New Visions in Science and Technology Vol. 9

The intrusion detection system using various machine learning algorithms have been developed. Various available datasets have been used for training and testing purposes. The performance matrix like accuracy, precision, recall etc., have been evaluated using various ML algorithms. A few deep learning methodologies have been also used to measure the performance metric on various data sets. As a challenge and the future work there is need of using other various deep learning methods which gives more accuracy with real time data traffic. In this article we will be studying on various methods of machine learning deep learning methods used for evaluating the performance measure on various data sets.

The study was aimed at determining the content of iodine in NAFDAC approved Table Salts used in Nigeria. Three Table Salts brands namely: Dangote fine edible salt, Royal edible salt and Mr. Chef edible salt were purchased from retailer level in Makurdi, Benue State, Nigeria. Salt iodine content is one of the indicators which is used for a sustainable elimination of iodine deficiency as a public health problem. The iodine content of each of the three brands of salt sample were carried out using the titrimetric method. Potassium Iodide (KI) was used for salt iodization. Results showed that the Dangote fine edible salt contain 39.6 ppm  of iodine while the Royal edible salt contain 41.8 ppm  and the Mr. Chef edible salt contain 42.9 ppm. The result confirms that each of the three samples met the iodine content requirements approved by NAFDAC. However, the results obtained were generally lower than the value found at the production level (50 ppm) for each table salt. The results were within the acceptable range for human consumption 50 ppm to 30ppm.

Persistence of frontal suture separating the two frontal bones in the adults is called metopism and the suture is called metopic suture. The fusion of metopic suture starts at around 18 months after birth and is completed by 8-9 years of age. As the metopic suture fuses, the two frontal bones become single which is seen normally in adult skulls. Constant metopic suture may be seen as complete or incomplete forms in some adult skulls. This feature of variant anatomy of the skulls seems to be increasingly on rise in the present era. Knowledge of this variant anatomy could be of paramount importance in certain fields like Forensic medicine where this could form a feature of identification. Complete metopism is rare in adult skulls where the metopic suture extends upto bregma- the point at which sagittal and coronal sutures meet. Incomplete metopic sutures exhibit different forms like shapes of ‘V’, ‘H’, ‘Y’, or ‘U’ that may be misinterpreted as hairline fractures in radiological findings. Incomplete metopism is usually seen at glabella, the bony prominence at the root of the nose. The present study aims at the presence of metopism in the adult skulls from South India in various forms. 180 adult skulls ranging from 40-65 years of age group from the department of Anatomy were studied for the presence of metopic suture. Their shapes and measurements were tabulated. The results were compared with those of other studies.  103 skulls were found to have no metopic suture, 9 skulls showed complete metopic suture extending from glabella up to bregma, 18 skulls revealed ‘V’ shaped, 14 skulls manifested to have ‘H’ shape, 16 skulls were discovered to have linear metopic suture in the midline, 7 ‘Y’ shape, 11 had inverted ‘U’ shaped metopic suture, 2 skulls showed ‘U’ shaped metopic suture with extension on to the right. These values strikingly show that the prevalence of metopism is on the rise. To conclude, 42.5 % of skulls revealed the presence of metopic suture in various forms and 57.2% showed no metopism.

Healthcare professionals commonly use Electrocardiogram (ECG) as a low-cost diagnostic tool for monitoring heart electrical signals. Arrhythmia, which is an abnormal heart signal, can be dangerous and cause death. The arrhythmia can be categorized in various types including tachycardia, bradycardia, supraventricular arrhythmias, and ventricular. The automated monitoring of arrhythmia and classification with ECG is very helpful for doctors. In this research we use deep machine learning for automated arrhythmia classification with the focus on the recent trends in arrhythmia classification. Using St. Mary’s University Deep Learning Platform, we conducted heavy and complex simulations to measure the performance of the various arrhythmia classification and detection models. Finally, we present the accuracy of the proposed deep learning algorithms, which surpasses the performance of the existing algorithms in precision and sensitivity.

This document presents the results obtained from different statistical norms to validate the quality of synthesized voices applied to an HTS-based spanish synthesizer. Two parameterizations were tried out: LSP and Cepstral Coefficients. Standard MOS tests were carried out. MUSHRA, ABX and CCR where also conducted to reinforce the MOS results. A SUS test was employed to verify intelligibility.

The problems of optimizing the operating modes of an asynchronous electric drive according to the criterion of minimum stator current, as well as the optimal control system for an induction motor with a reference rotor flux linkage vector, which can be used for most serial frequency converters, are added to the control channel of the longitudinal component of the stator current.

Air pollution, which is generated by emissions of hydrocarbons, nitrogen oxides, carbon oxides, and sulphur oxides from the combustion of fossil fuels, is currently the biggest threat to the environment and public health. The fast increase in the consumption of fossil fuels by various factories in recent years has prompted the quest for alternative fuels. These fuels are also known as non-conventional fuels since they can be utilised to replace conventional fuels. Algae oil is one of the most promising possible sources of microbe-derived biofuels. It is widely preferred since it is a long-lasting, environmentally friendly oil with several benefits.  As a result, algae oil has been used to test the performance and emissions of a diesel engine. The blends were created for B5, B10 testing. In which 5% of methanol has mixed and others are raw algae oil (5% for B5 and 10% for B10) and Diesel (90% for B5 and 85% for B10).  For performance analysis, the Kirlosker Engine with 6.97 HP (5.2KW)@1500rpm is employed. Parallel AVL emission analyzers and smoke detectors were connected to the engine's exhaust. All values of gases were displayed and compared. The catalyst used with both B5 and B10 blends was methanol. The use of a better catalyst in future may help in improving the performance of B10 blend, enabling us to use more and more organic algae oil instead of the non- renewable diesel.

