Abstract: The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.
Abstract: The current and future cellular mobile communication networks generate enormous amounts of data. Networks have become extremely complex with extensive space of parameters, features and counters. These networks are unmanageable with legacy methods and an enhanced design and optimization approach is necessary that is increasingly reliant on machine learning. This paper proposes that machine learning as a viable approach for uplink throughput prediction. LTE radio metric, such as Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), and Signal to Noise Ratio (SNR) are used to train models to estimate expected uplink throughput. The prediction accuracy with high determination coefficient of 91.2% is obtained from measurements collected with a simple smartphone application.
Abstract: The Arabic language is one of the most important languages. Learning it is so important for many people around the world because of its religious and economic importance and the real challenge lies in practicing it without grammatical or syntactical mistakes. This research focused on detecting and correcting the syntactic mistakes of Arabic syntax according to their position in the sentence and focused on two of the main syntactical rules in Arabic: Dual and Plural. It analyzes each sentence in the text, using Stanford CoreNLP morphological analyzer and machine-learning approach in order to detect the syntactical mistakes and then correct it. A prototype of the proposed system was implemented and evaluated. It uses support vector machine (SVM) algorithm to detect Arabic grammatical errors and correct them using the rule-based approach. The prototype system has a far accuracy 81%. In general, it shows a set of useful grammatical suggestions that the user may forget about while writing due to lack of familiarity with grammar or as a result of the speed of writing such as alerting the user when using a plural term to indicate one person.
Abstract: In this paper we develop a model that couples Two Concurrent Convolution Neural Network with different filters (TC*CNN) for face recognition and compare its performance to an existing sequential CNN (base model). We also test and compare the quality and performance of the models on three datasets with various levels of complexity (easy, moderate, and difficult) and show that for the most complex datasets, edges will produce the most accurate and efficient results. We further show that in such cases while Support Vector Machine (SVM) models are fast, they do not produce accurate results.
Abstract: Forecasting the stock market is a very challenging task. Various economic indicators such as GDP, exchange rates, interest rates, and unemployment have a substantial impact on the stock market. Time series models are the traditional methods used to predict stock market changes. In this paper, a machine learning method, Bayesian Additive Regression Tree (BART) is used in predicting stock market indexes based on multiple economic indicators. BART can be used to model heterogeneous treatment effects, and thereby works well when models are misspecified. It also has the capability to handle non-linear main effects and multi-way interactions without much input from financial analysts. In this research, BART is proposed to provide a reliable prediction on day-to-day stock market activities. By comparing the analysis results from BART and with time series method, BART can perform well and has better prediction capability than the traditional methods.
Abstract: The inability of organizations to put in place management control measures for Internet of Things (IoT) complexities persists to be a risk concern. Policy makers have been left to scamper in finding measures to combat these security and privacy concerns. IoT forensics is a cumbersome process as there is no standardization of the IoT products, no or limited historical data are stored on the devices. This paper highlights why IoT forensics is a unique adventure and brought out the legal challenges encountered in the investigation process. A quadrant model is presented to study the conflicting aspects in IoT forensics. The model analyses the effectiveness of forensic investigation process versus the admissibility of the evidence integrity; taking into account the user privacy and the providers’ compliance with the laws and regulations. Our analysis concludes that a semi-automated forensic process using machine learning, could eliminate the human factor from the profiling and surveillance processes, and hence resolves the issues of data protection (privacy and confidentiality).
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: This paper presents modeling and control strategy for the grid connected wind turbine system based on Permanent Magnet Synchronous Generator (PMSG). The considered system is based on back-to-back converter topology. The Grid Side Converter (GSC) achieves the DC bus voltage control and unity power factor. The Machine Side Converter (MSC) assures the PMSG speed control. The PMSG is used as a variable speed generator and connected directly to the turbine without gearbox. The pitch angle control is not either considered in this study. Further, Optimal Tip Speed Ratio (OTSR) based MPPT control strategy is used to ensure the most energy efficiency whatever the wind speed variations. A filter (L) is put between the GSC and the grid to reduce current ripple and to improve the injected power quality. The proposed grid connected wind system is built under MATLAB/Simulink environment. The simulation results show the feasibility of the proposed topology and performance of its control strategies.
Abstract: Nearly a hundred per million of the Filipino population is diagnosed with Chronic Kidney Disease (CKD). The early stage of CKD has no symptoms and can only be discovered once the patient undergoes urinalysis. Over the years, different methods were discovered and used for the quantification of the urinary albumin such as the immunochemical assays where most of these methods require large machinery that has a high cost in maintenance and resources, and a dipstick test which is yet to be proven and is still debated as a reliable method in detecting early stages of microalbuminuria. This research study involves the use of the liquid chromatography concept in microfluidic instruments with biosensor as a means of separation and detection respectively, and linear regression to quantify human urinary albumin. The researchers’ main objective was to create a miniature system that quantifies and detect patients’ urinary albumin while reducing the amount of volume used per five test samples. For this study, 30 urine samples of unknown albumin concentrations were tested using VITROS Analyzer and the microfluidic system for comparison. Based on the data shared by both methods, the actual vs. predicted regression were able to create a positive linear relationship with an R2 of 0.9995 and a linear equation of y = 1.09x + 0.07, indicating that the predicted values and actual values are approximately equal. Furthermore, the microfluidic instrument uses 75% less in total volume – sample and reagents combined, compared to the VITROS Analyzer per five test samples.
