Abstract: Twitter is one of the most popular social media platforms where users share their opinions on different subjects. Twitter can be considered a great source for mining text due to the high volumes of data generated through the platform daily. Many industries such as telecommunication companies can leverage the availability of Twitter data to better understand their markets and make an appropriate business decision. This study performs topic modeling on Twitter data using Latent Dirichlet Allocation (LDA). The obtained results are benchmarked with another topic modeling technique, Latent Semantic Indexing (LSI). The study aims to retrieve topics on a Twitter dataset containing user tweets on South African Telcos. Results from this study show that LSI is much faster than LDA. However, LDA yields better results with higher topic coherence by 8% for the best-performing model in this experiment. A higher topic coherence score indicates better performance of the model.
Abstract: This paper presents a multi population Differential Evolution (DE) with adaptive mutation and local search for global optimization, named AMMADE in order to better coordinate the cooperation between the populations and the rational use of resources. In AMMADE, the population is divided based on the Euclidean distance sorting method at each generation to appropriately coordinate the cooperation between subpopulations and the usage of resources, such that the best-performed subpopulation will get more computing resources in the next generation. Further, an adaptive local search strategy is employed on the best-performed subpopulation to achieve a balanced search. The proposed algorithm has been tested by solving optimization problems taken from CEC2014 benchmark problems. Experimental results show that our algorithm can achieve a competitive or better result than related methods. The results also confirm the significance of devised strategies in the proposed algorithm.
Abstract: In the current context, the engineering program educators need to think about how to develop the concepts and complex engineering problem-solving skills through various complex engineering activities by the undergraduate engineering students in various engineering courses. But most of them are facing challenges to assess and evaluate these skills of their students. In this study, detailed assessment and evaluation methods for the undergraduate Electrical and Electronic Engineering (EEE) program are stated using the Outcome-Based Education (OBE) approach. For this purpose, a final year course titled control systems has been selected. The assessment and evaluation approach, course contents, course objectives, course outcomes (COs), and their mapping to the program outcomes (POs) with complex engineering problems and activities via the knowledge profiles, performance indicators, rubrics of assessment, CO and PO attainment data, and other statistics, are reported for a student-cohort of control systems course registered by the students of BSc in EEE program in Spring 2021 Semester at the EEE Department of Southeast University (SEU). It is found that the target benchmark was achieved by the students of that course. Several recommendations for the continuous quality improvement (CQI) process are also provided.
Abstract: Large amounts of data on the web can provide valuable information. For example, product reviews help business owners measure customer satisfaction. Sentiment analysis classifies texts into two polarities: positive and negative. This paper examines movie reviews and tweets using a new term weighting scheme, called one-over-sigma (1/sigma), on benchmark datasets for sentiment classification. The proposed method aims to improve the performance of sentiment classification. The results show that 1/sigma is more accurate than the popular term weighting schemes. In order to verify if the entropy reflects the discriminating power of terms, we report a comparison of entropy values for different term weighting schemes.
Abstract: Kernelized Correlation Filter (KCF) based trackers have gained a lot of attention recently because of their accuracy and fast calculation speed. However, this algorithm is not robust in cases where the object is lost by a sudden change of direction, being obscured or going out of view. In order to improve KCF performance in long-term tracking, this paper proposes an anomaly detection method for target loss warning by analyzing the response map of each frame, and a classification algorithm for reliable target re-locating mechanism by using Random fern. Being tested with Visual Tracker Benchmark and Visual Object Tracking datasets, the experimental results indicated that the precision and success rate of the proposed algorithm were 2.92 and 2.61 times higher than that of the original KCF algorithm, respectively. Moreover, the proposed tracker handles occlusion better than many state-of-the-art long-term tracking methods while running at 60 frames per second.
