Index

Note: Page numbers followed by “f” and “t” refer to figures and tables respectively.

A
Active ageing services composition, 115–116, 117f
Activities of daily living (ADLs), 106–107
monitoring of, 104–105
ACTVAGE framework, 111–120
conceptual framework, 111, 112f
system architecture, 111–112, 113f, 117f–118f
Adaptive house, 103–104
Adaptive immune system, 233
AffectAura, 33
Affective computing, 33
Affective Diary, 33
Agro-food industry, 250–256, 253f, 255f
Aldi, 247–248
Allostatic load model, 29
Alzheimer’s disease (AD), 2–4, 13
mild, 13, 17–18
Ambulatory monitoring, 129–130
Amyloid beta (Aβ), 4
Amyotrophic lateral sclerosis (ALS), 5–6
Anger, and cardiovascular health, 29–30
Anger Out scale, 28
Ant colony optimization (ACO), 292
Antigen-presenting cell (APC), 233
Anxiety, and cardiovascular health, 29–30
Application Artificial Bee Colony (AABC) algorithm, 292–293
Apps, 183–184
Area under the curve (AUC), 137
Artificial Bee Colony (ABC) algorithm, 292–293
Artificial immune network algorithm (AINE), 234–235
Artificial immune system (AIS), 234–235
Artificial intelligence (AI), 288–289
Artificial neural network (ANN), 130, 147–148, 288–289, 291–292
Assistive robot technologies, 105–106
Auto-correlation, 15–16
Automatic neural network classifier (NEURC), 136
Average synchrony measure, 19, 20f
B
Back-propagation neural network (BNN), 291
Back-propagation trained feed-forward neural network classifier (BPXNC), 135–136
Backward feature selection, 46
Bat Algorithm, 292
B cells, 233–234
Bees Algorithm, 292
Behavioral monitoring, See Activities of daily living (ADLs)
Belief–desire–intention (BDI) framework, 167–168
Benton Visual Retention Test, 17
Bias field, 79–80
mathematical models of, 80–81
MRI image corrupted by, 85–86
correction strategy, 86
Big Data analytics, 106–111
Bio-inspired algorithms, 300
Biological immune system (BIS), 233–234
Blind source separation technique (BSS), 18
Bluetooth, 37
C
C4.5 algorithm, 232–233
CAALYX, 103–104
Canadian Cattle Identification Agency (CCIA), 247–248
Cancer, 289–290, 290t
Canny edge detector, 86–88
CAPIM, 114–115
Capturing context, 37–38
Cardiotocography (CTG), 127–129
data, intrapartum hypoxia from, prediction of, 125–146
ambulatory monitoring, 129–130
CTG-UHB intrapartum data set, 130–131
data preprocessing, 131–132
feature extraction, 133–134
machine learning algorithms, 135–136
synthetic minority oversampling, 134–135
using machine learning, 130
validation methods, 136–137
Cardiovascular disease (CVD), 28
Cardiovascular health, negative emotion and, 28–30
Care Process Organization Triangle (CPOT), 204–205, 206f
CART algorithm, 232–233
Change management, 219
Chi-square test, 51, 51t–52t
Classification, 149–150
RNNs for, 150–154
applications of, 154t
Classifier fusion strategy, 6–12, 10f–11f
Classifiers, 4
Clinical decision support, 169, 171–175
Clinical Dementia Rating Scale (CDRS), 17
Clonal selection algorithm (CLONAG), 234–235
CODEX Alimentarius, 246–249
Cognitive behavioral therapy (CBT), 27–28
Coherence, interhemispheric, 13
Combinatorial Artificial Bee Colony (CABC) algorithm, 292–293
Combining classifiers, 24
Community matron, 270–271
Confirmatory data analysis (CDA), 137
Context-awareness, lifestyle-oriented, 115
Correlation analysis, 137–138
C-reactive protein (CRP), 36
Cross-correlation, 15–16
Cross power spectrum, See Cross spectral density
Cross spectral density, 16
Cuckoo Search (CS), 292
Cultural value, 220
D
Danger theory inspired algorithms, 234–235
Data
description, 17–18
filtering, 4, 18
gathering, 6
mining, 1, 7f, 231–233
preprocessing, 6
resampling of, 6–8
visualization, 35
Decision support system, 168–169
