- All articles 732
-
International Journal of Information Engineering and Electronic Business @ijieeb
Journal articles - International Journal of Information Engineering and Electronic Business
All articles: 732
Sentence Clustering Using Parts-of-Speech
Scientific article
Clustering algorithms are used in many Natural Language Processing (NLP) tasks. They have proven to be popular and effective tools to use to discover groups of similar linguistic items. In this exploratory paper, we propose a new clustering algorithm to automatically cluster together similar sentences based on the sentences’ part-of-speech syntax. The algorithm generates and merges together the clusters using a syntactic similarity metric based on a hierarchical organization of the parts-of-speech. We demonstrate the features of this algorithm by implementing it in a question type classification system, in order to determine the positive or negative impact of different changes to the algorithm.
Free
Sentiment Analysis of Review Datasets Using Naïve Bayes' and K-NN Classifier
Scientific article
The advent of Web 2.0 has led to an increase in the amount of sentimental content available in the Web. Such content is often found in social media web sites in the form of movie or product reviews, user comments, testimonials, messages in discussion forums etc. Timely discovery of the sentimental or opinionated web content has a number of advantages, the most important of all being monetization. Understanding of the sentiments of human masses towards different entities and products enables better services for contextual advertisements, recommendation systems and analysis of market trends. The focus of our project is sentiment focussed web crawling framework to facilitate the quick discovery of sentimental contents of movie reviews and hotel reviews and analysis of the same. We use statistical methods to capture elements of subjective style and the sentence polarity. The paper elaborately discusses two supervised machine learning algorithms: K-Nearest Neighbour(K-NN) and Naïve Bayes' and compares their overall accuracy, precisions as well as recall values. It was seen that in case of movie reviews Naïve Bayes' gave far better results than K-NN but for hotel reviews these algorithms gave lesser, almost same accuracies.
Free
Shape Design of Lifting body Based on Genetic Algorithm
Scientific article
This paper briefly introduces the concept and history of lifting body, and puts forward a new method for the optimization of lifting body. This method has drawn lessons from the die line design of airplane is used to parametric numerical modeling for the lifting body, and extract the characterization of shape parameters as design variables, a combination of lifting body reentry vehicle aerodynamic conditions, aerodynamic heating, volumetric Rate and the stability of performance. Multi-objective hybrid genetic algorithm is adopted to complete the aerodynamic shape optimization and design of hypersonic lifting body vehicle when under more variable and constrained condition in order to obtain the Pareto optimal solution of Common Aero Vehicle shape.
Free
Simulation and Optimization of VHDL code for FPGA-Based Design using Simulink
Scientific article
Simulations and prototyping have been a very important part of the electronics industry since a very long time. In recent years, FPGA's have become increasingly important and have found their way into all kind of digital system design This paper presents a novel, easy and efficient approach of implementation and verification of VHDL code using Simulink and then to regenerate the optimized VHDL code again using Simulink. The VHDL code written for the complicated digital design of 32-bit floating point arithmetic unit has been synthesized on Xilinx, verified and simulated on Simulink. The same VHDL code in Modelsim was optimized using this approach and the optimized code so generated by Simulinkhas also been synthesized to compare the results. Power dissipations for both synthesized designs using Xilinx Power Estimator were also extracted for comparison.
Free
Simulation of electric power plant performance using Excel®-VBA
Scientific article
This paper presents the failure and repair simulation for electric power house with N Turbo-alternator, where N may be up to 32. The program employs a pseudo-random number generator for individual power plant that can be described by exponential probability density functions. The resulting sequences of failure and repair events are then combined for the plants to give scenarios for different time horizons. The implementation in Excel®-VBA includes an appropriately designed userform containing the macro Active-X control for input of relevant information. The result shows that as the number of samples increased the behavior of the random events better represented the desired form with a correlation of almost 99% for 25 trials. This corresponds to a confidence interval of better than 95% and hence should be used as the median for practical applications. The results were tested and the distributions of the events were found to be close approximation of the target exponential distributions.
Free
Scientific article
This paper presents a customized application in term of LCD interfacing through soft-core microcontroller by implementing its control circuitry in FPGA. Therefore optimum efficiency is achieved. This provide the single chip solution by replacing conventional model which contain separate microcontroller circuit, therefore the efficient resource utilization of FPGA is made, day by day as an increase in the complexity of Embedded system design thus gives many advantages over conventional designed processors such as platform independence, less cost, flexibility and greater immunity to obsolescence.