Abstract: Detecting subjectively biased statements is a vital task. This is because this kind of bias, when present in the text or other forms of information dissemination media such as news, social media, scientific texts, and encyclopedias, can weaken trust in the information and stir conflicts amongst consumers. Subjective bias detection is also critical for many Natural Language Processing (NLP) tasks like sentiment analysis, opinion identification, and bias neutralization. Having a system that can adequately detect subjectivity in text will boost research in the above-mentioned areas significantly. It can also come in handy for platforms like Wikipedia, where the use of neutral language is of importance. The goal of this work is to identify the subjectively biased language in text on a sentence level. With machine learning, we can solve complex AI problems, making it a good fit for the problem of subjective bias detection. A key step in this approach is to train a classifier based on BERT (Bidirectional Encoder Representations from Transformers) as upstream model. BERT by itself can be used as a classifier; however, in this study, we use BERT as data preprocessor as well as an embedding generator for a Bi-LSTM (Bidirectional Long Short-Term Memory) network incorporated with attention mechanism. This approach produces a deeper and better classifier. We evaluate the effectiveness of our model using the Wiki Neutrality Corpus (WNC), which was compiled from Wikipedia edits that removed various biased instances from sentences as a benchmark dataset, with which we also compare our model to existing approaches. Experimental analysis indicates an improved performance, as our model achieved state-of-the-art accuracy in detecting subjective bias. This study focuses on the English language, but the model can be fine-tuned to accommodate other languages.
Abstract: At present, it is an imperative and stimulating task to grow the concepts and skills of undergraduate students in any course. Educators must build up students' higher-order complex and critical thinking abilities. But many of them find it difficult to assess and evaluate these abilities of students who undertake their courses during undergraduate studies. In this research work, a simple assessment and evaluation process for the electrical circuit course of the undergraduate Electrical and Electronic Engineering (EEE) program is reported using the Outcome-Based Education (OBE) approach. The methodology of the work, course contents design, course outcomes (COs) preparation and mapping it with program outcomes (POs), question setting following Bloom's taxonomy, assessment strategy of the students, CO and PO evaluation records, statistics, and charts have been reported for a student-cohort of electrical circuit course taken in Spring 2019 Semester at EEE Department of Southeast University (SEU). It is found that the benchmark fixed by the course instructor has been achieved by the students of that course through CO assessment and evaluation. Recommendations of the course teacher for further quality enhancement based on CO achievement are also presented.
Abstract: Bayesian Network (BN) is one of the most efficient classification methods. It is widely used in several fields (i.e., medical diagnostics, risk analysis, bioinformatics research). The BN is defined as a probabilistic graphical model that represents a formalism for reasoning under uncertainty. This classification method has a high-performance rate in the extraction of new knowledge from data. The construction of this model consists of two phases for structure learning and parameter learning. For solving this problem, the K2 algorithm is one of the representative data-driven algorithms, which is based on score and search approach. In addition, the integration of the expert's knowledge in the structure learning process allows the obtainment of the highest accuracy. In this paper, we propose a hybrid approach combining the improvement of the K2 algorithm called K2 algorithm for Parents and Children search (K2PC) and the expert-driven method for learning the structure of BN. The evaluation of the experimental results, using the well-known benchmarks, proves that our K2PC algorithm has better performance in terms of correct structure detection. The real application of our model shows its efficiency in the analysis of the phosphate laundry effluents' impact on the watershed in the Gafsa area (southwestern Tunisia).
Abstract: Cold-start is a notoriously difficult problem which
can occur in recommendation systems, and arises when there is
insufficient information to draw inferences for users or items. To
address this challenge, a contextual bandit algorithm – the Fast
Approximate Bayesian Contextual Cold Start Learning algorithm
(FAB-COST) – is proposed, which is designed to provide improved
accuracy compared to the traditionally used Laplace approximation
in the logistic contextual bandit, while controlling both algorithmic
complexity and computational cost. To this end, FAB-COST uses
a combination of two moment projection variational methods:
Expectation Propagation (EP), which performs well at the cold
start, but becomes slow as the amount of data increases; and
Assumed Density Filtering (ADF), which has slower growth of
computational cost with data size but requires more data to obtain an
acceptable level of accuracy. By switching from EP to ADF when
the dataset becomes large, it is able to exploit their complementary
strengths. The empirical justification for FAB-COST is presented, and
systematically compared to other approaches on simulated data. In a
benchmark against the Laplace approximation on real data consisting
of over 670, 000 impressions from autotrader.co.uk, FAB-COST
demonstrates at one point increase of over 16% in user clicks. On
the basis of these results, it is argued that FAB-COST is likely to
be an attractive approach to cold-start recommendation systems in a
variety of contexts.
