Inline classification of polymer films using Machine learning methods.

Improving the sortability of plastic packaging film waste (PPFW) is crucial for increasing the recycling rate in Austria as they account for 150,000 t of the annually produced 300,000 t of plastic packaging waste. Currently PPFW is thermally recovered, as it is impossible to separate the mechanically recyclable monomaterial films from the non mechanically-recyclable multimaterial films. In this study, machine learning models capable of classifying inline into monolayer and multilayer films of PPFW according to their spectral fingerprint taken in transflection were created. Feature selection methods, like PCA and MRMR F-Tests, identified the most relevant spectral ranges for classification, that show the least redundancy and highest relevance. This effective subset of features decreases the required complexity of the model while reducing prediction time without compromising accuracy. The resulting models achieved a prediction accuracy of 85 % on unseen specimens with minimal prediction latency, effectively showing the inline applicability of these models in sorting aggregates.

Deep learning approaches for classification of copper-containing metal scrap in recycling processes.

Separating copper from iron scrap is a critical operation in metal recycling and achieving this with low cost sensoric equipment like RGB cameras instead of XRF/XRT is becoming increasingly attractive. In this article, the groundwork for creating an image classification model to separate copper from iron scrap has been performed. Twenty of the most common and most easily available CNN architectures were trained on 2200 metal scrap specimens and evaluated inline on a sensor-based sorting rig for their prediction accuracy and their inference latency to mimic real circumstances in an industrial setting. Out of these evaluated architectures, DenseNet-201 with 98% accuracy in inline tests is recommended if potent hardware is available. Otherwise AlexNet with 92% accuracy or MobileNet-V2 with 90% accuracy are recommended for further investigation and model creation if hardware restrictions apply. Based on the presented results in this article, the initial cumbersome surveyance of the most suitable network architecture can be substantially reduced and the creation of a sorting model can be streamlined. This article thus provides the basis for creating an inline applicable sorting method for scrap metal that uses low cost sensorics equipment and can provide reasonably high accuracy in its prediction.

Corrigendum to: Qualitative analysis of post-consumer and post-industrial waste via near-infrared, visual and induction identification with experimental sensor-based sorting setup.

[This corrects the article DOI: 10.1016/j.mex.2022.101686.].

Qualitative analysis of post-consumer and post-industrial waste via near-infrared, visual and induction identification with experimental sensor-based sorting setup.

Sensor-based sorting in waste management is a method to separate valuable material or contaminants from a waste stream. Depending on the separation property different types of sensors are used. Separation properties and their corresponding sensors are e.g. molecular composition with near-infrared sensors, colour with visual spectroscopy or colour line scan cameras, or electric conductivity with electromagnetic sensors. The methods described in this paper deal with the development of sorting models for a specific near-infrared, a visual spectroscopy and an induction sensor. For near-infrared and visual spectroscopy software is required to create sorting models, while for induction only machine settings have to be adjusted and optimized for a specific sorting task. These sensors are installed in the experimental sensor-based sorting setup at the Chair of Waste Processing Technology and Waste Management located at the Montanuniversitaet Leoben. This sorting stand is a special designed machine for the university to make experiments on sensor-based sorting in lab scale. It can be used for a variety of waste streams depending on the grain size and the pre-conditioning for the sensor-based sorting machine. In detail the methods to create these sorting models are described and validated with plastic, glass and metal waste.•Near-infrared spectroscopy measures the molecular composition of near-infrared-active particles.•Visual spectroscopy measures the absorption of visible light by chemical compounds.•Induction sensors use induced currents to detect nearby metal objects.

Influence of reflective materials, emitter intensity and foil thickness on the variability of near-infrared spectra of 2D plastic packaging materials.

Most two-dimensional plastic packaging materials are thermally recovered, which does not add to the recycling quota of 50 % required by EU legislation for all lightweight packaging until 2025. Furthermore, the separation processes for 2D materials cannot reach the same level of accuracy, which is possible in the sorting of rigid plastic packaging. This study proposes new adaptations to existing sorting aggregates to increase the near-infrared spectral quality of two-dimensional materials. It aims to improve the spectral quality, which was defined by the deviation of the spectra from a reference spectrum and the variability of the recorded spectra, which can be achieved by installing reflectors behind the material made up of copper or aluminium. This setup enables detection in transflection rather than reflection mode. The variability could be reduced by a factor of 6 through the use of a reflective background. Meanwhile, the spectral fidelity to the reference spectrum could be enhanced, in some cases decreasing the deviation from the reference spectrum by 30 %, which means enhancing a spectrum from unrecognisable to useable. Apart from using reflective materials, the effects of emitter intensity, material and thickness were evaluated.

Response of thyrotropin to thyrotropin-releasing hormone as predictor of treatment outcome. Prediction of recovery and relapse in treatment with antidepressants and neuroleptics.

