Linguistic Markers in Individuals With Symptoms of Depression in Bi-Multilingual Context

Depression has been identified as the most prevalent mental disorder worldwide. Due to the stigma of mental illness, the population remains unidentified, undiagnosed, and untreated. Various studies have been carried out to detect and track depression following symptoms of dichotomous thinking, absolutist thinking, linguistic markers, and linguistic behavior. However, there is little study focused on the linguistic behavior of bilingual and multilingual with anxiety and depression. This chapter aims to identify the bi-multilingual linguistic markers by analyzing the recorded verbal content of depressive discourse resulting from life situations and stressors causing anxiety, depression, and suicidal ideation. Different contextual domains of word usage, content words, function words (pronouns), and negative valance words have been identified as indicators of psychological process affecting cognitive behavior, emotional health, and mental illness. These findings are discussed within the framework of Beck's model of depression to support the linguistic connection to mental illness-depression.

Neurocognitive Mechanisms for Detecting Early Phase of Depressive Disorder

This chapter discusses neurocognitive mechanisms in terms of latency and amplitudes of EEG signals in depression that are presented in the form of event-related potentials (ERPs). Reviewing the available literature on depression, this chapter classifies early P100, ERN, N100, N170, P200, N200, and late P300 ERP components in frontal, mid-frontal, temporal, and parietal lobes. Using auditory oddball paradigm, most of the studies testing depressive patients have found robust P300 amplitude reduction. Proposing EEG methods and summarizing behavioral, neuroanatomical, and electrophysiological findings, this chapter discusses how the different tasks, paradigms, and stimuli contribute to the cohesiveness of neural signatures and psychobiological markers for identifying the patients with depression. Existing research gaps are directed to conduct ERP studies following go/no-go, flanker interference, and Stroop tasks on global and local attentional stimuli associated with happy and sad emotions to examine anterior cingulate cortex (ACC) dysfunction in depression.

Tremor Identification Using Machine Learning in Parkinson's Disease

Tremor is an involuntary quivering movement or shake. Characteristically occurring at rest, the classic slow, rhythmic tremor of Parkinson's disease (PD) typically starts in one hand, foot, or leg and can eventually affect both sides of the body. The resting tremor of PD can also occur in the jaw, chin, mouth, or tongue. Loss of dopamine leads to the symptoms of Parkinson's disease and may include a tremor. For some people, a tremor might be the first symptom of PD. Various studies have proposed measurable technologies and the analysis of the characteristics of Parkinsonian tremors using different techniques. Various machine-learning algorithms such as a support vector machine (SVM) with three kernels, a discriminant analysis, a random forest, and a kNN algorithm are also used to classify and identify various kinds of tremors. This chapter focuses on an in-depth review on identification and classification of various Parkinsonian tremors using machine learning algorithms.

Early Detection of Parkinson's Disease

Parkinson's disease (PD) is a neurodegenerative disorder that occurs due to corrosion of the substantia nigra, located in the thalamic region of the human brain, and is responsible for transmission of neural signals throughout the human body by means of a brain chemical, termed as “dopamine.” Diagnosis of PD is difficult, as it is often affected by the characteristics of the medical data of the patients, which include presence of various indicators, imbalance cases of patients' data records, similar cases of healthy/affected persons, etc. Through this chapter, an intelligent diagnostic system is proposed by integrating one-class SVM, extreme learning machine, and data preprocessing technique. The proposed diagnostic model is validated with six existing techniques and four learning models. The experimental results prove the combination of proposed method with ELM learning model to be highly effective in case of early detection of Parkinson's disease, even in presence of underlying data issues.

Neurological Disorders, Rehabilitation, and Associated Technologies

Patients with neurological disorders are increasing globally due to various factors such as change in lifestyle patterns, professional and personal stress, small nuclear families, etc. Neurological rehabilitation is an area focused by the several research and development organizations and scientists from different disciplines to invent new and advanced rehabilitation devices. This chapter starts with the classification of different neurological disorders and their potential causes. The rehabilitation devices available globally for neurological patients with their underlying associated technologies are explained in the chapter. Towards the end of the chapter, the reader can acquire the fundamental knowledge about the different neurological disorders and the mal-functionality associated with the corresponding organs. The utilization of advanced technologies such as artificial intelligence, machine learning, and deep learning by researchers to fabricate neuro rehabilitation devices to improve patients' quality of life (QOL) are discussed in concluding section of the chapter.