Decoupled extended Kalmen filter (DEKF) algorithm, 151
Dendritic cell algorithm (DCA), 234–235
Depression, and cardiovascular health, 29–30
Detection rate (DR), 238
Digital Life Story, 118
Disease data, 232–233
DNA microarray technology, 45
Doppler ultrasound monitoring, 125–126
DStress system, 34
E
Effective range–based gene selection (ERGS), 61–62, 62t–63t
Elderly care, Big Data analytics for
active ageing services composition, 115–116, 117f
ACTVAGE framework, 111–117, 112f–113f
data aggregation and processing, 113–114
lifestyle modeling and formalization, 114–115, 114f
lifestyle-oriented context-awareness recommendation, 115, 116f
requirements and challenges, 109–110
Electrocardiogram (ECG), 148, 152–153
Electroencephalographic (EEG) signals, 13–15, 14f
synchrony computation, 18–21
average synchrony measure, 19, 20f
PCA-based synchrony measure, 19–21, 20f
Electroencephalography (EEG), 148, 150–152
Electrohysterogram (EHG), 156–157
uterine signal processing, 157–159
Electronystagmography (EMG), 148–149
Elman–Jordan network, 149
Elman recurrent neural network (ERNN), 148–149, 152–154
EMIS Web, 282
Endoscopic third ventriculostomy, 188
Entropy, 83
Event condition action (ECA), 167–168
Exploratory data analysis (EDA), 137–138
F
False alarm rate (FAR), 238
Feature classification, 8–10, 9f–11f
Feature extraction
fetal heart rate, 133
uterine contraction, 133–134
Feature selection, 138
algorithms, filter-based supervised, 46–47
Feed Forward Neural Network (FFNN), 147–148, 291
Feed Forward Radial Basis Function (RBF), 291
Fetal heart rate (FHR)
feature extraction, 133
monitoring, 125–127
signal processing, 132
trace futures, 128t
Fish n’ Steps, 34
Food safety, 244–246
Food traceability, 244–246, 252f
current developments, 246–249
Footprint Tracker, 34
Fuzzy c-means (FCM), 83–84
G
Gene expression matrix, 45
Gene selection methods, for microarray data, 45–69
approaches for feature selection, 46
filter-based supervised feature selection algorithms, 46–47
chi-square test, 51, 51t–52t
comparison, 66–69, 67f
effective range–based gene selection, 61–62, 62t–63t
mRMR algorithm, 53–56, 56t–57t
MWMR algorithm, 63–66, 66t
Relief algorithm, 46–47
ReliefF algorithm, 47–50, 49t–50t
trace ratio, 58–60, 60t–61t
supervised, 46
unsupervised, 46
unsupervised filter-based feature selection algorithms, 72–76
Laplacian score, 72–73
multicluster feature selection, 73–74, 75f
results, simulation, 74–76
wrapper approach, feature selection algorithms based on, 69–72
sequential backward floating selection, 71–72
sequential backward selection, 70, 71t
sequential forward floating selection, 71
sequential forward selection, 70, 71t
simulation results on, 70
Genetic algorithm, 46
Geographic Information System (GIS), 250–251
Geriatric Depression Scale (GDS), 17
Global Guided Artificial Bee Colony (GGABC) algorithm, 293–295, 295f
Global Positioning System (GPS), 37
Google Glass, 36–37
H
Habit, impact on mHealth infusion, 221–222
Hazard Analysis Critical Control Point (HACCP) systems, 247–249
Healthy life expectancy (HLE), 30
Heart rate variability (HRV), 36
Hilbert transform, 15
Histogram, 83
Holdout Cross-Validation technique, 136
Hopfield Neural Network (HNN), 291
Human–computer interaction (HCI), 33–35
Human digital memory (HDM), 30–31
Human health, 289–291
Huntington’s disease, 5
Hybrid Guided Artificial Bee Colony (HGABC) algorithm, 296–297, 297f
Hydrocephalus, 186–187, 186f
causes, 187, 187t
pediatric hydrocephalus, 188–189
management, iNAS, 192–209, 199f–207f
I
ID3 algorithm, 232–233
Imbalanced data sets, 6–8
Improved Artificial Bee Colony (IABC) algorithm, 292–293