We determined whether the response of thyrotropin (TSH) to thyrotropin-releasing hormone could predict the outcome of treatment with antidepressant and neuroleptic drugs. We studied 114 female patients diagnosed as having major and minor depressive, manic, schizoaffective, and schizophrenic disorders. A blunted TSH response (less than 5 microU/mL [less than 5 mU/L]) at admission was associated with recovery after nine weeks of inpatient treatment using clomipramine hydrochloride for depression and haloperidol for psychosis. A blunted TSH response at discharge was associated with early relapse in depressives receiving clomipramine maintenance therapy. Our findings support the notion that the thyrotropin-releasing hormone test is a "state" marker that may be of use in predicting the outcome of treatment with antidepressant and neuroleptic drugs.

Hypothalamic-pituitary-gonadal axis in depressed premenopausal women: elevated blood testosterone concentrations compared to normal controls.

To assess the function of the hypothalamic-pituitary-gonadal (HPG) axis in major depression, a multihormonal study was carried out in 20 depressed premenopausal women. Serum concentrations of LH, FSH, estradiol, progesterone, testosterone, and GnRH-stimulated LH and FSH were measured before initiation of treatment (on the first day after menstruation) and during clomipramine treatment (same time one menstrual cycle later). Significantly higher blood concentrations of testosterone were found in untreated patients compared to normal controls. Furthermore, there was a significant negative correlation between Hamilton depression scores and estradiol concentrations of patients. The efficacy of clomipramine treatment was not related to hormonal parameters.

Release of human neurophysin I during insulin-induced hypoglycemia in depressed patients is abolished after recovery with clomipramine treatment.

Release of human neurophysin I (hNp I) and neurophysin II (hNp II) during insulin-induced hypoglycemia was studied in 10 unipolar depressed women before and after 4-5 weeks of standard antidepressant drug treatment with daily intravenous infusions of clomipramine. Before treatment, a significant increase of hNp I but not of hNp II serum levels in response to hypoglycemia was observed. At retest during clomipramine administration, a marked clinical amelioration occurred in all patients as determined with the Hamilton Rating Scale for Depression; the hNp I response to insulin was abolished, but no effect on hNp II concentration could be demonstrated. No correlation was found between the degree of the depression score decrease and the amplitude of the inhibition of hNp I release or serum levels of clomipramine or its metabolite, desmethylclomipramine. The meaning of this difference in reactivity of the neurohypophyseal system in the course of depressive illness, based on the pharmacological and biochemical profiles of clomipramine action, is discussed.

Andrological findings in young patients under long-term antidepressive therapy with clomipramine.

Serum hormone levels of follicle stimulating hormone (FSH), luteotropic hormone (LH), testosterone (T), prolactin (hPRL), estradiol (E2) and GnRH test were carried out in 11 patients after antidepressive therapy with clomipramine at a dosage of 75 mg/day for 3 months. Nine of these patients agreed with the evaluation of ejaculate parameter. As an age matched control group 15 patients without psychiatric disorders but under urological treatment because of erectile dysfunction were investigated in the same manner, with 11 patients being able to produce an ejaculate for examination. Both groups were closely comparable according to age, percentage of proven fertility and urological status. All spermiograms evaluated in the clomipramine group were pathological, especially with regard to volume, sperm motility and sperm morphology, whereas only 37% in the control group showed pathological findings, approximately the same as that of healthy individuals in this age range. Serum hormone levels as well as the hypothalamic-hypophyseal-gonadal axis proven with the Gn-RH test were in normal range in both groups. According to these results it seems evident that clomipramine does not alter sexual hormone profiles in males or interfere with the hypothalamic-hypophyseal-gonadal axis and has a significant negative effect on ejaculate parameters.

The TSH-response to TRH: A possible predictor of outcome to antidepressant and neuroleptic treatment.

This study was designed to investigate the possible common patterns of neuroendocrine mechanisms, which may be involved in the therapeutic effects of antidepressant drugs in depressive and of neuroleptic drugs in schizophrenic patients. Sixty-three depressed women (major depressive disorder) and 21 paranoid-hallucinatory women have been studied while on antidepressant (clomipramine) or neuroleptic (haloperidol) treatment, respectively. The neuroendocrine test (TRH-test) was performed at weekly intervals. The change of TSH-response to TRH during treatment, i.e. the treatment associated normalization of a former blunted TSH-response, can tentatively be regarded as a predictor of outcome for depressive and paranoid-hallucinatory patients to their respective drug treatments. Antidepressant and neuroleptic drugs appear to involve the normalization of the TSH-response in their therapeutic effects in that proportion of patients (40%) which showed a blunted TSH-response at admission.

TSH response to TRH and ECT.

In 31 female patients diagnosed according to DSM-III-R criteria as suffering from 'functional' psychosis (e.g., major depression, schizophrenia, mania) TRH tests were administered before, during and after a course of electroconvulsive therapy (ECT) to investigate the effects of ECT on HPT (hypothalamic-pituitary-thyroid) axis as well as the predictive value of TSH response to TRH on treatment outcome. In 20 patients all three TRH tests were available; no significant changes in the mean TSH response were found over the course of ECT; however, a change towards blunted TSH response at the end of treatment was observed. The initial TSH response did not predict the treatment outcome.

[Clinical relevance of changes in serum prolactin level caused by electroconvulsive therapy]. / Klinische Relevanz der Veränderungen der Serumprolaktinspiegel durch die Elektrokonvulsionstherapie.

