Subject Index Free

3D food printers

• binder jetting, 257

• concepts of, 274–275

• extrusion-based printing, 256

• future aspects, 260–263

• inkjet printing, 256–257

• positive and negative properties, 256

• selective laser sintering (SLS) technology, 257–258

3-mercaptopropyl trimethoxysilane (MPTS), 230

⁶⁰Co radioactive isotope, 309

¹³⁷Cs radioactive isotope, 309

adaptive neurofuzzy inference systems (ANFIS), 2

adulterants detection, 227–228

affinity-based nanosensors, 216–217

aflatoxin B1 antibody (AFB1), 234

aflatoxins, 234

AFM. See atomic force microscopy (AFM)

AI. See artificial intelligence (AI)

amperometric biosensors, 223

ANFIS. See adaptive neurofuzzy inference systems (ANFIS)

ANNs. See artificial neural networks (ANNs)

antibiotics detection, 235–236

AR. See augmented reality (AR)

artificial intelligence (AI), 238–239

• assisted 3D food printing technology

  • areas and applications, 271–272

  • challenges and future prospects, 278–279

  • education, 272

  • expert systems, 272–273

  • history of AI, 270–271

  • neural networks, 273

  • overview, 268–270

  • post-processing step, 277–278

  • pre-processing step, 275–276

  • processing step, 276–277

  • robotics, 273–274

• attractive performance, 2

• food processing and packaging, 2–3

• impact sustainability and food security, 15–16

• implementation

  • identification of non-halal components, 27–28

  • quantification of trans fatty acid, 30

  • rheological analysis for characterization, 26–27

  • shelf-life prediction, 30–32

  • thermal oxidation prediction, 29–30

  • waste cooking oil, 28–29

• ingredient usage, 10

• modeling applications

  • fruit and vegetable technology, 262

  • fuzzy logic, 259–260

  • genetic algorithms, 260

  • neural networks, 258–259

  • unwanted surface browning, 262

• optimizing recipes, 10

• overview, 23–24

• smart packaging solutions, 11–12

artificial neural networks (ANNs)

• application of, 148–172

• auto-encoders, 146–147

• baking, 161–166

• vs. biological network, 137

• convolutional neural networks (CNNs), 142–143

• development of, 137–139

• extrusion, 166–167

• fermentation, 167–168

• filtration, 168–169

• freeze-drying, 154

• future scope and use of, 172

• Hopfield network, 144–145

• Kohonen’s network, 143–144

• LSTM, 145–146

• microwave assisted extraction (MAE), 158–160

• microwave drying, 152

• microwave vacuum drying, 153–154

• multi-layer feed-forward networks, 140–141

• network learning, 137

• node character, 135

• optimisation methods, 147–148

• osmotic dehydration, 154–155

• RBM and DBM, 145

• recurrent neural network (RNN), 141–142

• shelf-life estimation, 170–172

• single layer feed-forward networks, 140

• soaking and canning, 169–170

• solvent extraction (SE), 158

• super critical fluid extraction (SCFE), 160–161

• tray drying, 149, 152

• ultra-sound assisted extraction (UAE), 160

• vacuum drying, 153

Asynchronous Byzantine Fault Tolerant (aBFT), 90

atomic force microscopy (AFM), 221

atrazine, 226

augmented reality (AR), 254

auto-encoders, 146–147

automation in food production, 3–4

• cutting automation, 7

• peeling automation, 6

• quality control and safety, 7

• sorting automation, 6

backpropagation (BP) neural network, 42–43

baking, 161–166

big data, 253

• benefits and challenges, 78–79

• blockchain, 77–78

• data analytics, 75

• definition of, 72

• digital and sensing technologies, 72–75

• final considerations, 79–80

• food safety and security, 76

• sensing technologies, 76–77

bio-nanosensors, 222–223

blockchain, 254

brevetoxins (BTXs), 233–234

calorimetric biosensors, 223

campylobacter, 309

CANN. See compute architecture for neural networks (CANN)