Free
Scientific article
Remote sensing images are complex, which makes it difficult to interpret and generate semantically appropriate textual description. To get a semantically relevant description, it is important to identify complex objects and understand the contextual relationships between them. In such cases, deriving contextually accurate information while maintaining semantic coherence is challenging. Therefore, a specifically designed model architecture is required to generate semantically relevant descriptions. This paper discusses a deep learning-based approach to generate remote sensing image descriptions using an end-to-end encoder-decoder model with soft attention. The UC Merced (UCM) dataset is used for training, which includes multiple captions per image capturing various scene aspects. To further assess the robustness and generalizability of the proposed approach, its performance is additionally evaluated on more complex datasets such as RSCID and Sydney Captions. This study presents an end-to-end CNN–LSTM encoder–decoder framework enhanced with soft attention for semantic description generation from remote sensing imagery. The framework employs a VGG16 encoder to extract a 4096-dimensional visual feature vector, which is projected into a 256-dimensional representation and processed by a 256-unit LSTM decoder. The soft attention mechanism dynamically computes attention weights using the encoder features and decoder hidden state, enabling the model to emphasize relevant visual information during word generation. Multiple CNN encoders and learning rates are evaluated with LSTM decoders, both with and without attention, on the UCM, RSCID, and Sydney Caption datasets. At a learning rate of 0.0001, VGG16–LSTM with soft attention achieves BLEU-4 (B4) scores of 0.6636, 0.6636, and 0.5864 on the UCM, RSCID, and Sydney Caption datasets, respectively, compared with 0.1643, 0.1647, and 0.1745 for VGG16–LSTM without attention. The results demonstrate that soft attention substantially improves description generation by strengthening visual–linguistic alignment and enabling more contextually relevant and semantically coherent descriptions across datasets with varying scene complexity.
Free
Software Module Clustering Using Hybrid Socio-Evolutionary Algorithms
Scientific article
Design of the software system plays a crucial role in the effective and efficient maintenance of the software system. In the absence of original design structure it might be required to re-identify the design by using the source code of the concerned software. Software clustering is one of the powerful techniques which could be used to cluster large software systems into smaller manageable subsystems containing modules of similar features. This paper examines the use of novel evolutionary imperialist competitive algorithms, genetic algorithms and their combinations for software clustering. Apparently, recursive application of these algorithms result in the best performance in terms of quality of clusters, number of epochs required for convergence and standard deviation obtained by repeated application of these algorithms.
Free
Software Quality Appraisal Using Multi-Criteria Decision Approach
Scientific article
Software quality measurement is the key factor in the development of any software system. Various software quality models are devised to measure the performance of a software system, which consists of numerous quality parameters on the basis of which software are quantified. Different types of software quality models are already present like an ISO/IEC9126 Quality model, Boehm's model, McCall's model, etc. In this paper, an attempt has been made to increase the quality of a software system by introducing some new quality parameters in ISO/IEC9126 model. Since the quality parameters are very unpredictable in nature, so as to evaluate the performance of quality parameters, the fuzzy multi criteria approach has been used.
Free
Solving the Problem of Pre-Selection of Personnel Based on Fuzzy Sets
Scientific article
The article proposes a method for clarifying the degree of correspondence between the request of a company looking for a specialist for a vacant position and the request of an applicant. As practice shows, the requirements in the requests of companies and the requests of applicants are linguistic, using vague boundaries of compliance parameters. Based on the results of a survey of graduate students and representatives of potential employer companies conducted by the author of the work, the company’s image, its experience in the market, and a decent salary are significant for graduates. For potential employers, applicants with some experience in the branch and low financial expectations are substantial first of all. Thus, from the statements of both sides, the author managed to identify two linguistic variables: “Time” and “Salary level.” These variables are applied to identify correlations between requests at the preliminary stage of staff selection. Indirect methods, namely methods of statistical data and expert assessments, were used in the variable membership functions. The algorithm for detecting matches is noticeably simple and can be in almost any table processor, which expands the field of the proposed approach. The recruitment agency acts as an intermediary in recruitment. The algorithm for identifying compliance in its activities will significantly reduce recruiters’ time and labor costs.
Free
Some Results on Optimal Dividend Problem in Two Risk Models
Scientific article
The compound Poisson risk model and the compound Poisson risk model perturbed by diffusion are considered in the presence of a dividend barrier with solvency constraints. Moreover, it extends the known result due to [1]. Ref. [1] finds the optimal dividend policy is of a barrier type for a jump-diffusion model with exponentially distributed jumps. In this paper, it turns out that there can be two different solutions depending on the model’s parameters. Furthermore, an interesting result is given: the proportional transaction cost has no effect on the dividend barrier. The objective of the corporation is to maximize the cumulative expected discounted dividends payout with solvency constraints before the time of ruin. It is well known that under some reasonable assumptions, optimal dividend strategy is a barrier strategy, i.e., there is a level b_{1}(b_{2}) so that whenever surplus goes above the level b_{1}(b_{2}), the excess is paid out as dividends. However, the optimal level b_{1}(b_{2}) may be unacceptably low from a solvency point of view. Therefore, some constraints should imposed on an insurance company such as to pay out dividends unless the surplus has reached a level b^{1}_{c}>b_{1}(b^2_{c}>b_{2}) . We show that in this case a barrier strategy at b^{1}_{c}(b^2_{c}) is optimal.
