A knowledge based decision support system for computer performance management

Computer systems managers make decisions about hardware and software selection, performance evaluation, capacity planning, and other resource variables on the basis of factual data, accounting data, subjective judgements, and assumptions about the resource consumption of the jobs being run. The importance of computer resource planning calls for effective support methods. A Knowledge-Based DSS (KBDSS) will be able to assist managers in making these policy decisions by utilizing knowledge of the existing configuration and its capabilities, the organizational computing environment, available external resources, and their suppliers. Combining procedural and declarative methods, such a KBDSS may provide early warning of possible bottlenecks, forecast growth of hardware usage, and employ knowledge based inferencing to suggest suitable remedial actions to the systems manager. This paper presents a KBDSS for supporting computer resource planning decisions using a procedural/declarative framework, and illustrates the system's usage aspects.     

In silico discovery of significant pathways in colorectal cancer metastasis using a two‐stage optimisation approach

Accurate and reliable modelling of protein–protein interaction networks for complex diseases such as colorectal cancer can help better understand mechanism of diseases and potentially discover new drugs. Different machine learning methods such as empirical mode decomposition combined with least square support vector machine, and discrete Fourier transform have been widely utilised as a classifier and for automatic discovery of biomarkers for the diagnosis of the disease. The existing methods are, however, less efficient as they tend to ignore interaction with the classifier. In this study, the authors propose a two‐stage optimisation approach to effectively select biomarkers and discover interactions among them. At the first stage, particle swarm optimisation (PSO) and differential evolution (DE) are used to optimise parameters of support vector machine recursive feature elimination algorithm, and dynamic Bayesian network is then used to predict temporal relationship between biomarkers across two time points. Results show that 18 and 25 biomarkers selected by PSO and DE‐based approach, respectively, yields the same accuracy of 97.3% and F1‐score of 97.7 and 97.6%, respectively. The stratified analysis reveals that Alpha‐2‐HS‐glycoprotein was a dominant hub gene with multiple interactions to other genes including Fibrinogen alpha chain, which is also a potential biomarker for colorectal cancer.Inspec keywords: cancer, proteins, particle swarm optimisation, evolutionary computation, support vector machines, recursive functions, Bayes methods, genetics, molecular biophysics, medical computingOther keywords: colorectal cancer metastasis, two‐stage optimisation approach, protein–protein interaction networks, biomarkers, particle swarm optimisation, differential evolution, support vector machine recursive feature elimination, dynamic Bayesian network, stratified analysis, Alpha‐2‐HS‐glycoprotein, hub gene, Fibrinogen alpha chain     

Thermal performance evaluation of active and passive water heat-storage schemes for solar energy applications

Because of easy availability and low cost, water is commonly used as a sensible heat-storage medium in solar energy applications. In this investigation two schemes of water thermal storage (active and passive) were designed and constructed from readily available materials. A dynamic computer model was developed to predict the thermal performance of the water thermal-storage systems under various charging and discharging conditions. Experimental tests were also conducted. The simulated results and measured data compared favourably, and these results showed that the water thermal-storage systems responded well to step and fluctuating input temperature changes. The water thermal storage may be satisfactorily used in varied solar energy applications where energy storage is necessary.     

DESIGN, EXPERIMENTAL AND ECONOMIC EVALUATION OF A COMMERCIAL-TYPE SOLAR DRYER FOR PRODUCTION OF HIGH-QUALITY HAY

Design features, development, experimental functional performance and economic evaluation of an energy efficient solar energy dryer for commercial production of high-quality hay and processed forage products are presented. The solar hay dryer consists of an improved solar collector with selective coated aluminum absorber plate and spaced fins, and a drying shed connected to the collector by an insulated duct and having a perforated metal grate floor, swing-away plywood frames and polyethylene curtains for effectively sealing the hay stack, and a crawl space below the floor where a 3-hp in-line centrifugal fan is housed for air circulation by suction. In late August and in early September, 1996, 160 small rectangular bales of alfalfa hay with about 25% bromegrass were successfully dried from 33% initial moisture content to 13%, and from 25% to 11% moisture in 4 and 3 days, respectively, under average weather conditions in Saskatoon, Saskatchewan, Canada. With about 18 m³/min per tonne airflow, 10-15 °C temperature rise above ambit was obtained during peak bright sunshine hours. Relatively high daily average collector Effciency of 76%, high drying effectiveness, drying uniformity, uniform air distribution and tight sealing of the stack were achieved which resulted in an attractive green color of hay, no mold growth on hay, and an overall system drying efficiency of about 79%. Compared to a conventional natural gas drying system or field-drying method, the payback period on extra investment costs recovered through drying cost savings of $3/ t to $6/ t or through over two times higher prices for high-quality hay produced by the solar drying system may be just one or two years, respectively.     

