FACULTY OF PHYSICAL SCIENCE

Face detection and recognition are computer vision techniques used to identify and locate human faces within digital images or video frames, and to subsequently analyze and verify the identity of individuals based on their unique facial features. Some of the algorithms used for implementing face detection and recognition are Local Binary Pattern, Histogram of oriented Gradient, Linear discriminant analysis, and convolutional neural networks with classifier such as Support Vector machine, e.t.c. Face detection and recognition system has become relevant in security and access control, automated Attendance tracking, user authentication, Biometric identification, Human Computer Interaction and many other areas. This project is implemented using python programming language, because python programming language allows programmers flexibility, therefore is of no threat to write- ability, readability and reliability, it has it libraries for the implementation of the project. And the test run of the project result is contained in Appendix D

The research looked at the sedimentary process and the exact period of environmental deposition in the imo formation. From the thirty-two (32) ditch cutting samples that were collected and processed, twelve (12) samples were forwarded to the Activation Laboratory for geochemical analysis with the aid of the Ultratrace 7 package. The sample was taken from a depth interval of 1060 feet (1,060 meters) at the Obaretin Well in Nigeria's Benin flanks, where it undergone a complete geochemical study. Twelve samples were taken, and they underwent an effervescence test using diluted hydrochloric acid (Hcl). On the sample, carbonate was detectable. There was some strong (3), moderate (2), and weak (1) effervescence notices. Applying the aforementioned elemental proxies, such as trace, major, rare element the following was determined: grain size, paleosalinity, paleoproductivity, and paleooxygenation. For the grain size, silicon and aluminum, (Si/Al), when silicon increase the aluminium decrease the grain size from sample was coaser and larger in size. While strontium and barium (Sr/Ba) were the proxies used for paleosalinity, the trend line shows that higher salinities created marine environments, while lower salinities create river channels. A decline in paleoproductivity results in a low input of terrigenous material, whereas an increase in paleoproductivity results in deposits of rich terrigenous material. Barium and aluminum (Ba/Al) were utilized as proxies in the paleoproductivity study. Oxic, suboxic, and anoxic environments are the core topics of paleo oxygenation. Numerous elemental proxies, such as Molybdenum and Vanadium (Mo/V), were employed. Environment quality is determined by paleooxygenation. This study has helped in understanding fully about the sedimentary processes and depositional environment.

A complaint takes place when something goes wrong with no one willing to deal with the topic. If a customer fails to express oneself about something that went wrong, the firm stands to lose: an opportunity to improve has been missed. In order to retain existing customers, complaint management should be more than just a system of monitoring customer satisfaction: customers must be encouraged to bring out their concerns in form of complaints. This study focuses on complaint management, creating an interfaced solution to unify communication between final year computer science students in order to improve data
acquisition and utilization for decision-making.

Warri and its environs have been recently challenged with incidences/imminence of building collapse with frequency of four incidences in the past four (4) years. Hence, geophysical, geotechnical and mineralogical investigations were conducted in an area of failed building and other areas in Warri with a view to comparatively analyse the geotechnical and mineralogical properties of subsurface soils for future building and road developments in Warri. This involved the drilling of ten (10) boreholes in the failed area and fifteen (15) holes in other areas which were all complimented with twenty five (25) Cone Penetration Tests. Samples from boreholes were subjected to geotechnical index/foundation analyses and X-ray Diffraction analyses (XRD). Geophysical and geotechnical investigations showed that the failed area had a laterally heterogeneous two-three layer soil profile which from top to bottom consisted of sandy silt/silty sand (3m thick), clayey silt (15-17m thick) and fine-medium grained sands (2m thick). This was at variance with the other areas which had a relatively homogeneous three layer soil profile which from top to bottom consisted of loose sandy humus top soil (0.25m thick), reddish brown silty sand and fine to medium grained sands (3-8m thick). Classification characteristics using the American Association of State and Highway Transport Officials (AASHTO) showed that the superficial soils in the failed area were mainly of A-7, A-6 and A-4 characteristics with California Bearing Ratio (CBR of 3-20.5%, average: 6.25%) indicating they are competent subgrade materials but incompetent sub-base and base course materials for road construction. Similar characterization in other areas reflected soils of A-2, A-6 and A-3 characteristics with CBR (10-17.9%, average: 15.02%) indicating similar competence and deficiency to that of the failed area. Sand stabilization increased the subgrade quality of the superficial soils in both areas. Cement and composite stabilization improved all soils to sub-base and base quality materials respectively. Foundation studies showed that superficial soils in the failed area are of lower foundation quality (bearing capacity of 184-229kpa, compression indices; 0.12-0.62) than the other areas (bearing capacity of 185-575kpa, compressibility indices; 0.31-0.34). Superficial soil mineralogy showed that the failed area consisted of quartz (75.33-94.20%), kaolinite (5.79- 11.99%), smectite, muscovite and microcline which is consistent with the other areas except for the absence smectite. This showed that structural failure in the challenged area was due to soil lateral variation and poor foundation quality.