Abstract: Traffic control has been one of the most common and irritating problems since the time automobiles have hit the roads. Problems like traffic congestion have led to a significant time burden around the world and one significant solution to these problems can be the proper implementation of the Intelligent Transport System (ITS). It involves the integration of various tools like smart sensors, artificial intelligence, position technologies and mobile data services to manage traffic flow, reduce congestion and enhance driver's ability to avoid accidents during adverse weather. Road and traffic signs’ recognition is an emerging field of research in ITS. Classification problem of traffic signs needs to be solved as it is a major step in our journey towards building semi-autonomous/autonomous driving systems. The purpose of this work focuses on implementing an approach to solve the problem of traffic sign classification by developing a Convolutional Neural Network (CNN) classifier using the GTSRB (German Traffic Sign Recognition Benchmark) dataset. Rather than using hand-crafted features, our model addresses the concern of exploding huge parameters and data method augmentations. Our model achieved an accuracy of around 97.6% which is comparable to various state-of-the-art architectures.
Abstract: This paper presents and benchmarks a number of
end-to-end Deep Learning based models for metaphor detection in
Greek. We combine Convolutional Neural Networks and Recurrent
Neural Networks with representation learning to bear on the metaphor
detection problem for the Greek language. The models presented
achieve exceptional accuracy scores, significantly improving the
previous state-of-the-art results, which had already achieved accuracy
0.82. Furthermore, no special preprocessing, feature engineering or
linguistic knowledge is used in this work. The methods presented
achieve accuracy of 0.92 and F-score 0.92 with Convolutional
Neural Networks (CNNs) and bidirectional Long Short Term Memory
networks (LSTMs). Comparable results of 0.91 accuracy and 0.91
F-score are also achieved with bidirectional Gated Recurrent Units
(GRUs) and Convolutional Recurrent Neural Nets (CRNNs). The
models are trained and evaluated only on the basis of training tuples,
the related sentences and their labels. The outcome is a state-of-the-art
collection of metaphor detection models, trained on limited labelled
resources, which can be extended to other languages and similar
tasks.
Abstract: There are currently many people living with limb loss in the USA. The main causes for amputation can range from vascular disease, to trauma, or cancer. This number is expected increase over the next decade. Many patients have a single prosthetic for the first year but end up getting a second one to accommodate their changing physique. Afterwards, the prosthesis gets replaced every three to five years depending on how often it is used. This could cost the patient up to $500,000 throughout their lifetime. Complications do not end there, however. Due to the absence of nerves, it becomes more difficult to traverse terrain with a prosthetic. Moving on an incline or decline becomes difficult, thus curbs and stairs can be a challenge. Certain physical activities, such as cycling, could be even more strenuous. It will need to be relearned to accommodate for the change in weight, center of gravity, and transfer of energy from the leg to the pedal. The purpose of this research project is to develop a new, alternate below-knee cycling prosthetic using Dieter & Schmidt’s design process approach. It will be subjected to fatigue analysis under dynamic loading to observe the limitations as well as the strengths and weaknesses of the prosthetic. Benchmark comparisons will be made between existing prosthetics and the proposed one, examining the benefits and disadvantages. The resulting prosthetic will be 3D printed using acrylonitrile butadiene styrene (ABS) or polycarbonate (PC) plastic.
Abstract: In the field of machine learning, the ensemble has been employed as a common methodology to improve the performance upon multiple base classifiers. However, the true predictions are often canceled out by the false ones during consensus due to a phenomenon called “curse of correlation” which is represented as the strong interferences among the predictions produced by the base classifiers. In addition, the existing practices are still not able to effectively mitigate the problem of imbalanced classification. Based on the analysis on our experiment results, we conclude that the two problems are caused by some inherent deficiencies in the approach of consensus. Therefore, we create an enhanced ensemble algorithm which adopts a designed rank-based chain-mode consensus to overcome the two problems. In order to evaluate the proposed ensemble algorithm, we employ a well-known benchmark data set NSL-KDD (the improved version of dataset KDDCup99 produced by University of New Brunswick) to make comparisons between the proposed and 8 common ensemble algorithms. Particularly, each compared ensemble classifier uses the same 22 base classifiers, so that the differences in terms of the improvements toward the accuracy and reliability upon the base classifiers can be truly revealed. As a result, the proposed rank-based chain-mode consensus is proved to be a more effective ensemble solution than the traditional consensus approach, which outperforms the 8 ensemble algorithms by 20% on almost all compared metrices which include accuracy, precision, recall, F1-score and area under receiver operating characteristic curve.