Free
SourceViz: A Tool for Supporting Software Metrics Visualization
Scientific article
Maintaining and understanding large software systems is a complex and time consuming process. Understanding the internal structure of such systems is not an easy task due to the invisible nature of software. Source Code Visualization, i.e. measuring the code metrics and then visualizing them, provides an efficient solution to this problem. There are many tools available which gives an insight to the internal structure of the software. But all of them don't provide visualizations of hierarchical relationships and code complexity of the source code. In this paper, we present a tool named "SourceViz". This application computes different software metrics, code complexity, class-relations and then visualizes the calculated metrics in different metaphors. This visual analysis assists the project managers and software developers in understanding the static structure of the software by presenting project-level as well as class-level view.
Free
Spatio-temporal Dynamic Evolution and Inhibiting Factor Analysis of TFEE in the CCTC Economic Circle
Scientific article
Accounting for 30.8% of the total economic volume of the western region by 2021, the "fourth pole" of China's economic development is progressively being established as the Chengdu-Chongqing twin-city(CCTC) Zone. Therefore, increasing Total Factor Energy Efficiency (TFEE) and reducing the disparities in energy efficiency amongst cities in the area are important for the economic development of the CCTC Economic Zone. Accordingly, this study employs an output-oriented, super-efficient DEA model with constant returns to scale to measure the total factor energy efficiency of 16 prefecture-level cities in the CCTC economic circle from 2006 to 2020. It also examines the spatial distribution and variation patterns of each city's prefecture-level total factor energy efficiency. Then, spatial autocorrelation and random forest were used to explore the interrelationship among the indicators of the drivers, and the variables were screened according to Gini importance, finally, PCA-GWR models and spatial panel regression models were constructed to dissect the key drivers. The empirical findings indicate that: (1) the average energy efficiency of Chongqing and Chengdu is only 0.708 and 0.788, and the overall efficiency shows a steady increase from 2009 to 2018. (2) The spatial distribution is mainly as follows: H-H agglomerations are distributed in the northeastern cities of the CCTC Economic Zone, L-L agglomerations are distributed in the south, H-L agglomerations and L-H agglomerations are distributed in the north-central part of Chengdu-Chongqing Economic Zone. (3) Industrial structure, population structure, and governmental behavior have significant effects on energy efficiency, with a population mortality rate as the inhibiting factor and the proportion of tertiary industry and policy behavior as the contributing factors. Based on the empirical findings, it is recommended to accelerate the industrial structure adjustment, implement the CCTC economic circle's core cities' target of energy-saving, and build a "community" bridge to improve energy efficiency and promote economic development.
Free
Scientific article
Spectrum sensing is an important task in cognitive radio (CR). Matched filter technique one of the techniques employed for spectrum sensing in cognitive radio which faces the challenge of low frequency offset tolerance in very low SNR environments. Hybrid matched filter architecture is used to improve this frequency offset tolerance. But, overall even such kind of architecture results in coarse detection. In very low SNR environments, where primary user is highly mobile, the multipath profile results in unknown phase of signal. Such kind of signal cannot even be detected by Hybrid Matched Filter. In this paper we propose combination of Hybrid Matched Filter and Single Cycle Cyclostationary Feature Detector to enhance the detection of such architecture. This results in both high frequency offset tolerance as well as fine detection of signal with unknown phase in very low SNR environments. Simulation results show significant improvement in the probability of detection and false alarm of the proposed scheme over Hybrid Matched Filter.
Free
Speech Compression Based on Discrete Walsh Hadamard Transform
Scientific article
This paper presents a new lossy compression algorithm for stationary signal based on Discrete Walsh Hadamard Transform (DWHT). The principle of compression algorithm consists in framing the original speech signal into stationary frames and applying the DWHT. Then, the obtained coefficients are thresholded in order to truncate all coefficients below a given thresholds values. Compression is achieved by efficient encoding of the string values of zeros. A comparative study of performance between the algorithms based on DWHT and Discrete Wavelet Transform (DWT) is performed in terms of some objective criteria: compression ratio (CR), signal to noise ratio, peak signal to noise ratio (SNR), normalized root mean square error (NRMSE) and CPU time. The simulation results show that the algorithm based on DWHT is characterized by a very low complexity implementation and improved CR, SNR, PSNR and NRMSE compared to the DWT algorithm and this for stationary frame.