An experimental investigation of the predictive accuracy of induction and regression

As both research efforts and commercial adoption of Expert Systems (ESs) increase, knowledge acquisition continues to engage the attention of many ES developers. Many view the development of automated knowledge acquisition methods as one of the last remaining barriers to more widespread ES adoption and use. Rule induction has been advanced as a promising method of knowledge acquisition for expert systems, both to understand the weighting and importance of decision criteria and to provide a predictive capability for new examples. One important strand of research has naturally begun to compare the performance of rule induction to those of traditional statistical methods, such as multiple regression. In pursuing this subject, we document a comparison of the predictive capabilities of both induction and multiple regression. The study uses a sample of over 400 MBA students, employing their current GPA as the dependent variable or goal and prior (undergraduate) GPA and GMAT scores as independent or causal variables. An extensive comparison of both methods yields conclusions at variance with many previous studies which assert the superiority of the inductive method. Furthermore, the study identifies conditions under which the inductive method may be more effective as a predictor and develops recommendations for a contingency-based approach to knowledge acquisition for ES.     

Characterization of a Bioflocculant (MBF-UFH) Produced by Bacillus sp. AEMREG7

A bioflocculant named MBF-UFH produced by a Bacillus species isolated from sediment samples of Algoa Bay of the Eastern Cape Province of South Africa was characterized. The bacterial identification was through 16S rDNA sequencing; nucleotide sequences were deposited in GenBank as Bacillus sp. AEMREG7 with Accession Number {"type":"entrez-nucleotide","attrs":{"text":"KP659187","term_id":"768700521","term_text":"KP659187"}}KP659187. The production of the bioflocculant was observed to be closely associated with cell growth. The bioflocculant had the highest flocculating activity of 83.2% after 72 h of cultivation, and approximately 1.6 g of purified MBF-UFH was recovered from 1 L of fermentation broth. Its chemical analyses indicated that it is a glycoprotein composed of polysaccharide (76%) and protein (14%). Fourier transform infrared spectroscopy (FTIR) revealed that it consisted of hydroxyl, amide, carboxyl and methoxyl as the functional moieties. Scanning electron microscopy (SEM) revealed the amorphous structure of MBF-UFH and flocculated kaolin clay particles. The maximum flocculating activity of 92.6% against kaolin clay suspension was achieved at 0.3 mg/mL over pH ranges of 3–11 with the peak flocculating rate at pH 8 in the presence of MgCl₂. The bioflocculant retained high flocculating activity of 90% after heating at 100 °C for 1 h. MBF-UFH appears to have immense potential as an alternative to conventional chemical flocculants.     

Saponin content of some Nigerian foods

Saponins have been extracted and purified from millet (Pennisetum typhoideum), beans (Phaseolus vulgaris), guinea-corn (Sorghum vulgare) and groundnut (Arachis hypogaea). Beans were found to contain a considerable amount of saponin—245.0 mg kg^?1, while millet, guinea-corn and groundnut contained 194.7, 72.7 and 48.8 mg kg^?1 dry weight basis respectively.     

Changes in phenol oxidase and peroxidase levels in cocoyam tubers of different postharvest ages infected by Sclerotium rolfsii sacc

Crude aqueous extracts from the peripheral rot zone of cocoyam tubers infected by Sclerotium rolfsii sacc were shown to be inhibitory to dialysed in vivo polygalacturonase (PG) of the pathogen. The PG inhibitory action, phenol oxidase and peroxidase activities were higher in cocoyam tubers of the Xanthosoma sagittifolium varieties than in those of the Coolocasia esculenta varieties. The levels of phenol oxidase, peroxidase and PG inhibitory activities also decreased as the postharvest age of the tubers increased.     

Effect of storage conditions on the resistance of sweet potato tissues to rotting by Botryodiplodia theobromae (Pat.) amd other fungi

Sweet potato tubers were exposed to a range of temperatures from 0–20°C, either as a pre-treatment before inoculation with Botryodiplodia theobromae, Botrytis cinerea or Cladosporium cucumerinum, or during storage of inoculated tubers. In the latter case, the effect of aeration was also investigated. Pre-exposure to temperatures below 9°C made tubers progressively more susceptible to rotting by all three fungi as the temperature was lowered. This chilling effect may be due to an increased sensitivity of the tissue to pectic enzymes from the pathogen, and to a reduced capacity to synthesize the phytoalexin ipomeamarone. As far as storage conditions after inoculation are concerned, rotting by B. theobromae was prevented by good aeration and lower temperatures (13–15°C). Tubers were not rotted by the other species even under the most unfavourable conditions tested (no aeration, 25°C).