Abstract: Fake news and false information are big challenges of all types of media, especially social media. There is a lot of false information, fake likes, views and duplicated accounts as big social networks such as Facebook and Twitter admitted. Most information appearing on social media is doubtful and in some cases misleading. They need to be detected as soon as possible to avoid a negative impact on society. The dimensions of the fake news datasets are growing rapidly, so to obtain a better result of detecting false information with less computation time and complexity, the dimensions need to be reduced. One of the best techniques of reducing data size is using feature selection method. The aim of this technique is to choose a feature subset from the original set to improve the classification performance. In this paper, a feature selection method is proposed with the integration of K-means clustering and Support Vector Machine (SVM) approaches which work in four steps. First, the similarities between all features are calculated. Then, features are divided into several clusters. Next, the final feature set is selected from all clusters, and finally, fake news is classified based on the final feature subset using the SVM method. The proposed method was evaluated by comparing its performance with other state-of-the-art methods on several specific benchmark datasets and the outcome showed a better classification of false information for our work. The detection performance was improved in two aspects. On the one hand, the detection runtime process decreased, and on the other hand, the classification accuracy increased because of the elimination of redundant features and the reduction of datasets dimensions.
Abstract: Despite being one of the most significant economic contributors of the country, Canada’s construction industry is lagging behind other sectors when it comes to labor productivity improvements. The construction industry is very collaborative as a general contractor, will hire trade contractors to perform most of a project’s work; meaning low productivity from one contractor can have a domino effect on the shared success of a project. To address this issue and encourage trade contractors to improve their productivity tracking methods, an investigative study was done on the productivity views and tracking methods of various trade contractors. Additionally, an in-depth review was done on four standard tracking methods used in the construction industry: cost codes, benchmarking, the job productivity measurement (JPM) standard, and WorkFace Planning (WFP). The four tracking methods were used as a baseline in comparing the trade contractors’ responses, determining gaps within their current tracking methods, and for making improvement recommendations. 15 interviews were conducted with different trades to analyze how contractors value productivity. The results of these analyses indicated that there seem to be gaps within the construction industry when it comes to an understanding of the purpose and value in productivity tracking. The trade contractors also shared their current productivity tracking systems; which were then compared to the four standard tracking methods used in the construction industry. Gaps were identified in their various tracking methods and using a framework; recommendations were made based on the type of trade on how to improve how they track productivity.
Abstract: Individuals with Autism, Intellectual and Developmental disabilities (AIDD) are one of the most vulnerable groups in society, hampered not only by their own limitations to understand and interact with the wider society, but also societal limitations in perception and understanding. Communication to express their needs and wishes is fundamental to enable such individuals to live and prosper in society. This research project was designed as an organisational case study, in a large secondary health care hospital within the National Health Service (NHS), to assess the quality of care provided to people with AIDD and to review the role of advocacy to reduce health inequalities in these individuals. Methods: The research methodology adopted was as an “insider researcher”. Data collection included both quantitative and qualitative data i.e. a mixed method approach. A semi-structured interview schedule was designed and used to obtain qualitative and quantitative primary data from a wide range of interdisciplinary frontline health care workers to assess their understanding and awareness of systems, processes and evidence based practice to offer a quality service to people with AIDD. Secondary data were obtained from sources within the organisation, in keeping with “Case Study” as a primary method, and organisational performance data were then compared against national benchmarking standards. Further data sources were accessed to help evaluate the effectiveness of different types of advocacy that were present in the organisation. This was gauged by measures of user and carer experience in the form of retrospective survey analysis, incidents and complaints. Results: Secondary data demonstrate near compliance of the Organisation with the current national benchmarking standard (Monitor Compliance Framework). However, primary data demonstrate poor knowledge of the Mental Capacity Act 2005, poor knowledge of organisational systems, processes and evidence based practice applied for people with AIDD. In addition there was poor knowledge and awareness of frontline health care workers of advocacy and advocacy schemes for this group. Conclusions: A significant amount of work needs to be undertaken to improve the quality of care delivered to individuals with AIDD. An operational strategy promoting the widespread dissemination of information may not be the best approach to deliver quality care and optimal patient experience and patient advocacy. In addition, a more robust set of standards, with appropriate metrics, needs to be developed to assess organisational performance which will stand the test of professional and public scrutiny.