Abstract: Learning from very big datasets is a significant problem for most present data mining and machine learning algorithms. MicroRNA (miRNA) is one of the important big genomic and non-coding datasets presenting the genome sequences. In this paper, a hybrid method for the classification of the miRNA data is proposed. Due to the variety of cancers and high number of genes, analyzing the miRNA dataset has been a challenging problem for researchers. The number of features corresponding to the number of samples is high and the data suffer from being imbalanced. The feature selection method has been used to select features having more ability to distinguish classes and eliminating obscures features. Afterward, a Convolutional Neural Network (CNN) classifier for classification of cancer types is utilized, which employs a Genetic Algorithm to highlight optimized hyper-parameters of CNN. In order to make the process of classification by CNN faster, Graphics Processing Unit (GPU) is recommended for calculating the mathematic equation in a parallel way. The proposed method is tested on a real-world dataset with 8,129 patients, 29 different types of tumors, and 1,046 miRNA biomarkers, taken from The Cancer Genome Atlas (TCGA) database.
Abstract: This work is intended to study the post-failure characteristic behaviour of rocks and the techniques of controlling the post-failure regime based on the mechanism of rocks deformation process. It is impossible to determine the post-failure regime of rocks using conventional laboratory testing equipment. This is because most testing machines are soft and therefore no information can be obtained after the peak load. Stress-strain deformation tests were conducted using both conventional and unconventional method (i.e. the closed loop servo-controlled testing machine) in accordance to ISRM standard. Normalised pre-failure curves were constructed to show the stages in the deformation process. The first type contains the Class I and progress to Class II with low strength soft brittle rocks. The second type shows entirely Class II characteristic behaviour. The third type is extremely brittle under axial loading, resulted in explosive failure, so its class could not be determined. The difficulty in obtaining the post-failure curves increases as the total volumetric strain approaches a positive value. The author’s use of normalised pre-failure curves enables identification of additional type of deformation process with very brittle response under axial loading. Testing the third type without confinement could cause equipment damage. Identification of the deformation process with the rock classes using conventional test could guide the personnel conducting tests using closed-loop servo-controlled system, to avoid equipment damage when testing rocks with third type deformation process so that testing is performed safely. It has also improved our understanding on total specimen failure and brittleness of rocks (e.g. brittle for Class II and less brittle or ductile for Class I).
Abstract: This work is carried out to evaluate the possibility of using to-be-wasted steel as reinforcement after welding together pieces of reinforcing steel bars, left over during construction activities. Tests were performed on a total of nine samples. These were made by welding pieces of reinforcing steel bars purchased from the local scrap steel market. The samples were tested in uniaxial tension using a universal testing machine (UTM). It was found that the failure of the welded bars is governed by the thickness of the weld. It is concluded that suitable design of the weld is essential for achieving the desired level of ductility/elongation of these bars, if they are to be used as conventional reinforcement in reinforced concrete members.
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: The diversity and complexity of modern IT systems make it almost impossible for internal teams to find vulnerabilities in all software before the software is officially released. The emergence of threat intelligence and vulnerability reporting policy has greatly reduced the burden on software vendors and organizations to find vulnerabilities. However, to prove the existence of the reported vulnerability, it is necessary but difficult for security incident response team to build a deliberated vulnerable environment from the vulnerability report with limited and incomplete information. This paper presents a structured, standardized, machine-oriented vulnerability intelligence format, that can be used to automate the orchestration of Deliberated Vulnerable Environment (DVE). This paper highlights the important role of software configuration and proof of vulnerable specifications in vulnerability intelligence, and proposes a triad model, which is called DIR (Dependency Configuration, Installation Configuration, Runtime Configuration), to define software configuration. Finally, this paper has also implemented a prototype system to demonstrate that the orchestration of DVE can be automated with the intelligence.
Abstract: Additive Manufacturing is utilized in medical automation to optimize and integrate materials in accordance to energy source type leading to treatment gaps in industrial designs for extreme biomechanical forces in relation with vibration, fluid transfer, and multi-physics performance. Elastic/piezoelectric materials are strongly ordered inter-metallics for characterization of distinct features that can provide excellent compositional strength, ductility, and uniformity for superelastic shape memory alloy on medical devices. Several theories can be derived to analyze and interpret complex problems on the application of functionally graded materials used in medical machinery for genome architecture. Numerical principles on fluid and thermodynamics such as Reynolds number, Darcy rule, Friction Factor and Heat Rate are integrated with fundamental equation of numerical vibrations using Helmholtz equation. Simulation by Large Eddy approach and genetic modeling can be done using Physical and Chemical Vapor Deposition following various theories on Carrera’s Unified Formulations by comparing with various Classical Plate Theories, Equivalent Single Layer Theories, Layer-Wise Theories, Zig-Zag Theories, and Mixed Refined Variational Theories. The subject is approached towards the application of ethical and legal problems in order to resolve issues on consent and return of results.