This research is focused on the sedimentological characterization and petrographic analysis of a sedimentary outlier unit at the outskirts of Ikpeshi area. The sedimentological study of sections of the rock units involved the description, measurements and sampling of various sections and samples broken off from the rock unit in situ. The laboratory studies carried out in this research include petrographic analysis involving thin section petrography. This rock unit occurs as boulders on a narrow ridge and they are
surrounded by basement complex rocks, they have a coarse texture, and contain particle size that range from about 1mm – 15mm with a dominant clast size of 2mm, they are poorly sorted and they range from sub-angular to angular in roundness. They contain about 85% quartz, 10% clay minerals and lithic fragments account for the rest. The rock unit was observed to be texturally and mineralogically immature. These rock units have been established as sandstones, made up of very coarse sands – small pebbles mineral grains, they are sub-arkosic in nature which is a function of the percentage of the mineral content and the lithic fragments. The sandstone unit consists of series of sedimentary structures which include cross beds, which formed as a result of sudden rise and fall in the depositional energy, the direction of dips of these cross beds indicates the paleocurrent direction of the transporting medium at the time of deposition. The rock unit outcrops in the Benin flank, the sandstone is described as
Pre-Santonian due to its age, the sandstone is observed to be older than sandstones that were formed in the Anambra Basin. This is evident in the compaction difference or diagenetic process that occurred between the two, the sediments as well as the depositional processes that make up these sandstones is suggested to have come from the lower Benue Trough this can be said to be true as a result of 2 the clear distinct lithological and textural characteristics of the sandstones formed in Anambra Basin and the sandstones that is been examined.

Soil, surface water and groundwater samples were collected for physico-chemical, microbial and heavy metal analysis from different locations in Ologbo and environs. Thirteen (13) soil samples including Three controls (Pristine environment) were randomly collected at subsurface depth of 0-30cm, Thirteen surface water samples were collected including three controls and Ten (10) Groundwater samples were collected using random sampling Technique. The samples were collected in order to evaluate the level of pollution/Contamination of the media as a result of petroleum activities, wood industries and other anthropogenic activities within the study area. The results for the groundwater analysis showed pH (5.61-5-78), EC (54.64-65.74), Turbidity (0.05-0.12NTU), Cu (0.38-0.49mg/l), Zn (0.3-0.39mg/l), Cr (0.09-0.16mg/l), Ni (0.64-0.85mg/l), Fe (0.38 2.49mg/l), Mn (0.1-0.15mg/l and Pb (0.01-0.16mg/l). The results for the surface water showed pH (5.71-6.05), turbidity (7.31-13.92NTU), EC (87.11-95.2uS/cm), Zn (0.41-0.45mg/l), Fe (1.24-1.3mg/l), Cu (0.51-0.54mg/l), Cr (0.35-0.38mg/l), Ni (0.09-0.21mg/l) and Pb (0.02- 0.06). These results were compared with world and national standards, and control samples were
collected and used for comparison where needed .The result, of the analyses were further subjected to statistical treatment such as Spearman’s correlation Co-efficient, ANOVA and concentration Factor Analysis, to ultimately ascertain the spatial relationship between sample. The ANOVA results for soil samples indicated a very strong significant difference at (p<0.01)
between control and soil samples for all parameters. Correlation results revealed positive and negative correlation Co-efficient at r (0.01) and r (0.05) indicating strong relationship between them, which probably reflects their source of Contamination. Concentration maps generated for the area showed high concentrations of Lead, Copper and Iron around the central area, increasing towards the southwestern part of the maps. The groundwater flow map showed a 2-way flow direction towards the central part where the major river dividing the map is located. The overall results revealed moderate contamination/pollution of all varieties of samples analyzed and it’s here by recommended that important steps be taken to minimize the negative effects of oil exploration and wood industries in Ologbo.