Abstract: In today’s world, the growing demand for urban built forms has resulted in the production and consumption of building materials i.e. embodied energy in building construction, leading to pollution and greenhouse gas (GHG) emissions. Therefore, new buildings will offer a unique opportunity to implement more energy efficient building without compromising on building performance of the building. Embodied energy of building materials forms major contribution to embodied energy in buildings. The paper results in an approach towards designing an energy efficient apartment building through embodied energy assessment. This paper discusses the trend of residential development in Rourkela, which includes three case studies of the contemporary houses, followed by architectural elements, number of storeys, predominant material use and plot sizes using primary data. It results in identification of predominant material used and other characteristics in urban area. Further, the embodied energy coefficients of various dominant building materials and alternative materials manufactured in Indian Industry is taken in consideration from secondary source i.e. literature study. The paper analyses the embodied energy by estimating materials and operational energy of proposed building followed by altering the specifications of the materials based on the building components i.e. walls, flooring, windows, insulation and roof through res build India software and comparison of different options is assessed with consideration of sustainable parameters. This paper results that autoclaved aerated concrete block only reaches the energy performance Index benchmark i.e. 69.35 kWh/m2 yr i.e. by saving 4% of operational energy and as embodied energy has no particular index, out of all materials it has the highest EE 23206202.43 MJ.
Abstract: Back propagation algorithm (BP) is a widely used
technique in artificial neural network and has been used as a tool
for solving the time series problems, such as decreasing training
time, maximizing the ability to fall into local minima, and optimizing
sensitivity of the initial weights and bias. This paper proposes an
improvement of a BP technique which is called IM-COH algorithm
(IM-COH). By combining IM-COH algorithm with cuckoo search
algorithm (CS), the result is cuckoo search improved control output
hidden layer algorithm (CS-IM-COH). This new algorithm has a
better ability in optimizing sensitivity of the initial weights and bias
than the original BP algorithm. In this research, the algorithm of
CS-IM-COH is compared with the original BP, the IM-COH, and the
original BP with CS (CS-BP). Furthermore, the selected benchmarks,
four time series samples, are shown in this research for illustration.
The research shows that the CS-IM-COH algorithm give the best
forecasting results compared with the selected samples.
Abstract: For precise geoid determination, we use a reference field to subtract long and medium wavelength of the gravity field from observations data when we use the remove-compute-restore technique. Therefore, a comparison study between considered models should be made in order to select the optimal reference gravity field to be used. In this context, two recent global geopotential models have been selected to perform this comparison study over Northern Algeria. The Earth Gravitational Model (EGM2008) and the Global Gravity Model (GECO) conceived with a combination of the first model with anomalous potential derived from a GOCE satellite-only global model. Free air gravity anomalies in the area under study have been used to compute residual data using both gravity field models and a Digital Terrain Model (DTM) to subtract the residual terrain effect from the gravity observations. Residual data were used to generate local empirical covariance functions and their fitting to the closed form in order to compare their statistical behaviors according to both cases. Finally, height anomalies were computed from both geopotential models and compared to a set of GPS levelled points on benchmarks using least squares adjustment. The result described in details in this paper regarding these two models has pointed out a slight advantage of GECO global model globally through error degree variances comparison and ground-truth evaluation.
Abstract: The ever-increasing presence and use of information and communication technology (ICT) influences the different social relationships of today's society. Gender differences are especially important from the viewpoint of modern society since ICT can either deepen the existing inequalities or diminish them. In a developed Western world, gender equality has been a well-focused area for decades in many parts of society including education, employment or politics and has led to a decrease in the inequality of women and men in these and other areas. The area of digital equality, or inequality for that matter, is one of the areas where gender differences still exist in many countries of the world. The research presented in this paper focuses on Slovenia, one of the smallest EU member states, being an average achiever in the area of e-society according to the many different European benchmarking indexes. On the other hand, Slovenia is working in an alignment with many European gender equality guidelines and showing good results. The results of our research are based on the analysis of survey data from 2014 to 2017 dealing with Slovenian citizens and their households and the use of ICT. Considering gender issues, the synthesis showed that cultural differences influence some measured ICT indicators but on the other hand the differences are low and only sometimes statistically significant.