO-BSP) protocol with Low Earth Orbit (LEO) constellations system. Discussion: Right now, passengers of flight are forced to interact with the flight’s pre-recorded entertainment system. Most of the airlines do not allow passengers to use the internet or any other type of interaction medium with the ground while during the flight. They force passengers to even switch their mobile to the flight mode so that there is no active communication between a passenger and the remaining world. Method: This paper investigates four different possible scenarios of relative movement of flight and satellite constellations. All four possible scenarios simulated in Network Simulator 2 (NS-2). Result: Results were discussed with respect to the network performance perspective. Parameters like an end-to-end delay, jitter, throughput, and other such parameters were obtained and discussed in detail. Conclusion: This paper proposes a method to deal with the internet connection issue of flights. The proposed system of LEO satellite and NEMO-BSP protocol works efficiently in the simulation study.