canning, 169–170

cantilever nanosensor, 222

capacitive sensors, 295

catalytic-based nanosensors, 217

chemical nanosensors, 221–222

chemometrics, digital images assisted by

• digital images acquisition, 185–187

• ora-pro-nobis leaves, 184–185

chlorophyll, 187

cholera toxin (CT), 235

C–H stretching overtone, 32

CNNs. See convolutional neural networks (CNNs)

cold chain logistics (CCL), 95

compute architecture for neural networks (CANN), 277

COMSOL Multiphysics, 201

convolutional neural networks (CNNs), 142–143

CT. See cholera toxin (CT)

cyber physical systems, 254

deep Boltzmann machines (DBM), 140, 145, 173

deployable nanosensors, 222

Deskjet scanner, 185

digitalization, food industry

• augmented reality (AR), 254–255

• big data, 253

• blockchain, 254

• cyber physical systems, 254

• digital industry, 253

• food design phenomenon, 255

• Internet of Things (IoT), 253

• smart robots, 255

dynamic headspace-needle trap extraction method, 291–292

dynamic headspace sampling with sorbent tubes, 290–291

edge computing, 91

eicosapentaenoic acid (EPA), 36

electrical current measurements, 219–220

electrochemical nanosensors, 221

electrochemical sensors, 295

electromagnetic nanosensors, 218–220

electrometers, 222

electronic nose (e-nose), 74, 283

• basal cells, 284

• challenges, 305–306

• detection system

  • applications of, 303, 304

  • data analysis system, 296

  • history of, 294–295

  • measurement principles, 295–296

• future trends, 306

• odor molecules, 285

• odor (scent) receptors, 285–286

• olfactory receptors, 283–284

• sample handling system

  • dynamic headspace-needle trap extraction method, 291–292

  • dynamic headspace sampling with sorbent tubes, 290–291

  • membrane-inlet mass spectrometry (MIMS), 292–293

  • solid phase microextraction (SPME) method, 288–290

  • static headspace (SHS) method, 287–288

  • trapping and purging method, 288

• schematic illustration, 287

• sensory receptors, 283

electronic tongue (e-tongue), 74, 296–297

• applications of, 303–305

• bitterness, 298

• challenges, 305–306

• circuit level, 299

• future trends, 306

• perception level, 299

• receptor level, 299

• saltiness, 298

• sourness, 298

• statistical data analysis

  • chemometric techniques, 302

  • data interpretation and validation, 302–303

  • frequency-domain features, 301–302

  • pattern recognition, 302

  • signal acquisition, 299–300

  • signal preprocessing, 300–301

  • software and tools, 303

  • statistical and mathematical features, 302

  • time-domain features, 301

  • workflow, 303

• sweetness, 298

• taste buds, 297

• umami, 298

ELM. See extreme learning machine (ELM)

e-nose. See electronic nose (e-nose)

EPA. See eicosapentaenoic acid (EPA)

Escherichia Coli, 230–231

e-tongue. See electronic tongue (e-tongue)

extreme learning machine (ELM), 43–44

extrusion, 166–167

fats and oils production, 25–26

FDM. See fused deposition modeling (FDM)

fermentation, 167–168

fertilizer and pesticide analytes, 224–227

FET. See field effect transistor (FET)