Abstract: High Voltage Substations (HVS) are the intermediate step between production of power and successfully transmitting it to clients, making them one of the most important checkpoints in power grids. Nowadays - renewable resources and consequently distributed generation are growing fast, the construction of HVS is of high importance both in terms of quality and time completion so that new energy producers can quickly and safely intergrade in power grids. The resources needed, such as machines and workers, should be carefully allocated so that the construction of a HVS is completed on time, with the lowest possible cost (e.g. not spending additional cost that were not taken into consideration, because of project delays), but in the highest quality. In addition, there are milestones and several checkpoints to be precisely achieved during construction to ensure the cost and timeline control and to ensure that the percentage of governmental funding will be granted. The management of such a demanding project is a NP-hard problem that consists of prerequisite constraints and resource limits for each task of the project. In this work, a hybrid meta-heuristic method is implemented to solve this problem. Meta-heuristics have been proven to be quite useful when dealing with high-dimensional constraint optimization problems. Hybridization of them results in boost of their performance.
Abstract: Synchronizing and damping torque coefficients of a synchronous machine can give a quite clear picture for machine behavior during transients. These coefficients are used as a power system transient stability measurement. In this paper, a crow search optimization algorithm is presented and implemented to study the power system stability during transients. The algorithm makes use of the machine responses to perform the stability study in time domain. The problem is formulated as a dynamic estimation problem. An objective function that minimizes the error square in the estimated coefficients is designed. The method is tested using practical system with different study cases. Results are reported and a thorough discussion is presented. The study illustrates that the proposed method can estimate the stability coefficients for the critical stable cases where other methods may fail. The tests proved that the proposed tool is an accurate and reliable tool for estimating the machine coefficients for assessment of power system stability.
Abstract: Piezoelectric linear motors have the characteristics of great electromagnetic compatibility, high positioning accuracy, compact structure and no deceleration mechanism, which make it promising to applicate in micro-miniature precision drive systems. However, most piezoelectric motors are employed by flexible clamping, which has insufficient rigidity and is difficult to use in rapid positioning. Another problem is that this clamping method seriously affects the vibration efficiency of the vibrating unit. In order to solve these problems, this paper proposes a piezoelectric stack linear motor based on double-end rigid clamping. First, a piezoelectric linear motor with a length of only 35.5 mm is designed. This motor is mainly composed of a motor stator, a driving foot, a ceramic friction strip, a linear guide, a pre-tightening mechanism and a base. This structure is much simpler and smaller than most similar motors, and it is easy to assemble as well as to realize precise control. In addition, the properties of piezoelectric stack are reviewed and in order to obtain the elliptic motion trajectory of the driving head, a driving scheme of the longitudinal-shear composite stack is innovatively proposed. Finally, impedance analysis and speed performance testing were performed on the piezoelectric linear motor prototype. The motor can measure speed up to 25.5 mm/s under the excitation of signal voltage of 120 V and frequency of 390 Hz. The result shows that the proposed piezoelectric stacked linear motor obtains great performance. It can run smoothly in a large speed range, which is suitable for various precision control in medical images, aerospace, precision machinery and many other fields.
Abstract: Surface Mount Technology (SMT) is widely used in the area of the electronic assembly in which the electronic components are mounted to the surface of the printed circuit board (PCB). Most of the defects in the SMT process are mainly related to the quality of solder paste printing. These defects lead to considerable manufacturing costs in the electronics assembly industry. Therefore, the solder paste inspection (SPI) machine for controlling and monitoring the amount of solder paste printing has become an important part of the production process. So far, the setting of the SPI threshold is based on statistical analysis and experts’ experiences to determine the appropriate threshold settings. Because the production data are not normal distribution and there are various variations in the production processes, defects related to solder paste printing still occur. In order to solve this problem, this paper proposes an online machine learning algorithm, called the automatic threshold adjustment (ATA) algorithm, and closed-loop architecture in the SMT process to determine the best threshold settings. Simulation experiments prove that our proposed threshold settings improve the accuracy from 99.85% to 100%.
Abstract: In the past, we could increase profit by increasing product prices. But in the new decade, a competitive market does not let us to increase profit with increase prices. Therefore, the only way to increase profit will be reduce costs. A significant percentage of production costs are the maintenance costs, and analysis of these costs could achieve more profit. Most maintenance strategies such as RCM (Reliability-Center-Maintenance), TPM (Total Productivity Maintenance), PM (Preventive Maintenance) etc., are trying to reduce maintenance costs. In this paper, decreasing the maintenance costs of Concentration Plant of Golgohar Company (GEG) was examined by using of MTBF (Mean Time between Failures) and MTTR (Mean Time to Repair) analyses. These analyses showed that instead of buying new machines and increasing costs in order to promote capacity, the improving of MTBF and MTTR indexes would solve capacity problems in the best way and decrease costs.