This research analyzed the effect of processing (boiling and roasting) on the proximate, antinutrient, and mineral composition of Vigna subterranea seeds. The proximate composition analysis showed significant difference (P<0.05) between the levels of crude lipid, crude fiber, gross energy, carbohydrate, and moisture content in the raw and processed V. subterranea. However, no significant difference (P<0.05) was observed in protein content of processed V. subterranea as compared to the raw seeds. Analyses of antinutrient composition show that processing significantly reduced the levels of oxalate, tannins, phytate, trypsin inhibitor, and hydrogen cyanide contents of V. subterranea. While magnesium, potassium, and phosphorus were the most abundant macrominerals in V. subterranea, zinc was the most abundant micromineral. Correlation analysis revealed that the levels of crude protein, ash, moisture, and lipid were negatively affected by phytate, tannins, and oxalate. The results, therefore, suggest that processing significantly lowered the levels of antinutrients in V. subterranea, thereby making it safer for consumption.

PurposeOne of the contributions of artificial intelligent (AI) in modern technology is emotion recognition which is mostly based on facial expression and modification of its inference engine. The facial recognition scheme is mostly built to understand user expression in an online business webpage on a marketing site but has limited abilities to recognise elusive expressions. The basic emotions are expressed when interrelating and socialising with other personnel online. At most times, studying how to understand user expression is often a most tedious task, especially the subtle expressions. An emotion recognition system can be used to optimise and reduce complexity in understanding users' subconscious thoughts and reasoning through their pupil changes.Design/methodology/approachThis paper demonstrates the use of personal computer (PC) webcam to read in eye movement data that includes pupil changes as part of distinct user attributes. A custom eye movement algorithm (CEMA) is used to capture users' activity and record the data which is served as an input model to an inference engine (artificial neural network (ANN)) that helps to predict user emotional response conveyed as emoticons on the webpage.FindingsThe result from the error in performance shows that ANN is most adaptable to user behaviour prediction and can be used for the system's modification paradigm.Research limitations/implicationsOne of the drawbacks of the analytical tool is its inability in some cases to set some of the emoticons within the boundaries of the visual field, this is a limitation to be tackled within subsequent runs with standard techniques.Originality/valueThe originality of the proposed model is its ability to predict basic user emotional response based on changes in pupil size between average recorded baseline boundaries and convey the emoticons chronologically with the gaze points.

Purpose Basic capturing of emotion on user experience of web applications and browsing is important in many ways. Quite often, online user experience is studied via tangible measures such as task completion time, surveys and comprehensive tests from which data attributes are generated. Prediction of users’ emotion and behaviour in some of these cases depends mostly on task completion time and number of clicks per given time interval. However, such approaches are generally subjective and rely heavily on distributional assumptions making the results prone to recording errors. This paper aims to propose a novel method – a window dynamic control system – that addresses the foregoing issues. Design/methodology/approach Primary data were obtained from laboratory experiments during which 44 volunteers had their synchronized physiological readings – skin conductance response, skin temperature, eye movement behaviour and users activity attributes taken by biosensors. The window-based dynamic control system (PHYCOB I) is integrated to the biosensor which collects secondary data attributes from these synchronized physiological readings and uses them for two purposes: for detection of both optimal emotional responses and users’ stress levels. The method’s novelty derives from its ability to integrate physiological readings and eye movement records to identify hidden correlates on a webpage. Findings The results from the analyses show that the control system detects basic emotions and outperforms other conventional models in terms of both accuracy and reliability, when subjected to model comparison – that is, the average recoverable natural structures for the three models with respect to accuracy and reliability are more consistent within the window-based control system environment than with the conventional methods. Research limitations/implications Graphical simulation and an example scenario are only provided for the control’s system design. Originality/value The novelty of the proposed model is its strained resistance to overfitting and its ability to automatically assess user emotion while dealing with specific web contents. The procedure can be used to predict which contents of webpages cause stress-induced emotions to users.