fiber optic nanosensors, 218

field effect transistor (FET), 296

filtration, 168–169

fish and fisheries products

• AI systems for quality measurement, 48–49

• applications of AI

  • automated sorting and grading, 56

  • predictive analytics for quality assurance, 56

  • quality inspection and defect detection, 57

• automated visual inspection systems

  • computer vision systems, 38–39

  • real-time quality grading, 39

• challenges and limitations, 57

• challenges and prospects, 58–59

• eicosapentaenoic acid (EPA), 36

• food shelf-life prediction

  • backpropagation (BP) neural network, 42–43

  • extreme learning machine (ELM), 43–44

  • genetic algorithm–BP, 43

  • machine learning (ML), 41

  • radial basis function (RBF) neural network, 44–45

  • shelf-life prediction, 45

• future directions and opportunities, 57–58

• hyperspectral and multispectral imaging, 39–41

• machine learning for defect detection, 51–54

• machine olfaction, 46–47, 50–51

• overview, 36–37

• role of AI, 58

• seafood processing industry, 37

• traceability and compliance

  • automated packaging and labeling, 56

  • data integration and analysis, 56

  • fish processing and circular economy, 55–56

  • quality control robotics and automation, 56

  • seafood product integrity, 55

food adulteration, 71

food irradiation

• applications of, 316–317

• disinfection technology, 311

• dose measurement, 313–315

• doses of ionizing radiation, 312

• EPR dosimeter, 314

• in European Union, 314–316

• facilities and control, 313

• foodstuffs, 315

• health aspects, 317–318

• irradiation sources, 312

• operational parameters, 320–321

• overview, 309

• practices, 310–312

• requirements for, 316

• sterile packaging radiation, 318–319

• sugar content, 319–320

• WHO/FAO documentation, 315

food processing industry

• artificial neural network (ANN)

  • application of, 148–172

  • auto-encoders, 146–147

  • baking, 161–166

  • vs. biological network, 137

  • convolutional neural networks (CNNs), 142–143

  • development of, 137–139

  • extrusion, 166–167

  • fermentation, 167–168

  • filtration, 168–169

  • freeze-drying, 154

  • future scope and use of, 172

  • Hopfield network, 144–145

  • Kohonen’s network, 143–144

  • LSTM, 145–146

  • microwave assisted extraction (MAE), 158–160

  • microwave drying, 152

  • microwave vacuum drying, 153–154

  • multi-layer feed-forward networks, 140–141

  • network learning, 137

  • node character, 135

  • optimisation methods, 147–148

  • osmotic dehydration, 154–155

  • RBM and DBM, 145

  • recurrent neural network (RNN), 141–142

  • shelf-life estimation, 170–172

  • single layer feed-forward networks, 140

  • soaking and canning, 169–170

  • solvent extraction (SE), 158

  • super critical fluid extraction (SCFE), 160–161

  • tray drying, 149, 152

  • ultra-sound assisted extraction (UAE), 160

  • vacuum drying, 153

• biological neural network, 134–135

• overview, 133–134

food shelf-life prediction

• backpropagation (BP) neural network, 42–43

• extreme learning machine (ELM), 43–44

• genetic algorithm–BP, 43

• machine learning (ML), 41

• radial basis function (RBF) neural network, 44–45

• shelf-life prediction, 45

food sterilization, 318

food supply chain (FSC)

• agricultural sector, 111–113

• dairy industry, 113–114

• meat and poultry industry, 114–115

• traceability in, 94–96

foreign object detection in milk packaging

• COMSOL Multiphysics, 201

• dot plot graph, 208

• experimental setup, 201–203

• food contamination detection, 194

• hair, 206, 207

• invasive and intrusive techniques, 196

• issues and challenges, 197

• literature review, 193–197

• material parameters, 201

• metal, 203

• non-invasive and non-intrusive techniques, 197, 198

• overview, 192–193

• plastic, 203

• research methodology, 197–203

• specification of, 201

• time arrival analysis, 209–211

• wave amplitude comparison, 209

Fourier transform infrared spectroscopy (FTIR), 263

free cell dye method, 218

freeze-drying, 154

FTIR. See Fourier transform infrared spectroscopy (FTIR)