In this study 15 (4 males, 11 females) depressive patients (according to DSM-III-R criteria), who were refractory to psychopharmacological treatment were referred for electroconvulsive therapy (ECT). Six ECTs were administered within a period of 3 weeks. Before the first, third and fifth ECT and 15, 30, and 60 minutes after each of these 3 treatments serum levels of prolactin were determined. After six ECTs eight patients showed significant symptomatic improvement, whilst the depressive symptoms in the other seven patients remained more or less unchanged. There was no statistically significant difference with respect to prolactin response following the three ECTs between the symptomatically improved and the unchanged group. There was no correlation of severity of depression and prolactin baseline levels before the first ECT. Neither baseline prolactin levels prior to the first ECT nor prolactin response predicted therapeutic outcome. From this point of view changes in serum prolactin levels do not reflect therapeutic pathways in depression or mechanisms of action of ECT.

Rapid psychotherapeutic effects of anesthesia with isoflurane (ES narcotherapy) in treatment-refractory depressed patients.

Treatment-refractory depressed patients who objected to electroconvulsive therapy (ECT) were given a series of anesthesias with isoflurane (Forane), a modern and established inhalation anesthetic. According to our hypothesis to be tested, the brief period of electrocerebral silence (ES), which can be observed shortly after the grand mal seizure in ECT, may be in itself a crucial biological determinant for the therapeutic effects of ECT. Isoflurane is the only drug known to effect an ES in the EEG in nontoxic concentrations, which does not result in adverse effects on any body organ including the brain; no seizure activity can be observed. Eleven depressed patients received a total of 36 anesthesias with isoflurane (ES narcotherapy). Rapid antidepressant effects were observed in 9 patients (p less than 0.0001). Effects were reproducible and lasted up to several weeks. No adverse effects of anesthesia were noticed.

[Comparison of the bioavailability of two diazepam preparations. Clinical comparison between a new commercial preparation and a standard preparation after oral and intramuscular administration]. / Vergleich der Bioverfügbarkeit von zwei Diazepam-Zubereitungen. Klinische Vergleichsstudie zwischen einer neuen Handelszubereitung und einem Standardpräparat nach oraler und intramuskulärer Applikation.

The following pharmacokinetic study was aimed at a comparison of the bioavailability of two different preparations of diazepam (Gewacalm and a further wellknown formulation). 40 healthy volunteers were subjected to a cross-over design in which plasma levels of diazepam were assayed after oral and intramuscular application of 10 mg of a preparation. In the comparison (N = 30) of oral bioavailability (rate and completeness of enteral absorption) no statistical difference between both preparations was observed. In the study of intramuscular bioavailability (N = 10), a trend of quicker and more complete resorption of Gewacalm was of statistical significance (p less than 0.05), however, because of the small number of subjects tested in the intramuscular study a replication study is advisable.

TSH-response patterns to TRH stimulation may indicate therapeutic mechanisms of antidepressant and neuroleptic drugs.

The study was designed to investigate, by weekly thyrotropin-releasing hormone tests, possible patterns of thyroid-stimulating hormone (TSH) responses which may indicate therapeutic mechanisms of antidepressant and neuroleptic drugs in patients with depressive and paranoid-hallucinatory syndrome during their process of recovery (3-9 weeks). 65 depressed women and 33 paranoid-hallucinatory women have been studied while on antidepressant (clomipramine) or neuroleptic (haloperidol) treatment, respectively. Four patterns of TSH response were observed. Patients with a pattern of a 'disblunting TSH response' (normalization of an abnormal low response) during drug treatment had a significantly higher chance to recover compared to patients with other TSH response patterns. This finding was independent of psychopathological features and drugs used for treatment. A hypothesis of 'malactivation' as a pathogenetic indicator of various psychotic states is being presented.

Plasma concentrations of haloperidol and prolactin and clinical outcome in acutely psychotic patients.

This study was aimed at disclosing possible relationships between short term therapeutic outcome and certain ranges in plasma concentrations of haloperidol and of prolactin. Acutely psychotic patients (n = 28) were diagnosed (by RDC) as schizophrenics acute subtype (n = 17), schizoaffectives manic type, acute subtype (n = 8) and manics (n = 3). Parenteral haloperidol was the pharmacological treatment mostly given; the dose was kept constant intraindividually but varied between patients from 5 to 40 mg/d (median 15 mg/d). Data for statistical analyses of possible psychobiological relationships were analyzed at 12 days (median) of haloperidol regimen, that is at a relatively early cut-off in treatment. Keeping the methodological difficulties in mind, certain ranges in plasma concentrations of haloperidol (16-26.9 mg/ml; (Fig. 1) and of prolactin (64-159.9 mg/ml; (Fig. 2) were found to be associated-statistically independently-with a favourable therapeutic outcome. The rate of recovery was best if a patient came to lie with both plasma levels within these therapeutic ranges (Fig. 3). It is concluded that the combination of pharmacological and neuroendocrinological techniques in psychiatric research may be of substantial use for clinical purposes.