iNAS (intelligent NeuroDiary Application System), 184, 192–209
for hydrocephalus management
implementation, 199–201, 201f–205f
methods of analysis, 202–209, 206f–207f
requirements, 196–198
Independent component analysis (ICA), 18
Independent living, 100, 111–116, 119
Information and communication technology (ICT), 99–104, 119
Information technology (IT), 250–256, 253f, 255f
Innate immune system, 233
Integrated home systems, 103–104
Intelligent health care systems
development methodology, 190
Intelligent room, 103–104
Interhemispheric coherence (IHCoh), 13
Interleukin 6 (IL-6), 36
Internet of Things (IoT), 30–31, 31f
Intrapartum hypoxia, 126–127
cardiotocography data, 125–146
ambulatory monitoring, 129–130
CTG-UHB intrapartum data set, 130–131
data preprocessing, 131–132
feature extraction, 133–134
feature research directions, 137–139
machine learning algorithms, 135–136
synthetic minority oversampling, 134–135
validation methods, 136–137
Italian Standards Institute, 247–248
J
jQuery Mobile, 196, 199
K
K4CARE, 103–104
k-fold cross-validation, 136–137
K-means clustering, 80
L
Language barriers to mHealth, 218
Laplacian score, 72–73
Level set, 83
Levenberg–Marquardt leaning algorithm, 152–153
Levenberg–Marquardt trained feed-forward neural network classifier (LMNC), 136
Lidl, 247–248
Life 2.0, 103–104
Lifelogging technology, 30–32
background, 33–35
capturing data, 37–38
clinically relevant measurements, 36–37
personal information data sets, 38–39
research challenges, 35–39, 36f
Lifestyle modeling and formalization, 114–115, 114f
Lifestyle monitoring, See Activities of daily living (ADLs)
Low-frequency filtering, 82–83
M
Machine Learning, 3–4
Magnetic resonance imaging (MRI) intensity inhomogeneity correction, 79–98
algorithm limitations, 84
bias field, 80–81
current algorithms, 82–83
experimental design, 88
experimental results, 88
globally nonsmooth, 90, 94
locally smooth, 79–80, 84–85, 90, 94
methods, 85–88
algorithm design, 86–88, 87f
bias field correction strategy, 86
theory and problem formulation, 85–86
model limitations, 84
Magnitude squared coherence, 16–17
Mango traceability data construction, 261–263, 262f–263f
Mann–Whitney U test, 21–22
Market uncertainty, and mHealth, 215
MATCH Home Care Project, 103–104
MATrix LABoratory (MATLAB), 236–237
Maturity of technology, 222–223
Maximum relevance–minimum redundancy (mRMR) algorithm, 53–56, 56t–57t
Maximum weight–minimum redundancy (MWMR) algorithm, 63–66, 66t
Medical data preprocessing, 148–149
Memex, 32
Memory recall tests, 17
Metro, 247–248
Microarray data, 45–69
Relief algorithm, 46–47
ReliefF algorithm, 47–50, 49t–50t
trace ratio, 58–60, 60t–61t
supervised, 46
unsupervised, 46
unsupervised filter-based feature selection algorithms, 72–76
Laplacian score, 72–73
multicluster feature selection, 73–74, 75f
results, simulation, 74–76
wrapper approach, feature selection algorithms based on, 69–72
sequential backward floating selection, 71–72
sequential backward selection, 70, 71t
sequential forward floating selection, 71
sequential forward selection, 70, 71t
simulation results on, 70
Mild Alzheimer’s disease (MiAD), 13, 17–18
Mild cognitive impairment (MCI), 13
Mini-Mental State Examination (MMSE), 5, 17
Min-max normalization process, 237
Missing data, handling, 3
Mixture models, 83
Mobile computing, 32
Mobile decision support systems, 167–168
calculus of situations for, 169–174
implementation, 174–177
Mobile farming information system, 260–265
development, 250–260
agro-food industry, IT applications for, 250–256, 253f, 255f
system architecture, 256–260, 256f–259f
mango traceability data construction, 261–263, 262f–263f
public and private traceability sectors, 260–261