In this era, the best problem solving method is needed in all field irrespective of the complexity or simplicity of the problem. Researchers and developers are doing their best to make software’s and machines more potent and intelligent. This is the advantage of artificial intelligent in developing solutions to searching algorithms that are potent and optimal. The most potent highly developed investigate method in Artificial Intelligence is the genetic algorithm. Genetic algorithm was developed to get best result to a known difficulty premised on inheritance, collection, crossover, mutation and further method. It has been proven that
genetic algorithm is the most potent, impartial optimization method for analyzing a solution with large space. this research have been able to define what is genetic algorithm, how it differs from other existing traditional search optimization method, review of ten (10) traditional techniques of finding the best route in a given network. Also the design of genetic algorithm, it’s implementation on finding the best route within 20 cities (point) which is invariably the travelling salesman problem (TSP), and areas of application of application of genetic algorithms. The best route is invariably the shortest path.

Football appears to be the most popular sports the world over, making it a game of betting for money making among other thing. This business of betting, over the years has gown making it a difficult and complex task in predicting correctly the outcome of football matches. This is as a result of the numerous number of factors that are considered but cannot be quantitatively valued or modeled. The aim of the project is to develop a machine learning algorithms for the prediction of football matches. The classification algorithms adopted in this project includes: K-Nearest Neighbor (KNN), support vector machines (SVM), Gaussian naïve Bayes (GNB), decision tree (DT) and Logistic Regression (LR) techniques. The dataset used was gathered from football- data-co.uk. The models was built using python programming language environment. The comparative analysis carried out in this project support that machine learning algorithms perform well and shows room for future improvement.

A key branch of artificial intelligence is machine learning models. The incorporation of these models into petrophysical analysis has gained popularity since it gives a more cost-effective and efficient method of acquiring petrophysical parameters. Porosity prediction was performed for this study utilizing machine learning models and 10 well log data from Niger Delta X-Fields wells. The well data from well 02 was used to train four machine learning models. The Ridge Regression model, Bagging Regressor model, ExtraTrees Regressor model, and Xgboost model were employed. The model that predicted porosity the best was chosen and used to forecast missing permeability logs from nine (9) other well log data sets. The available log data include Caliper, Gamma, Res_Deep (Resistivity), Density, PHIE (Porosity), SW (Water Saturation), VSH (Volume of Shale), and (Permeability) logs. The bagging model was selected as it was the most effective, with a mean absolute error of 0.003, a root mean squared error of 0.010, and a mean absolute percentage error of 2.3%. This in turn enabled the prediction of porosity logs for the aforementioned amount of wells with a very low percentage error. Predictions were carried out using mainly the Permeability and Density logs as they provide a very strong correlation to Porosity. It was discovered that the difference between AIC value and mean absolute error value cannot be used as the only method of model evaluation; hence, the entire error margin, as well as the visualization using subplots must be taken into consideration when evaluating model performance. It should also be noted that, the percentage error of the various models differ slightly; however, the model with the smallest error margin should be used.