Harmattan workshop holds annually at Agbarha-Otor in Delta state of Nigeria. It is a realization of a vision of a great artist-Bruce Onobrakpeya who established Bruce Onobrakpeya Foundation (BOF). He focuses his contributions towards the realization of African identity through his artistic medium. The serene environment where the harmattan workshop situates leaves no participant untouched and uninfluenced by the consummating bliss of art influence and radiation. Artists and associates from Africa and outside participate in this annual art practice, discussions and exhibition shows. The innovative works of art produced and exhibited there are applauded by many. Onobrakpeya generates inspiration from different issues among which include; traditional issues, design discovery, motif manipulation, plastograph experiments, tryptilinen, plastocast, zerograph, installation and others. It is worthwhile to have an experience of the harmattan workshop in order to have a taste of African identity through art.

Conventional underground coal mining relies upon the use of continuous miners in order to extract coal reserves from underground coal seams. In combination with the continuous miners- shuttle cars are used to transport the extracted coal from the face to a transfer point (feeder breaker). From there the coal is typically tipped onto the underground conveyor system, which transports the coal to the surface in order to be distributed to customers. Effective management of the cutting, loading and tipping cycles utilised will serve as a possible area for productivity improvement. Continuous miner technology will drastically increase the production, productivity and safety in the underground mining.

The fidelity of an image subjected to digital processing, such as a contour / texture highlighting process or a noise reduction algorithm, can be evaluated based on two types of criteria: objective and subjective, sometimes the two types of criteria being considered together. Subjective criteria are the best tool for evaluating an image when the image obtained at the end of the processing is interpreted by man. The objective criteria are based on the difference, pixel by pixel, between the original and the reconstructed image and ensure a good approximation of the image quality perceived by a human observer. There is also the possibility that in evaluating the fidelity of a remade (reconstructed) image, the pixel-by-pixel differences will be weighted according to the sensitivity of the human visual system. The problem of improving medical images is particularly important in assisted diagnosis, with the aim of providing physicians with information as useful as possible in diagnosing diseases. Given that this information must be available in real time, we proposed a solution for reconstructing the contours in the images that uses a modified Wiener filter in the wavelet domain and a nonlinear cellular network and that is useful both to improve the contrast of its contours and to eliminate noise. In addition to the need to improve imaging, medical applications also need these applications to run in real time, and this need has been the basis for the design of the method described below, based on the modified Wiener filter and nonlinear cellular networks.

The research aims to empower the learning agent to control the way of reaching a goal. More specifically objectives of the study are to explore the possibility of intelligent virtual agents learning to make acceptable tradeoffs only when a goal cannot be achieved if all user-defined requirements on how to achieve it are met. This chapter proposes a modification of the Q-learning algorithm to achieve these goals. In this way, it is expected to take a step towards achieving goals such as modelling shopping therapy, understanding the preferences of others, understanding whether the shopping habit is becoming a problem, detecting problems with cognitive memory, modelling behaviour specific to different age groups. To make the Q-learning agent find the optimal path to the goal by meeting particular complex criteria, the use of measures model (a model of environmental criteria and/or emotional models), represented as a new memory matrix, is introduced. If the goal cannot be reached by following the pre-set criteria, the learning agent can compromise a given criterion. The agent makes the least possible number of tradeoffs and appropriate compromises only to reach the goal. If the criteria are arranged by their level of importance, then the agent can choose more in number and more acceptable compromises instead of unacceptable ones. The modified algorithm was applied to train three different intelligent learning agents, respectively a shopping cart agent, a gift-shopping agent, and a broker.  The tests show improvement in their behavior.

This paper presents a new approach to human hair colorization and relighting. Human hair colorization, concerning given model hair image without changing neither hairstyle nor hair texture, is challenging. The fundamental problem making this task complicated is the difference in the hair texture and the illumination between a user and model images. Natural human hair consists of a mix of hair swatches. Each swatch has its chromaticity distribution, which, generally, is non-Gaussian. The proposed method treats these swatches as color clusters in the hair image. In this case, matching the user and the model hair swatches or color clusters solves the problem. After this matching, the color transfer between the relevant model and user swatches is applied. Besides, the model’s hair should be compressed to a reasonable size to provide simultaneous representation for numerous hair colors. The model’s hair colors are taken from the images of hair color packs that usually are available in decorative cosmetic stores. These images, however, are taken in standard illumination conditions, so appropriate relighting should be applied to provide a photorealistic user’s appearance. Experimental results with 530 different color models and more than 20,000 users show that the proposed technique achieves high photorealistic perception and a reasonable compression ratio. On average, a high pick signal to noise ratio (39 dB) indicates just a noticeable difference between original and reproduced model hair color.

Information and security are elements which are dependent on one another. Information security has now evolved to be a matter of global importance, requiring a variety of tools, policies and assurance of technologies against any relevant security risks to achieve its significance. Countless writers are rapidly attracted towards internet influx which provides a flexible means of sharing the online information economically. Text being an important constituent of online information sharing, creates a huge demand of intellectual copyright protection of text and web itself. A variety of visible watermarking techniques are being studied for text documents but few for web- based text in the present paper. The objective of the present study is to emphasize the significance of watermarking and cryptography techniques to protect the online text information which is vulnerable to a variety of threats.