white gourd, private traceability system for, 263–265, 264f–265f
Mobile health (mHealth), 212–230
barriers to acceptance, 219–221
barriers to adaptation, 218–219
barriers to adoption, 216–217
barriers to infusion, 221–223
barriers to implementation, 223, 223f
barriers to initiation, 215–216
barriers to routinization, 221
discussion and findings, 225
methodology, 214–215, 214f
Mobile sensing platform (MSP), 34
Mobile technologies, 214–215
Mobility, 179–180
Modified Artificial Bee Colony (MABC) algorithm, 292–293
Motion sensors, 37
Motiva pilot project, 269–286
Movement signals, 4, 8
Multiclass data sets, 3
Multicluster feature selection (MCFS), 73–74, 75f
Multi-layer perceptron (MLP), 236, 238–241
Multiple knot spline-smooth support vector machine (MKS-SSVM), 232–233
N
National Health Service (NHS), 269
Negative emotion, and cardiovascular health, 28–30
Negative selection algorithm (NSA), 231–243
real-valued, 235–236
assessment measures, 238
experimental investigation and classification results, 236–241
experimental procedure, 237
simulation results and discussions, 238–241, 238t, 239f, 239t–241t
variable-sized detectors, 236
Neural synchronization, 13–15, 14f
Neural synchrony measurement technique, 15–17
cross-correlation, 15–16
magnitude squared coherence, 16–17
phase synchrony (Hilbert transform), 15
Neurodegenerative diseases (NDDs), 1
Alzheimer’s disease, 4
amyotrophic lateral sclerosis, 5
classification algorithms for, 5–12
classifier fusion strategy, 6–12, 9f
cross-correlation, 15–16
data description, 17–18
data filtering, 18
early diagnosis of, 2–3
EEG synchrony computation, 18–21
average synchrony measure, 19, 20f
PCA-based synchrony measure, 19–21, 20f
Huntington’s disease, 5
magnitude squared coherence, 10f–12f, 16–17
Parkinson’s disease, 5
phase synchrony (Hilbert transform), 15
results and discussion, 22–23, 23t–24t
statistical analysis, 21–23
Noncommunicable diseases (NCDs), 30
Nonnested generalized exemplars (NNGEs), 236, 238–241
Novel Artificial Bee Colony (NABC) algorithm, 292–293
O
OLDES, 103–104
Otsu method, 86–88
Oversampling, 8
P
PABIC, 83
Parallel Artificial Bee Colony (PABC) algorithm, 292–293
Parkinson’s disease, 5
Particle swarm optimization (PSO), 292
Pattern recognition, 4
Pediatric hydrocephalus, 188
treatment options for, 188–189
Perceptron linear classifier (PERLC), 136
Personal digital assistants (PDAs), 166, 250–251
Personal innovativeness, 222
Personalized elderly care, 99–124
ACTVAGE framework, 111–117, 112f–113f
data aggregation and processing, 113–114
lifestyle modeling and formalization, 114–115, 114f
lifestyle-oriented context-awareness recommendation, 115, 116f
requirements and challenges, 109–110
role of context, 110–111
Phase synchrony, 15
Pi-Sigma Neural Network (PNN), 291
Policy, defined, 217
Power Spectral Density (PSD), 16–17
Preterm, 154–156
birth, 154–155
labor, 154–156
Principal components analysis (PCA), 138
PROforma system, 169
PSO-ABC algorithm, 292–293
Psychophysiology, 35
Pulse Wave Velocity (PWV), 36
Q
Quantified self, 107–108
Quick response (QR) code, 251–254, 251f, 256–260
R
Radio frequency identification (RFID), 248, 250–251
Real-valued negative selection algorithm (RNSA), 235–236
assessment measures, 238
experimental investigation and classification results, 236–241
experimental procedure, 237
simulation results and discussions, 238–241, 238t, 239f, 239t–241t
Receiver operating characteristic (ROC) analysis, 10–12, 12f
Recurrent neural networks (RNNs), 147–165
for classification, 150–154, 154t
Elman, 148–149
for forecasting, modeling, 159–160, 160t
for medical data preprocessing, 148–149