Motor Imagery Classification Using EEG Signals for Brain-Computer Interface Applications

In this chapter, a nearest neighbor (k-NN)-based method for efficient classification of motor imagery using EEG for brain-computer interfacing (BCI) applications has been proposed. Electroencephalogram (EEG) signals are obtained from multiple channels from brain. These EEG signals are taken as input features and given to the k-NN-based classifier to classify motor imagery. More specifically, the chapter gives an outline of the Berlin brain-computer interface that can be operated with minimal subject change. All the design and simulation works are carried out with MATLAB software. k-NN-based classifier is trained with data from continuous signals of EEG channels. After the network is trained, it is tested with various test cases. Performance of the network is checked in terms of percentage accuracy, which is found to be 99.25%. The result suggested that the proposed method is accurate for BCI applications.

Social Media Analytics to Predict Depression Level in the Users

As people around the world are spending increasing amounts of time online, the question of how online experiences are linked to health and wellbeing is essential. Depression has become a public health concern around the world. Traditional methods for detecting depression rely on self-report techniques, which suffer from inefficient data collection and processing. Research shows that symptoms linked to mental illness are detectable on social media like Twitter, Facebook, and web forums, and automatic methods are more and more able to locate inactivity and other mental disease. The pattern of social media usage can be very helpful to predict the mental state of a user. This chapter also presents how activities on Facebook are associated with the depressive states of users. Based on online logs, we can predict the mental state of users.

Epileptic Seizure Detection and Classification Using Machine Learning

Epilepsy is a brain ailment identified by unpredictable interruptions of normal brain activity. Around 1% of mankind experience epileptic seizures. Around 10% of the United States population experiences at least a single seizure in their life. Epilepsy is distinguished by the tendency of the brain to generate unexpected bursts of unusual electrical activity that disrupts the normal functioning of the brain. As seizures usually occur rarely and are unforeseeable, seizure recognition systems are recommended for seizure detection during long-term electroencephalography (EEG). In this chapter, ANN models, namely, BPA, RNN, CL, PNN, and LVQ, have been implemented. A prominent dataset was employed to assess the proposed method. The proposed method is capable of achieving an accuracy of 97.5%; the high accuracy obtained has confirmed the great success of the method.

Soft Computing-Based Early Detection of Parkinson's Disease Using Non-Invasive Method Based on Speech Analysis

This chapter aims to use the speech signals that are a behavioral bio-marker for Parkinson's disease. The victim's vocabulary is mostly lost, or big gaps are observed when they are talking or the conversation is abruptly stopped. Therefore, speech analysis could help to identify the complications in conversation from the inception of the symptoms of Parkinson's disease in initial phases itself. Speech can be regularly logged in an unobstructed approach and machine learning techniques can be applied and analyzed. Fuzzy logic-based classifier is proposed for learning from the training speech signals and classifying the test speech signals. Brainstorm optimization algorithm is proposed for extracting the fuzzy rules from the speech data, which is used by fuzzy classifier for learning and classification. The performance of the proposed classifier is evaluated using metrics like accuracy, specificity, and sensitivity, and compared with benchmark classifiers like SVM, naïve Bayes, k-means, and decision tree. It is observed that the proposed classifier outperforms the benchmark classifiers.

Medical Image Segmentation

Today, IoT in therapeutic administrations has ended up being more productive in light of the fact that the correspondence among authorities and patients has been improved with versatile applications. These applications are made by the associations with the objective that the pros can screen the patient's prosperity. If any issue has hopped out at the patient, by then the authority approaches the patient and gives the correct treatment. In this proposition, particular focus is given to infant human administrations, in light of the fact that the greatest fear of gatekeepers is that they would lose their infant kids at whatever point. Therefore, in this part, a business contraption has been recognized which screens the consistent information about the infant's heart rate, oxygen levels, resting position. In case anything happens to the tyke, the information will get to the adaptable application, which has been made by an association and is mechanically available by finishing a representation field test for the kid; the information is recorded and examined.