fused deposition modeling (FDM), 252, 274

fuzzy logic systems, 102–104

• AI and modeling applications, 259–260

• application-control system, 103

• classical Boolean logic, 103

• crisp sets, 106

• defuzzification, 109

• in food supply chains

  • agricultural sector, 111–113

  • dairy industry, 113–114

  • meat and poultry industry, 114–115

• framework, 104–106

• future aspects, 125–126

• fuzzification, 109

• fuzzy sets, 106

• IF–THEN rules, 104

• inference, 107–108

• membership functions, 110

• multivalued logic, 103

• nonlinear mapping, 104

• overview, 101–102

• processing and manufacturing

  • data-driven approach, 118

  • expert-knowledge driven approach, 118, 119

  • fault diagnosis, 118–120

  • process optimization, 121–122

  • production planning, 121–122

  • quality diagnosis sensors, 120–121

  • sensory quality, 115–118

  • storage and distribution, 122–125

• rule models, 108–109

• theories, 102–103

fuzzy modeling, 102

glassy carbon electrode (GCE), 225

greenhouse gas emissions (GHG), 89, 260

HACCP. See Hazard Analysis and Critical Control Points (HACCP)

Halalan Toyyiban safety rating, 120

Hazard Analysis and Critical Control Points (HACCP), 311

heavy metals detection, 236–237

Hopfield network, 144–145

Hue angle, 189

ICT. See information and communication technologies (ICT)

Industry 4.0

• concept of, 252

• production technologies, 251

information and communication technologies (ICT), 12

inkjet printing, 256–257

innovations in food technology

• AI in food processing and packaging, 2–3

• assessing the quality of foods, 8

• automation in food production, 3–4

  • cutting automation, 7

  • peeling automation, 6

  • quality control and safety, 7

  • sorting automation, 6

• challenges and solutions, 14

• computer vision for detecting defects, 8

• evolutionary trends in packaging, 12–13

• future aspects, 16–17

• incorporating existing systems, 15

• ingredient usage, 10

• monitoring and adjusting processing parameters, 10–11

• optimizing recipes, 10

• overview, 2

• predictive maintenance for machinery and equipment, 8–9

• process optimization, 9–10

• RFID technology, 13–14

• robotics, sensors, and AI-driven analytics, 4–5

• smart packaging solutions, 11–12

• sustainability and food security, 15–16

• technical, ethical, and regulatory considerations, 15

insect consumption (entomophagy), 261

Internet of Things (IoT), 253

• architecture, 90

• blockchain types, 91

• food supply chain (FSC), 94–96

• precision agriculture, 93–94

• smart farming, 91–93

• sustainability, 89

• systems overview, 89–91

ion sensitive biosensors, 223

IoT. See Internet of Things (IoT)

Karenia brevis, 233

Kohonen’s network, 143–144

labeled nanoparticles method, 218

Listeria monocytogenes, 228, 232

long short-term memory (LSTM), 140, 145–146

machine learning (ML), 41

MAE. See microwave assisted extraction (MAE)

magnetism measurements, 220

mass spectrometry (MS), 296

Materials Genome Initiative (MGI), 276

mechanical nanosensors, 220–221

membrane-inlet mass spectrometry (MIMS), 292–293

metal oxide semiconductor (MOS), 295

methyl parathion, 225

microwave assisted extraction (MAE), 158–160

microwave drying, 152

microwave vacuum drying, 153–154

MIMS. See membrane-inlet mass spectrometry (MIMS)

ML. See machine learning (ML)

MOS. See metal oxide semiconductor (MOS)

MS. See mass spectrometry (MS)

multi-layer feed-forward networks, 140–141

multi-walled carbon nanotubes (MWCNTs), 225

nanosensors

• classification of

  • affinity-based nanosensors, 216–217

  • bio-nanosensors, 222–223

  • catalytic-based nanosensors, 217

  • chemical nanosensors, 221–222

  • deployable nanosensors, 222

  • electromagnetic nanosensors, 218–220

  • electrometers, 222

  • mechanical nanosensors, 220–221

  • optical nanosensors, 217–218

• configurations and hybrid techniques, 223

• in food safety

  • adulterants detection, 227–228

  • antibiotics detection, 235–236

  • artificial intelligence, 238–239

  • fertilizer and pesticide analytes, 224–227

  • heavy metals detection, 236–237

  • pathogens detection, 228–232

  • toxins detection, 232–235

• manufacturing of, 215

• overview, 215–216

natural language processing (NLP), 2, 3, 142, 145

network learning, 137

NLP. See natural language processing (NLP)