Free
Spelling Error Patterns in Typed Yorùbá Text Documents
Scientific article
While writing in most of the world’s major languages have a long history, Yorùbá is a relatively young language as far as writing it down is concerned. It is therefore an under-resourced language as far as tools for processing it in digital format is concerned. Spell checking is one of these tools. An analysis of the spelling error pattern is fundamental to the task of producing a good spell checker. We addressed this challenge in this article and our findings showed that spelling error pattern in Yorùbá followed that of other languages in general. There were, however, obvious departure from the norms in the specific. Diacritic-related misspelling accounted for more than 80% of all errors and words with single edit error were less than the generally expected minimum threshold of 80%. In addition, most of the errors were vowel-related with consonants accounting for less than 15% of all errors. Word-length does not seem to have any direct bearing on number of errors in a word. The research showed that the impact of diacritics on spelling error is more in Yorùbá where diacritics are majorly used for tone marking where it accounts for more than 80% of spelling errors than in languages like Brazilian Portuguese and Spanish where diacritics are used for differentiating characters where spelling error due to diacritics covered less than 60% of all errors. We thus conclude that while, to a significant extent, the character set used in a language determines distribution of spelling error, the purpose to which diacritics is employed in language also affect the distribution of spelling error in a language.
Free
State Of The Art: A Study of Human-Robot Interaction in Healthcare
Scientific article
In general, the applications of robots have shifted rapidly from industrial uses to social uses. This provides robots with the ability to naturally interact with human beings and socially fit into the human environment. The deployment of social robots in the healthcare system is becoming extensive as a result of the shortage of healthcare professionals, rising costs of healthcare and the exponential growth in the number of vulnerable populations such as the sick, the aged and children with developmental disabilities. Consequently, social robots are used in healthcare for providing health education and entertainment for patients in the hospital and for providing aids for the sick and aged. They are also used for dispensing drugs and providing rehabilitation as well as emotional and aging care. Hence, social robots improve the efficiency and quality of healthcare services. The interaction between social robots and human beings is known as human-robot interaction. Human-robot interaction in healthcare is faced with numerous challenges such as the fear of displacement of caregivers by robots, safety, usefulness, acceptability as well as appropriateness. These challenges ultimately lead to a low rate of acceptance of the robotic technology. Consequently, this paper extensively appraises human-robot interaction in healthcare, their applications and challenges. Design, ethical and usability issues such as privacy, trust, safety, users' attitude, culture, robot morphology as well as emotions and deception arising from the interaction between humans and robots in healthcare are also reviewed in this paper.
Free
Statistical Analysis of Resulting Palm vein Image through Enhancement Operations
Scientific article
Nowadays biometric is playing a key role in the field of forensic and commercial applications. The vein biometrics is a robust biometric in recent trends.The vein pattern is very difficult to forge or fake. The traits are not going to be changed from birth to death. This paper discusses image enhancement operations and its result when applied on multispectral palm vein image. The image enhancement operations are much helpful to extract the vein patternas features.The experiments can be used to highlight or trace a vein pattern lies at palm region of hand. The proposed work gains vein pattern and considered as the stepping stone towards feature extraction. The paperalso discusses the comparison of statistical properties such as mean, standard deviation and coefficient of original image and images resulting out through enhancement operations. The enhancement operation is a key to gain the vein pattern. The image analysis can be framed well usingstatistical image measurements.
Free
Statistical analysis on result prediction in chess
Scientific article
In this paper, authors have proposed a technique which uses the existing database of chess games and machine learning algorithms to predict the game results. Authors have also developed various relationships among different combinations of attributes like half-moves, move sequence, chess engine evaluated score, opening sequence and the game result. The database of 10,000 actual chess games, imported and processed using Shane’s Chess Information Database (SCID), is annotated with evaluation score for each half-move using Stockfish chess engine running constantly on depth 17. This provided us with a total of 8,40,289 board evaluations. The idea is to make the Multi-Variate Linear Regression algorithm learn from these evaluation scores for same sequence of opening moves and game outcome, then using it to calculate the winning score of a side for each possible move and thus suggesting the move with highest score. The output is also tested with including move details. Game attributes are also classified into classes. Using Naïve Bayes classification, the data result is classified into three classes namely move preferable to white, black or a tie and then the data is validated on 20% of the dataset to determine accuracies for different combinations of considered attributes.
Free
Study of Response Time in Cloud Computing
Scientific article
Performance of a cloud is a critical issue and dependent on various factors that include load balancing used to distribute the load at data center. Proliferation of the cloud paradigm is profoundly dependent on the performance of the cloud. Therefore, to examine the cloud performance, it is significant to identify the factors that govern cloud performance. This work is focused to identify the factors that may have significant impact on the cloud performance. To identify the performance factors, we have reviewed the major publications of the last five years as well as the major real time cloud performance tools offered. Study revealed that response time is the major factor that has the significant impact on cloud computing performance. Finally, we have conducted an experiment to establish the dependency of response time on various load balancing techniques and number of data center. Experiment revealed that the round robin is directly proportional to the number of data center
Free