Recurrent self-organizing map (RSOM), 150–151
Region of interest (ROI), 80, 86–88, 89f, 90, 91f–94f, 92
Rehabilitation integrated systems, 103–104
Relief algorithm, 46–47
ReliefF algorithm, 47–50, 49t–50t
RESTful (Representational State Transfer) API, 198
Rey Auditory Verbal Learning Test, 17
Rician noise, 79–80
Ridge Polynomial Neural Networks (RPNN), 291
S
Security and privacy issues, and mHealth, 219
Segmentation, 83
Self-forgetting system, 38
Self-governance, 166–167, 177, 180
Self–nonself discrimination, 234–235, 237
Self-Organizing Map (SOM), 291
SenseCam™, 32, 38
Sequential backward floating selection (SBFS), 46, 71–72
Sequential backward selection (SBS), 70, 71t
Sequential forward floating selection (SFFS), 46, 71
Sequential forward selection (SFS), 46, 70, 71t
Sequential minimal optimization (SMO), 236, 238–241
Signal-to-noise ratio (SNR), 82, 157, 159–160, 159f
Simple Recurrent Network (SRN), 291
Situation Calculus, 166–167, 169–170
foundational axioms of, 170–171
mobile decision support system context in, 171–174, 173f
Skewed data sets, 3
Small data, 107–108
Smart homes, 103–104
Smartphone technology, 37
Smooth Cell Contraction, 156, 156f
Statistical analysis, 21–23
Stress management, 34–35
Superoxide dismutase 1 (SOD1), 5
Supervised filter-based feature selection algorithms, 46–47
accuracy, comparison of, 66–69, 67f
based on wrapper approach, 69–72
sequential backward floating selection, 71
sequential backward selection, 70, 71t
sequential forward floating selection, 71
sequential forward selection, 70, 71t
simulation results on, 70
Supervised gene selection, 46
Supply chain management, 245–246
Support vector machine (SVM) classifier, 130
Surface fitting, 83
Swarm-based artificial neural system, 291–293
human heal data classification, 298, 299t–300t
experimental design, 298–300
simulation results, 300–305, 301t–302t, 303f–304f
Swarm intelligence, 292
Switching costs, 216
Symptom quantification, 5
Synthetic minority oversampling technique (SMOTE), 134–135, 139
T
Taiwan Good Agriculture Practice (TGAP), 249
T cells, 233
helper cells, 233–234
killer cells, 233
suppressor cells, 233
Technical infrastructure, and mHealth, 218–219
Telehealth, 269–286
recommendations, 283–284
Telehomecare, 103–104
Thick data, 107–108
Tianjin Shunzi Vegetable Cooperative (TSVC), traceability system, 263–265, 264f–265f
Traceable Agriculture Product (TAP) system, 249, 252–256, 253f, 260
mango traceability data construction for, 261–263, 262f–263f
Trace ratio, 58–60, 60t–61t
U
UbiFit Garden, 34
Ubiquitous computing, 35
Undersampling, 8
Unsupervised filter-based feature selection algorithms, 72–76
Laplacian score, 72–73
multicluster feature selection, 73–74, 75f
results, simulation, 74–76
Unsupervised gene selection, 46
User resistance, 219–220
Uterine contraction
feature extraction, 133–134
signal filtering, 131–132
Uterine EHG signal processing, 157–159, 158f
V
Variable-sized detectors (V-Detectors), 236, 238–241
Ventriculoatrial (VA) shunt, 188, 189f
Ventriculoperitoneal (VP) shunt, 188–189, 189f
Viticulture service–oriented framework (VSOF), 251
W
Wilcoxon rank sum test, 21–22
World Cancer Research Fund (WCRF), 289
World Population Ageing Report, 99
Wrapper approach, feature selection algorithms based on, 69–72
sequential backward floating selection, 71–72
sequential backward selection, 70, 71t
sequential forward floating selection, 71
sequential forward selection, 70, 71t
simulation results on, 70
X
XML document, 176
..................Content has been hidden....................

You can't read the all page of ebook, please click here login for view all page.
Reset
3.145.125.51