node character, 135

non-destructive method, 31

non-halal components, identification of, 27–28

ochratoxins (OCT), 234–235

O–H and N–H stretching overtone, 32

optical nanosensors, 217–218

optical sensors, 295

optic nanosensors, 221

osmotic dehydration, 154–155

partial least squares regression (PLSR), 30, 32, 40, 50, 54, 75

pathogens detection, 228–232

PCA. See principal component analysis (PCA)

pesticides, 225

pheophorbide, 189

photochromatic ink, 96

photoionization detectors (PID), 296

PID. See photoionization detectors (PID)

piezoelectric nanosensors, 221

PLSR. See partial least squares regression (PLSR)

polymer sensors, 295

potentiometric biosensors, 223

Practical Byzantine Fault Tolerance (PBFT), 90

precision agriculture, 93–94

principal component analysis (PCA), 27, 47, 75, 185, 294, 299, 301, 302

process optimization, 9–10

Proof of Authority (PoA), 90

Proof of Stake (PoS), 90

Proof of Work (PoW), 90

quartz crystal microbalance (QCM), 295

radial basis function (RBF) neural network, 44–45

radio frequency identification (RFID), 12–14, 94

recurrent neural networks (RNNs), 140–142

resonant biosensors, 223

response surface methodology (RSM), 102

restricted Boltzmann machines (RBM), 140, 145, 146, 173

RFID. See radio frequency identification (RFID)

RNNs. See recurrent neural networks (RNNs)

RSM. See response surface methodology (RSM)

Salmonella species, 229–230, 232, 239

Salmonella typhimurium, 230

SAW. See surface acoustic wave (SAW)

SCFE. See super critical fluid extraction (SCFE)

science of deception, 70

screen-printed electrode (SPE), 233

SE. See solvent extraction (SE)

selective laser sintering (SLS), 252, 256, 257–258

shelf-life estimation, 170–172

shelf-life prediction, 30–32

single layer feed-forward networks, 140

SLS. See selective laser sintering (SLS)

smart farming, 91–93

soaking, 169–170

solid phase microextraction (SPME), 288–290

solvent extraction (SE), 25, 156, 158

SPE. See screen-printed electrode (SPE)

SPME. See solid phase microextraction (SPME)

Staphylococcal enterotoxin B (SEB), 233

Staphylococcus aureus, 228, 231–232

static headspace (SHS) method, 287–288

statistical data analysis, 299

• chemometric techniques, 302

• data interpretation and validation, 302–303

• frequency-domain features, 301–302

• pattern recognition, 302

• signal acquisition, 299–300

• signal preprocessing, 300–301

• software and tools, 303

• statistical and mathematical features, 302

• time-domain features, 301

• workflow, 303

stereolithography (STL) format files, 276

super critical fluid extraction (SCFE), 157, 160–161

surface acoustic wave (SAW), 295

sustainability, 89

TANB. See Tree augmented naïve Bayes algorithm (TANB)

TFA. See trans fatty acid (TFA)

thermal nanosensors, 221

thermal oxidation prediction, 29–30

toxins detection, 232–235

trans fatty acid (TFA), 30

trapping and purging method, 288

tray drying, 149, 152

Tree Augmented Naïve Bayes algorithm (TANB), 94

UFPs. See unconventional food plants (UFPs)

ultra-sound assisted extraction (UAE), 160

unconventional food plants (UFPs), 184

vacuum drying, 153

volatile organic compounds (VOCs), 290

waste cooking oil, 28–29

XG Boost regression model, 277