PurposeDetecting emotion on user experience of web applications and browsing is important in many ways. Web designers and developers find such approach quite useful in enhancing navigational features of webpages, and biomedical personnel regularly use computer simulations to monitor and control the behaviour of patients. On the other hand, law enforcement agents rely on human physiological functions to determine the likelihood of falsehood in interrogations. Quite often, online user experience is studied via tangible measures such as task completion time, surveys and comprehensive tests from which data attributes are generated. Prediction of users' emotion and behaviour in some of these cases depends mostly on task completion time and number of clicks per given time interval. However, such approaches are generally subjective and rely heavily on distributional assumptions making the results prone to recording errors.Design/methodology/approachThe authors propose a novel method-a window dynamic control system that addresses the foregoing issues. Primary data were obtained from laboratory experiments during which forty-four volunteers had their synchronised physiological readings, skin conductance response (SCR), skin temperature (ST), eye movement behaviour and users’ activity attributes taken using biosensors. The window-based dynamic control system (PHYCOB I) is integrated to the biosensor which collects secondary data attributes from these synchronised physiological readings and uses them for two purposes. For both detection of optimal emotional responses and users' stress levels. The method's novelty derives from its ability to integrate physiological readings and eye movement records to identify hidden correlates on a webpage.FindingsResults show that the control system detects basic emotions and outperforms other conventional models in terms of both accuracy and reliability, when subjected to model comparison that is, the average recoverable natural structures for the three models with respect to accuracy and reliability are more consistent within the window-based control system environment than with the conventional methods.Research limitations/implicationsThe paper is limited to using a window control system to detect emotions on webpages, while integrated to biosensors and eye-tracker.Originality/valueThe originality of the proposed model is its resistance to overfitting and its ability to automatically assess human emotion (stress levels) while dealing with specific web contents. The latter is particularly important in that it can be used to predict which contents of webpages cause stress-induced emotions to users when involved in online activities.

This study was carried out to determine the proximate composition of raw milk produced in pastoral settlements. Six hundred pastoralists' raw milk samples were collected from 20 local governments in Adamawa and Taraba states, Nigeria. Milk samples were collected from White Fulani (WF), Red Bororo (RB) and Sokoto Gudali (SG) breeds of cattle and were analyzed for protein, fat, ash and moisture contents. The protein content ranged between 3.62±0.38% -3.95±0.11% in WF, 3.29±0.8% - 3.94±0.10% in RB and 3.31±0.27%- 3.95±0.09% in SG in Adamawa and Taraba states. The fat content ranged between 3.55±0.47% - 3.99±0.03% in WF, 3.98±0.04% - 3.98±0.06% in RB and 3.32±0.20% - 3.45±0.27% in SG. The ash content recorded was between 0.40±0.06% -0.41±0.04% in WF, 0.40±0.06% - 0.43±0.07% in RB and0.39±0.06% - 0.41±0.08% in SG, and the moisture content in Adamawa and Taraba states were between 83.52±2.07% - 84.00±0.57% in WF, 82.28±1.05% - 83.73±0.63% in RB and 82.90±1.48% - 83.56±1.35%in SG. The study from the two states revealed protein value between 3.29± 0.8% - 3.95±0.11%, fat content range of3.32±0.20% - 3.99±0.03%, ash content of between 0.39± 0.06% - 0.43±0.07% and moisture content that ranged between 82.28± 1.05% - 84.00±0.57%. Constituents of milkfrom Taraba state were higher in values than those from Adamawa sate. The statistical analysis of the results at95% confidence level showed significant difference among breeds and states. In comparison, the three breeds that resided in Adamawa state had least values, which could be attributed to herd management practices. This study showed that all the three pastoralists' breeds indicated desirable components in their milk Cross breeding with higher breeds and provision of quality feed and water may lead to better yield in all the breeds in this study.